| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.944281524926687, |
| "eval_steps": 500, |
| "global_step": 1700, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005865102639296188, |
| "grad_norm": 36.851659359587856, |
| "learning_rate": 7.843137254901962e-07, |
| "loss": 2.4374, |
| "mean_token_accuracy": 0.5096197873353958, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011730205278592375, |
| "grad_norm": 37.00745341487253, |
| "learning_rate": 1.5686274509803923e-06, |
| "loss": 2.5183, |
| "mean_token_accuracy": 0.5060627236962318, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.017595307917888565, |
| "grad_norm": 33.06806834510508, |
| "learning_rate": 2.3529411764705885e-06, |
| "loss": 2.3759, |
| "mean_token_accuracy": 0.5072058513760567, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.02346041055718475, |
| "grad_norm": 24.17744815738214, |
| "learning_rate": 3.1372549019607846e-06, |
| "loss": 2.291, |
| "mean_token_accuracy": 0.5175964683294296, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.02932551319648094, |
| "grad_norm": 15.532179533817953, |
| "learning_rate": 3.92156862745098e-06, |
| "loss": 2.0552, |
| "mean_token_accuracy": 0.5564254969358444, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03519061583577713, |
| "grad_norm": 12.400572852662727, |
| "learning_rate": 4.705882352941177e-06, |
| "loss": 1.8973, |
| "mean_token_accuracy": 0.5799022987484932, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.04105571847507331, |
| "grad_norm": 12.714649590022084, |
| "learning_rate": 5.4901960784313735e-06, |
| "loss": 1.8896, |
| "mean_token_accuracy": 0.5862231701612473, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0469208211143695, |
| "grad_norm": 15.580490797392397, |
| "learning_rate": 6.274509803921569e-06, |
| "loss": 1.7358, |
| "mean_token_accuracy": 0.5966581851243973, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05278592375366569, |
| "grad_norm": 11.702112786205797, |
| "learning_rate": 7.058823529411766e-06, |
| "loss": 1.5665, |
| "mean_token_accuracy": 0.6283580958843231, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.05865102639296188, |
| "grad_norm": 8.70207348765521, |
| "learning_rate": 7.84313725490196e-06, |
| "loss": 1.4954, |
| "mean_token_accuracy": 0.6435549259185791, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06451612903225806, |
| "grad_norm": 10.43187874858921, |
| "learning_rate": 8.627450980392157e-06, |
| "loss": 1.3849, |
| "mean_token_accuracy": 0.661979116499424, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07038123167155426, |
| "grad_norm": 8.446666521329538, |
| "learning_rate": 9.411764705882354e-06, |
| "loss": 1.3824, |
| "mean_token_accuracy": 0.6618056520819664, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.07624633431085044, |
| "grad_norm": 8.252951365329222, |
| "learning_rate": 1.0196078431372549e-05, |
| "loss": 1.3473, |
| "mean_token_accuracy": 0.6602734103798866, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.08211143695014662, |
| "grad_norm": 6.8948482176419015, |
| "learning_rate": 1.0980392156862747e-05, |
| "loss": 1.4417, |
| "mean_token_accuracy": 0.6434540897607803, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.08797653958944282, |
| "grad_norm": 6.539460909791532, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 1.4346, |
| "mean_token_accuracy": 0.6494264975190163, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.093841642228739, |
| "grad_norm": 5.434354265326855, |
| "learning_rate": 1.2549019607843138e-05, |
| "loss": 1.3035, |
| "mean_token_accuracy": 0.6783203706145287, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.09970674486803519, |
| "grad_norm": 4.7148773508202515, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 1.2174, |
| "mean_token_accuracy": 0.6834078431129456, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.10557184750733138, |
| "grad_norm": 5.873881991004589, |
| "learning_rate": 1.4117647058823532e-05, |
| "loss": 1.1852, |
| "mean_token_accuracy": 0.6986361294984818, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.11143695014662756, |
| "grad_norm": 25.463977260503608, |
| "learning_rate": 1.4901960784313726e-05, |
| "loss": 1.4844, |
| "mean_token_accuracy": 0.6396931707859039, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.11730205278592376, |
| "grad_norm": 7.1572160909660125, |
| "learning_rate": 1.568627450980392e-05, |
| "loss": 1.2791, |
| "mean_token_accuracy": 0.6703987568616867, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12316715542521994, |
| "grad_norm": 4.095861178832352, |
| "learning_rate": 1.647058823529412e-05, |
| "loss": 1.2234, |
| "mean_token_accuracy": 0.6897248178720474, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.12903225806451613, |
| "grad_norm": 4.773764142523696, |
| "learning_rate": 1.7254901960784314e-05, |
| "loss": 1.2771, |
| "mean_token_accuracy": 0.6836260929703712, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.1348973607038123, |
| "grad_norm": 4.037667101234835, |
| "learning_rate": 1.8039215686274513e-05, |
| "loss": 1.1467, |
| "mean_token_accuracy": 0.7134711667895317, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.14076246334310852, |
| "grad_norm": 4.935180182733481, |
| "learning_rate": 1.8823529411764708e-05, |
| "loss": 1.2157, |
| "mean_token_accuracy": 0.6998878344893456, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.1466275659824047, |
| "grad_norm": 4.721141853747017, |
| "learning_rate": 1.9607843137254903e-05, |
| "loss": 1.1784, |
| "mean_token_accuracy": 0.6964201852679253, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15249266862170088, |
| "grad_norm": 5.246228951758431, |
| "learning_rate": 2.0392156862745097e-05, |
| "loss": 1.204, |
| "mean_token_accuracy": 0.7094837054610252, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.15835777126099707, |
| "grad_norm": 4.682236592289397, |
| "learning_rate": 2.1176470588235296e-05, |
| "loss": 1.2207, |
| "mean_token_accuracy": 0.7027621790766716, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.16422287390029325, |
| "grad_norm": 3.9239160089159455, |
| "learning_rate": 2.1960784313725494e-05, |
| "loss": 1.0857, |
| "mean_token_accuracy": 0.7144983857870102, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.17008797653958943, |
| "grad_norm": 4.527625873838982, |
| "learning_rate": 2.274509803921569e-05, |
| "loss": 1.1507, |
| "mean_token_accuracy": 0.7080343216657639, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.17595307917888564, |
| "grad_norm": 4.522012886880006, |
| "learning_rate": 2.3529411764705884e-05, |
| "loss": 1.2317, |
| "mean_token_accuracy": 0.6883119121193886, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 4.0469531644008505, |
| "learning_rate": 2.431372549019608e-05, |
| "loss": 1.3669, |
| "mean_token_accuracy": 0.6731580421328545, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.187683284457478, |
| "grad_norm": 3.9549406080521745, |
| "learning_rate": 2.5098039215686277e-05, |
| "loss": 1.113, |
| "mean_token_accuracy": 0.7163452804088593, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.1935483870967742, |
| "grad_norm": 4.515614395996245, |
| "learning_rate": 2.5882352941176475e-05, |
| "loss": 1.2258, |
| "mean_token_accuracy": 0.694293312728405, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.19941348973607037, |
| "grad_norm": 3.7187249983876667, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 1.0837, |
| "mean_token_accuracy": 0.72011748701334, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.20527859237536658, |
| "grad_norm": 4.216460194700125, |
| "learning_rate": 2.7450980392156865e-05, |
| "loss": 1.1397, |
| "mean_token_accuracy": 0.7128811702132225, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.21114369501466276, |
| "grad_norm": 5.046740107610314, |
| "learning_rate": 2.8235294117647063e-05, |
| "loss": 1.1826, |
| "mean_token_accuracy": 0.7074279710650444, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.21700879765395895, |
| "grad_norm": 3.998671819509439, |
| "learning_rate": 2.9019607843137258e-05, |
| "loss": 1.0887, |
| "mean_token_accuracy": 0.7202624008059502, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.22287390029325513, |
| "grad_norm": 3.82846591040134, |
| "learning_rate": 2.9803921568627453e-05, |
| "loss": 1.0302, |
| "mean_token_accuracy": 0.7288055121898651, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2287390029325513, |
| "grad_norm": 4.328947102808582, |
| "learning_rate": 3.0588235294117644e-05, |
| "loss": 1.3474, |
| "mean_token_accuracy": 0.665394015610218, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.23460410557184752, |
| "grad_norm": 3.534740245743921, |
| "learning_rate": 3.137254901960784e-05, |
| "loss": 1.0633, |
| "mean_token_accuracy": 0.7198921740055084, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2404692082111437, |
| "grad_norm": 3.392870597157443, |
| "learning_rate": 3.215686274509804e-05, |
| "loss": 1.0412, |
| "mean_token_accuracy": 0.7338574528694153, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.24633431085043989, |
| "grad_norm": 3.8940128199078816, |
| "learning_rate": 3.294117647058824e-05, |
| "loss": 1.0445, |
| "mean_token_accuracy": 0.7283758819103241, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.25219941348973607, |
| "grad_norm": 3.3975334500995986, |
| "learning_rate": 3.372549019607844e-05, |
| "loss": 0.8871, |
| "mean_token_accuracy": 0.7578002512454987, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.25806451612903225, |
| "grad_norm": 3.4126700803478633, |
| "learning_rate": 3.450980392156863e-05, |
| "loss": 1.0618, |
| "mean_token_accuracy": 0.7234469875693321, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.26392961876832843, |
| "grad_norm": 3.8586208099678645, |
| "learning_rate": 3.529411764705883e-05, |
| "loss": 0.9222, |
| "mean_token_accuracy": 0.749978631734848, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.2697947214076246, |
| "grad_norm": 3.9582516129682803, |
| "learning_rate": 3.6078431372549025e-05, |
| "loss": 1.1156, |
| "mean_token_accuracy": 0.7032267674803734, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.2756598240469208, |
| "grad_norm": 3.8710398537085586, |
| "learning_rate": 3.686274509803922e-05, |
| "loss": 1.0898, |
| "mean_token_accuracy": 0.7087654024362564, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.28152492668621704, |
| "grad_norm": 3.689167131330777, |
| "learning_rate": 3.7647058823529415e-05, |
| "loss": 1.0075, |
| "mean_token_accuracy": 0.7357660159468651, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.2873900293255132, |
| "grad_norm": 3.514337462533497, |
| "learning_rate": 3.8431372549019614e-05, |
| "loss": 1.0222, |
| "mean_token_accuracy": 0.7442046403884888, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.2932551319648094, |
| "grad_norm": 3.8762873582868718, |
| "learning_rate": 3.9215686274509805e-05, |
| "loss": 1.23, |
| "mean_token_accuracy": 0.6920453310012817, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2991202346041056, |
| "grad_norm": 3.0719439332779332, |
| "learning_rate": 4e-05, |
| "loss": 0.9398, |
| "mean_token_accuracy": 0.7474829107522964, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.30498533724340177, |
| "grad_norm": 3.5924564436025497, |
| "learning_rate": 3.999996733363487e-05, |
| "loss": 1.0803, |
| "mean_token_accuracy": 0.7261487022042274, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.31085043988269795, |
| "grad_norm": 3.416094380030762, |
| "learning_rate": 3.9999869334658026e-05, |
| "loss": 1.0064, |
| "mean_token_accuracy": 0.7352629378437996, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.31671554252199413, |
| "grad_norm": 3.391864669571874, |
| "learning_rate": 3.9999706003425177e-05, |
| "loss": 1.0714, |
| "mean_token_accuracy": 0.7223077043890953, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3225806451612903, |
| "grad_norm": 3.706914591081663, |
| "learning_rate": 3.999947734052915e-05, |
| "loss": 1.1963, |
| "mean_token_accuracy": 0.704016849398613, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.3284457478005865, |
| "grad_norm": 3.372340432488623, |
| "learning_rate": 3.999918334679989e-05, |
| "loss": 1.0763, |
| "mean_token_accuracy": 0.7157147005200386, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3343108504398827, |
| "grad_norm": 3.36158570045305, |
| "learning_rate": 3.999882402330448e-05, |
| "loss": 1.0139, |
| "mean_token_accuracy": 0.7262187004089355, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.34017595307917886, |
| "grad_norm": 3.451164603835625, |
| "learning_rate": 3.999839937134712e-05, |
| "loss": 0.9333, |
| "mean_token_accuracy": 0.7455613538622856, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.3460410557184751, |
| "grad_norm": 3.9810759690964876, |
| "learning_rate": 3.999790939246912e-05, |
| "loss": 1.2167, |
| "mean_token_accuracy": 0.6962130814790726, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3519061583577713, |
| "grad_norm": 3.519609525609912, |
| "learning_rate": 3.999735408844892e-05, |
| "loss": 0.9685, |
| "mean_token_accuracy": 0.7478121444582939, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.35777126099706746, |
| "grad_norm": 3.1213934449857277, |
| "learning_rate": 3.999673346130203e-05, |
| "loss": 1.0734, |
| "mean_token_accuracy": 0.7303350269794464, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 3.4796741528734656, |
| "learning_rate": 3.999604751328109e-05, |
| "loss": 0.9029, |
| "mean_token_accuracy": 0.7691665366292, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.36950146627565983, |
| "grad_norm": 3.452794361053103, |
| "learning_rate": 3.999529624687581e-05, |
| "loss": 0.8333, |
| "mean_token_accuracy": 0.7859309017658234, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.375366568914956, |
| "grad_norm": 3.388415827235031, |
| "learning_rate": 3.999447966481298e-05, |
| "loss": 1.0312, |
| "mean_token_accuracy": 0.7555889338254929, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.3812316715542522, |
| "grad_norm": 3.573995994060177, |
| "learning_rate": 3.999359777005647e-05, |
| "loss": 1.1018, |
| "mean_token_accuracy": 0.711833767592907, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.3870967741935484, |
| "grad_norm": 3.3622463956437576, |
| "learning_rate": 3.999265056580719e-05, |
| "loss": 0.8182, |
| "mean_token_accuracy": 0.7698798477649689, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.39296187683284456, |
| "grad_norm": 3.8430356274770063, |
| "learning_rate": 3.999163805550313e-05, |
| "loss": 1.2049, |
| "mean_token_accuracy": 0.7203006744384766, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.39882697947214074, |
| "grad_norm": 3.3760389403116977, |
| "learning_rate": 3.9990560242819274e-05, |
| "loss": 1.0742, |
| "mean_token_accuracy": 0.7316281497478485, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.4046920821114369, |
| "grad_norm": 3.0177034229887947, |
| "learning_rate": 3.9989417131667647e-05, |
| "loss": 0.8724, |
| "mean_token_accuracy": 0.7838785424828529, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.41055718475073316, |
| "grad_norm": 2.9210681589288323, |
| "learning_rate": 3.9988208726197293e-05, |
| "loss": 0.8838, |
| "mean_token_accuracy": 0.7562002912163734, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.41642228739002934, |
| "grad_norm": 4.12729120204305, |
| "learning_rate": 3.998693503079423e-05, |
| "loss": 1.1041, |
| "mean_token_accuracy": 0.7364362850785255, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4222873900293255, |
| "grad_norm": 3.6965716329786513, |
| "learning_rate": 3.998559605008146e-05, |
| "loss": 0.9396, |
| "mean_token_accuracy": 0.7411833629012108, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.4281524926686217, |
| "grad_norm": 3.515036685731384, |
| "learning_rate": 3.9984191788918936e-05, |
| "loss": 1.0019, |
| "mean_token_accuracy": 0.7481007277965546, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4340175953079179, |
| "grad_norm": 3.2827315115719475, |
| "learning_rate": 3.998272225240356e-05, |
| "loss": 1.0716, |
| "mean_token_accuracy": 0.7445208355784416, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4398826979472141, |
| "grad_norm": 3.4002738542391864, |
| "learning_rate": 3.9981187445869165e-05, |
| "loss": 0.9189, |
| "mean_token_accuracy": 0.7811929360032082, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.44574780058651026, |
| "grad_norm": 3.189019628719659, |
| "learning_rate": 3.9979587374886466e-05, |
| "loss": 1.0077, |
| "mean_token_accuracy": 0.7385336235165596, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.45161290322580644, |
| "grad_norm": 3.567260269970604, |
| "learning_rate": 3.997792204526309e-05, |
| "loss": 0.9266, |
| "mean_token_accuracy": 0.7527733370661736, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.4574780058651026, |
| "grad_norm": 2.8177642527128977, |
| "learning_rate": 3.99761914630435e-05, |
| "loss": 0.8658, |
| "mean_token_accuracy": 0.7683205679059029, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.4633431085043988, |
| "grad_norm": 2.977084955813338, |
| "learning_rate": 3.997439563450901e-05, |
| "loss": 0.8314, |
| "mean_token_accuracy": 0.7646985054016113, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.46920821114369504, |
| "grad_norm": 3.326612634601017, |
| "learning_rate": 3.997253456617775e-05, |
| "loss": 0.9131, |
| "mean_token_accuracy": 0.7705802395939827, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4750733137829912, |
| "grad_norm": 2.8536925285281827, |
| "learning_rate": 3.997060826480465e-05, |
| "loss": 0.8028, |
| "mean_token_accuracy": 0.7799694091081619, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.4809384164222874, |
| "grad_norm": 2.7871810127043863, |
| "learning_rate": 3.9968616737381414e-05, |
| "loss": 0.9226, |
| "mean_token_accuracy": 0.7754707932472229, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.4868035190615836, |
| "grad_norm": 2.7373917465082354, |
| "learning_rate": 3.996655999113647e-05, |
| "loss": 0.7868, |
| "mean_token_accuracy": 0.7968426421284676, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.49266862170087977, |
| "grad_norm": 2.6733857555268847, |
| "learning_rate": 3.9964438033534994e-05, |
| "loss": 0.6813, |
| "mean_token_accuracy": 0.806500993669033, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.49853372434017595, |
| "grad_norm": 2.710796729205208, |
| "learning_rate": 3.996225087227881e-05, |
| "loss": 0.8327, |
| "mean_token_accuracy": 0.7808489948511124, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5043988269794721, |
| "grad_norm": 2.767538588379973, |
| "learning_rate": 3.995999851530645e-05, |
| "loss": 0.8104, |
| "mean_token_accuracy": 0.8030309081077576, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.5102639296187683, |
| "grad_norm": 2.791748527828644, |
| "learning_rate": 3.995768097079305e-05, |
| "loss": 0.8377, |
| "mean_token_accuracy": 0.7796871438622475, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.5161290322580645, |
| "grad_norm": 17.10160874448148, |
| "learning_rate": 3.9955298247150365e-05, |
| "loss": 1.0538, |
| "mean_token_accuracy": 0.7283467650413513, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.5219941348973607, |
| "grad_norm": 2.9697344797921774, |
| "learning_rate": 3.9952850353026715e-05, |
| "loss": 0.8371, |
| "mean_token_accuracy": 0.7595526427030563, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.5278592375366569, |
| "grad_norm": 3.063089786027371, |
| "learning_rate": 3.9950337297306976e-05, |
| "loss": 0.9252, |
| "mean_token_accuracy": 0.765510194003582, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.533724340175953, |
| "grad_norm": 3.2593335067842117, |
| "learning_rate": 3.994775908911251e-05, |
| "loss": 0.9852, |
| "mean_token_accuracy": 0.7499447464942932, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.5395894428152492, |
| "grad_norm": 2.755070128063194, |
| "learning_rate": 3.9945115737801183e-05, |
| "loss": 0.805, |
| "mean_token_accuracy": 0.779099851846695, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 3.0713510061837743, |
| "learning_rate": 3.99424072529673e-05, |
| "loss": 0.9714, |
| "mean_token_accuracy": 0.7578205242753029, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.5513196480938416, |
| "grad_norm": 5.577700081592657, |
| "learning_rate": 3.993963364444155e-05, |
| "loss": 0.8266, |
| "mean_token_accuracy": 0.7803476750850677, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.5571847507331378, |
| "grad_norm": 3.0701912646852225, |
| "learning_rate": 3.9936794922291015e-05, |
| "loss": 0.9948, |
| "mean_token_accuracy": 0.7452556863427162, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5630498533724341, |
| "grad_norm": 17.60337365182807, |
| "learning_rate": 3.993389109681912e-05, |
| "loss": 1.0502, |
| "mean_token_accuracy": 0.7418598681688309, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.5689149560117303, |
| "grad_norm": 3.5846812500371357, |
| "learning_rate": 3.993092217856557e-05, |
| "loss": 0.8611, |
| "mean_token_accuracy": 0.7773077115416527, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.5747800586510264, |
| "grad_norm": 6.77146659060288, |
| "learning_rate": 3.9927888178306346e-05, |
| "loss": 0.9778, |
| "mean_token_accuracy": 0.7604374513030052, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.5806451612903226, |
| "grad_norm": 3.736494622645263, |
| "learning_rate": 3.992478910705364e-05, |
| "loss": 0.9402, |
| "mean_token_accuracy": 0.7550177425146103, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.5865102639296188, |
| "grad_norm": 2.675434314951168, |
| "learning_rate": 3.992162497605583e-05, |
| "loss": 0.7708, |
| "mean_token_accuracy": 0.8071942776441574, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.592375366568915, |
| "grad_norm": 3.3217948172570586, |
| "learning_rate": 3.991839579679742e-05, |
| "loss": 0.8784, |
| "mean_token_accuracy": 0.7734089642763138, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.5982404692082112, |
| "grad_norm": 2.771224155637984, |
| "learning_rate": 3.991510158099905e-05, |
| "loss": 0.63, |
| "mean_token_accuracy": 0.8300730064511299, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.6041055718475073, |
| "grad_norm": 2.778513902291998, |
| "learning_rate": 3.991174234061738e-05, |
| "loss": 0.7114, |
| "mean_token_accuracy": 0.8191840052604675, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.6099706744868035, |
| "grad_norm": 2.9362931569310113, |
| "learning_rate": 3.9908318087845104e-05, |
| "loss": 0.8523, |
| "mean_token_accuracy": 0.7773655205965042, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.6158357771260997, |
| "grad_norm": 2.9316191976481516, |
| "learning_rate": 3.990482883511086e-05, |
| "loss": 0.6483, |
| "mean_token_accuracy": 0.8267587870359421, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.6217008797653959, |
| "grad_norm": 3.0440297107545917, |
| "learning_rate": 3.990127459507924e-05, |
| "loss": 0.7311, |
| "mean_token_accuracy": 0.8009310364723206, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.6275659824046921, |
| "grad_norm": 2.8590753777344324, |
| "learning_rate": 3.98976553806507e-05, |
| "loss": 0.7072, |
| "mean_token_accuracy": 0.805036373436451, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.6334310850439883, |
| "grad_norm": 2.6771045583267137, |
| "learning_rate": 3.989397120496152e-05, |
| "loss": 0.5646, |
| "mean_token_accuracy": 0.8565261512994766, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.6392961876832844, |
| "grad_norm": 3.0186022781962074, |
| "learning_rate": 3.989022208138377e-05, |
| "loss": 0.6418, |
| "mean_token_accuracy": 0.83050137758255, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "grad_norm": 3.8525032256000267, |
| "learning_rate": 3.9886408023525256e-05, |
| "loss": 0.9126, |
| "mean_token_accuracy": 0.7831842973828316, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6510263929618768, |
| "grad_norm": 3.1696627914446314, |
| "learning_rate": 3.9882529045229475e-05, |
| "loss": 0.9495, |
| "mean_token_accuracy": 0.7556833699345589, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.656891495601173, |
| "grad_norm": 3.0391907313935658, |
| "learning_rate": 3.987858516057554e-05, |
| "loss": 0.6691, |
| "mean_token_accuracy": 0.8235155344009399, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.6627565982404692, |
| "grad_norm": 3.1884729753748267, |
| "learning_rate": 3.9874576383878165e-05, |
| "loss": 0.7276, |
| "mean_token_accuracy": 0.8132852613925934, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.6686217008797654, |
| "grad_norm": 2.8702285262921188, |
| "learning_rate": 3.9870502729687594e-05, |
| "loss": 0.7586, |
| "mean_token_accuracy": 0.8025686517357826, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.6744868035190615, |
| "grad_norm": 3.477327705325461, |
| "learning_rate": 3.986636421278954e-05, |
| "loss": 0.7962, |
| "mean_token_accuracy": 0.801344022154808, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6803519061583577, |
| "grad_norm": 2.478525996153529, |
| "learning_rate": 3.986216084820515e-05, |
| "loss": 0.5867, |
| "mean_token_accuracy": 0.8358008116483688, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.6862170087976539, |
| "grad_norm": 2.954408831168468, |
| "learning_rate": 3.985789265119095e-05, |
| "loss": 0.642, |
| "mean_token_accuracy": 0.8179620429873466, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.6920821114369502, |
| "grad_norm": 2.448877211660101, |
| "learning_rate": 3.985355963723875e-05, |
| "loss": 0.5627, |
| "mean_token_accuracy": 0.8517102301120758, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.6979472140762464, |
| "grad_norm": 2.79210837705298, |
| "learning_rate": 3.9849161822075655e-05, |
| "loss": 0.627, |
| "mean_token_accuracy": 0.824343703687191, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.7038123167155426, |
| "grad_norm": 3.135497073478835, |
| "learning_rate": 3.984469922166396e-05, |
| "loss": 0.7399, |
| "mean_token_accuracy": 0.8141955435276031, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7096774193548387, |
| "grad_norm": 3.296087451604132, |
| "learning_rate": 3.984017185220109e-05, |
| "loss": 0.8949, |
| "mean_token_accuracy": 0.7819836810231209, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.7155425219941349, |
| "grad_norm": 2.7562945396523584, |
| "learning_rate": 3.9835579730119576e-05, |
| "loss": 0.805, |
| "mean_token_accuracy": 0.7919190227985382, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.7214076246334311, |
| "grad_norm": 2.667758292238495, |
| "learning_rate": 3.9830922872086974e-05, |
| "loss": 0.8093, |
| "mean_token_accuracy": 0.806427076458931, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 2.8478048457167584, |
| "learning_rate": 3.9826201295005784e-05, |
| "loss": 0.8689, |
| "mean_token_accuracy": 0.7796251475811005, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.7331378299120235, |
| "grad_norm": 2.88793329176012, |
| "learning_rate": 3.982141501601343e-05, |
| "loss": 0.8385, |
| "mean_token_accuracy": 0.779462069272995, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7390029325513197, |
| "grad_norm": 2.6368519953403418, |
| "learning_rate": 3.9816564052482164e-05, |
| "loss": 0.741, |
| "mean_token_accuracy": 0.7980659455060959, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.7448680351906158, |
| "grad_norm": 2.6609506778610172, |
| "learning_rate": 3.981164842201904e-05, |
| "loss": 0.81, |
| "mean_token_accuracy": 0.8032805398106575, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.750733137829912, |
| "grad_norm": 2.6663223208590776, |
| "learning_rate": 3.9806668142465804e-05, |
| "loss": 0.8363, |
| "mean_token_accuracy": 0.8015436008572578, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.7565982404692082, |
| "grad_norm": 2.7057881563332487, |
| "learning_rate": 3.9801623231898856e-05, |
| "loss": 0.6372, |
| "mean_token_accuracy": 0.8209338411688805, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.7624633431085044, |
| "grad_norm": 2.5687358685227664, |
| "learning_rate": 3.9796513708629186e-05, |
| "loss": 0.6557, |
| "mean_token_accuracy": 0.82688008248806, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7683284457478006, |
| "grad_norm": 2.6773701427099668, |
| "learning_rate": 3.979133959120229e-05, |
| "loss": 0.626, |
| "mean_token_accuracy": 0.8373893424868584, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.7741935483870968, |
| "grad_norm": 2.587857152937776, |
| "learning_rate": 3.9786100898398145e-05, |
| "loss": 0.662, |
| "mean_token_accuracy": 0.8253741338849068, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.7800586510263929, |
| "grad_norm": 2.5567903495608557, |
| "learning_rate": 3.9780797649231085e-05, |
| "loss": 0.7087, |
| "mean_token_accuracy": 0.8196479603648186, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.7859237536656891, |
| "grad_norm": 2.8459978973895055, |
| "learning_rate": 3.9775429862949745e-05, |
| "loss": 0.8041, |
| "mean_token_accuracy": 0.7983852028846741, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.7917888563049853, |
| "grad_norm": 2.687549165432222, |
| "learning_rate": 3.976999755903704e-05, |
| "loss": 0.7966, |
| "mean_token_accuracy": 0.7903356328606606, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7976539589442815, |
| "grad_norm": 2.3804933775980297, |
| "learning_rate": 3.976450075721003e-05, |
| "loss": 0.6608, |
| "mean_token_accuracy": 0.8316953554749489, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.8035190615835777, |
| "grad_norm": 2.670873668569676, |
| "learning_rate": 3.975893947741989e-05, |
| "loss": 0.6061, |
| "mean_token_accuracy": 0.8426604494452477, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.8093841642228738, |
| "grad_norm": 2.5007269896547784, |
| "learning_rate": 3.9753313739851824e-05, |
| "loss": 0.7976, |
| "mean_token_accuracy": 0.796313926577568, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.8152492668621701, |
| "grad_norm": 2.9023488126536483, |
| "learning_rate": 3.974762356492498e-05, |
| "loss": 0.9283, |
| "mean_token_accuracy": 0.7767031267285347, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.8211143695014663, |
| "grad_norm": 2.3838468185396082, |
| "learning_rate": 3.974186897329239e-05, |
| "loss": 0.6223, |
| "mean_token_accuracy": 0.8510593101382256, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8269794721407625, |
| "grad_norm": 2.707549081974321, |
| "learning_rate": 3.97360499858409e-05, |
| "loss": 0.6268, |
| "mean_token_accuracy": 0.8382851779460907, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.8328445747800587, |
| "grad_norm": 3.7838908615103692, |
| "learning_rate": 3.9730166623691096e-05, |
| "loss": 0.8547, |
| "mean_token_accuracy": 0.7846512198448181, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.8387096774193549, |
| "grad_norm": 2.5548687454598604, |
| "learning_rate": 3.9724218908197194e-05, |
| "loss": 0.5932, |
| "mean_token_accuracy": 0.83430977165699, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.844574780058651, |
| "grad_norm": 3.199919744808126, |
| "learning_rate": 3.971820686094701e-05, |
| "loss": 0.9231, |
| "mean_token_accuracy": 0.7737978771328926, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.8504398826979472, |
| "grad_norm": 2.8910753925453934, |
| "learning_rate": 3.971213050376183e-05, |
| "loss": 0.8144, |
| "mean_token_accuracy": 0.7877362817525864, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.8563049853372434, |
| "grad_norm": 2.3603427477860395, |
| "learning_rate": 3.9705989858696387e-05, |
| "loss": 0.5849, |
| "mean_token_accuracy": 0.8466823399066925, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.8621700879765396, |
| "grad_norm": 2.304209736108249, |
| "learning_rate": 3.969978494803876e-05, |
| "loss": 0.5765, |
| "mean_token_accuracy": 0.841646671295166, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.8680351906158358, |
| "grad_norm": 2.6376352843496926, |
| "learning_rate": 3.969351579431024e-05, |
| "loss": 0.6115, |
| "mean_token_accuracy": 0.8385377004742622, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.873900293255132, |
| "grad_norm": 2.7296649476772807, |
| "learning_rate": 3.968718242026533e-05, |
| "loss": 0.6022, |
| "mean_token_accuracy": 0.8428103923797607, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.8797653958944281, |
| "grad_norm": 2.2084195177668, |
| "learning_rate": 3.968078484889163e-05, |
| "loss": 0.4707, |
| "mean_token_accuracy": 0.8667677119374275, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8856304985337243, |
| "grad_norm": 2.7078580526227976, |
| "learning_rate": 3.9674323103409736e-05, |
| "loss": 0.6618, |
| "mean_token_accuracy": 0.8220425173640251, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.8914956011730205, |
| "grad_norm": 2.840612532292078, |
| "learning_rate": 3.966779720727317e-05, |
| "loss": 0.8325, |
| "mean_token_accuracy": 0.7944880649447441, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.8973607038123167, |
| "grad_norm": 2.567048273653788, |
| "learning_rate": 3.9661207184168305e-05, |
| "loss": 0.6274, |
| "mean_token_accuracy": 0.8346653878688812, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.9032258064516129, |
| "grad_norm": 2.4868154973678545, |
| "learning_rate": 3.9654553058014265e-05, |
| "loss": 0.7639, |
| "mean_token_accuracy": 0.8028886467218399, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 2.347709315999483, |
| "learning_rate": 3.9647834852962825e-05, |
| "loss": 0.6179, |
| "mean_token_accuracy": 0.8445746973156929, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.9149560117302052, |
| "grad_norm": 2.7197025616507804, |
| "learning_rate": 3.964105259339838e-05, |
| "loss": 0.8655, |
| "mean_token_accuracy": 0.7824793308973312, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.9208211143695014, |
| "grad_norm": 2.2237444753974063, |
| "learning_rate": 3.9634206303937773e-05, |
| "loss": 0.5044, |
| "mean_token_accuracy": 0.8604275360703468, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.9266862170087976, |
| "grad_norm": 2.0464596548682663, |
| "learning_rate": 3.962729600943028e-05, |
| "loss": 0.5075, |
| "mean_token_accuracy": 0.8705720156431198, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.9325513196480938, |
| "grad_norm": 2.8654977822500167, |
| "learning_rate": 3.962032173495748e-05, |
| "loss": 0.5989, |
| "mean_token_accuracy": 0.8563590124249458, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.9384164222873901, |
| "grad_norm": 2.095493932904228, |
| "learning_rate": 3.961328350583316e-05, |
| "loss": 0.5158, |
| "mean_token_accuracy": 0.8581189513206482, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9442815249266863, |
| "grad_norm": 2.4110117754062923, |
| "learning_rate": 3.960618134760327e-05, |
| "loss": 0.6664, |
| "mean_token_accuracy": 0.8309664577245712, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.9501466275659824, |
| "grad_norm": 2.130310237043839, |
| "learning_rate": 3.959901528604575e-05, |
| "loss": 0.438, |
| "mean_token_accuracy": 0.8650497943162918, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.9560117302052786, |
| "grad_norm": 2.7110395857688534, |
| "learning_rate": 3.959178534717053e-05, |
| "loss": 0.7384, |
| "mean_token_accuracy": 0.8108371719717979, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.9618768328445748, |
| "grad_norm": 2.3266814167894356, |
| "learning_rate": 3.9584491557219366e-05, |
| "loss": 0.692, |
| "mean_token_accuracy": 0.8317501842975616, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.967741935483871, |
| "grad_norm": 2.227229660768314, |
| "learning_rate": 3.957713394266576e-05, |
| "loss": 0.5823, |
| "mean_token_accuracy": 0.8335886374115944, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.9736070381231672, |
| "grad_norm": 2.5029650929135907, |
| "learning_rate": 3.956971253021489e-05, |
| "loss": 0.5433, |
| "mean_token_accuracy": 0.8478502333164215, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.9794721407624634, |
| "grad_norm": 2.5935021305346884, |
| "learning_rate": 3.956222734680348e-05, |
| "loss": 0.6178, |
| "mean_token_accuracy": 0.839194655418396, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.9853372434017595, |
| "grad_norm": 2.4490076558704454, |
| "learning_rate": 3.955467841959972e-05, |
| "loss": 0.6454, |
| "mean_token_accuracy": 0.8422679975628853, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.9912023460410557, |
| "grad_norm": 2.3280083402193092, |
| "learning_rate": 3.954706577600318e-05, |
| "loss": 0.6046, |
| "mean_token_accuracy": 0.8274341821670532, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.9970674486803519, |
| "grad_norm": 2.1986709980959795, |
| "learning_rate": 3.953938944364467e-05, |
| "loss": 0.7424, |
| "mean_token_accuracy": 0.8125108182430267, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.1986709980959795, |
| "learning_rate": 3.953164945038618e-05, |
| "loss": 0.6563, |
| "mean_token_accuracy": 0.8526751548051834, |
| "step": 171 |
| }, |
| { |
| "epoch": 1.0058651026392962, |
| "grad_norm": 3.2772084342860626, |
| "learning_rate": 3.952384582432076e-05, |
| "loss": 0.4182, |
| "mean_token_accuracy": 0.8776650503277779, |
| "step": 172 |
| }, |
| { |
| "epoch": 1.0117302052785924, |
| "grad_norm": 2.5235581743376145, |
| "learning_rate": 3.9515978593772426e-05, |
| "loss": 0.3567, |
| "mean_token_accuracy": 0.8968701064586639, |
| "step": 173 |
| }, |
| { |
| "epoch": 1.0175953079178885, |
| "grad_norm": 2.297685151844413, |
| "learning_rate": 3.9508047787296034e-05, |
| "loss": 0.2678, |
| "mean_token_accuracy": 0.9174044728279114, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.0234604105571847, |
| "grad_norm": 2.2108090381629717, |
| "learning_rate": 3.9500053433677226e-05, |
| "loss": 0.3188, |
| "mean_token_accuracy": 0.9073121473193169, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.029325513196481, |
| "grad_norm": 2.0055668794708144, |
| "learning_rate": 3.949199556193226e-05, |
| "loss": 0.3792, |
| "mean_token_accuracy": 0.8863450139760971, |
| "step": 176 |
| }, |
| { |
| "epoch": 1.035190615835777, |
| "grad_norm": 2.1578927026914116, |
| "learning_rate": 3.948387420130796e-05, |
| "loss": 0.268, |
| "mean_token_accuracy": 0.926617331802845, |
| "step": 177 |
| }, |
| { |
| "epoch": 1.0410557184750733, |
| "grad_norm": 2.107269518420395, |
| "learning_rate": 3.94756893812816e-05, |
| "loss": 0.3907, |
| "mean_token_accuracy": 0.8920909613370895, |
| "step": 178 |
| }, |
| { |
| "epoch": 1.0469208211143695, |
| "grad_norm": 2.528904479053577, |
| "learning_rate": 3.946744113156075e-05, |
| "loss": 0.3055, |
| "mean_token_accuracy": 0.8956907019019127, |
| "step": 179 |
| }, |
| { |
| "epoch": 1.0527859237536656, |
| "grad_norm": 2.3965215093079557, |
| "learning_rate": 3.945912948208324e-05, |
| "loss": 0.4794, |
| "mean_token_accuracy": 0.8625766634941101, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.0586510263929618, |
| "grad_norm": 2.4900117595217726, |
| "learning_rate": 3.9450754463016994e-05, |
| "loss": 0.4096, |
| "mean_token_accuracy": 0.8826896324753761, |
| "step": 181 |
| }, |
| { |
| "epoch": 1.064516129032258, |
| "grad_norm": 2.4103564653720153, |
| "learning_rate": 3.9442316104759955e-05, |
| "loss": 0.3678, |
| "mean_token_accuracy": 0.9017849788069725, |
| "step": 182 |
| }, |
| { |
| "epoch": 1.0703812316715542, |
| "grad_norm": 1.861075597205315, |
| "learning_rate": 3.943381443793994e-05, |
| "loss": 0.4068, |
| "mean_token_accuracy": 0.8929754197597504, |
| "step": 183 |
| }, |
| { |
| "epoch": 1.0762463343108504, |
| "grad_norm": 2.4115954465623477, |
| "learning_rate": 3.9425249493414585e-05, |
| "loss": 0.6112, |
| "mean_token_accuracy": 0.8370330631732941, |
| "step": 184 |
| }, |
| { |
| "epoch": 1.0821114369501466, |
| "grad_norm": 4.567207793686968, |
| "learning_rate": 3.941662130227118e-05, |
| "loss": 0.4997, |
| "mean_token_accuracy": 0.8561821803450584, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.0879765395894427, |
| "grad_norm": 2.4183931239021184, |
| "learning_rate": 3.940792989582654e-05, |
| "loss": 0.4121, |
| "mean_token_accuracy": 0.8887381628155708, |
| "step": 186 |
| }, |
| { |
| "epoch": 1.093841642228739, |
| "grad_norm": 1.970433465247901, |
| "learning_rate": 3.939917530562701e-05, |
| "loss": 0.3054, |
| "mean_token_accuracy": 0.9093934372067451, |
| "step": 187 |
| }, |
| { |
| "epoch": 1.099706744868035, |
| "grad_norm": 2.0703604995218243, |
| "learning_rate": 3.939035756344818e-05, |
| "loss": 0.3744, |
| "mean_token_accuracy": 0.9033533856272697, |
| "step": 188 |
| }, |
| { |
| "epoch": 1.1055718475073313, |
| "grad_norm": 2.101467735227217, |
| "learning_rate": 3.93814767012949e-05, |
| "loss": 0.4006, |
| "mean_token_accuracy": 0.8802796825766563, |
| "step": 189 |
| }, |
| { |
| "epoch": 1.1114369501466275, |
| "grad_norm": 2.455916126917878, |
| "learning_rate": 3.937253275140113e-05, |
| "loss": 0.2646, |
| "mean_token_accuracy": 0.923853725194931, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.1173020527859236, |
| "grad_norm": 2.1535792407926446, |
| "learning_rate": 3.936352574622978e-05, |
| "loss": 0.2866, |
| "mean_token_accuracy": 0.9053800255060196, |
| "step": 191 |
| }, |
| { |
| "epoch": 1.1231671554252198, |
| "grad_norm": 1.775502805179243, |
| "learning_rate": 3.9354455718472646e-05, |
| "loss": 0.396, |
| "mean_token_accuracy": 0.8891168534755707, |
| "step": 192 |
| }, |
| { |
| "epoch": 1.129032258064516, |
| "grad_norm": 2.5487239609300123, |
| "learning_rate": 3.934532270105026e-05, |
| "loss": 0.4241, |
| "mean_token_accuracy": 0.8907202184200287, |
| "step": 193 |
| }, |
| { |
| "epoch": 1.1348973607038122, |
| "grad_norm": 2.7940170270563534, |
| "learning_rate": 3.933612672711179e-05, |
| "loss": 0.4029, |
| "mean_token_accuracy": 0.8868995606899261, |
| "step": 194 |
| }, |
| { |
| "epoch": 1.1407624633431086, |
| "grad_norm": 2.2167275228202854, |
| "learning_rate": 3.9326867830034915e-05, |
| "loss": 0.4188, |
| "mean_token_accuracy": 0.8792544528841972, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.1466275659824048, |
| "grad_norm": 2.304107316447215, |
| "learning_rate": 3.931754604342568e-05, |
| "loss": 0.3405, |
| "mean_token_accuracy": 0.8975262865424156, |
| "step": 196 |
| }, |
| { |
| "epoch": 1.152492668621701, |
| "grad_norm": 1.9938659279661923, |
| "learning_rate": 3.930816140111842e-05, |
| "loss": 0.2866, |
| "mean_token_accuracy": 0.909386046230793, |
| "step": 197 |
| }, |
| { |
| "epoch": 1.1583577712609971, |
| "grad_norm": 2.1198141801508283, |
| "learning_rate": 3.929871393717558e-05, |
| "loss": 0.3839, |
| "mean_token_accuracy": 0.9004511907696724, |
| "step": 198 |
| }, |
| { |
| "epoch": 1.1642228739002933, |
| "grad_norm": 2.7406704106077573, |
| "learning_rate": 3.9289203685887644e-05, |
| "loss": 0.4047, |
| "mean_token_accuracy": 0.8865419179201126, |
| "step": 199 |
| }, |
| { |
| "epoch": 1.1700879765395895, |
| "grad_norm": 2.5501983405080817, |
| "learning_rate": 3.927963068177299e-05, |
| "loss": 0.4452, |
| "mean_token_accuracy": 0.8658623695373535, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1759530791788857, |
| "grad_norm": 2.5615420993615925, |
| "learning_rate": 3.926999495957775e-05, |
| "loss": 0.5242, |
| "mean_token_accuracy": 0.8514630421996117, |
| "step": 201 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 2.2053976497237104, |
| "learning_rate": 3.9260296554275704e-05, |
| "loss": 0.5312, |
| "mean_token_accuracy": 0.8589539080858231, |
| "step": 202 |
| }, |
| { |
| "epoch": 1.187683284457478, |
| "grad_norm": 2.112972722429536, |
| "learning_rate": 3.925053550106815e-05, |
| "loss": 0.3756, |
| "mean_token_accuracy": 0.8889518976211548, |
| "step": 203 |
| }, |
| { |
| "epoch": 1.1935483870967742, |
| "grad_norm": 1.9377609554676252, |
| "learning_rate": 3.9240711835383766e-05, |
| "loss": 0.3399, |
| "mean_token_accuracy": 0.8915588706731796, |
| "step": 204 |
| }, |
| { |
| "epoch": 1.1994134897360704, |
| "grad_norm": 2.21970803239968, |
| "learning_rate": 3.9230825592878494e-05, |
| "loss": 0.3734, |
| "mean_token_accuracy": 0.8954818993806839, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.2052785923753666, |
| "grad_norm": 2.4553958141146444, |
| "learning_rate": 3.92208768094354e-05, |
| "loss": 0.3015, |
| "mean_token_accuracy": 0.9162927344441414, |
| "step": 206 |
| }, |
| { |
| "epoch": 1.2111436950146628, |
| "grad_norm": 1.9800319673267526, |
| "learning_rate": 3.921086552116455e-05, |
| "loss": 0.3349, |
| "mean_token_accuracy": 0.9030973836779594, |
| "step": 207 |
| }, |
| { |
| "epoch": 1.217008797653959, |
| "grad_norm": 2.1007218191930335, |
| "learning_rate": 3.920079176440288e-05, |
| "loss": 0.3028, |
| "mean_token_accuracy": 0.916605718433857, |
| "step": 208 |
| }, |
| { |
| "epoch": 1.2228739002932552, |
| "grad_norm": 2.547001474595905, |
| "learning_rate": 3.9190655575714045e-05, |
| "loss": 0.5017, |
| "mean_token_accuracy": 0.8750176280736923, |
| "step": 209 |
| }, |
| { |
| "epoch": 1.2287390029325513, |
| "grad_norm": 2.4821613370193045, |
| "learning_rate": 3.918045699188833e-05, |
| "loss": 0.3779, |
| "mean_token_accuracy": 0.8920472636818886, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.2346041055718475, |
| "grad_norm": 1.9926481632824355, |
| "learning_rate": 3.9170196049942474e-05, |
| "loss": 0.3206, |
| "mean_token_accuracy": 0.9034112691879272, |
| "step": 211 |
| }, |
| { |
| "epoch": 1.2404692082111437, |
| "grad_norm": 1.8149346899691008, |
| "learning_rate": 3.915987278711954e-05, |
| "loss": 0.2996, |
| "mean_token_accuracy": 0.9074381738901138, |
| "step": 212 |
| }, |
| { |
| "epoch": 1.2463343108504399, |
| "grad_norm": 1.690371089487332, |
| "learning_rate": 3.914948724088883e-05, |
| "loss": 0.4503, |
| "mean_token_accuracy": 0.8817943632602692, |
| "step": 213 |
| }, |
| { |
| "epoch": 1.252199413489736, |
| "grad_norm": 2.3425310839455933, |
| "learning_rate": 3.913903944894565e-05, |
| "loss": 0.3848, |
| "mean_token_accuracy": 0.8884705975651741, |
| "step": 214 |
| }, |
| { |
| "epoch": 1.2580645161290323, |
| "grad_norm": 1.8082230444778677, |
| "learning_rate": 3.912852944921129e-05, |
| "loss": 0.3576, |
| "mean_token_accuracy": 0.8995041996240616, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.2639296187683284, |
| "grad_norm": 2.156095363781735, |
| "learning_rate": 3.911795727983279e-05, |
| "loss": 0.3768, |
| "mean_token_accuracy": 0.9000616893172264, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.2697947214076246, |
| "grad_norm": 2.056525651901662, |
| "learning_rate": 3.910732297918285e-05, |
| "loss": 0.4354, |
| "mean_token_accuracy": 0.8829119503498077, |
| "step": 217 |
| }, |
| { |
| "epoch": 1.2756598240469208, |
| "grad_norm": 2.569771491183553, |
| "learning_rate": 3.90966265858597e-05, |
| "loss": 0.4653, |
| "mean_token_accuracy": 0.8823570907115936, |
| "step": 218 |
| }, |
| { |
| "epoch": 1.281524926686217, |
| "grad_norm": 2.132704573151928, |
| "learning_rate": 3.908586813868693e-05, |
| "loss": 0.4343, |
| "mean_token_accuracy": 0.884559653699398, |
| "step": 219 |
| }, |
| { |
| "epoch": 1.2873900293255132, |
| "grad_norm": 2.4720965949429736, |
| "learning_rate": 3.9075047676713354e-05, |
| "loss": 0.4649, |
| "mean_token_accuracy": 0.874346137046814, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.2932551319648093, |
| "grad_norm": 2.0429710071111704, |
| "learning_rate": 3.9064165239212874e-05, |
| "loss": 0.4416, |
| "mean_token_accuracy": 0.8792015537619591, |
| "step": 221 |
| }, |
| { |
| "epoch": 1.2991202346041055, |
| "grad_norm": 2.0216506902906413, |
| "learning_rate": 3.905322086568434e-05, |
| "loss": 0.4349, |
| "mean_token_accuracy": 0.8829491958022118, |
| "step": 222 |
| }, |
| { |
| "epoch": 1.3049853372434017, |
| "grad_norm": 2.7526271970057388, |
| "learning_rate": 3.904221459585142e-05, |
| "loss": 0.3743, |
| "mean_token_accuracy": 0.887954942882061, |
| "step": 223 |
| }, |
| { |
| "epoch": 1.310850439882698, |
| "grad_norm": 2.0368517762814884, |
| "learning_rate": 3.903114646966242e-05, |
| "loss": 0.4253, |
| "mean_token_accuracy": 0.8919025957584381, |
| "step": 224 |
| }, |
| { |
| "epoch": 1.316715542521994, |
| "grad_norm": 1.9783869883280967, |
| "learning_rate": 3.9020016527290166e-05, |
| "loss": 0.3979, |
| "mean_token_accuracy": 0.8797405809164047, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.3225806451612903, |
| "grad_norm": 1.7298586661221587, |
| "learning_rate": 3.900882480913185e-05, |
| "loss": 0.2768, |
| "mean_token_accuracy": 0.9170741513371468, |
| "step": 226 |
| }, |
| { |
| "epoch": 1.3284457478005864, |
| "grad_norm": 1.9723648447844537, |
| "learning_rate": 3.899757135580891e-05, |
| "loss": 0.6138, |
| "mean_token_accuracy": 0.8599758371710777, |
| "step": 227 |
| }, |
| { |
| "epoch": 1.3343108504398826, |
| "grad_norm": 3.9254570692519297, |
| "learning_rate": 3.898625620816681e-05, |
| "loss": 0.3718, |
| "mean_token_accuracy": 0.887211762368679, |
| "step": 228 |
| }, |
| { |
| "epoch": 1.3401759530791788, |
| "grad_norm": 2.399705196668241, |
| "learning_rate": 3.8974879407275e-05, |
| "loss": 0.5152, |
| "mean_token_accuracy": 0.858745202422142, |
| "step": 229 |
| }, |
| { |
| "epoch": 1.3460410557184752, |
| "grad_norm": 2.5271848770288563, |
| "learning_rate": 3.896344099442663e-05, |
| "loss": 0.3902, |
| "mean_token_accuracy": 0.8907849490642548, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.3519061583577714, |
| "grad_norm": 1.9404506617545383, |
| "learning_rate": 3.895194101113855e-05, |
| "loss": 0.3174, |
| "mean_token_accuracy": 0.8844568431377411, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.3577712609970676, |
| "grad_norm": 2.0665741764137984, |
| "learning_rate": 3.894037949915104e-05, |
| "loss": 0.361, |
| "mean_token_accuracy": 0.9073267132043839, |
| "step": 232 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 1.7521385020924563, |
| "learning_rate": 3.8928756500427735e-05, |
| "loss": 0.3729, |
| "mean_token_accuracy": 0.8856314644217491, |
| "step": 233 |
| }, |
| { |
| "epoch": 1.36950146627566, |
| "grad_norm": 4.272339166861924, |
| "learning_rate": 3.89170720571554e-05, |
| "loss": 0.3891, |
| "mean_token_accuracy": 0.8926250636577606, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.3753665689149561, |
| "grad_norm": 2.0844003036828957, |
| "learning_rate": 3.890532621174387e-05, |
| "loss": 0.3451, |
| "mean_token_accuracy": 0.8915408626198769, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.3812316715542523, |
| "grad_norm": 1.9289770077407407, |
| "learning_rate": 3.8893519006825806e-05, |
| "loss": 0.3459, |
| "mean_token_accuracy": 0.8924594298005104, |
| "step": 236 |
| }, |
| { |
| "epoch": 1.3870967741935485, |
| "grad_norm": 2.2301290012638133, |
| "learning_rate": 3.88816504852566e-05, |
| "loss": 0.3396, |
| "mean_token_accuracy": 0.9005770832300186, |
| "step": 237 |
| }, |
| { |
| "epoch": 1.3929618768328447, |
| "grad_norm": 2.171361614601455, |
| "learning_rate": 3.886972069011419e-05, |
| "loss": 0.5869, |
| "mean_token_accuracy": 0.8503864109516144, |
| "step": 238 |
| }, |
| { |
| "epoch": 1.3988269794721409, |
| "grad_norm": 2.6775249334268616, |
| "learning_rate": 3.885772966469891e-05, |
| "loss": 0.366, |
| "mean_token_accuracy": 0.8903994932770729, |
| "step": 239 |
| }, |
| { |
| "epoch": 1.404692082111437, |
| "grad_norm": 4.079621344494869, |
| "learning_rate": 3.884567745253335e-05, |
| "loss": 0.2753, |
| "mean_token_accuracy": 0.9139163419604301, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.4105571847507332, |
| "grad_norm": 1.776096950687329, |
| "learning_rate": 3.8833564097362157e-05, |
| "loss": 0.4289, |
| "mean_token_accuracy": 0.8798037841916084, |
| "step": 241 |
| }, |
| { |
| "epoch": 1.4164222873900294, |
| "grad_norm": 1.834917253645093, |
| "learning_rate": 3.8821389643151924e-05, |
| "loss": 0.2886, |
| "mean_token_accuracy": 0.9188757091760635, |
| "step": 242 |
| }, |
| { |
| "epoch": 1.4222873900293256, |
| "grad_norm": 1.902514045474563, |
| "learning_rate": 3.880915413409102e-05, |
| "loss": 0.3386, |
| "mean_token_accuracy": 0.9072437360882759, |
| "step": 243 |
| }, |
| { |
| "epoch": 1.4281524926686218, |
| "grad_norm": 1.6924480184967565, |
| "learning_rate": 3.879685761458938e-05, |
| "loss": 0.4339, |
| "mean_token_accuracy": 0.8632926791906357, |
| "step": 244 |
| }, |
| { |
| "epoch": 1.434017595307918, |
| "grad_norm": 1.911568055017853, |
| "learning_rate": 3.8784500129278405e-05, |
| "loss": 0.2714, |
| "mean_token_accuracy": 0.9203036949038506, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.4398826979472141, |
| "grad_norm": 1.9969412513036282, |
| "learning_rate": 3.877208172301079e-05, |
| "loss": 0.4284, |
| "mean_token_accuracy": 0.8679738715291023, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.4457478005865103, |
| "grad_norm": 1.787789982945381, |
| "learning_rate": 3.875960244086032e-05, |
| "loss": 0.345, |
| "mean_token_accuracy": 0.9001687616109848, |
| "step": 247 |
| }, |
| { |
| "epoch": 1.4516129032258065, |
| "grad_norm": 2.1914713980298757, |
| "learning_rate": 3.8747062328121756e-05, |
| "loss": 0.3879, |
| "mean_token_accuracy": 0.8989882245659828, |
| "step": 248 |
| }, |
| { |
| "epoch": 1.4574780058651027, |
| "grad_norm": 1.7197818602016577, |
| "learning_rate": 3.873446143031064e-05, |
| "loss": 0.2785, |
| "mean_token_accuracy": 0.9228793308138847, |
| "step": 249 |
| }, |
| { |
| "epoch": 1.4633431085043989, |
| "grad_norm": 1.9165780404977792, |
| "learning_rate": 3.872179979316314e-05, |
| "loss": 0.3064, |
| "mean_token_accuracy": 0.908599853515625, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.469208211143695, |
| "grad_norm": 1.6704715586382999, |
| "learning_rate": 3.870907746263589e-05, |
| "loss": 0.2689, |
| "mean_token_accuracy": 0.9201952144503593, |
| "step": 251 |
| }, |
| { |
| "epoch": 1.4750733137829912, |
| "grad_norm": 1.6995923765648426, |
| "learning_rate": 3.869629448490582e-05, |
| "loss": 0.3333, |
| "mean_token_accuracy": 0.9088203087449074, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.4809384164222874, |
| "grad_norm": 1.564555577131926, |
| "learning_rate": 3.868345090636995e-05, |
| "loss": 0.3582, |
| "mean_token_accuracy": 0.9006411507725716, |
| "step": 253 |
| }, |
| { |
| "epoch": 1.4868035190615836, |
| "grad_norm": 1.944612250081467, |
| "learning_rate": 3.867054677364531e-05, |
| "loss": 0.347, |
| "mean_token_accuracy": 0.8948578387498856, |
| "step": 254 |
| }, |
| { |
| "epoch": 1.4926686217008798, |
| "grad_norm": 1.9767571384054532, |
| "learning_rate": 3.865758213356868e-05, |
| "loss": 0.3588, |
| "mean_token_accuracy": 0.892326109111309, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.498533724340176, |
| "grad_norm": 2.1786507345414625, |
| "learning_rate": 3.8644557033196456e-05, |
| "loss": 0.3443, |
| "mean_token_accuracy": 0.900772362947464, |
| "step": 256 |
| }, |
| { |
| "epoch": 1.5043988269794721, |
| "grad_norm": 1.727787016452984, |
| "learning_rate": 3.8631471519804514e-05, |
| "loss": 0.3939, |
| "mean_token_accuracy": 0.899748906493187, |
| "step": 257 |
| }, |
| { |
| "epoch": 1.5102639296187683, |
| "grad_norm": 2.2435616485276584, |
| "learning_rate": 3.861832564088797e-05, |
| "loss": 0.4526, |
| "mean_token_accuracy": 0.8786605149507523, |
| "step": 258 |
| }, |
| { |
| "epoch": 1.5161290322580645, |
| "grad_norm": 2.1226358626723485, |
| "learning_rate": 3.860511944416105e-05, |
| "loss": 0.2974, |
| "mean_token_accuracy": 0.911198802292347, |
| "step": 259 |
| }, |
| { |
| "epoch": 1.5219941348973607, |
| "grad_norm": 1.9277458511435361, |
| "learning_rate": 3.859185297755693e-05, |
| "loss": 0.3021, |
| "mean_token_accuracy": 0.9092141538858414, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.5278592375366569, |
| "grad_norm": 1.5812796708802024, |
| "learning_rate": 3.857852628922751e-05, |
| "loss": 0.2656, |
| "mean_token_accuracy": 0.9256365522742271, |
| "step": 261 |
| }, |
| { |
| "epoch": 1.533724340175953, |
| "grad_norm": 2.037937113721398, |
| "learning_rate": 3.856513942754329e-05, |
| "loss": 0.3173, |
| "mean_token_accuracy": 0.904233492910862, |
| "step": 262 |
| }, |
| { |
| "epoch": 1.5395894428152492, |
| "grad_norm": 1.6287239034648493, |
| "learning_rate": 3.8551692441093183e-05, |
| "loss": 0.2402, |
| "mean_token_accuracy": 0.927992507815361, |
| "step": 263 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 1.7234547040810766, |
| "learning_rate": 3.85381853786843e-05, |
| "loss": 0.4069, |
| "mean_token_accuracy": 0.8724810630083084, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.5513196480938416, |
| "grad_norm": 1.9738399030452272, |
| "learning_rate": 3.852461828934184e-05, |
| "loss": 0.3796, |
| "mean_token_accuracy": 0.8994789123535156, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.5571847507331378, |
| "grad_norm": 1.7419666030613636, |
| "learning_rate": 3.851099122230885e-05, |
| "loss": 0.2919, |
| "mean_token_accuracy": 0.9129809066653252, |
| "step": 266 |
| }, |
| { |
| "epoch": 1.563049853372434, |
| "grad_norm": 1.628062291876651, |
| "learning_rate": 3.849730422704608e-05, |
| "loss": 0.4191, |
| "mean_token_accuracy": 0.8906111344695091, |
| "step": 267 |
| }, |
| { |
| "epoch": 1.5689149560117301, |
| "grad_norm": 2.0803530282960305, |
| "learning_rate": 3.84835573532318e-05, |
| "loss": 0.2656, |
| "mean_token_accuracy": 0.9183074086904526, |
| "step": 268 |
| }, |
| { |
| "epoch": 1.5747800586510263, |
| "grad_norm": 1.8607789222018924, |
| "learning_rate": 3.84697506507616e-05, |
| "loss": 0.3953, |
| "mean_token_accuracy": 0.8888256177306175, |
| "step": 269 |
| }, |
| { |
| "epoch": 1.5806451612903225, |
| "grad_norm": 2.130794994174186, |
| "learning_rate": 3.845588416974824e-05, |
| "loss": 0.3848, |
| "mean_token_accuracy": 0.9071919843554497, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.5865102639296187, |
| "grad_norm": 1.9020220222823165, |
| "learning_rate": 3.844195796052144e-05, |
| "loss": 0.3578, |
| "mean_token_accuracy": 0.9020521864295006, |
| "step": 271 |
| }, |
| { |
| "epoch": 1.5923753665689149, |
| "grad_norm": 1.8658553019399349, |
| "learning_rate": 3.8427972073627724e-05, |
| "loss": 0.5285, |
| "mean_token_accuracy": 0.8661686107516289, |
| "step": 272 |
| }, |
| { |
| "epoch": 1.598240469208211, |
| "grad_norm": 2.0730360398150642, |
| "learning_rate": 3.841392655983021e-05, |
| "loss": 0.2402, |
| "mean_token_accuracy": 0.9231050238013268, |
| "step": 273 |
| }, |
| { |
| "epoch": 1.6041055718475072, |
| "grad_norm": 1.34555292540441, |
| "learning_rate": 3.8399821470108444e-05, |
| "loss": 0.2042, |
| "mean_token_accuracy": 0.9374109655618668, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.6099706744868034, |
| "grad_norm": 1.9527205991987846, |
| "learning_rate": 3.838565685565819e-05, |
| "loss": 0.4687, |
| "mean_token_accuracy": 0.8773292899131775, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.6158357771260996, |
| "grad_norm": 1.8883224403836536, |
| "learning_rate": 3.8371432767891295e-05, |
| "loss": 0.3526, |
| "mean_token_accuracy": 0.903610423207283, |
| "step": 276 |
| }, |
| { |
| "epoch": 1.6217008797653958, |
| "grad_norm": 1.7546704899486176, |
| "learning_rate": 3.8357149258435444e-05, |
| "loss": 0.2904, |
| "mean_token_accuracy": 0.9173143953084946, |
| "step": 277 |
| }, |
| { |
| "epoch": 1.627565982404692, |
| "grad_norm": 2.0511854336671473, |
| "learning_rate": 3.8342806379134005e-05, |
| "loss": 0.4361, |
| "mean_token_accuracy": 0.8790148869156837, |
| "step": 278 |
| }, |
| { |
| "epoch": 1.6334310850439882, |
| "grad_norm": 2.0568091503722035, |
| "learning_rate": 3.8328404182045854e-05, |
| "loss": 0.3654, |
| "mean_token_accuracy": 0.9027048945426941, |
| "step": 279 |
| }, |
| { |
| "epoch": 1.6392961876832843, |
| "grad_norm": 2.0230684624428235, |
| "learning_rate": 3.831394271944512e-05, |
| "loss": 0.358, |
| "mean_token_accuracy": 0.9075604230165482, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.6451612903225805, |
| "grad_norm": 1.894319774470119, |
| "learning_rate": 3.82994220438211e-05, |
| "loss": 0.3609, |
| "mean_token_accuracy": 0.8942530304193497, |
| "step": 281 |
| }, |
| { |
| "epoch": 1.6510263929618767, |
| "grad_norm": 1.8981276803059295, |
| "learning_rate": 3.828484220787797e-05, |
| "loss": 0.3854, |
| "mean_token_accuracy": 0.89190324395895, |
| "step": 282 |
| }, |
| { |
| "epoch": 1.6568914956011729, |
| "grad_norm": 2.2732377477966326, |
| "learning_rate": 3.8270203264534644e-05, |
| "loss": 0.4659, |
| "mean_token_accuracy": 0.8762017115950584, |
| "step": 283 |
| }, |
| { |
| "epoch": 1.662756598240469, |
| "grad_norm": 1.836975254349824, |
| "learning_rate": 3.8255505266924585e-05, |
| "loss": 0.3508, |
| "mean_token_accuracy": 0.897898942232132, |
| "step": 284 |
| }, |
| { |
| "epoch": 1.6686217008797652, |
| "grad_norm": 1.8958858575917799, |
| "learning_rate": 3.824074826839557e-05, |
| "loss": 0.2678, |
| "mean_token_accuracy": 0.9237991869449615, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.6744868035190614, |
| "grad_norm": 2.4908800796256765, |
| "learning_rate": 3.822593232250956e-05, |
| "loss": 0.4807, |
| "mean_token_accuracy": 0.8728378862142563, |
| "step": 286 |
| }, |
| { |
| "epoch": 1.6803519061583576, |
| "grad_norm": 2.449596026859127, |
| "learning_rate": 3.8211057483042446e-05, |
| "loss": 0.5197, |
| "mean_token_accuracy": 0.8701219037175179, |
| "step": 287 |
| }, |
| { |
| "epoch": 1.6862170087976538, |
| "grad_norm": 2.126362403478398, |
| "learning_rate": 3.8196123803983895e-05, |
| "loss": 0.3782, |
| "mean_token_accuracy": 0.8976033478975296, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.6920821114369502, |
| "grad_norm": 1.9552263402442664, |
| "learning_rate": 3.818113133953712e-05, |
| "loss": 0.3354, |
| "mean_token_accuracy": 0.9046521782875061, |
| "step": 289 |
| }, |
| { |
| "epoch": 1.6979472140762464, |
| "grad_norm": 1.559218994516208, |
| "learning_rate": 3.816608014411872e-05, |
| "loss": 0.2451, |
| "mean_token_accuracy": 0.9280602782964706, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.7038123167155426, |
| "grad_norm": 1.5955884312797561, |
| "learning_rate": 3.815097027235845e-05, |
| "loss": 0.3444, |
| "mean_token_accuracy": 0.8998289778828621, |
| "step": 291 |
| }, |
| { |
| "epoch": 1.7096774193548387, |
| "grad_norm": 1.923537625514968, |
| "learning_rate": 3.813580177909906e-05, |
| "loss": 0.2937, |
| "mean_token_accuracy": 0.9103951752185822, |
| "step": 292 |
| }, |
| { |
| "epoch": 1.715542521994135, |
| "grad_norm": 1.627753503508524, |
| "learning_rate": 3.8120574719396023e-05, |
| "loss": 0.3034, |
| "mean_token_accuracy": 0.918914794921875, |
| "step": 293 |
| }, |
| { |
| "epoch": 1.721407624633431, |
| "grad_norm": 2.3014152350526924, |
| "learning_rate": 3.810528914851745e-05, |
| "loss": 0.4585, |
| "mean_token_accuracy": 0.878827765583992, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 1.9488757659462697, |
| "learning_rate": 3.808994512194376e-05, |
| "loss": 0.3841, |
| "mean_token_accuracy": 0.8855108916759491, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.7331378299120235, |
| "grad_norm": 1.8510675195890514, |
| "learning_rate": 3.807454269536758e-05, |
| "loss": 0.4001, |
| "mean_token_accuracy": 0.8860180526971817, |
| "step": 296 |
| }, |
| { |
| "epoch": 1.7390029325513197, |
| "grad_norm": 1.9187885250043828, |
| "learning_rate": 3.805908192469351e-05, |
| "loss": 0.2789, |
| "mean_token_accuracy": 0.9083529412746429, |
| "step": 297 |
| }, |
| { |
| "epoch": 1.7448680351906158, |
| "grad_norm": 1.9174627349215367, |
| "learning_rate": 3.80435628660379e-05, |
| "loss": 0.3674, |
| "mean_token_accuracy": 0.8953339979052544, |
| "step": 298 |
| }, |
| { |
| "epoch": 1.750733137829912, |
| "grad_norm": 2.0113269897331416, |
| "learning_rate": 3.802798557572867e-05, |
| "loss": 0.3684, |
| "mean_token_accuracy": 0.8994771614670753, |
| "step": 299 |
| }, |
| { |
| "epoch": 1.7565982404692082, |
| "grad_norm": 2.2118619867672207, |
| "learning_rate": 3.801235011030506e-05, |
| "loss": 0.3636, |
| "mean_token_accuracy": 0.896511547267437, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.7624633431085044, |
| "grad_norm": 1.7539387925625358, |
| "learning_rate": 3.799665652651754e-05, |
| "loss": 0.2227, |
| "mean_token_accuracy": 0.9379914700984955, |
| "step": 301 |
| }, |
| { |
| "epoch": 1.7683284457478006, |
| "grad_norm": 1.6438481796571975, |
| "learning_rate": 3.7980904881327446e-05, |
| "loss": 0.3014, |
| "mean_token_accuracy": 0.9185338690876961, |
| "step": 302 |
| }, |
| { |
| "epoch": 1.7741935483870968, |
| "grad_norm": 1.9612873325388276, |
| "learning_rate": 3.796509523190691e-05, |
| "loss": 0.3237, |
| "mean_token_accuracy": 0.9047940298914909, |
| "step": 303 |
| }, |
| { |
| "epoch": 1.780058651026393, |
| "grad_norm": 1.7622576932704024, |
| "learning_rate": 3.794922763563857e-05, |
| "loss": 0.2483, |
| "mean_token_accuracy": 0.9288651943206787, |
| "step": 304 |
| }, |
| { |
| "epoch": 1.7859237536656891, |
| "grad_norm": 2.176660314874238, |
| "learning_rate": 3.793330215011538e-05, |
| "loss": 0.3704, |
| "mean_token_accuracy": 0.9133122861385345, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.7917888563049853, |
| "grad_norm": 1.8647037847416894, |
| "learning_rate": 3.791731883314043e-05, |
| "loss": 0.3288, |
| "mean_token_accuracy": 0.9017655923962593, |
| "step": 306 |
| }, |
| { |
| "epoch": 1.7976539589442815, |
| "grad_norm": 2.0287011162165647, |
| "learning_rate": 3.790127774272671e-05, |
| "loss": 0.2683, |
| "mean_token_accuracy": 0.9209354743361473, |
| "step": 307 |
| }, |
| { |
| "epoch": 1.8035190615835777, |
| "grad_norm": 1.5719010823135073, |
| "learning_rate": 3.7885178937096884e-05, |
| "loss": 0.4283, |
| "mean_token_accuracy": 0.8839877769351006, |
| "step": 308 |
| }, |
| { |
| "epoch": 1.8093841642228738, |
| "grad_norm": 2.060543329624031, |
| "learning_rate": 3.7869022474683125e-05, |
| "loss": 0.4768, |
| "mean_token_accuracy": 0.8875997290015221, |
| "step": 309 |
| }, |
| { |
| "epoch": 1.8152492668621703, |
| "grad_norm": 2.350189411212048, |
| "learning_rate": 3.7852808414126876e-05, |
| "loss": 0.4034, |
| "mean_token_accuracy": 0.8856799080967903, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.8211143695014664, |
| "grad_norm": 1.5440198943153403, |
| "learning_rate": 3.783653681427861e-05, |
| "loss": 0.2551, |
| "mean_token_accuracy": 0.9266308322548866, |
| "step": 311 |
| }, |
| { |
| "epoch": 1.8269794721407626, |
| "grad_norm": 2.8616037129091634, |
| "learning_rate": 3.7820207734197676e-05, |
| "loss": 0.3565, |
| "mean_token_accuracy": 0.8989051878452301, |
| "step": 312 |
| }, |
| { |
| "epoch": 1.8328445747800588, |
| "grad_norm": 1.655020538470568, |
| "learning_rate": 3.780382123315203e-05, |
| "loss": 0.2381, |
| "mean_token_accuracy": 0.932477205991745, |
| "step": 313 |
| }, |
| { |
| "epoch": 1.838709677419355, |
| "grad_norm": 1.634046108030118, |
| "learning_rate": 3.778737737061807e-05, |
| "loss": 0.3528, |
| "mean_token_accuracy": 0.901824451982975, |
| "step": 314 |
| }, |
| { |
| "epoch": 1.8445747800586512, |
| "grad_norm": 1.8055968405353495, |
| "learning_rate": 3.777087620628035e-05, |
| "loss": 0.2607, |
| "mean_token_accuracy": 0.9298326820135117, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.8504398826979473, |
| "grad_norm": 1.565331504140896, |
| "learning_rate": 3.775431780003145e-05, |
| "loss": 0.2588, |
| "mean_token_accuracy": 0.9298610910773277, |
| "step": 316 |
| }, |
| { |
| "epoch": 1.8563049853372435, |
| "grad_norm": 2.4969352173136725, |
| "learning_rate": 3.7737702211971684e-05, |
| "loss": 0.2831, |
| "mean_token_accuracy": 0.9310391396284103, |
| "step": 317 |
| }, |
| { |
| "epoch": 1.8621700879765397, |
| "grad_norm": 1.6415395253616827, |
| "learning_rate": 3.772102950240895e-05, |
| "loss": 0.2813, |
| "mean_token_accuracy": 0.9285251498222351, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.868035190615836, |
| "grad_norm": 1.9305348853876765, |
| "learning_rate": 3.770429973185842e-05, |
| "loss": 0.3427, |
| "mean_token_accuracy": 0.9079779386520386, |
| "step": 319 |
| }, |
| { |
| "epoch": 1.873900293255132, |
| "grad_norm": 1.9953718686593638, |
| "learning_rate": 3.768751296104243e-05, |
| "loss": 0.2254, |
| "mean_token_accuracy": 0.9326372891664505, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.8797653958944283, |
| "grad_norm": 1.320578324916696, |
| "learning_rate": 3.767066925089017e-05, |
| "loss": 0.3231, |
| "mean_token_accuracy": 0.9050979241728783, |
| "step": 321 |
| }, |
| { |
| "epoch": 1.8856304985337244, |
| "grad_norm": 1.630307723589402, |
| "learning_rate": 3.765376866253749e-05, |
| "loss": 0.2295, |
| "mean_token_accuracy": 0.9237135499715805, |
| "step": 322 |
| }, |
| { |
| "epoch": 1.8914956011730206, |
| "grad_norm": 1.8687730597426178, |
| "learning_rate": 3.763681125732672e-05, |
| "loss": 0.2979, |
| "mean_token_accuracy": 0.9019790291786194, |
| "step": 323 |
| }, |
| { |
| "epoch": 1.8973607038123168, |
| "grad_norm": 1.9421616274693134, |
| "learning_rate": 3.7619797096806386e-05, |
| "loss": 0.3197, |
| "mean_token_accuracy": 0.9111294597387314, |
| "step": 324 |
| }, |
| { |
| "epoch": 1.903225806451613, |
| "grad_norm": 1.7208098178259272, |
| "learning_rate": 3.7602726242731016e-05, |
| "loss": 0.366, |
| "mean_token_accuracy": 0.9027081355452538, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 2.006658041095116, |
| "learning_rate": 3.758559875706092e-05, |
| "loss": 0.2679, |
| "mean_token_accuracy": 0.9249737039208412, |
| "step": 326 |
| }, |
| { |
| "epoch": 1.9149560117302054, |
| "grad_norm": 1.4026289668561007, |
| "learning_rate": 3.756841470196195e-05, |
| "loss": 0.3585, |
| "mean_token_accuracy": 0.9043615832924843, |
| "step": 327 |
| }, |
| { |
| "epoch": 1.9208211143695015, |
| "grad_norm": 1.694343333897619, |
| "learning_rate": 3.7551174139805284e-05, |
| "loss": 0.3979, |
| "mean_token_accuracy": 0.8909201622009277, |
| "step": 328 |
| }, |
| { |
| "epoch": 1.9266862170087977, |
| "grad_norm": 1.8540786148822945, |
| "learning_rate": 3.75338771331672e-05, |
| "loss": 0.369, |
| "mean_token_accuracy": 0.8931919634342194, |
| "step": 329 |
| }, |
| { |
| "epoch": 1.932551319648094, |
| "grad_norm": 1.8043389433770838, |
| "learning_rate": 3.7516523744828856e-05, |
| "loss": 0.4165, |
| "mean_token_accuracy": 0.8895757496356964, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.93841642228739, |
| "grad_norm": 1.7007383330359485, |
| "learning_rate": 3.7499114037776036e-05, |
| "loss": 0.3277, |
| "mean_token_accuracy": 0.8950676620006561, |
| "step": 331 |
| }, |
| { |
| "epoch": 1.9442815249266863, |
| "grad_norm": 1.8371484503426208, |
| "learning_rate": 3.748164807519894e-05, |
| "loss": 0.4762, |
| "mean_token_accuracy": 0.8785777390003204, |
| "step": 332 |
| }, |
| { |
| "epoch": 1.9501466275659824, |
| "grad_norm": 1.9576933523351108, |
| "learning_rate": 3.746412592049197e-05, |
| "loss": 0.3305, |
| "mean_token_accuracy": 0.9062154516577721, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.9560117302052786, |
| "grad_norm": 1.4572901805688738, |
| "learning_rate": 3.7446547637253464e-05, |
| "loss": 0.2221, |
| "mean_token_accuracy": 0.9385078474879265, |
| "step": 334 |
| }, |
| { |
| "epoch": 1.9618768328445748, |
| "grad_norm": 1.7468272756441137, |
| "learning_rate": 3.742891328928549e-05, |
| "loss": 0.3222, |
| "mean_token_accuracy": 0.9129680246114731, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.967741935483871, |
| "grad_norm": 1.273850432393817, |
| "learning_rate": 3.74112229405936e-05, |
| "loss": 0.2864, |
| "mean_token_accuracy": 0.9150940924882889, |
| "step": 336 |
| }, |
| { |
| "epoch": 1.9736070381231672, |
| "grad_norm": 1.6128401848475018, |
| "learning_rate": 3.739347665538664e-05, |
| "loss": 0.3245, |
| "mean_token_accuracy": 0.9111495912075043, |
| "step": 337 |
| }, |
| { |
| "epoch": 1.9794721407624634, |
| "grad_norm": 1.8812573264821617, |
| "learning_rate": 3.7375674498076445e-05, |
| "loss": 0.4184, |
| "mean_token_accuracy": 0.8886971697211266, |
| "step": 338 |
| }, |
| { |
| "epoch": 1.9853372434017595, |
| "grad_norm": 2.12365255006061, |
| "learning_rate": 3.7357816533277646e-05, |
| "loss": 0.3149, |
| "mean_token_accuracy": 0.9159363061189651, |
| "step": 339 |
| }, |
| { |
| "epoch": 1.9912023460410557, |
| "grad_norm": 1.6503920768703404, |
| "learning_rate": 3.733990282580745e-05, |
| "loss": 0.3169, |
| "mean_token_accuracy": 0.9083178415894508, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.997067448680352, |
| "grad_norm": 1.7743070899939994, |
| "learning_rate": 3.732193344068539e-05, |
| "loss": 0.3129, |
| "mean_token_accuracy": 0.9127020239830017, |
| "step": 341 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.5233914351994167, |
| "learning_rate": 3.7303908443133054e-05, |
| "loss": 0.2022, |
| "mean_token_accuracy": 0.9405500143766403, |
| "step": 342 |
| }, |
| { |
| "epoch": 2.005865102639296, |
| "grad_norm": 1.6693513338029358, |
| "learning_rate": 3.728582789857393e-05, |
| "loss": 0.2042, |
| "mean_token_accuracy": 0.9472683444619179, |
| "step": 343 |
| }, |
| { |
| "epoch": 2.0117302052785924, |
| "grad_norm": 1.6340282087097624, |
| "learning_rate": 3.726769187263308e-05, |
| "loss": 0.2367, |
| "mean_token_accuracy": 0.9289553239941597, |
| "step": 344 |
| }, |
| { |
| "epoch": 2.0175953079178885, |
| "grad_norm": 1.2768152185347872, |
| "learning_rate": 3.724950043113695e-05, |
| "loss": 0.1532, |
| "mean_token_accuracy": 0.9543287456035614, |
| "step": 345 |
| }, |
| { |
| "epoch": 2.0234604105571847, |
| "grad_norm": 1.4037689102542255, |
| "learning_rate": 3.723125364011313e-05, |
| "loss": 0.1561, |
| "mean_token_accuracy": 0.9580844938755035, |
| "step": 346 |
| }, |
| { |
| "epoch": 2.029325513196481, |
| "grad_norm": 1.4427756644988328, |
| "learning_rate": 3.7212951565790094e-05, |
| "loss": 0.1636, |
| "mean_token_accuracy": 0.9480728134512901, |
| "step": 347 |
| }, |
| { |
| "epoch": 2.035190615835777, |
| "grad_norm": 1.7720364579189496, |
| "learning_rate": 3.7194594274597e-05, |
| "loss": 0.1859, |
| "mean_token_accuracy": 0.940785750746727, |
| "step": 348 |
| }, |
| { |
| "epoch": 2.0410557184750733, |
| "grad_norm": 1.6271299438235751, |
| "learning_rate": 3.7176181833163385e-05, |
| "loss": 0.1929, |
| "mean_token_accuracy": 0.9450634941458702, |
| "step": 349 |
| }, |
| { |
| "epoch": 2.0469208211143695, |
| "grad_norm": 1.7097076323820675, |
| "learning_rate": 3.7157714308318966e-05, |
| "loss": 0.1878, |
| "mean_token_accuracy": 0.948820598423481, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.0527859237536656, |
| "grad_norm": 2.0125156134083753, |
| "learning_rate": 3.713919176709343e-05, |
| "loss": 0.217, |
| "mean_token_accuracy": 0.9398675486445427, |
| "step": 351 |
| }, |
| { |
| "epoch": 2.058651026392962, |
| "grad_norm": 1.513801237369741, |
| "learning_rate": 3.712061427671609e-05, |
| "loss": 0.1608, |
| "mean_token_accuracy": 0.9536798968911171, |
| "step": 352 |
| }, |
| { |
| "epoch": 2.064516129032258, |
| "grad_norm": 1.7205171569969244, |
| "learning_rate": 3.710198190461575e-05, |
| "loss": 0.1991, |
| "mean_token_accuracy": 0.9481086954474449, |
| "step": 353 |
| }, |
| { |
| "epoch": 2.070381231671554, |
| "grad_norm": 1.6612412428232648, |
| "learning_rate": 3.7083294718420394e-05, |
| "loss": 0.1958, |
| "mean_token_accuracy": 0.94148388504982, |
| "step": 354 |
| }, |
| { |
| "epoch": 2.0762463343108504, |
| "grad_norm": 1.6267501719327955, |
| "learning_rate": 3.706455278595696e-05, |
| "loss": 0.1845, |
| "mean_token_accuracy": 0.9427782371640205, |
| "step": 355 |
| }, |
| { |
| "epoch": 2.0821114369501466, |
| "grad_norm": 1.5866786415809722, |
| "learning_rate": 3.7045756175251086e-05, |
| "loss": 0.1861, |
| "mean_token_accuracy": 0.942706435918808, |
| "step": 356 |
| }, |
| { |
| "epoch": 2.0879765395894427, |
| "grad_norm": 1.5012592202625572, |
| "learning_rate": 3.7026904954526884e-05, |
| "loss": 0.161, |
| "mean_token_accuracy": 0.9514438956975937, |
| "step": 357 |
| }, |
| { |
| "epoch": 2.093841642228739, |
| "grad_norm": 1.341766760682961, |
| "learning_rate": 3.7007999192206676e-05, |
| "loss": 0.1527, |
| "mean_token_accuracy": 0.9533711373806, |
| "step": 358 |
| }, |
| { |
| "epoch": 2.099706744868035, |
| "grad_norm": 1.320127310766138, |
| "learning_rate": 3.698903895691073e-05, |
| "loss": 0.1811, |
| "mean_token_accuracy": 0.9414249658584595, |
| "step": 359 |
| }, |
| { |
| "epoch": 2.1055718475073313, |
| "grad_norm": 1.6248661841477403, |
| "learning_rate": 3.697002431745706e-05, |
| "loss": 0.1874, |
| "mean_token_accuracy": 0.9447718486189842, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.1114369501466275, |
| "grad_norm": 1.6590729632222045, |
| "learning_rate": 3.695095534286111e-05, |
| "loss": 0.201, |
| "mean_token_accuracy": 0.945906400680542, |
| "step": 361 |
| }, |
| { |
| "epoch": 2.1173020527859236, |
| "grad_norm": 1.5275030906913138, |
| "learning_rate": 3.693183210233557e-05, |
| "loss": 0.1859, |
| "mean_token_accuracy": 0.9475782960653305, |
| "step": 362 |
| }, |
| { |
| "epoch": 2.12316715542522, |
| "grad_norm": 1.982158053574525, |
| "learning_rate": 3.691265466529007e-05, |
| "loss": 0.1766, |
| "mean_token_accuracy": 0.9372566938400269, |
| "step": 363 |
| }, |
| { |
| "epoch": 2.129032258064516, |
| "grad_norm": 1.9819879546520034, |
| "learning_rate": 3.689342310133097e-05, |
| "loss": 0.1494, |
| "mean_token_accuracy": 0.9539884477853775, |
| "step": 364 |
| }, |
| { |
| "epoch": 2.134897360703812, |
| "grad_norm": 1.5751039070401411, |
| "learning_rate": 3.687413748026108e-05, |
| "loss": 0.1735, |
| "mean_token_accuracy": 0.9495319053530693, |
| "step": 365 |
| }, |
| { |
| "epoch": 2.1407624633431084, |
| "grad_norm": 1.4585998236912616, |
| "learning_rate": 3.68547978720794e-05, |
| "loss": 0.1734, |
| "mean_token_accuracy": 0.9489102214574814, |
| "step": 366 |
| }, |
| { |
| "epoch": 2.1466275659824046, |
| "grad_norm": 1.5221638866423055, |
| "learning_rate": 3.683540434698093e-05, |
| "loss": 0.1723, |
| "mean_token_accuracy": 0.9449229016900063, |
| "step": 367 |
| }, |
| { |
| "epoch": 2.1524926686217007, |
| "grad_norm": 1.481044246133322, |
| "learning_rate": 3.681595697535629e-05, |
| "loss": 0.1545, |
| "mean_token_accuracy": 0.9535570293664932, |
| "step": 368 |
| }, |
| { |
| "epoch": 2.158357771260997, |
| "grad_norm": 1.5478884613470323, |
| "learning_rate": 3.6796455827791614e-05, |
| "loss": 0.16, |
| "mean_token_accuracy": 0.9515524953603745, |
| "step": 369 |
| }, |
| { |
| "epoch": 2.164222873900293, |
| "grad_norm": 1.5557336850213985, |
| "learning_rate": 3.677690097506819e-05, |
| "loss": 0.1896, |
| "mean_token_accuracy": 0.9467919543385506, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.1700879765395893, |
| "grad_norm": 1.361152442880772, |
| "learning_rate": 3.6757292488162224e-05, |
| "loss": 0.1785, |
| "mean_token_accuracy": 0.9459036141633987, |
| "step": 371 |
| }, |
| { |
| "epoch": 2.1759530791788855, |
| "grad_norm": 1.6123633223927731, |
| "learning_rate": 3.673763043824461e-05, |
| "loss": 0.2162, |
| "mean_token_accuracy": 0.9359398260712624, |
| "step": 372 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 1.812017533620379, |
| "learning_rate": 3.671791489668065e-05, |
| "loss": 0.2023, |
| "mean_token_accuracy": 0.9429754018783569, |
| "step": 373 |
| }, |
| { |
| "epoch": 2.187683284457478, |
| "grad_norm": 1.6502036792084445, |
| "learning_rate": 3.6698145935029794e-05, |
| "loss": 0.1845, |
| "mean_token_accuracy": 0.9518390074372292, |
| "step": 374 |
| }, |
| { |
| "epoch": 2.193548387096774, |
| "grad_norm": 1.545266807845691, |
| "learning_rate": 3.66783236250454e-05, |
| "loss": 0.1823, |
| "mean_token_accuracy": 0.9467039182782173, |
| "step": 375 |
| }, |
| { |
| "epoch": 2.19941348973607, |
| "grad_norm": 1.6477618113035692, |
| "learning_rate": 3.665844803867443e-05, |
| "loss": 0.2145, |
| "mean_token_accuracy": 0.9425032809376717, |
| "step": 376 |
| }, |
| { |
| "epoch": 2.2052785923753664, |
| "grad_norm": 1.5604687026013282, |
| "learning_rate": 3.663851924805725e-05, |
| "loss": 0.1997, |
| "mean_token_accuracy": 0.9416602700948715, |
| "step": 377 |
| }, |
| { |
| "epoch": 2.2111436950146626, |
| "grad_norm": 1.550988527543912, |
| "learning_rate": 3.66185373255273e-05, |
| "loss": 0.1757, |
| "mean_token_accuracy": 0.9436255395412445, |
| "step": 378 |
| }, |
| { |
| "epoch": 2.2170087976539588, |
| "grad_norm": 1.2327976923264585, |
| "learning_rate": 3.6598502343610906e-05, |
| "loss": 0.1482, |
| "mean_token_accuracy": 0.9562384858727455, |
| "step": 379 |
| }, |
| { |
| "epoch": 2.222873900293255, |
| "grad_norm": 1.6237415577928969, |
| "learning_rate": 3.657841437502697e-05, |
| "loss": 0.2253, |
| "mean_token_accuracy": 0.9289913475513458, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.228739002932551, |
| "grad_norm": 1.8607660215120763, |
| "learning_rate": 3.6558273492686686e-05, |
| "loss": 0.2089, |
| "mean_token_accuracy": 0.9374095126986504, |
| "step": 381 |
| }, |
| { |
| "epoch": 2.2346041055718473, |
| "grad_norm": 1.360745609090226, |
| "learning_rate": 3.6538079769693334e-05, |
| "loss": 0.1671, |
| "mean_token_accuracy": 0.9510230720043182, |
| "step": 382 |
| }, |
| { |
| "epoch": 2.2404692082111435, |
| "grad_norm": 1.257785870906961, |
| "learning_rate": 3.6517833279341954e-05, |
| "loss": 0.1522, |
| "mean_token_accuracy": 0.9563170224428177, |
| "step": 383 |
| }, |
| { |
| "epoch": 2.2463343108504397, |
| "grad_norm": 1.3172632320528042, |
| "learning_rate": 3.649753409511916e-05, |
| "loss": 0.1561, |
| "mean_token_accuracy": 0.9573013335466385, |
| "step": 384 |
| }, |
| { |
| "epoch": 2.252199413489736, |
| "grad_norm": 1.5928604842461005, |
| "learning_rate": 3.6477182290702766e-05, |
| "loss": 0.1973, |
| "mean_token_accuracy": 0.9359570667147636, |
| "step": 385 |
| }, |
| { |
| "epoch": 2.258064516129032, |
| "grad_norm": 1.6603723493729567, |
| "learning_rate": 3.645677793996161e-05, |
| "loss": 0.1963, |
| "mean_token_accuracy": 0.9404471442103386, |
| "step": 386 |
| }, |
| { |
| "epoch": 2.263929618768328, |
| "grad_norm": 1.6206060274389453, |
| "learning_rate": 3.643632111695525e-05, |
| "loss": 0.1939, |
| "mean_token_accuracy": 0.9425263479351997, |
| "step": 387 |
| }, |
| { |
| "epoch": 2.2697947214076244, |
| "grad_norm": 1.6657671791715885, |
| "learning_rate": 3.6415811895933685e-05, |
| "loss": 0.1856, |
| "mean_token_accuracy": 0.9430495277047157, |
| "step": 388 |
| }, |
| { |
| "epoch": 2.2756598240469206, |
| "grad_norm": 1.2712705911697364, |
| "learning_rate": 3.639525035133712e-05, |
| "loss": 0.1552, |
| "mean_token_accuracy": 0.9557842835783958, |
| "step": 389 |
| }, |
| { |
| "epoch": 2.281524926686217, |
| "grad_norm": 1.5205774866081296, |
| "learning_rate": 3.637463655779563e-05, |
| "loss": 0.1895, |
| "mean_token_accuracy": 0.9432679936289787, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.2873900293255134, |
| "grad_norm": 1.4033621614345595, |
| "learning_rate": 3.6353970590128975e-05, |
| "loss": 0.1686, |
| "mean_token_accuracy": 0.9537108987569809, |
| "step": 391 |
| }, |
| { |
| "epoch": 2.2932551319648096, |
| "grad_norm": 1.5519352504831416, |
| "learning_rate": 3.633325252334628e-05, |
| "loss": 0.1778, |
| "mean_token_accuracy": 0.9453356117010117, |
| "step": 392 |
| }, |
| { |
| "epoch": 2.2991202346041058, |
| "grad_norm": 1.5128374434884113, |
| "learning_rate": 3.6312482432645746e-05, |
| "loss": 0.1947, |
| "mean_token_accuracy": 0.9424128010869026, |
| "step": 393 |
| }, |
| { |
| "epoch": 2.304985337243402, |
| "grad_norm": 1.390174798784679, |
| "learning_rate": 3.6291660393414414e-05, |
| "loss": 0.1598, |
| "mean_token_accuracy": 0.9516776651144028, |
| "step": 394 |
| }, |
| { |
| "epoch": 2.310850439882698, |
| "grad_norm": 1.5333512021648155, |
| "learning_rate": 3.6270786481227885e-05, |
| "loss": 0.1986, |
| "mean_token_accuracy": 0.9424618110060692, |
| "step": 395 |
| }, |
| { |
| "epoch": 2.3167155425219943, |
| "grad_norm": 1.3874329069918987, |
| "learning_rate": 3.624986077185003e-05, |
| "loss": 0.1862, |
| "mean_token_accuracy": 0.9473976641893387, |
| "step": 396 |
| }, |
| { |
| "epoch": 2.3225806451612905, |
| "grad_norm": 1.483625628532948, |
| "learning_rate": 3.622888334123272e-05, |
| "loss": 0.1714, |
| "mean_token_accuracy": 0.9534925371408463, |
| "step": 397 |
| }, |
| { |
| "epoch": 2.3284457478005867, |
| "grad_norm": 1.4383158878361242, |
| "learning_rate": 3.620785426551555e-05, |
| "loss": 0.1634, |
| "mean_token_accuracy": 0.9539240747690201, |
| "step": 398 |
| }, |
| { |
| "epoch": 2.334310850439883, |
| "grad_norm": 1.1273627628727119, |
| "learning_rate": 3.618677362102558e-05, |
| "loss": 0.1316, |
| "mean_token_accuracy": 0.961469940841198, |
| "step": 399 |
| }, |
| { |
| "epoch": 2.340175953079179, |
| "grad_norm": 1.5220516996155353, |
| "learning_rate": 3.616564148427703e-05, |
| "loss": 0.1792, |
| "mean_token_accuracy": 0.9433942660689354, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.346041055718475, |
| "grad_norm": 1.4608955929711822, |
| "learning_rate": 3.614445793197103e-05, |
| "loss": 0.1638, |
| "mean_token_accuracy": 0.9492457285523415, |
| "step": 401 |
| }, |
| { |
| "epoch": 2.3519061583577714, |
| "grad_norm": 1.5063014900643235, |
| "learning_rate": 3.61232230409953e-05, |
| "loss": 0.1816, |
| "mean_token_accuracy": 0.9452838078141212, |
| "step": 402 |
| }, |
| { |
| "epoch": 2.3577712609970676, |
| "grad_norm": 1.5879916738204585, |
| "learning_rate": 3.6101936888423936e-05, |
| "loss": 0.199, |
| "mean_token_accuracy": 0.9505869597196579, |
| "step": 403 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 1.6190060093628065, |
| "learning_rate": 3.6080599551517076e-05, |
| "loss": 0.1829, |
| "mean_token_accuracy": 0.9452532529830933, |
| "step": 404 |
| }, |
| { |
| "epoch": 2.36950146627566, |
| "grad_norm": 1.591052066609119, |
| "learning_rate": 3.605921110772063e-05, |
| "loss": 0.1952, |
| "mean_token_accuracy": 0.9436501488089561, |
| "step": 405 |
| }, |
| { |
| "epoch": 2.375366568914956, |
| "grad_norm": 1.4651530670386483, |
| "learning_rate": 3.603777163466601e-05, |
| "loss": 0.1626, |
| "mean_token_accuracy": 0.949164867401123, |
| "step": 406 |
| }, |
| { |
| "epoch": 2.3812316715542523, |
| "grad_norm": 1.5197490454848215, |
| "learning_rate": 3.6016281210169844e-05, |
| "loss": 0.1892, |
| "mean_token_accuracy": 0.9424419403076172, |
| "step": 407 |
| }, |
| { |
| "epoch": 2.3870967741935485, |
| "grad_norm": 1.5088850567602756, |
| "learning_rate": 3.599473991223369e-05, |
| "loss": 0.1816, |
| "mean_token_accuracy": 0.9471491128206253, |
| "step": 408 |
| }, |
| { |
| "epoch": 2.3929618768328447, |
| "grad_norm": 1.6258161225406804, |
| "learning_rate": 3.5973147819043765e-05, |
| "loss": 0.2049, |
| "mean_token_accuracy": 0.9332642704248428, |
| "step": 409 |
| }, |
| { |
| "epoch": 2.398826979472141, |
| "grad_norm": 1.4444906258969137, |
| "learning_rate": 3.595150500897065e-05, |
| "loss": 0.1983, |
| "mean_token_accuracy": 0.9415558204054832, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.404692082111437, |
| "grad_norm": 1.6160102435014505, |
| "learning_rate": 3.5929811560569e-05, |
| "loss": 0.2069, |
| "mean_token_accuracy": 0.9475803673267365, |
| "step": 411 |
| }, |
| { |
| "epoch": 2.410557184750733, |
| "grad_norm": 1.3447926697756785, |
| "learning_rate": 3.590806755257726e-05, |
| "loss": 0.1654, |
| "mean_token_accuracy": 0.94842179864645, |
| "step": 412 |
| }, |
| { |
| "epoch": 2.4164222873900294, |
| "grad_norm": 1.4798870575264065, |
| "learning_rate": 3.5886273063917426e-05, |
| "loss": 0.178, |
| "mean_token_accuracy": 0.9414676427841187, |
| "step": 413 |
| }, |
| { |
| "epoch": 2.4222873900293256, |
| "grad_norm": 1.519064400272912, |
| "learning_rate": 3.586442817369467e-05, |
| "loss": 0.1913, |
| "mean_token_accuracy": 0.9318802356719971, |
| "step": 414 |
| }, |
| { |
| "epoch": 2.4281524926686218, |
| "grad_norm": 1.3625628764482547, |
| "learning_rate": 3.5842532961197114e-05, |
| "loss": 0.1462, |
| "mean_token_accuracy": 0.9540624096989632, |
| "step": 415 |
| }, |
| { |
| "epoch": 2.434017595307918, |
| "grad_norm": 1.7373315854675837, |
| "learning_rate": 3.582058750589555e-05, |
| "loss": 0.2119, |
| "mean_token_accuracy": 0.9377310499548912, |
| "step": 416 |
| }, |
| { |
| "epoch": 2.439882697947214, |
| "grad_norm": 1.830130965645857, |
| "learning_rate": 3.579859188744311e-05, |
| "loss": 0.2505, |
| "mean_token_accuracy": 0.9223317727446556, |
| "step": 417 |
| }, |
| { |
| "epoch": 2.4457478005865103, |
| "grad_norm": 1.5168358594406, |
| "learning_rate": 3.5776546185675014e-05, |
| "loss": 0.1973, |
| "mean_token_accuracy": 0.9436168894171715, |
| "step": 418 |
| }, |
| { |
| "epoch": 2.4516129032258065, |
| "grad_norm": 1.7875580792704173, |
| "learning_rate": 3.5754450480608244e-05, |
| "loss": 0.2109, |
| "mean_token_accuracy": 0.9373271837830544, |
| "step": 419 |
| }, |
| { |
| "epoch": 2.4574780058651027, |
| "grad_norm": 1.5883528874075437, |
| "learning_rate": 3.5732304852441294e-05, |
| "loss": 0.2147, |
| "mean_token_accuracy": 0.936000183224678, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.463343108504399, |
| "grad_norm": 1.8065099011242889, |
| "learning_rate": 3.571010938155386e-05, |
| "loss": 0.2619, |
| "mean_token_accuracy": 0.9260461702942848, |
| "step": 421 |
| }, |
| { |
| "epoch": 2.469208211143695, |
| "grad_norm": 1.6418092211911852, |
| "learning_rate": 3.5687864148506515e-05, |
| "loss": 0.1867, |
| "mean_token_accuracy": 0.9402009174227715, |
| "step": 422 |
| }, |
| { |
| "epoch": 2.4750733137829912, |
| "grad_norm": 1.381906338016382, |
| "learning_rate": 3.566556923404048e-05, |
| "loss": 0.1505, |
| "mean_token_accuracy": 0.955479122698307, |
| "step": 423 |
| }, |
| { |
| "epoch": 2.4809384164222874, |
| "grad_norm": 1.213287645392281, |
| "learning_rate": 3.5643224719077294e-05, |
| "loss": 0.1565, |
| "mean_token_accuracy": 0.9560166001319885, |
| "step": 424 |
| }, |
| { |
| "epoch": 2.4868035190615836, |
| "grad_norm": 1.375404431939761, |
| "learning_rate": 3.5620830684718515e-05, |
| "loss": 0.1706, |
| "mean_token_accuracy": 0.9489535689353943, |
| "step": 425 |
| }, |
| { |
| "epoch": 2.4926686217008798, |
| "grad_norm": 1.2465742978161383, |
| "learning_rate": 3.5598387212245456e-05, |
| "loss": 0.1606, |
| "mean_token_accuracy": 0.9529033079743385, |
| "step": 426 |
| }, |
| { |
| "epoch": 2.498533724340176, |
| "grad_norm": 1.4045133580111415, |
| "learning_rate": 3.5575894383118846e-05, |
| "loss": 0.1873, |
| "mean_token_accuracy": 0.9499105364084244, |
| "step": 427 |
| }, |
| { |
| "epoch": 2.504398826979472, |
| "grad_norm": 1.372490625148224, |
| "learning_rate": 3.5553352278978574e-05, |
| "loss": 0.1816, |
| "mean_token_accuracy": 0.9412456303834915, |
| "step": 428 |
| }, |
| { |
| "epoch": 2.5102639296187683, |
| "grad_norm": 1.5354559639804668, |
| "learning_rate": 3.553076098164337e-05, |
| "loss": 0.1774, |
| "mean_token_accuracy": 0.9477965086698532, |
| "step": 429 |
| }, |
| { |
| "epoch": 2.5161290322580645, |
| "grad_norm": 1.4778203902809248, |
| "learning_rate": 3.5508120573110516e-05, |
| "loss": 0.1958, |
| "mean_token_accuracy": 0.9413925185799599, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.5219941348973607, |
| "grad_norm": 1.2514914338303438, |
| "learning_rate": 3.548543113555557e-05, |
| "loss": 0.1433, |
| "mean_token_accuracy": 0.9577402174472809, |
| "step": 431 |
| }, |
| { |
| "epoch": 2.527859237536657, |
| "grad_norm": 1.3305108203635878, |
| "learning_rate": 3.5462692751332014e-05, |
| "loss": 0.1778, |
| "mean_token_accuracy": 0.9476026743650436, |
| "step": 432 |
| }, |
| { |
| "epoch": 2.533724340175953, |
| "grad_norm": 1.1742572503020614, |
| "learning_rate": 3.5439905502970996e-05, |
| "loss": 0.1366, |
| "mean_token_accuracy": 0.9584061652421951, |
| "step": 433 |
| }, |
| { |
| "epoch": 2.5395894428152492, |
| "grad_norm": 1.230197597142779, |
| "learning_rate": 3.541706947318103e-05, |
| "loss": 0.157, |
| "mean_token_accuracy": 0.9515904188156128, |
| "step": 434 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 1.5660487728940458, |
| "learning_rate": 3.539418474484768e-05, |
| "loss": 0.2105, |
| "mean_token_accuracy": 0.9401791095733643, |
| "step": 435 |
| }, |
| { |
| "epoch": 2.5513196480938416, |
| "grad_norm": 1.553521419511032, |
| "learning_rate": 3.537125140103327e-05, |
| "loss": 0.1949, |
| "mean_token_accuracy": 0.9433295205235481, |
| "step": 436 |
| }, |
| { |
| "epoch": 2.557184750733138, |
| "grad_norm": 1.2711027329016076, |
| "learning_rate": 3.534826952497657e-05, |
| "loss": 0.1594, |
| "mean_token_accuracy": 0.9537053257226944, |
| "step": 437 |
| }, |
| { |
| "epoch": 2.563049853372434, |
| "grad_norm": 1.5314862483881024, |
| "learning_rate": 3.5325239200092505e-05, |
| "loss": 0.1896, |
| "mean_token_accuracy": 0.9418998286128044, |
| "step": 438 |
| }, |
| { |
| "epoch": 2.56891495601173, |
| "grad_norm": 1.5637934300785588, |
| "learning_rate": 3.5302160509971866e-05, |
| "loss": 0.2203, |
| "mean_token_accuracy": 0.9355995953083038, |
| "step": 439 |
| }, |
| { |
| "epoch": 2.5747800586510263, |
| "grad_norm": 1.4714637306784724, |
| "learning_rate": 3.5279033538380974e-05, |
| "loss": 0.1911, |
| "mean_token_accuracy": 0.9404008537530899, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "grad_norm": 1.2122932740008598, |
| "learning_rate": 3.5255858369261385e-05, |
| "loss": 0.1289, |
| "mean_token_accuracy": 0.9619543105363846, |
| "step": 441 |
| }, |
| { |
| "epoch": 2.5865102639296187, |
| "grad_norm": 1.505105430019669, |
| "learning_rate": 3.523263508672961e-05, |
| "loss": 0.203, |
| "mean_token_accuracy": 0.939716748893261, |
| "step": 442 |
| }, |
| { |
| "epoch": 2.592375366568915, |
| "grad_norm": 1.4166574253102397, |
| "learning_rate": 3.520936377507679e-05, |
| "loss": 0.1776, |
| "mean_token_accuracy": 0.9428360909223557, |
| "step": 443 |
| }, |
| { |
| "epoch": 2.598240469208211, |
| "grad_norm": 1.6648203766423546, |
| "learning_rate": 3.5186044518768376e-05, |
| "loss": 0.2281, |
| "mean_token_accuracy": 0.9257840067148209, |
| "step": 444 |
| }, |
| { |
| "epoch": 2.6041055718475072, |
| "grad_norm": 1.5336110988003941, |
| "learning_rate": 3.5162677402443864e-05, |
| "loss": 0.1976, |
| "mean_token_accuracy": 0.938742958009243, |
| "step": 445 |
| }, |
| { |
| "epoch": 2.6099706744868034, |
| "grad_norm": 1.4379546067534612, |
| "learning_rate": 3.513926251091644e-05, |
| "loss": 0.1971, |
| "mean_token_accuracy": 0.9414190128445625, |
| "step": 446 |
| }, |
| { |
| "epoch": 2.6158357771260996, |
| "grad_norm": 1.339537757201692, |
| "learning_rate": 3.51157999291727e-05, |
| "loss": 0.1814, |
| "mean_token_accuracy": 0.9400840774178505, |
| "step": 447 |
| }, |
| { |
| "epoch": 2.621700879765396, |
| "grad_norm": 1.9285181710925006, |
| "learning_rate": 3.509228974237235e-05, |
| "loss": 0.2581, |
| "mean_token_accuracy": 0.9255566149950027, |
| "step": 448 |
| }, |
| { |
| "epoch": 2.627565982404692, |
| "grad_norm": 1.424766252886363, |
| "learning_rate": 3.506873203584787e-05, |
| "loss": 0.1849, |
| "mean_token_accuracy": 0.9422862157225609, |
| "step": 449 |
| }, |
| { |
| "epoch": 2.633431085043988, |
| "grad_norm": 1.203628816210816, |
| "learning_rate": 3.504512689510422e-05, |
| "loss": 0.1477, |
| "mean_token_accuracy": 0.9604510739445686, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.6392961876832843, |
| "grad_norm": 1.3126311664229962, |
| "learning_rate": 3.5021474405818525e-05, |
| "loss": 0.1648, |
| "mean_token_accuracy": 0.9464056417346001, |
| "step": 451 |
| }, |
| { |
| "epoch": 2.6451612903225805, |
| "grad_norm": 1.5683417522165155, |
| "learning_rate": 3.499777465383977e-05, |
| "loss": 0.2085, |
| "mean_token_accuracy": 0.9423654973506927, |
| "step": 452 |
| }, |
| { |
| "epoch": 2.6510263929618767, |
| "grad_norm": 1.7124391179299574, |
| "learning_rate": 3.497402772518848e-05, |
| "loss": 0.2197, |
| "mean_token_accuracy": 0.9286736026406288, |
| "step": 453 |
| }, |
| { |
| "epoch": 2.656891495601173, |
| "grad_norm": 1.2928522615635958, |
| "learning_rate": 3.4950233706056415e-05, |
| "loss": 0.1646, |
| "mean_token_accuracy": 0.9472004845738411, |
| "step": 454 |
| }, |
| { |
| "epoch": 2.662756598240469, |
| "grad_norm": 1.6263040380796228, |
| "learning_rate": 3.4926392682806265e-05, |
| "loss": 0.2055, |
| "mean_token_accuracy": 0.9389370456337929, |
| "step": 455 |
| }, |
| { |
| "epoch": 2.6686217008797652, |
| "grad_norm": 1.5520555225769765, |
| "learning_rate": 3.490250474197131e-05, |
| "loss": 0.1979, |
| "mean_token_accuracy": 0.9429981112480164, |
| "step": 456 |
| }, |
| { |
| "epoch": 2.6744868035190614, |
| "grad_norm": 1.520377373848019, |
| "learning_rate": 3.4878569970255116e-05, |
| "loss": 0.1817, |
| "mean_token_accuracy": 0.9455464854836464, |
| "step": 457 |
| }, |
| { |
| "epoch": 2.6803519061583576, |
| "grad_norm": 1.6159409423049518, |
| "learning_rate": 3.485458845453125e-05, |
| "loss": 0.1919, |
| "mean_token_accuracy": 0.9442776069045067, |
| "step": 458 |
| }, |
| { |
| "epoch": 2.686217008797654, |
| "grad_norm": 1.536515683927506, |
| "learning_rate": 3.483056028184293e-05, |
| "loss": 0.1514, |
| "mean_token_accuracy": 0.9531370028853416, |
| "step": 459 |
| }, |
| { |
| "epoch": 2.6920821114369504, |
| "grad_norm": 1.5998217769260568, |
| "learning_rate": 3.4806485539402716e-05, |
| "loss": 0.1886, |
| "mean_token_accuracy": 0.940488263964653, |
| "step": 460 |
| }, |
| { |
| "epoch": 2.6979472140762466, |
| "grad_norm": 1.2681668634545191, |
| "learning_rate": 3.4782364314592186e-05, |
| "loss": 0.1491, |
| "mean_token_accuracy": 0.956335611641407, |
| "step": 461 |
| }, |
| { |
| "epoch": 2.703812316715543, |
| "grad_norm": 1.618911195594093, |
| "learning_rate": 3.475819669496167e-05, |
| "loss": 0.1757, |
| "mean_token_accuracy": 0.9452315121889114, |
| "step": 462 |
| }, |
| { |
| "epoch": 2.709677419354839, |
| "grad_norm": 1.356819620967187, |
| "learning_rate": 3.473398276822985e-05, |
| "loss": 0.1736, |
| "mean_token_accuracy": 0.9476948976516724, |
| "step": 463 |
| }, |
| { |
| "epoch": 2.715542521994135, |
| "grad_norm": 1.6105950634922812, |
| "learning_rate": 3.47097226222835e-05, |
| "loss": 0.2048, |
| "mean_token_accuracy": 0.9410142675042152, |
| "step": 464 |
| }, |
| { |
| "epoch": 2.7214076246334313, |
| "grad_norm": 1.441168567633283, |
| "learning_rate": 3.468541634517716e-05, |
| "loss": 0.1733, |
| "mean_token_accuracy": 0.9470472857356071, |
| "step": 465 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 1.219154125397772, |
| "learning_rate": 3.4661064025132796e-05, |
| "loss": 0.1407, |
| "mean_token_accuracy": 0.9544103369116783, |
| "step": 466 |
| }, |
| { |
| "epoch": 2.7331378299120237, |
| "grad_norm": 1.735956549135718, |
| "learning_rate": 3.463666575053949e-05, |
| "loss": 0.2209, |
| "mean_token_accuracy": 0.9372992217540741, |
| "step": 467 |
| }, |
| { |
| "epoch": 2.73900293255132, |
| "grad_norm": 1.0723058902393905, |
| "learning_rate": 3.4612221609953126e-05, |
| "loss": 0.1465, |
| "mean_token_accuracy": 0.9592811986804008, |
| "step": 468 |
| }, |
| { |
| "epoch": 2.744868035190616, |
| "grad_norm": 1.266106561576398, |
| "learning_rate": 3.4587731692096065e-05, |
| "loss": 0.1616, |
| "mean_token_accuracy": 0.9548813477158546, |
| "step": 469 |
| }, |
| { |
| "epoch": 2.7507331378299122, |
| "grad_norm": 1.5709556980717925, |
| "learning_rate": 3.4563196085856815e-05, |
| "loss": 0.2231, |
| "mean_token_accuracy": 0.9351802319288254, |
| "step": 470 |
| }, |
| { |
| "epoch": 2.7565982404692084, |
| "grad_norm": 1.6033382298160437, |
| "learning_rate": 3.4538614880289724e-05, |
| "loss": 0.2066, |
| "mean_token_accuracy": 0.9434246122837067, |
| "step": 471 |
| }, |
| { |
| "epoch": 2.7624633431085046, |
| "grad_norm": 1.2791754585446349, |
| "learning_rate": 3.4513988164614635e-05, |
| "loss": 0.1566, |
| "mean_token_accuracy": 0.9580570235848427, |
| "step": 472 |
| }, |
| { |
| "epoch": 2.768328445747801, |
| "grad_norm": 1.1734761099061624, |
| "learning_rate": 3.4489316028216584e-05, |
| "loss": 0.1465, |
| "mean_token_accuracy": 0.9552415683865547, |
| "step": 473 |
| }, |
| { |
| "epoch": 2.774193548387097, |
| "grad_norm": 1.2022871722577544, |
| "learning_rate": 3.446459856064545e-05, |
| "loss": 0.1517, |
| "mean_token_accuracy": 0.9557396098971367, |
| "step": 474 |
| }, |
| { |
| "epoch": 2.780058651026393, |
| "grad_norm": 1.6434058067923774, |
| "learning_rate": 3.443983585161568e-05, |
| "loss": 0.2084, |
| "mean_token_accuracy": 0.9364630356431007, |
| "step": 475 |
| }, |
| { |
| "epoch": 2.7859237536656893, |
| "grad_norm": 1.2827362600117416, |
| "learning_rate": 3.441502799100588e-05, |
| "loss": 0.1602, |
| "mean_token_accuracy": 0.960084393620491, |
| "step": 476 |
| }, |
| { |
| "epoch": 2.7917888563049855, |
| "grad_norm": 1.4811407319146348, |
| "learning_rate": 3.439017506885858e-05, |
| "loss": 0.1867, |
| "mean_token_accuracy": 0.948580302298069, |
| "step": 477 |
| }, |
| { |
| "epoch": 2.7976539589442817, |
| "grad_norm": 1.4737225017755107, |
| "learning_rate": 3.436527717537985e-05, |
| "loss": 0.1942, |
| "mean_token_accuracy": 0.9491779133677483, |
| "step": 478 |
| }, |
| { |
| "epoch": 2.803519061583578, |
| "grad_norm": 1.4212779057861695, |
| "learning_rate": 3.434033440093899e-05, |
| "loss": 0.1898, |
| "mean_token_accuracy": 0.9374239072203636, |
| "step": 479 |
| }, |
| { |
| "epoch": 2.809384164222874, |
| "grad_norm": 1.4834687519316923, |
| "learning_rate": 3.431534683606818e-05, |
| "loss": 0.2084, |
| "mean_token_accuracy": 0.9470439925789833, |
| "step": 480 |
| }, |
| { |
| "epoch": 2.8152492668621703, |
| "grad_norm": 1.3536053573095326, |
| "learning_rate": 3.4290314571462214e-05, |
| "loss": 0.1664, |
| "mean_token_accuracy": 0.9505494609475136, |
| "step": 481 |
| }, |
| { |
| "epoch": 2.8211143695014664, |
| "grad_norm": 1.4654358825691278, |
| "learning_rate": 3.426523769797808e-05, |
| "loss": 0.1719, |
| "mean_token_accuracy": 0.9511361643671989, |
| "step": 482 |
| }, |
| { |
| "epoch": 2.8269794721407626, |
| "grad_norm": 1.534865173849534, |
| "learning_rate": 3.424011630663472e-05, |
| "loss": 0.2035, |
| "mean_token_accuracy": 0.9370648711919785, |
| "step": 483 |
| }, |
| { |
| "epoch": 2.832844574780059, |
| "grad_norm": 1.5975723094077148, |
| "learning_rate": 3.421495048861262e-05, |
| "loss": 0.1841, |
| "mean_token_accuracy": 0.9466887265443802, |
| "step": 484 |
| }, |
| { |
| "epoch": 2.838709677419355, |
| "grad_norm": 1.380939441601992, |
| "learning_rate": 3.418974033525355e-05, |
| "loss": 0.1764, |
| "mean_token_accuracy": 0.9512438848614693, |
| "step": 485 |
| }, |
| { |
| "epoch": 2.844574780058651, |
| "grad_norm": 1.44638081838838, |
| "learning_rate": 3.416448593806019e-05, |
| "loss": 0.2103, |
| "mean_token_accuracy": 0.9422366619110107, |
| "step": 486 |
| }, |
| { |
| "epoch": 2.8504398826979473, |
| "grad_norm": 1.3027147165778983, |
| "learning_rate": 3.4139187388695774e-05, |
| "loss": 0.1751, |
| "mean_token_accuracy": 0.9415677487850189, |
| "step": 487 |
| }, |
| { |
| "epoch": 2.8563049853372435, |
| "grad_norm": 1.442286918678071, |
| "learning_rate": 3.411384477898385e-05, |
| "loss": 0.1784, |
| "mean_token_accuracy": 0.9486387521028519, |
| "step": 488 |
| }, |
| { |
| "epoch": 2.8621700879765397, |
| "grad_norm": 1.1864310979576265, |
| "learning_rate": 3.408845820090784e-05, |
| "loss": 0.1641, |
| "mean_token_accuracy": 0.9475547969341278, |
| "step": 489 |
| }, |
| { |
| "epoch": 2.868035190615836, |
| "grad_norm": 1.5938391452894787, |
| "learning_rate": 3.406302774661077e-05, |
| "loss": 0.2135, |
| "mean_token_accuracy": 0.9362959042191505, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.873900293255132, |
| "grad_norm": 1.8187898306480366, |
| "learning_rate": 3.403755350839492e-05, |
| "loss": 0.2208, |
| "mean_token_accuracy": 0.9381490647792816, |
| "step": 491 |
| }, |
| { |
| "epoch": 2.8797653958944283, |
| "grad_norm": 1.0176203937436277, |
| "learning_rate": 3.401203557872149e-05, |
| "loss": 0.131, |
| "mean_token_accuracy": 0.963982343673706, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.8856304985337244, |
| "grad_norm": 1.2944881554086942, |
| "learning_rate": 3.398647405021026e-05, |
| "loss": 0.1791, |
| "mean_token_accuracy": 0.9504873305559158, |
| "step": 493 |
| }, |
| { |
| "epoch": 2.8914956011730206, |
| "grad_norm": 1.7979282502116185, |
| "learning_rate": 3.396086901563925e-05, |
| "loss": 0.2224, |
| "mean_token_accuracy": 0.9352485239505768, |
| "step": 494 |
| }, |
| { |
| "epoch": 2.897360703812317, |
| "grad_norm": 1.1750005366326866, |
| "learning_rate": 3.3935220567944395e-05, |
| "loss": 0.1545, |
| "mean_token_accuracy": 0.950984425842762, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.903225806451613, |
| "grad_norm": 1.5949219047411234, |
| "learning_rate": 3.39095288002192e-05, |
| "loss": 0.2162, |
| "mean_token_accuracy": 0.9337630718946457, |
| "step": 496 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 1.3433147451555392, |
| "learning_rate": 3.3883793805714406e-05, |
| "loss": 0.1659, |
| "mean_token_accuracy": 0.9481701776385307, |
| "step": 497 |
| }, |
| { |
| "epoch": 2.9149560117302054, |
| "grad_norm": 1.5996494396127081, |
| "learning_rate": 3.3858015677837656e-05, |
| "loss": 0.2149, |
| "mean_token_accuracy": 0.9419268667697906, |
| "step": 498 |
| }, |
| { |
| "epoch": 2.9208211143695015, |
| "grad_norm": 1.3050500946865204, |
| "learning_rate": 3.3832194510153126e-05, |
| "loss": 0.1924, |
| "mean_token_accuracy": 0.9457806721329689, |
| "step": 499 |
| }, |
| { |
| "epoch": 2.9266862170087977, |
| "grad_norm": 1.3938033327743358, |
| "learning_rate": 3.380633039638125e-05, |
| "loss": 0.1871, |
| "mean_token_accuracy": 0.9511330723762512, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.932551319648094, |
| "grad_norm": 1.7111259960860905, |
| "learning_rate": 3.37804234303983e-05, |
| "loss": 0.2148, |
| "mean_token_accuracy": 0.9375216588377953, |
| "step": 501 |
| }, |
| { |
| "epoch": 2.93841642228739, |
| "grad_norm": 1.5676984126616746, |
| "learning_rate": 3.37544737062361e-05, |
| "loss": 0.2069, |
| "mean_token_accuracy": 0.9395978674292564, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.9442815249266863, |
| "grad_norm": 1.3024069551411093, |
| "learning_rate": 3.372848131808167e-05, |
| "loss": 0.1775, |
| "mean_token_accuracy": 0.94802475720644, |
| "step": 503 |
| }, |
| { |
| "epoch": 2.9501466275659824, |
| "grad_norm": 1.6781903083104455, |
| "learning_rate": 3.370244636027688e-05, |
| "loss": 0.1932, |
| "mean_token_accuracy": 0.9439413473010063, |
| "step": 504 |
| }, |
| { |
| "epoch": 2.9560117302052786, |
| "grad_norm": 1.2084010552335631, |
| "learning_rate": 3.367636892731812e-05, |
| "loss": 0.1705, |
| "mean_token_accuracy": 0.9432723671197891, |
| "step": 505 |
| }, |
| { |
| "epoch": 2.961876832844575, |
| "grad_norm": 1.4876928960475226, |
| "learning_rate": 3.365024911385593e-05, |
| "loss": 0.1669, |
| "mean_token_accuracy": 0.9567491114139557, |
| "step": 506 |
| }, |
| { |
| "epoch": 2.967741935483871, |
| "grad_norm": 1.4129569433402656, |
| "learning_rate": 3.362408701469469e-05, |
| "loss": 0.1779, |
| "mean_token_accuracy": 0.9438919052481651, |
| "step": 507 |
| }, |
| { |
| "epoch": 2.973607038123167, |
| "grad_norm": 1.4008768614077696, |
| "learning_rate": 3.359788272479225e-05, |
| "loss": 0.1988, |
| "mean_token_accuracy": 0.9402952864766121, |
| "step": 508 |
| }, |
| { |
| "epoch": 2.9794721407624634, |
| "grad_norm": 1.2490328336150844, |
| "learning_rate": 3.35716363392596e-05, |
| "loss": 0.1846, |
| "mean_token_accuracy": 0.9396477043628693, |
| "step": 509 |
| }, |
| { |
| "epoch": 2.9853372434017595, |
| "grad_norm": 1.8703998203747494, |
| "learning_rate": 3.354534795336052e-05, |
| "loss": 0.267, |
| "mean_token_accuracy": 0.9222179055213928, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.9912023460410557, |
| "grad_norm": 1.3688615608986425, |
| "learning_rate": 3.351901766251123e-05, |
| "loss": 0.189, |
| "mean_token_accuracy": 0.9435115680098534, |
| "step": 511 |
| }, |
| { |
| "epoch": 2.997067448680352, |
| "grad_norm": 1.7584850077090424, |
| "learning_rate": 3.349264556228006e-05, |
| "loss": 0.2295, |
| "mean_token_accuracy": 0.9362204223871231, |
| "step": 512 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.7584850077090424, |
| "learning_rate": 3.3466231748387077e-05, |
| "loss": 0.2552, |
| "mean_token_accuracy": 0.9123900383710861, |
| "step": 513 |
| }, |
| { |
| "epoch": 3.005865102639296, |
| "grad_norm": 2.1995675752841906, |
| "learning_rate": 3.343977631670376e-05, |
| "loss": 0.1173, |
| "mean_token_accuracy": 0.9707249626517296, |
| "step": 514 |
| }, |
| { |
| "epoch": 3.0117302052785924, |
| "grad_norm": 1.1331312828942772, |
| "learning_rate": 3.341327936325264e-05, |
| "loss": 0.146, |
| "mean_token_accuracy": 0.9599213600158691, |
| "step": 515 |
| }, |
| { |
| "epoch": 3.0175953079178885, |
| "grad_norm": 1.066284672763136, |
| "learning_rate": 3.338674098420695e-05, |
| "loss": 0.1109, |
| "mean_token_accuracy": 0.965148963034153, |
| "step": 516 |
| }, |
| { |
| "epoch": 3.0234604105571847, |
| "grad_norm": 1.0074944736951232, |
| "learning_rate": 3.33601612758903e-05, |
| "loss": 0.1283, |
| "mean_token_accuracy": 0.9635849222540855, |
| "step": 517 |
| }, |
| { |
| "epoch": 3.029325513196481, |
| "grad_norm": 1.2258415386092127, |
| "learning_rate": 3.3333540334776286e-05, |
| "loss": 0.1329, |
| "mean_token_accuracy": 0.9582738950848579, |
| "step": 518 |
| }, |
| { |
| "epoch": 3.035190615835777, |
| "grad_norm": 1.0778695406875511, |
| "learning_rate": 3.330687825748818e-05, |
| "loss": 0.118, |
| "mean_token_accuracy": 0.966682031750679, |
| "step": 519 |
| }, |
| { |
| "epoch": 3.0410557184750733, |
| "grad_norm": 1.0364880624857191, |
| "learning_rate": 3.328017514079855e-05, |
| "loss": 0.1216, |
| "mean_token_accuracy": 0.9677037075161934, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.0469208211143695, |
| "grad_norm": 1.1236650847876453, |
| "learning_rate": 3.325343108162893e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9645716473460197, |
| "step": 521 |
| }, |
| { |
| "epoch": 3.0527859237536656, |
| "grad_norm": 1.1551918085779922, |
| "learning_rate": 3.3226646177049446e-05, |
| "loss": 0.1425, |
| "mean_token_accuracy": 0.963393472135067, |
| "step": 522 |
| }, |
| { |
| "epoch": 3.058651026392962, |
| "grad_norm": 1.2648329188721996, |
| "learning_rate": 3.3199820524278485e-05, |
| "loss": 0.1299, |
| "mean_token_accuracy": 0.9622451663017273, |
| "step": 523 |
| }, |
| { |
| "epoch": 3.064516129032258, |
| "grad_norm": 1.325697584264539, |
| "learning_rate": 3.317295422068234e-05, |
| "loss": 0.1263, |
| "mean_token_accuracy": 0.9606219977140427, |
| "step": 524 |
| }, |
| { |
| "epoch": 3.070381231671554, |
| "grad_norm": 1.130741369640608, |
| "learning_rate": 3.314604736377484e-05, |
| "loss": 0.0992, |
| "mean_token_accuracy": 0.9693296328186989, |
| "step": 525 |
| }, |
| { |
| "epoch": 3.0762463343108504, |
| "grad_norm": 0.8955946893420774, |
| "learning_rate": 3.3119100051217005e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.9741750881075859, |
| "step": 526 |
| }, |
| { |
| "epoch": 3.0821114369501466, |
| "grad_norm": 1.0121677552730586, |
| "learning_rate": 3.3092112380816696e-05, |
| "loss": 0.1324, |
| "mean_token_accuracy": 0.9608965739607811, |
| "step": 527 |
| }, |
| { |
| "epoch": 3.0879765395894427, |
| "grad_norm": 1.060519939355375, |
| "learning_rate": 3.306508445052826e-05, |
| "loss": 0.1335, |
| "mean_token_accuracy": 0.9608549624681473, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.093841642228739, |
| "grad_norm": 1.3572690475788862, |
| "learning_rate": 3.303801635845216e-05, |
| "loss": 0.1198, |
| "mean_token_accuracy": 0.9593236073851585, |
| "step": 529 |
| }, |
| { |
| "epoch": 3.099706744868035, |
| "grad_norm": 1.1464512354729663, |
| "learning_rate": 3.301090820283465e-05, |
| "loss": 0.1367, |
| "mean_token_accuracy": 0.9591869786381721, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.1055718475073313, |
| "grad_norm": 1.2823035767765665, |
| "learning_rate": 3.298376008206739e-05, |
| "loss": 0.113, |
| "mean_token_accuracy": 0.9657314345240593, |
| "step": 531 |
| }, |
| { |
| "epoch": 3.1114369501466275, |
| "grad_norm": 1.0403767904872765, |
| "learning_rate": 3.295657209468707e-05, |
| "loss": 0.112, |
| "mean_token_accuracy": 0.9685370773077011, |
| "step": 532 |
| }, |
| { |
| "epoch": 3.1173020527859236, |
| "grad_norm": 1.15498558857311, |
| "learning_rate": 3.2929344339375125e-05, |
| "loss": 0.159, |
| "mean_token_accuracy": 0.9546686410903931, |
| "step": 533 |
| }, |
| { |
| "epoch": 3.12316715542522, |
| "grad_norm": 1.3853285053067845, |
| "learning_rate": 3.290207691495731e-05, |
| "loss": 0.1386, |
| "mean_token_accuracy": 0.9635892808437347, |
| "step": 534 |
| }, |
| { |
| "epoch": 3.129032258064516, |
| "grad_norm": 1.0913823383162526, |
| "learning_rate": 3.2874769920403355e-05, |
| "loss": 0.1264, |
| "mean_token_accuracy": 0.9625230208039284, |
| "step": 535 |
| }, |
| { |
| "epoch": 3.134897360703812, |
| "grad_norm": 1.0080636135286674, |
| "learning_rate": 3.2847423454826616e-05, |
| "loss": 0.1255, |
| "mean_token_accuracy": 0.9642705172300339, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.1407624633431084, |
| "grad_norm": 1.3384707349035834, |
| "learning_rate": 3.2820037617483734e-05, |
| "loss": 0.1438, |
| "mean_token_accuracy": 0.958034835755825, |
| "step": 537 |
| }, |
| { |
| "epoch": 3.1466275659824046, |
| "grad_norm": 1.3200934144993954, |
| "learning_rate": 3.2792612507774224e-05, |
| "loss": 0.1273, |
| "mean_token_accuracy": 0.9666285142302513, |
| "step": 538 |
| }, |
| { |
| "epoch": 3.1524926686217007, |
| "grad_norm": 1.2829027100001151, |
| "learning_rate": 3.2765148225240176e-05, |
| "loss": 0.1325, |
| "mean_token_accuracy": 0.9617817550897598, |
| "step": 539 |
| }, |
| { |
| "epoch": 3.158357771260997, |
| "grad_norm": 1.2749195398082585, |
| "learning_rate": 3.273764486956583e-05, |
| "loss": 0.1396, |
| "mean_token_accuracy": 0.9613074734807014, |
| "step": 540 |
| }, |
| { |
| "epoch": 3.164222873900293, |
| "grad_norm": 1.8832759061462432, |
| "learning_rate": 3.2710102540577256e-05, |
| "loss": 0.1359, |
| "mean_token_accuracy": 0.9631753191351891, |
| "step": 541 |
| }, |
| { |
| "epoch": 3.1700879765395893, |
| "grad_norm": 1.3360701106894814, |
| "learning_rate": 3.268252133824198e-05, |
| "loss": 0.1511, |
| "mean_token_accuracy": 0.9591165855526924, |
| "step": 542 |
| }, |
| { |
| "epoch": 3.1759530791788855, |
| "grad_norm": 1.0402537478170215, |
| "learning_rate": 3.2654901362668656e-05, |
| "loss": 0.1131, |
| "mean_token_accuracy": 0.9691095277667046, |
| "step": 543 |
| }, |
| { |
| "epoch": 3.1818181818181817, |
| "grad_norm": 0.9125849553677988, |
| "learning_rate": 3.262724271410661e-05, |
| "loss": 0.1236, |
| "mean_token_accuracy": 0.9633389338850975, |
| "step": 544 |
| }, |
| { |
| "epoch": 3.187683284457478, |
| "grad_norm": 1.3682014683553543, |
| "learning_rate": 3.2599545492945584e-05, |
| "loss": 0.1454, |
| "mean_token_accuracy": 0.9624962136149406, |
| "step": 545 |
| }, |
| { |
| "epoch": 3.193548387096774, |
| "grad_norm": 1.3325018585193886, |
| "learning_rate": 3.257180979971529e-05, |
| "loss": 0.1328, |
| "mean_token_accuracy": 0.9589158594608307, |
| "step": 546 |
| }, |
| { |
| "epoch": 3.19941348973607, |
| "grad_norm": 1.0097361820340343, |
| "learning_rate": 3.25440357350851e-05, |
| "loss": 0.144, |
| "mean_token_accuracy": 0.959138460457325, |
| "step": 547 |
| }, |
| { |
| "epoch": 3.2052785923753664, |
| "grad_norm": 1.323820448706562, |
| "learning_rate": 3.251622339986366e-05, |
| "loss": 0.1345, |
| "mean_token_accuracy": 0.9602171406149864, |
| "step": 548 |
| }, |
| { |
| "epoch": 3.2111436950146626, |
| "grad_norm": 1.2388531251498671, |
| "learning_rate": 3.24883728949985e-05, |
| "loss": 0.1327, |
| "mean_token_accuracy": 0.9595544189214706, |
| "step": 549 |
| }, |
| { |
| "epoch": 3.2170087976539588, |
| "grad_norm": 1.0310891892624763, |
| "learning_rate": 3.2460484321575714e-05, |
| "loss": 0.1168, |
| "mean_token_accuracy": 0.9652495458722115, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.222873900293255, |
| "grad_norm": 1.4715352145558056, |
| "learning_rate": 3.2432557780819556e-05, |
| "loss": 0.1132, |
| "mean_token_accuracy": 0.9686658978462219, |
| "step": 551 |
| }, |
| { |
| "epoch": 3.228739002932551, |
| "grad_norm": 1.1419372965685666, |
| "learning_rate": 3.240459337409209e-05, |
| "loss": 0.1374, |
| "mean_token_accuracy": 0.9581699892878532, |
| "step": 552 |
| }, |
| { |
| "epoch": 3.2346041055718473, |
| "grad_norm": 1.065263225106119, |
| "learning_rate": 3.237659120289282e-05, |
| "loss": 0.1221, |
| "mean_token_accuracy": 0.9630059227347374, |
| "step": 553 |
| }, |
| { |
| "epoch": 3.2404692082111435, |
| "grad_norm": 1.4131885769796437, |
| "learning_rate": 3.2348551368858315e-05, |
| "loss": 0.1315, |
| "mean_token_accuracy": 0.9611981958150864, |
| "step": 554 |
| }, |
| { |
| "epoch": 3.2463343108504397, |
| "grad_norm": 1.1809907629919947, |
| "learning_rate": 3.2320473973761845e-05, |
| "loss": 0.1451, |
| "mean_token_accuracy": 0.9615741968154907, |
| "step": 555 |
| }, |
| { |
| "epoch": 3.252199413489736, |
| "grad_norm": 1.2393516472369321, |
| "learning_rate": 3.229235911951303e-05, |
| "loss": 0.1331, |
| "mean_token_accuracy": 0.9634448885917664, |
| "step": 556 |
| }, |
| { |
| "epoch": 3.258064516129032, |
| "grad_norm": 1.172077426283371, |
| "learning_rate": 3.2264206908157425e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9665073528885841, |
| "step": 557 |
| }, |
| { |
| "epoch": 3.263929618768328, |
| "grad_norm": 0.935534799272401, |
| "learning_rate": 3.2236017441876185e-05, |
| "loss": 0.133, |
| "mean_token_accuracy": 0.9626928493380547, |
| "step": 558 |
| }, |
| { |
| "epoch": 3.2697947214076244, |
| "grad_norm": 1.2339532266360087, |
| "learning_rate": 3.220779082298569e-05, |
| "loss": 0.1448, |
| "mean_token_accuracy": 0.9604134261608124, |
| "step": 559 |
| }, |
| { |
| "epoch": 3.2756598240469206, |
| "grad_norm": 1.329389534253784, |
| "learning_rate": 3.2179527153937165e-05, |
| "loss": 0.1369, |
| "mean_token_accuracy": 0.9576560631394386, |
| "step": 560 |
| }, |
| { |
| "epoch": 3.281524926686217, |
| "grad_norm": 1.156112312255903, |
| "learning_rate": 3.2151226537316315e-05, |
| "loss": 0.1158, |
| "mean_token_accuracy": 0.9680624380707741, |
| "step": 561 |
| }, |
| { |
| "epoch": 3.2873900293255134, |
| "grad_norm": 1.00465704885852, |
| "learning_rate": 3.212288907584296e-05, |
| "loss": 0.1212, |
| "mean_token_accuracy": 0.9627675563097, |
| "step": 562 |
| }, |
| { |
| "epoch": 3.2932551319648096, |
| "grad_norm": 1.3728468957769566, |
| "learning_rate": 3.209451487237062e-05, |
| "loss": 0.1641, |
| "mean_token_accuracy": 0.9527490735054016, |
| "step": 563 |
| }, |
| { |
| "epoch": 3.2991202346041058, |
| "grad_norm": 1.4900435856401562, |
| "learning_rate": 3.206610402988621e-05, |
| "loss": 0.1214, |
| "mean_token_accuracy": 0.9644360318779945, |
| "step": 564 |
| }, |
| { |
| "epoch": 3.304985337243402, |
| "grad_norm": 1.0411190450621626, |
| "learning_rate": 3.20376566515096e-05, |
| "loss": 0.1249, |
| "mean_token_accuracy": 0.9645769596099854, |
| "step": 565 |
| }, |
| { |
| "epoch": 3.310850439882698, |
| "grad_norm": 1.0952909991789344, |
| "learning_rate": 3.20091728404933e-05, |
| "loss": 0.1105, |
| "mean_token_accuracy": 0.9669332653284073, |
| "step": 566 |
| }, |
| { |
| "epoch": 3.3167155425219943, |
| "grad_norm": 0.9567829518623286, |
| "learning_rate": 3.1980652700222024e-05, |
| "loss": 0.1217, |
| "mean_token_accuracy": 0.9665136188268661, |
| "step": 567 |
| }, |
| { |
| "epoch": 3.3225806451612905, |
| "grad_norm": 1.054550029779028, |
| "learning_rate": 3.195209633421237e-05, |
| "loss": 0.1319, |
| "mean_token_accuracy": 0.959479384124279, |
| "step": 568 |
| }, |
| { |
| "epoch": 3.3284457478005867, |
| "grad_norm": 1.3054160354686266, |
| "learning_rate": 3.192350384611242e-05, |
| "loss": 0.1488, |
| "mean_token_accuracy": 0.9539597705006599, |
| "step": 569 |
| }, |
| { |
| "epoch": 3.334310850439883, |
| "grad_norm": 1.2721386924556894, |
| "learning_rate": 3.1894875339701354e-05, |
| "loss": 0.1147, |
| "mean_token_accuracy": 0.9713543429970741, |
| "step": 570 |
| }, |
| { |
| "epoch": 3.340175953079179, |
| "grad_norm": 1.1485327319472471, |
| "learning_rate": 3.186621091888909e-05, |
| "loss": 0.1427, |
| "mean_token_accuracy": 0.9585296213626862, |
| "step": 571 |
| }, |
| { |
| "epoch": 3.346041055718475, |
| "grad_norm": 1.1203261027735305, |
| "learning_rate": 3.183751068771588e-05, |
| "loss": 0.1331, |
| "mean_token_accuracy": 0.9624553993344307, |
| "step": 572 |
| }, |
| { |
| "epoch": 3.3519061583577714, |
| "grad_norm": 1.3902351538919793, |
| "learning_rate": 3.180877475035199e-05, |
| "loss": 0.1117, |
| "mean_token_accuracy": 0.9641240537166595, |
| "step": 573 |
| }, |
| { |
| "epoch": 3.3577712609970676, |
| "grad_norm": 0.9631311874139538, |
| "learning_rate": 3.178000321109727e-05, |
| "loss": 0.155, |
| "mean_token_accuracy": 0.9597619101405144, |
| "step": 574 |
| }, |
| { |
| "epoch": 3.3636363636363638, |
| "grad_norm": 1.1864850108982898, |
| "learning_rate": 3.175119617438078e-05, |
| "loss": 0.1393, |
| "mean_token_accuracy": 0.9603194743394852, |
| "step": 575 |
| }, |
| { |
| "epoch": 3.36950146627566, |
| "grad_norm": 1.389013217967289, |
| "learning_rate": 3.172235374476043e-05, |
| "loss": 0.1252, |
| "mean_token_accuracy": 0.9618887901306152, |
| "step": 576 |
| }, |
| { |
| "epoch": 3.375366568914956, |
| "grad_norm": 1.1171938023918093, |
| "learning_rate": 3.169347602692259e-05, |
| "loss": 0.1534, |
| "mean_token_accuracy": 0.9561700448393822, |
| "step": 577 |
| }, |
| { |
| "epoch": 3.3812316715542523, |
| "grad_norm": 1.7092816964612618, |
| "learning_rate": 3.166456312568171e-05, |
| "loss": 0.1325, |
| "mean_token_accuracy": 0.9581268802285194, |
| "step": 578 |
| }, |
| { |
| "epoch": 3.3870967741935485, |
| "grad_norm": 1.625258065533391, |
| "learning_rate": 3.1635615145979955e-05, |
| "loss": 0.1511, |
| "mean_token_accuracy": 0.9582557752728462, |
| "step": 579 |
| }, |
| { |
| "epoch": 3.3929618768328447, |
| "grad_norm": 1.1331081762433888, |
| "learning_rate": 3.160663219288679e-05, |
| "loss": 0.1215, |
| "mean_token_accuracy": 0.9631478041410446, |
| "step": 580 |
| }, |
| { |
| "epoch": 3.398826979472141, |
| "grad_norm": 1.1978807973332801, |
| "learning_rate": 3.157761437159863e-05, |
| "loss": 0.152, |
| "mean_token_accuracy": 0.9533499404788017, |
| "step": 581 |
| }, |
| { |
| "epoch": 3.404692082111437, |
| "grad_norm": 1.4814381302951631, |
| "learning_rate": 3.1548561787438445e-05, |
| "loss": 0.1301, |
| "mean_token_accuracy": 0.9643861651420593, |
| "step": 582 |
| }, |
| { |
| "epoch": 3.410557184750733, |
| "grad_norm": 0.8692151588216875, |
| "learning_rate": 3.15194745458554e-05, |
| "loss": 0.1218, |
| "mean_token_accuracy": 0.9649089276790619, |
| "step": 583 |
| }, |
| { |
| "epoch": 3.4164222873900294, |
| "grad_norm": 1.0681213749638105, |
| "learning_rate": 3.149035275242441e-05, |
| "loss": 0.1139, |
| "mean_token_accuracy": 0.9638341292738914, |
| "step": 584 |
| }, |
| { |
| "epoch": 3.4222873900293256, |
| "grad_norm": 1.1840279179274757, |
| "learning_rate": 3.1461196512845834e-05, |
| "loss": 0.156, |
| "mean_token_accuracy": 0.9580442979931831, |
| "step": 585 |
| }, |
| { |
| "epoch": 3.4281524926686218, |
| "grad_norm": 1.1755866291718038, |
| "learning_rate": 3.143200593294504e-05, |
| "loss": 0.1299, |
| "mean_token_accuracy": 0.9646251425147057, |
| "step": 586 |
| }, |
| { |
| "epoch": 3.434017595307918, |
| "grad_norm": 1.2021040143685826, |
| "learning_rate": 3.1402781118672065e-05, |
| "loss": 0.1452, |
| "mean_token_accuracy": 0.960387721657753, |
| "step": 587 |
| }, |
| { |
| "epoch": 3.439882697947214, |
| "grad_norm": 1.2658177391122667, |
| "learning_rate": 3.137352217610115e-05, |
| "loss": 0.1318, |
| "mean_token_accuracy": 0.9596589729189873, |
| "step": 588 |
| }, |
| { |
| "epoch": 3.4457478005865103, |
| "grad_norm": 1.161450002460737, |
| "learning_rate": 3.1344229211430465e-05, |
| "loss": 0.1424, |
| "mean_token_accuracy": 0.9619096294045448, |
| "step": 589 |
| }, |
| { |
| "epoch": 3.4516129032258065, |
| "grad_norm": 1.1764503462466256, |
| "learning_rate": 3.131490233098164e-05, |
| "loss": 0.1086, |
| "mean_token_accuracy": 0.9722210243344307, |
| "step": 590 |
| }, |
| { |
| "epoch": 3.4574780058651027, |
| "grad_norm": 1.0200394197140978, |
| "learning_rate": 3.1285541641199383e-05, |
| "loss": 0.1298, |
| "mean_token_accuracy": 0.9627177715301514, |
| "step": 591 |
| }, |
| { |
| "epoch": 3.463343108504399, |
| "grad_norm": 1.0891847830733288, |
| "learning_rate": 3.1256147248651166e-05, |
| "loss": 0.1121, |
| "mean_token_accuracy": 0.9680601879954338, |
| "step": 592 |
| }, |
| { |
| "epoch": 3.469208211143695, |
| "grad_norm": 1.2405132487377248, |
| "learning_rate": 3.122671926002675e-05, |
| "loss": 0.1446, |
| "mean_token_accuracy": 0.9562314078211784, |
| "step": 593 |
| }, |
| { |
| "epoch": 3.4750733137829912, |
| "grad_norm": 1.0110802653353386, |
| "learning_rate": 3.119725778213785e-05, |
| "loss": 0.1387, |
| "mean_token_accuracy": 0.9566402360796928, |
| "step": 594 |
| }, |
| { |
| "epoch": 3.4809384164222874, |
| "grad_norm": 1.1974141187037954, |
| "learning_rate": 3.116776292191774e-05, |
| "loss": 0.1597, |
| "mean_token_accuracy": 0.9548348411917686, |
| "step": 595 |
| }, |
| { |
| "epoch": 3.4868035190615836, |
| "grad_norm": 1.1165196094909804, |
| "learning_rate": 3.1138234786420834e-05, |
| "loss": 0.1148, |
| "mean_token_accuracy": 0.9665255323052406, |
| "step": 596 |
| }, |
| { |
| "epoch": 3.4926686217008798, |
| "grad_norm": 1.0169170518057122, |
| "learning_rate": 3.110867348282235e-05, |
| "loss": 0.1295, |
| "mean_token_accuracy": 0.9588236883282661, |
| "step": 597 |
| }, |
| { |
| "epoch": 3.498533724340176, |
| "grad_norm": 1.153587103488231, |
| "learning_rate": 3.107907911841787e-05, |
| "loss": 0.1223, |
| "mean_token_accuracy": 0.9607840701937675, |
| "step": 598 |
| }, |
| { |
| "epoch": 3.504398826979472, |
| "grad_norm": 1.087199024371378, |
| "learning_rate": 3.104945180062301e-05, |
| "loss": 0.1179, |
| "mean_token_accuracy": 0.9659548401832581, |
| "step": 599 |
| }, |
| { |
| "epoch": 3.5102639296187683, |
| "grad_norm": 1.0293281607388844, |
| "learning_rate": 3.1019791636972936e-05, |
| "loss": 0.1238, |
| "mean_token_accuracy": 0.9601342305541039, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.5161290322580645, |
| "grad_norm": 1.031917003106208, |
| "learning_rate": 3.099009873512208e-05, |
| "loss": 0.1261, |
| "mean_token_accuracy": 0.9628048911690712, |
| "step": 601 |
| }, |
| { |
| "epoch": 3.5219941348973607, |
| "grad_norm": 0.9953120358900215, |
| "learning_rate": 3.0960373202843685e-05, |
| "loss": 0.1124, |
| "mean_token_accuracy": 0.9684698581695557, |
| "step": 602 |
| }, |
| { |
| "epoch": 3.527859237536657, |
| "grad_norm": 1.1759720953251884, |
| "learning_rate": 3.093061514802943e-05, |
| "loss": 0.1526, |
| "mean_token_accuracy": 0.9586720243096352, |
| "step": 603 |
| }, |
| { |
| "epoch": 3.533724340175953, |
| "grad_norm": 1.2509364663673235, |
| "learning_rate": 3.090082467868901e-05, |
| "loss": 0.1153, |
| "mean_token_accuracy": 0.9655359834432602, |
| "step": 604 |
| }, |
| { |
| "epoch": 3.5395894428152492, |
| "grad_norm": 1.184032879476615, |
| "learning_rate": 3.087100190294983e-05, |
| "loss": 0.1387, |
| "mean_token_accuracy": 0.9585594981908798, |
| "step": 605 |
| }, |
| { |
| "epoch": 3.5454545454545454, |
| "grad_norm": 1.2334299730537033, |
| "learning_rate": 3.0841146929056505e-05, |
| "loss": 0.1336, |
| "mean_token_accuracy": 0.9633355215191841, |
| "step": 606 |
| }, |
| { |
| "epoch": 3.5513196480938416, |
| "grad_norm": 1.3935758743568316, |
| "learning_rate": 3.0811259865370535e-05, |
| "loss": 0.1196, |
| "mean_token_accuracy": 0.9636550173163414, |
| "step": 607 |
| }, |
| { |
| "epoch": 3.557184750733138, |
| "grad_norm": 1.2490583488517504, |
| "learning_rate": 3.07813408203699e-05, |
| "loss": 0.1272, |
| "mean_token_accuracy": 0.9602638855576515, |
| "step": 608 |
| }, |
| { |
| "epoch": 3.563049853372434, |
| "grad_norm": 1.0415243566749401, |
| "learning_rate": 3.075138990264863e-05, |
| "loss": 0.1651, |
| "mean_token_accuracy": 0.9521684423089027, |
| "step": 609 |
| }, |
| { |
| "epoch": 3.56891495601173, |
| "grad_norm": 1.3002877876142311, |
| "learning_rate": 3.072140722091648e-05, |
| "loss": 0.1157, |
| "mean_token_accuracy": 0.9622488170862198, |
| "step": 610 |
| }, |
| { |
| "epoch": 3.5747800586510263, |
| "grad_norm": 1.1177745433027027, |
| "learning_rate": 3.0691392883998455e-05, |
| "loss": 0.1553, |
| "mean_token_accuracy": 0.9571073427796364, |
| "step": 611 |
| }, |
| { |
| "epoch": 3.5806451612903225, |
| "grad_norm": 1.097455875690594, |
| "learning_rate": 3.0661347000834496e-05, |
| "loss": 0.1207, |
| "mean_token_accuracy": 0.966348297894001, |
| "step": 612 |
| }, |
| { |
| "epoch": 3.5865102639296187, |
| "grad_norm": 0.92337518870407, |
| "learning_rate": 3.063126968047901e-05, |
| "loss": 0.1241, |
| "mean_token_accuracy": 0.9607681557536125, |
| "step": 613 |
| }, |
| { |
| "epoch": 3.592375366568915, |
| "grad_norm": 1.1556433274194684, |
| "learning_rate": 3.060116103210053e-05, |
| "loss": 0.103, |
| "mean_token_accuracy": 0.9667187258601189, |
| "step": 614 |
| }, |
| { |
| "epoch": 3.598240469208211, |
| "grad_norm": 0.8803863695333437, |
| "learning_rate": 3.057102116498129e-05, |
| "loss": 0.1184, |
| "mean_token_accuracy": 0.9620434492826462, |
| "step": 615 |
| }, |
| { |
| "epoch": 3.6041055718475072, |
| "grad_norm": 1.1066441109805365, |
| "learning_rate": 3.0540850188516826e-05, |
| "loss": 0.1278, |
| "mean_token_accuracy": 0.9623741805553436, |
| "step": 616 |
| }, |
| { |
| "epoch": 3.6099706744868034, |
| "grad_norm": 0.9565613650928324, |
| "learning_rate": 3.051064821221561e-05, |
| "loss": 0.1007, |
| "mean_token_accuracy": 0.9718799218535423, |
| "step": 617 |
| }, |
| { |
| "epoch": 3.6158357771260996, |
| "grad_norm": 1.1056816724683267, |
| "learning_rate": 3.0480415345698606e-05, |
| "loss": 0.1548, |
| "mean_token_accuracy": 0.9537332579493523, |
| "step": 618 |
| }, |
| { |
| "epoch": 3.621700879765396, |
| "grad_norm": 1.1557201136270507, |
| "learning_rate": 3.045015169869892e-05, |
| "loss": 0.1302, |
| "mean_token_accuracy": 0.9655744209885597, |
| "step": 619 |
| }, |
| { |
| "epoch": 3.627565982404692, |
| "grad_norm": 1.0673108801225792, |
| "learning_rate": 3.0419857381061355e-05, |
| "loss": 0.1308, |
| "mean_token_accuracy": 0.9608449414372444, |
| "step": 620 |
| }, |
| { |
| "epoch": 3.633431085043988, |
| "grad_norm": 0.9556116815559285, |
| "learning_rate": 3.0389532502742066e-05, |
| "loss": 0.1151, |
| "mean_token_accuracy": 0.9625567346811295, |
| "step": 621 |
| }, |
| { |
| "epoch": 3.6392961876832843, |
| "grad_norm": 1.2310880687685863, |
| "learning_rate": 3.0359177173808104e-05, |
| "loss": 0.1298, |
| "mean_token_accuracy": 0.9569227620959282, |
| "step": 622 |
| }, |
| { |
| "epoch": 3.6451612903225805, |
| "grad_norm": 1.2080524487010553, |
| "learning_rate": 3.032879150443705e-05, |
| "loss": 0.1309, |
| "mean_token_accuracy": 0.9636347144842148, |
| "step": 623 |
| }, |
| { |
| "epoch": 3.6510263929618767, |
| "grad_norm": 1.1297303257876061, |
| "learning_rate": 3.029837560491662e-05, |
| "loss": 0.1222, |
| "mean_token_accuracy": 0.9660240784287453, |
| "step": 624 |
| }, |
| { |
| "epoch": 3.656891495601173, |
| "grad_norm": 1.1107968747130714, |
| "learning_rate": 3.0267929585644236e-05, |
| "loss": 0.1432, |
| "mean_token_accuracy": 0.9562357887625694, |
| "step": 625 |
| }, |
| { |
| "epoch": 3.662756598240469, |
| "grad_norm": 1.0536153520517821, |
| "learning_rate": 3.0237453557126656e-05, |
| "loss": 0.1141, |
| "mean_token_accuracy": 0.9647841155529022, |
| "step": 626 |
| }, |
| { |
| "epoch": 3.6686217008797652, |
| "grad_norm": 0.9835257570608045, |
| "learning_rate": 3.020694762997956e-05, |
| "loss": 0.1219, |
| "mean_token_accuracy": 0.9642433151602745, |
| "step": 627 |
| }, |
| { |
| "epoch": 3.6744868035190614, |
| "grad_norm": 0.9339989411565239, |
| "learning_rate": 3.017641191492714e-05, |
| "loss": 0.1064, |
| "mean_token_accuracy": 0.9676420092582703, |
| "step": 628 |
| }, |
| { |
| "epoch": 3.6803519061583576, |
| "grad_norm": 0.9153048871411351, |
| "learning_rate": 3.0145846522801703e-05, |
| "loss": 0.1108, |
| "mean_token_accuracy": 0.9640639424324036, |
| "step": 629 |
| }, |
| { |
| "epoch": 3.686217008797654, |
| "grad_norm": 1.1702691358319068, |
| "learning_rate": 3.0115251564543287e-05, |
| "loss": 0.1546, |
| "mean_token_accuracy": 0.9555616602301598, |
| "step": 630 |
| }, |
| { |
| "epoch": 3.6920821114369504, |
| "grad_norm": 1.4176417497299738, |
| "learning_rate": 3.008462715119922e-05, |
| "loss": 0.1784, |
| "mean_token_accuracy": 0.9492093324661255, |
| "step": 631 |
| }, |
| { |
| "epoch": 3.6979472140762466, |
| "grad_norm": 1.6185985821173499, |
| "learning_rate": 3.0053973393923768e-05, |
| "loss": 0.1197, |
| "mean_token_accuracy": 0.9643609151244164, |
| "step": 632 |
| }, |
| { |
| "epoch": 3.703812316715543, |
| "grad_norm": 1.1281455495325605, |
| "learning_rate": 3.0023290403977694e-05, |
| "loss": 0.1435, |
| "mean_token_accuracy": 0.9565146565437317, |
| "step": 633 |
| }, |
| { |
| "epoch": 3.709677419354839, |
| "grad_norm": 1.3100047889969146, |
| "learning_rate": 2.9992578292727842e-05, |
| "loss": 0.1398, |
| "mean_token_accuracy": 0.9574306532740593, |
| "step": 634 |
| }, |
| { |
| "epoch": 3.715542521994135, |
| "grad_norm": 0.9544359363476402, |
| "learning_rate": 2.9961837171646778e-05, |
| "loss": 0.1197, |
| "mean_token_accuracy": 0.9641690477728844, |
| "step": 635 |
| }, |
| { |
| "epoch": 3.7214076246334313, |
| "grad_norm": 1.3561935467580721, |
| "learning_rate": 2.993106715231237e-05, |
| "loss": 0.1426, |
| "mean_token_accuracy": 0.9598167091608047, |
| "step": 636 |
| }, |
| { |
| "epoch": 3.7272727272727275, |
| "grad_norm": 1.3660455931780044, |
| "learning_rate": 2.9900268346407336e-05, |
| "loss": 0.1389, |
| "mean_token_accuracy": 0.9577052295207977, |
| "step": 637 |
| }, |
| { |
| "epoch": 3.7331378299120237, |
| "grad_norm": 1.2249643635751344, |
| "learning_rate": 2.986944086571893e-05, |
| "loss": 0.1589, |
| "mean_token_accuracy": 0.9522917121648788, |
| "step": 638 |
| }, |
| { |
| "epoch": 3.73900293255132, |
| "grad_norm": 1.1782525356070939, |
| "learning_rate": 2.983858482213843e-05, |
| "loss": 0.1173, |
| "mean_token_accuracy": 0.9656160920858383, |
| "step": 639 |
| }, |
| { |
| "epoch": 3.744868035190616, |
| "grad_norm": 0.9773028695412396, |
| "learning_rate": 2.9807700327660834e-05, |
| "loss": 0.1376, |
| "mean_token_accuracy": 0.9574134349822998, |
| "step": 640 |
| }, |
| { |
| "epoch": 3.7507331378299122, |
| "grad_norm": 1.3161873189358173, |
| "learning_rate": 2.977678749438437e-05, |
| "loss": 0.134, |
| "mean_token_accuracy": 0.9588236212730408, |
| "step": 641 |
| }, |
| { |
| "epoch": 3.7565982404692084, |
| "grad_norm": 0.9442201655104536, |
| "learning_rate": 2.9745846434510146e-05, |
| "loss": 0.1181, |
| "mean_token_accuracy": 0.965650200843811, |
| "step": 642 |
| }, |
| { |
| "epoch": 3.7624633431085046, |
| "grad_norm": 1.1777506571798453, |
| "learning_rate": 2.9714877260341705e-05, |
| "loss": 0.1451, |
| "mean_token_accuracy": 0.9522349908947945, |
| "step": 643 |
| }, |
| { |
| "epoch": 3.768328445747801, |
| "grad_norm": 0.8478782526737215, |
| "learning_rate": 2.9683880084284648e-05, |
| "loss": 0.0946, |
| "mean_token_accuracy": 0.9708394706249237, |
| "step": 644 |
| }, |
| { |
| "epoch": 3.774193548387097, |
| "grad_norm": 1.1002209843660342, |
| "learning_rate": 2.96528550188462e-05, |
| "loss": 0.1452, |
| "mean_token_accuracy": 0.9609697312116623, |
| "step": 645 |
| }, |
| { |
| "epoch": 3.780058651026393, |
| "grad_norm": 1.0977670049624841, |
| "learning_rate": 2.962180217663483e-05, |
| "loss": 0.1444, |
| "mean_token_accuracy": 0.95732332020998, |
| "step": 646 |
| }, |
| { |
| "epoch": 3.7859237536656893, |
| "grad_norm": 1.2094117212667317, |
| "learning_rate": 2.95907216703598e-05, |
| "loss": 0.131, |
| "mean_token_accuracy": 0.9598681703209877, |
| "step": 647 |
| }, |
| { |
| "epoch": 3.7917888563049855, |
| "grad_norm": 1.0971502312685675, |
| "learning_rate": 2.9559613612830797e-05, |
| "loss": 0.1468, |
| "mean_token_accuracy": 0.9556907713413239, |
| "step": 648 |
| }, |
| { |
| "epoch": 3.7976539589442817, |
| "grad_norm": 1.0613202166159812, |
| "learning_rate": 2.952847811695751e-05, |
| "loss": 0.1305, |
| "mean_token_accuracy": 0.965257078409195, |
| "step": 649 |
| }, |
| { |
| "epoch": 3.803519061583578, |
| "grad_norm": 1.0099659020872942, |
| "learning_rate": 2.9497315295749218e-05, |
| "loss": 0.1319, |
| "mean_token_accuracy": 0.9646901562809944, |
| "step": 650 |
| }, |
| { |
| "epoch": 3.809384164222874, |
| "grad_norm": 1.2808080436278302, |
| "learning_rate": 2.9466125262314368e-05, |
| "loss": 0.1712, |
| "mean_token_accuracy": 0.9523722976446152, |
| "step": 651 |
| }, |
| { |
| "epoch": 3.8152492668621703, |
| "grad_norm": 1.7647260306652934, |
| "learning_rate": 2.9434908129860193e-05, |
| "loss": 0.1405, |
| "mean_token_accuracy": 0.9618514180183411, |
| "step": 652 |
| }, |
| { |
| "epoch": 3.8211143695014664, |
| "grad_norm": 1.1534843084754791, |
| "learning_rate": 2.9403664011692276e-05, |
| "loss": 0.1544, |
| "mean_token_accuracy": 0.954981729388237, |
| "step": 653 |
| }, |
| { |
| "epoch": 3.8269794721407626, |
| "grad_norm": 1.2939646511087926, |
| "learning_rate": 2.9372393021214134e-05, |
| "loss": 0.1588, |
| "mean_token_accuracy": 0.9539552256464958, |
| "step": 654 |
| }, |
| { |
| "epoch": 3.832844574780059, |
| "grad_norm": 1.188278943842319, |
| "learning_rate": 2.9341095271926842e-05, |
| "loss": 0.1359, |
| "mean_token_accuracy": 0.9616807624697685, |
| "step": 655 |
| }, |
| { |
| "epoch": 3.838709677419355, |
| "grad_norm": 1.0856399855222887, |
| "learning_rate": 2.930977087742859e-05, |
| "loss": 0.1249, |
| "mean_token_accuracy": 0.9609912484884262, |
| "step": 656 |
| }, |
| { |
| "epoch": 3.844574780058651, |
| "grad_norm": 0.9803813921122001, |
| "learning_rate": 2.9278419951414277e-05, |
| "loss": 0.144, |
| "mean_token_accuracy": 0.96265958994627, |
| "step": 657 |
| }, |
| { |
| "epoch": 3.8504398826979473, |
| "grad_norm": 1.0825588438292633, |
| "learning_rate": 2.9247042607675105e-05, |
| "loss": 0.1355, |
| "mean_token_accuracy": 0.9593116492033005, |
| "step": 658 |
| }, |
| { |
| "epoch": 3.8563049853372435, |
| "grad_norm": 0.7272092106468886, |
| "learning_rate": 2.9215638960098164e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9734610915184021, |
| "step": 659 |
| }, |
| { |
| "epoch": 3.8621700879765397, |
| "grad_norm": 0.7981455863455788, |
| "learning_rate": 2.9184209122665996e-05, |
| "loss": 0.1209, |
| "mean_token_accuracy": 0.9625027552247047, |
| "step": 660 |
| }, |
| { |
| "epoch": 3.868035190615836, |
| "grad_norm": 1.0644155114590241, |
| "learning_rate": 2.915275320945623e-05, |
| "loss": 0.1342, |
| "mean_token_accuracy": 0.962261438369751, |
| "step": 661 |
| }, |
| { |
| "epoch": 3.873900293255132, |
| "grad_norm": 1.3058968639705204, |
| "learning_rate": 2.9121271334641127e-05, |
| "loss": 0.1375, |
| "mean_token_accuracy": 0.9608859419822693, |
| "step": 662 |
| }, |
| { |
| "epoch": 3.8797653958944283, |
| "grad_norm": 1.1888950650427426, |
| "learning_rate": 2.908976361248717e-05, |
| "loss": 0.1335, |
| "mean_token_accuracy": 0.9634340405464172, |
| "step": 663 |
| }, |
| { |
| "epoch": 3.8856304985337244, |
| "grad_norm": 0.9694975031185143, |
| "learning_rate": 2.9058230157354674e-05, |
| "loss": 0.1444, |
| "mean_token_accuracy": 0.9566892609000206, |
| "step": 664 |
| }, |
| { |
| "epoch": 3.8914956011730206, |
| "grad_norm": 1.1575330596885278, |
| "learning_rate": 2.902667108369734e-05, |
| "loss": 0.1252, |
| "mean_token_accuracy": 0.9613283276557922, |
| "step": 665 |
| }, |
| { |
| "epoch": 3.897360703812317, |
| "grad_norm": 1.1277073069882797, |
| "learning_rate": 2.8995086506061862e-05, |
| "loss": 0.1279, |
| "mean_token_accuracy": 0.9618002399802208, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.903225806451613, |
| "grad_norm": 1.121397297414267, |
| "learning_rate": 2.896347653908749e-05, |
| "loss": 0.1151, |
| "mean_token_accuracy": 0.9665411338210106, |
| "step": 667 |
| }, |
| { |
| "epoch": 3.909090909090909, |
| "grad_norm": 0.9012462300498526, |
| "learning_rate": 2.8931841297505657e-05, |
| "loss": 0.1127, |
| "mean_token_accuracy": 0.9637566730380058, |
| "step": 668 |
| }, |
| { |
| "epoch": 3.9149560117302054, |
| "grad_norm": 0.9109562227585535, |
| "learning_rate": 2.8900180896139503e-05, |
| "loss": 0.0955, |
| "mean_token_accuracy": 0.969886414706707, |
| "step": 669 |
| }, |
| { |
| "epoch": 3.9208211143695015, |
| "grad_norm": 1.1687790994100906, |
| "learning_rate": 2.8868495449903498e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.9717061296105385, |
| "step": 670 |
| }, |
| { |
| "epoch": 3.9266862170087977, |
| "grad_norm": 0.7755929180254743, |
| "learning_rate": 2.8836785073803014e-05, |
| "loss": 0.1094, |
| "mean_token_accuracy": 0.9656796231865883, |
| "step": 671 |
| }, |
| { |
| "epoch": 3.932551319648094, |
| "grad_norm": 0.9446774901165217, |
| "learning_rate": 2.880504988293391e-05, |
| "loss": 0.1344, |
| "mean_token_accuracy": 0.9652603045105934, |
| "step": 672 |
| }, |
| { |
| "epoch": 3.93841642228739, |
| "grad_norm": 1.111729269543401, |
| "learning_rate": 2.8773289992482115e-05, |
| "loss": 0.1215, |
| "mean_token_accuracy": 0.9619983360171318, |
| "step": 673 |
| }, |
| { |
| "epoch": 3.9442815249266863, |
| "grad_norm": 1.3795999777982066, |
| "learning_rate": 2.87415055177232e-05, |
| "loss": 0.1157, |
| "mean_token_accuracy": 0.9651115536689758, |
| "step": 674 |
| }, |
| { |
| "epoch": 3.9501466275659824, |
| "grad_norm": 1.0118979486417967, |
| "learning_rate": 2.870969657402197e-05, |
| "loss": 0.1345, |
| "mean_token_accuracy": 0.9584571942687035, |
| "step": 675 |
| }, |
| { |
| "epoch": 3.9560117302052786, |
| "grad_norm": 1.326426843091007, |
| "learning_rate": 2.867786327683205e-05, |
| "loss": 0.158, |
| "mean_token_accuracy": 0.9536311253905296, |
| "step": 676 |
| }, |
| { |
| "epoch": 3.961876832844575, |
| "grad_norm": 0.9390313577441797, |
| "learning_rate": 2.864600574169545e-05, |
| "loss": 0.1238, |
| "mean_token_accuracy": 0.9652499556541443, |
| "step": 677 |
| }, |
| { |
| "epoch": 3.967741935483871, |
| "grad_norm": 1.0821150137608206, |
| "learning_rate": 2.861412408424216e-05, |
| "loss": 0.1205, |
| "mean_token_accuracy": 0.9640393927693367, |
| "step": 678 |
| }, |
| { |
| "epoch": 3.973607038123167, |
| "grad_norm": 1.1046019376949232, |
| "learning_rate": 2.8582218420189706e-05, |
| "loss": 0.1419, |
| "mean_token_accuracy": 0.9601811021566391, |
| "step": 679 |
| }, |
| { |
| "epoch": 3.9794721407624634, |
| "grad_norm": 1.3616091121662732, |
| "learning_rate": 2.855028886534278e-05, |
| "loss": 0.1511, |
| "mean_token_accuracy": 0.9565163180232048, |
| "step": 680 |
| }, |
| { |
| "epoch": 3.9853372434017595, |
| "grad_norm": 1.2082659273486551, |
| "learning_rate": 2.851833553559276e-05, |
| "loss": 0.1271, |
| "mean_token_accuracy": 0.9636896699666977, |
| "step": 681 |
| }, |
| { |
| "epoch": 3.9912023460410557, |
| "grad_norm": 1.0850403614399995, |
| "learning_rate": 2.848635854691733e-05, |
| "loss": 0.1368, |
| "mean_token_accuracy": 0.9602132365107536, |
| "step": 682 |
| }, |
| { |
| "epoch": 3.997067448680352, |
| "grad_norm": 0.9493712048082743, |
| "learning_rate": 2.8454358015380046e-05, |
| "loss": 0.0986, |
| "mean_token_accuracy": 0.9702668786048889, |
| "step": 683 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.558059945609864, |
| "learning_rate": 2.8422334057129913e-05, |
| "loss": 0.1191, |
| "mean_token_accuracy": 0.9623651206493378, |
| "step": 684 |
| }, |
| { |
| "epoch": 4.005865102639296, |
| "grad_norm": 0.842862500749142, |
| "learning_rate": 2.8390286788400967e-05, |
| "loss": 0.0957, |
| "mean_token_accuracy": 0.9664551466703415, |
| "step": 685 |
| }, |
| { |
| "epoch": 4.011730205278592, |
| "grad_norm": 0.6795835077138793, |
| "learning_rate": 2.8358216325511847e-05, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.9761439710855484, |
| "step": 686 |
| }, |
| { |
| "epoch": 4.0175953079178885, |
| "grad_norm": 1.1456567621753069, |
| "learning_rate": 2.832612278486538e-05, |
| "loss": 0.1198, |
| "mean_token_accuracy": 0.963876485824585, |
| "step": 687 |
| }, |
| { |
| "epoch": 4.023460410557185, |
| "grad_norm": 7.8979363537657035, |
| "learning_rate": 2.8294006282948165e-05, |
| "loss": 0.2698, |
| "mean_token_accuracy": 0.9692637398838997, |
| "step": 688 |
| }, |
| { |
| "epoch": 4.029325513196481, |
| "grad_norm": 1.1045222161731982, |
| "learning_rate": 2.8261866936330123e-05, |
| "loss": 0.1049, |
| "mean_token_accuracy": 0.965548038482666, |
| "step": 689 |
| }, |
| { |
| "epoch": 4.035190615835777, |
| "grad_norm": 1.2554508151838817, |
| "learning_rate": 2.8229704861664113e-05, |
| "loss": 0.1036, |
| "mean_token_accuracy": 0.9706982374191284, |
| "step": 690 |
| }, |
| { |
| "epoch": 4.041055718475073, |
| "grad_norm": 1.1041277073123883, |
| "learning_rate": 2.8197520175685462e-05, |
| "loss": 0.0998, |
| "mean_token_accuracy": 0.9741102978587151, |
| "step": 691 |
| }, |
| { |
| "epoch": 4.0469208211143695, |
| "grad_norm": 0.8006560792352735, |
| "learning_rate": 2.8165312995211596e-05, |
| "loss": 0.0927, |
| "mean_token_accuracy": 0.9737097099423409, |
| "step": 692 |
| }, |
| { |
| "epoch": 4.052785923753666, |
| "grad_norm": 0.8655138713705752, |
| "learning_rate": 2.813308343714156e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9713312909007072, |
| "step": 693 |
| }, |
| { |
| "epoch": 4.058651026392962, |
| "grad_norm": 0.9516836003751642, |
| "learning_rate": 2.810083161845564e-05, |
| "loss": 0.111, |
| "mean_token_accuracy": 0.9674246981739998, |
| "step": 694 |
| }, |
| { |
| "epoch": 4.064516129032258, |
| "grad_norm": 0.8720519712759406, |
| "learning_rate": 2.8068557656214913e-05, |
| "loss": 0.0866, |
| "mean_token_accuracy": 0.9744721204042435, |
| "step": 695 |
| }, |
| { |
| "epoch": 4.070381231671554, |
| "grad_norm": 0.6222607867296382, |
| "learning_rate": 2.8036261667560826e-05, |
| "loss": 0.0932, |
| "mean_token_accuracy": 0.9742299988865852, |
| "step": 696 |
| }, |
| { |
| "epoch": 4.07624633431085, |
| "grad_norm": 0.7960989210401829, |
| "learning_rate": 2.8003943769714776e-05, |
| "loss": 0.1093, |
| "mean_token_accuracy": 0.9663450121879578, |
| "step": 697 |
| }, |
| { |
| "epoch": 4.0821114369501466, |
| "grad_norm": 1.1019502994755033, |
| "learning_rate": 2.7971604079977673e-05, |
| "loss": 0.1185, |
| "mean_token_accuracy": 0.96397615224123, |
| "step": 698 |
| }, |
| { |
| "epoch": 4.087976539589443, |
| "grad_norm": 0.7470501123132239, |
| "learning_rate": 2.793924271572954e-05, |
| "loss": 0.0873, |
| "mean_token_accuracy": 0.9746774211525917, |
| "step": 699 |
| }, |
| { |
| "epoch": 4.093841642228739, |
| "grad_norm": 0.8010505075241883, |
| "learning_rate": 2.7906859794429047e-05, |
| "loss": 0.0995, |
| "mean_token_accuracy": 0.9679571017622948, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.099706744868035, |
| "grad_norm": 0.8813053810673643, |
| "learning_rate": 2.787445543361313e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.9711523503065109, |
| "step": 701 |
| }, |
| { |
| "epoch": 4.105571847507331, |
| "grad_norm": 1.1338479600606155, |
| "learning_rate": 2.7842029750896525e-05, |
| "loss": 0.1293, |
| "mean_token_accuracy": 0.9662352055311203, |
| "step": 702 |
| }, |
| { |
| "epoch": 4.1114369501466275, |
| "grad_norm": 1.1524380891393422, |
| "learning_rate": 2.7809582863971373e-05, |
| "loss": 0.1123, |
| "mean_token_accuracy": 0.9671714976429939, |
| "step": 703 |
| }, |
| { |
| "epoch": 4.117302052785924, |
| "grad_norm": 0.9880154262384708, |
| "learning_rate": 2.777711489060676e-05, |
| "loss": 0.1175, |
| "mean_token_accuracy": 0.9668581932783127, |
| "step": 704 |
| }, |
| { |
| "epoch": 4.12316715542522, |
| "grad_norm": 0.8689806304769432, |
| "learning_rate": 2.7744625948648316e-05, |
| "loss": 0.0974, |
| "mean_token_accuracy": 0.9735423848032951, |
| "step": 705 |
| }, |
| { |
| "epoch": 4.129032258064516, |
| "grad_norm": 0.941884543587427, |
| "learning_rate": 2.7712116156017783e-05, |
| "loss": 0.1003, |
| "mean_token_accuracy": 0.9737986624240875, |
| "step": 706 |
| }, |
| { |
| "epoch": 4.134897360703812, |
| "grad_norm": 0.9450484339416181, |
| "learning_rate": 2.7679585630712585e-05, |
| "loss": 0.1072, |
| "mean_token_accuracy": 0.9653824865818024, |
| "step": 707 |
| }, |
| { |
| "epoch": 4.140762463343108, |
| "grad_norm": 0.7072259315634002, |
| "learning_rate": 2.764703449080538e-05, |
| "loss": 0.0998, |
| "mean_token_accuracy": 0.9729399904608727, |
| "step": 708 |
| }, |
| { |
| "epoch": 4.146627565982405, |
| "grad_norm": 0.950898645982569, |
| "learning_rate": 2.761446285444366e-05, |
| "loss": 0.1123, |
| "mean_token_accuracy": 0.9680687040090561, |
| "step": 709 |
| }, |
| { |
| "epoch": 4.152492668621701, |
| "grad_norm": 0.738092645530511, |
| "learning_rate": 2.758187083984931e-05, |
| "loss": 0.0884, |
| "mean_token_accuracy": 0.9752467274665833, |
| "step": 710 |
| }, |
| { |
| "epoch": 4.158357771260997, |
| "grad_norm": 1.0204267654285655, |
| "learning_rate": 2.754925856531819e-05, |
| "loss": 0.1179, |
| "mean_token_accuracy": 0.9653342291712761, |
| "step": 711 |
| }, |
| { |
| "epoch": 4.164222873900293, |
| "grad_norm": 0.9770563801600024, |
| "learning_rate": 2.7516626149219678e-05, |
| "loss": 0.0976, |
| "mean_token_accuracy": 0.9727638140320778, |
| "step": 712 |
| }, |
| { |
| "epoch": 4.170087976539589, |
| "grad_norm": 1.0725235604843808, |
| "learning_rate": 2.7483973709996267e-05, |
| "loss": 0.1082, |
| "mean_token_accuracy": 0.9659662619233131, |
| "step": 713 |
| }, |
| { |
| "epoch": 4.1759530791788855, |
| "grad_norm": 0.8958740426822329, |
| "learning_rate": 2.7451301366163116e-05, |
| "loss": 0.1224, |
| "mean_token_accuracy": 0.9643898904323578, |
| "step": 714 |
| }, |
| { |
| "epoch": 4.181818181818182, |
| "grad_norm": 0.6766982108825446, |
| "learning_rate": 2.741860923630765e-05, |
| "loss": 0.0815, |
| "mean_token_accuracy": 0.9771873876452446, |
| "step": 715 |
| }, |
| { |
| "epoch": 4.187683284457478, |
| "grad_norm": 1.048072499756525, |
| "learning_rate": 2.7385897439089086e-05, |
| "loss": 0.1171, |
| "mean_token_accuracy": 0.9654709845781326, |
| "step": 716 |
| }, |
| { |
| "epoch": 4.193548387096774, |
| "grad_norm": 0.8912351764553597, |
| "learning_rate": 2.735316609323804e-05, |
| "loss": 0.1169, |
| "mean_token_accuracy": 0.9646259918808937, |
| "step": 717 |
| }, |
| { |
| "epoch": 4.19941348973607, |
| "grad_norm": 0.9390469569028205, |
| "learning_rate": 2.7320415317556085e-05, |
| "loss": 0.1046, |
| "mean_token_accuracy": 0.9704753458499908, |
| "step": 718 |
| }, |
| { |
| "epoch": 4.205278592375366, |
| "grad_norm": 0.8560329829131477, |
| "learning_rate": 2.72876452309153e-05, |
| "loss": 0.0841, |
| "mean_token_accuracy": 0.9733430370688438, |
| "step": 719 |
| }, |
| { |
| "epoch": 4.211143695014663, |
| "grad_norm": 0.8933889301548646, |
| "learning_rate": 2.7254855952257867e-05, |
| "loss": 0.102, |
| "mean_token_accuracy": 0.9689731150865555, |
| "step": 720 |
| }, |
| { |
| "epoch": 4.217008797653959, |
| "grad_norm": 1.102744978983958, |
| "learning_rate": 2.7222047600595626e-05, |
| "loss": 0.1391, |
| "mean_token_accuracy": 0.9602887108922005, |
| "step": 721 |
| }, |
| { |
| "epoch": 4.222873900293255, |
| "grad_norm": 0.7769746447260107, |
| "learning_rate": 2.718922029500965e-05, |
| "loss": 0.1051, |
| "mean_token_accuracy": 0.9703327119350433, |
| "step": 722 |
| }, |
| { |
| "epoch": 4.228739002932551, |
| "grad_norm": 0.8830152108120385, |
| "learning_rate": 2.7156374154649787e-05, |
| "loss": 0.1, |
| "mean_token_accuracy": 0.9667406901717186, |
| "step": 723 |
| }, |
| { |
| "epoch": 4.234604105571847, |
| "grad_norm": 0.9571228011975423, |
| "learning_rate": 2.7123509298734267e-05, |
| "loss": 0.1015, |
| "mean_token_accuracy": 0.970310315489769, |
| "step": 724 |
| }, |
| { |
| "epoch": 4.2404692082111435, |
| "grad_norm": 0.9452784130844039, |
| "learning_rate": 2.7090625846549247e-05, |
| "loss": 0.1046, |
| "mean_token_accuracy": 0.9675817862153053, |
| "step": 725 |
| }, |
| { |
| "epoch": 4.24633431085044, |
| "grad_norm": 1.0691326279227324, |
| "learning_rate": 2.705772391744837e-05, |
| "loss": 0.123, |
| "mean_token_accuracy": 0.970280796289444, |
| "step": 726 |
| }, |
| { |
| "epoch": 4.252199413489736, |
| "grad_norm": 0.9002102935983834, |
| "learning_rate": 2.7024803630852362e-05, |
| "loss": 0.1127, |
| "mean_token_accuracy": 0.9712927043437958, |
| "step": 727 |
| }, |
| { |
| "epoch": 4.258064516129032, |
| "grad_norm": 1.1839994161421517, |
| "learning_rate": 2.699186510624856e-05, |
| "loss": 0.1183, |
| "mean_token_accuracy": 0.9680011197924614, |
| "step": 728 |
| }, |
| { |
| "epoch": 4.263929618768328, |
| "grad_norm": 0.9930191904934016, |
| "learning_rate": 2.6958908463190506e-05, |
| "loss": 0.1281, |
| "mean_token_accuracy": 0.9630226120352745, |
| "step": 729 |
| }, |
| { |
| "epoch": 4.269794721407624, |
| "grad_norm": 0.9676556571129576, |
| "learning_rate": 2.6925933821297497e-05, |
| "loss": 0.1171, |
| "mean_token_accuracy": 0.9654005244374275, |
| "step": 730 |
| }, |
| { |
| "epoch": 4.275659824046921, |
| "grad_norm": 1.1227004079371043, |
| "learning_rate": 2.6892941300254176e-05, |
| "loss": 0.1151, |
| "mean_token_accuracy": 0.9704194962978363, |
| "step": 731 |
| }, |
| { |
| "epoch": 4.281524926686217, |
| "grad_norm": 0.938382034990061, |
| "learning_rate": 2.685993101981007e-05, |
| "loss": 0.1058, |
| "mean_token_accuracy": 0.968720979988575, |
| "step": 732 |
| }, |
| { |
| "epoch": 4.287390029325513, |
| "grad_norm": 0.9381935165005029, |
| "learning_rate": 2.6826903099779157e-05, |
| "loss": 0.1034, |
| "mean_token_accuracy": 0.9666604846715927, |
| "step": 733 |
| }, |
| { |
| "epoch": 4.293255131964809, |
| "grad_norm": 0.9325917617385888, |
| "learning_rate": 2.679385766003945e-05, |
| "loss": 0.1131, |
| "mean_token_accuracy": 0.9669909775257111, |
| "step": 734 |
| }, |
| { |
| "epoch": 4.299120234604105, |
| "grad_norm": 0.831981688674269, |
| "learning_rate": 2.676079482053255e-05, |
| "loss": 0.1094, |
| "mean_token_accuracy": 0.9680541455745697, |
| "step": 735 |
| }, |
| { |
| "epoch": 4.3049853372434015, |
| "grad_norm": 1.1028897779609337, |
| "learning_rate": 2.6727714701263212e-05, |
| "loss": 0.1122, |
| "mean_token_accuracy": 0.9693733751773834, |
| "step": 736 |
| }, |
| { |
| "epoch": 4.310850439882698, |
| "grad_norm": 0.8459161475890958, |
| "learning_rate": 2.669461742229891e-05, |
| "loss": 0.0998, |
| "mean_token_accuracy": 0.9723160266876221, |
| "step": 737 |
| }, |
| { |
| "epoch": 4.316715542521994, |
| "grad_norm": 0.8842003257292316, |
| "learning_rate": 2.6661503103769404e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.971040166914463, |
| "step": 738 |
| }, |
| { |
| "epoch": 4.32258064516129, |
| "grad_norm": 0.9346441595866154, |
| "learning_rate": 2.6628371865866286e-05, |
| "loss": 0.1192, |
| "mean_token_accuracy": 0.9664890840649605, |
| "step": 739 |
| }, |
| { |
| "epoch": 4.328445747800586, |
| "grad_norm": 0.7353206267430158, |
| "learning_rate": 2.6595223828842578e-05, |
| "loss": 0.1031, |
| "mean_token_accuracy": 0.9708716943860054, |
| "step": 740 |
| }, |
| { |
| "epoch": 4.334310850439882, |
| "grad_norm": 0.8150751328388751, |
| "learning_rate": 2.6562059113012253e-05, |
| "loss": 0.0953, |
| "mean_token_accuracy": 0.9729399308562279, |
| "step": 741 |
| }, |
| { |
| "epoch": 4.340175953079179, |
| "grad_norm": 0.800064137257197, |
| "learning_rate": 2.6528877838749853e-05, |
| "loss": 0.0888, |
| "mean_token_accuracy": 0.9730389565229416, |
| "step": 742 |
| }, |
| { |
| "epoch": 4.346041055718475, |
| "grad_norm": 0.8094750752535848, |
| "learning_rate": 2.6495680126489984e-05, |
| "loss": 0.099, |
| "mean_token_accuracy": 0.9690711572766304, |
| "step": 743 |
| }, |
| { |
| "epoch": 4.351906158357771, |
| "grad_norm": 0.7956878136167119, |
| "learning_rate": 2.6462466096726954e-05, |
| "loss": 0.1071, |
| "mean_token_accuracy": 0.9694640338420868, |
| "step": 744 |
| }, |
| { |
| "epoch": 4.357771260997067, |
| "grad_norm": 0.9902999973042317, |
| "learning_rate": 2.6429235870014256e-05, |
| "loss": 0.0993, |
| "mean_token_accuracy": 0.9691943004727364, |
| "step": 745 |
| }, |
| { |
| "epoch": 4.363636363636363, |
| "grad_norm": 1.138966726928597, |
| "learning_rate": 2.639598956696421e-05, |
| "loss": 0.1296, |
| "mean_token_accuracy": 0.9653717577457428, |
| "step": 746 |
| }, |
| { |
| "epoch": 4.3695014662756595, |
| "grad_norm": 0.8390006741125879, |
| "learning_rate": 2.6362727308247458e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.9693955853581429, |
| "step": 747 |
| }, |
| { |
| "epoch": 4.375366568914956, |
| "grad_norm": 0.9486724629738932, |
| "learning_rate": 2.6329449214592568e-05, |
| "loss": 0.1134, |
| "mean_token_accuracy": 0.9696745052933693, |
| "step": 748 |
| }, |
| { |
| "epoch": 4.381231671554252, |
| "grad_norm": 1.1974747553210443, |
| "learning_rate": 2.6296155406785578e-05, |
| "loss": 0.1097, |
| "mean_token_accuracy": 0.9677048176527023, |
| "step": 749 |
| }, |
| { |
| "epoch": 4.387096774193548, |
| "grad_norm": 0.8717615502118474, |
| "learning_rate": 2.6262846005669572e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9716934859752655, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.392961876832844, |
| "grad_norm": 0.8679886161549661, |
| "learning_rate": 2.6229521132144212e-05, |
| "loss": 0.0983, |
| "mean_token_accuracy": 0.9671519547700882, |
| "step": 751 |
| }, |
| { |
| "epoch": 4.39882697947214, |
| "grad_norm": 0.9182101559650703, |
| "learning_rate": 2.619618090716534e-05, |
| "loss": 0.1026, |
| "mean_token_accuracy": 0.9699187725782394, |
| "step": 752 |
| }, |
| { |
| "epoch": 4.404692082111437, |
| "grad_norm": 0.7557881709721908, |
| "learning_rate": 2.61628254517445e-05, |
| "loss": 0.0937, |
| "mean_token_accuracy": 0.9722714796662331, |
| "step": 753 |
| }, |
| { |
| "epoch": 4.410557184750733, |
| "grad_norm": 0.9753894611598296, |
| "learning_rate": 2.612945488694853e-05, |
| "loss": 0.1196, |
| "mean_token_accuracy": 0.9658621773123741, |
| "step": 754 |
| }, |
| { |
| "epoch": 4.416422287390029, |
| "grad_norm": 0.8489499216990712, |
| "learning_rate": 2.6096069333899094e-05, |
| "loss": 0.1004, |
| "mean_token_accuracy": 0.9738951250910759, |
| "step": 755 |
| }, |
| { |
| "epoch": 4.422287390029325, |
| "grad_norm": 1.0767290195457695, |
| "learning_rate": 2.6062668913772275e-05, |
| "loss": 0.1339, |
| "mean_token_accuracy": 0.9635637626051903, |
| "step": 756 |
| }, |
| { |
| "epoch": 4.428152492668621, |
| "grad_norm": 2.284013657163814, |
| "learning_rate": 2.60292537477981e-05, |
| "loss": 0.1072, |
| "mean_token_accuracy": 0.9691743478178978, |
| "step": 757 |
| }, |
| { |
| "epoch": 4.4340175953079175, |
| "grad_norm": 0.9671090732833222, |
| "learning_rate": 2.5995823957260132e-05, |
| "loss": 0.127, |
| "mean_token_accuracy": 0.9612483829259872, |
| "step": 758 |
| }, |
| { |
| "epoch": 4.439882697947214, |
| "grad_norm": 0.7101994331100041, |
| "learning_rate": 2.596237966349501e-05, |
| "loss": 0.0992, |
| "mean_token_accuracy": 0.968992717564106, |
| "step": 759 |
| }, |
| { |
| "epoch": 4.44574780058651, |
| "grad_norm": 0.7693183821795423, |
| "learning_rate": 2.592892098789201e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9723697900772095, |
| "step": 760 |
| }, |
| { |
| "epoch": 4.451612903225806, |
| "grad_norm": 1.4733487666954843, |
| "learning_rate": 2.589544805189261e-05, |
| "loss": 0.0984, |
| "mean_token_accuracy": 0.9718485102057457, |
| "step": 761 |
| }, |
| { |
| "epoch": 4.457478005865102, |
| "grad_norm": 1.1763193238951348, |
| "learning_rate": 2.5861960976990056e-05, |
| "loss": 0.0965, |
| "mean_token_accuracy": 0.9736879169940948, |
| "step": 762 |
| }, |
| { |
| "epoch": 4.463343108504398, |
| "grad_norm": 1.1738256998389192, |
| "learning_rate": 2.5828459884728898e-05, |
| "loss": 0.1122, |
| "mean_token_accuracy": 0.9685143828392029, |
| "step": 763 |
| }, |
| { |
| "epoch": 4.469208211143695, |
| "grad_norm": 0.8326366862614876, |
| "learning_rate": 2.5794944896704572e-05, |
| "loss": 0.0956, |
| "mean_token_accuracy": 0.971512608230114, |
| "step": 764 |
| }, |
| { |
| "epoch": 4.475073313782991, |
| "grad_norm": 0.6126184789066507, |
| "learning_rate": 2.5761416134562955e-05, |
| "loss": 0.0904, |
| "mean_token_accuracy": 0.9716848284006119, |
| "step": 765 |
| }, |
| { |
| "epoch": 4.480938416422287, |
| "grad_norm": 0.9032550905603639, |
| "learning_rate": 2.5727873719999904e-05, |
| "loss": 0.0974, |
| "mean_token_accuracy": 0.9702484384179115, |
| "step": 766 |
| }, |
| { |
| "epoch": 4.486803519061583, |
| "grad_norm": 0.8188882179465061, |
| "learning_rate": 2.569431777476084e-05, |
| "loss": 0.1032, |
| "mean_token_accuracy": 0.9705123081803322, |
| "step": 767 |
| }, |
| { |
| "epoch": 4.492668621700879, |
| "grad_norm": 0.7156230718197097, |
| "learning_rate": 2.566074842064029e-05, |
| "loss": 0.0836, |
| "mean_token_accuracy": 0.9748258590698242, |
| "step": 768 |
| }, |
| { |
| "epoch": 4.4985337243401755, |
| "grad_norm": 0.7243676974968629, |
| "learning_rate": 2.562716577948145e-05, |
| "loss": 0.0913, |
| "mean_token_accuracy": 0.9733809903264046, |
| "step": 769 |
| }, |
| { |
| "epoch": 4.504398826979472, |
| "grad_norm": 0.956927225584052, |
| "learning_rate": 2.5593569973175757e-05, |
| "loss": 0.109, |
| "mean_token_accuracy": 0.9674596711993217, |
| "step": 770 |
| }, |
| { |
| "epoch": 4.510263929618768, |
| "grad_norm": 0.839214059168221, |
| "learning_rate": 2.5559961123662405e-05, |
| "loss": 0.1025, |
| "mean_token_accuracy": 0.9712679237127304, |
| "step": 771 |
| }, |
| { |
| "epoch": 4.516129032258064, |
| "grad_norm": 0.9417512208409332, |
| "learning_rate": 2.5526339352927956e-05, |
| "loss": 0.1198, |
| "mean_token_accuracy": 0.9672188460826874, |
| "step": 772 |
| }, |
| { |
| "epoch": 4.52199413489736, |
| "grad_norm": 0.9006219316570291, |
| "learning_rate": 2.5492704783005847e-05, |
| "loss": 0.1067, |
| "mean_token_accuracy": 0.9678135216236115, |
| "step": 773 |
| }, |
| { |
| "epoch": 4.527859237536656, |
| "grad_norm": 1.5476058537705526, |
| "learning_rate": 2.5459057535975985e-05, |
| "loss": 0.1365, |
| "mean_token_accuracy": 0.9669143557548523, |
| "step": 774 |
| }, |
| { |
| "epoch": 4.533724340175953, |
| "grad_norm": 0.956697552558829, |
| "learning_rate": 2.542539773396429e-05, |
| "loss": 0.1115, |
| "mean_token_accuracy": 0.9633852392435074, |
| "step": 775 |
| }, |
| { |
| "epoch": 4.539589442815249, |
| "grad_norm": 1.197546908803636, |
| "learning_rate": 2.5391725499142253e-05, |
| "loss": 0.1357, |
| "mean_token_accuracy": 0.9662409871816635, |
| "step": 776 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 0.7588534732881831, |
| "learning_rate": 2.535804095372648e-05, |
| "loss": 0.0901, |
| "mean_token_accuracy": 0.9716041162610054, |
| "step": 777 |
| }, |
| { |
| "epoch": 4.551319648093841, |
| "grad_norm": 0.8780606997286142, |
| "learning_rate": 2.5324344219978273e-05, |
| "loss": 0.0973, |
| "mean_token_accuracy": 0.9695460423827171, |
| "step": 778 |
| }, |
| { |
| "epoch": 4.557184750733137, |
| "grad_norm": 0.8045552377061164, |
| "learning_rate": 2.5290635420203162e-05, |
| "loss": 0.1021, |
| "mean_token_accuracy": 0.9703366085886955, |
| "step": 779 |
| }, |
| { |
| "epoch": 4.563049853372434, |
| "grad_norm": 0.9358205564032939, |
| "learning_rate": 2.525691467675048e-05, |
| "loss": 0.1159, |
| "mean_token_accuracy": 0.9681701958179474, |
| "step": 780 |
| }, |
| { |
| "epoch": 4.568914956011731, |
| "grad_norm": 0.7554713795930256, |
| "learning_rate": 2.5223182112012897e-05, |
| "loss": 0.101, |
| "mean_token_accuracy": 0.9721342325210571, |
| "step": 781 |
| }, |
| { |
| "epoch": 4.574780058651027, |
| "grad_norm": 0.5804191186796761, |
| "learning_rate": 2.5189437848426016e-05, |
| "loss": 0.0809, |
| "mean_token_accuracy": 0.9757244363427162, |
| "step": 782 |
| }, |
| { |
| "epoch": 4.580645161290323, |
| "grad_norm": 1.0167268132012308, |
| "learning_rate": 2.515568200846787e-05, |
| "loss": 0.1193, |
| "mean_token_accuracy": 0.9649367853999138, |
| "step": 783 |
| }, |
| { |
| "epoch": 4.586510263929619, |
| "grad_norm": 0.9322914799762485, |
| "learning_rate": 2.5121914714658526e-05, |
| "loss": 0.1034, |
| "mean_token_accuracy": 0.9690342247486115, |
| "step": 784 |
| }, |
| { |
| "epoch": 4.592375366568915, |
| "grad_norm": 0.7802061746954657, |
| "learning_rate": 2.5088136089559636e-05, |
| "loss": 0.0898, |
| "mean_token_accuracy": 0.9727255925536156, |
| "step": 785 |
| }, |
| { |
| "epoch": 4.5982404692082115, |
| "grad_norm": 0.5844702630089805, |
| "learning_rate": 2.5054346255773952e-05, |
| "loss": 0.0783, |
| "mean_token_accuracy": 0.9748023822903633, |
| "step": 786 |
| }, |
| { |
| "epoch": 4.604105571847508, |
| "grad_norm": 0.7971317025860829, |
| "learning_rate": 2.502054533594493e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9730968326330185, |
| "step": 787 |
| }, |
| { |
| "epoch": 4.609970674486804, |
| "grad_norm": 0.7592860917285904, |
| "learning_rate": 2.4986733452756264e-05, |
| "loss": 0.0994, |
| "mean_token_accuracy": 0.9701942130923271, |
| "step": 788 |
| }, |
| { |
| "epoch": 4.6158357771261, |
| "grad_norm": 0.8974946786275971, |
| "learning_rate": 2.495291072893142e-05, |
| "loss": 0.1094, |
| "mean_token_accuracy": 0.9706485345959663, |
| "step": 789 |
| }, |
| { |
| "epoch": 4.621700879765396, |
| "grad_norm": 0.9918330093432357, |
| "learning_rate": 2.4919077287233237e-05, |
| "loss": 0.1131, |
| "mean_token_accuracy": 0.9685276672244072, |
| "step": 790 |
| }, |
| { |
| "epoch": 4.627565982404692, |
| "grad_norm": 0.7579797556002252, |
| "learning_rate": 2.4885233250463445e-05, |
| "loss": 0.0999, |
| "mean_token_accuracy": 0.9702299237251282, |
| "step": 791 |
| }, |
| { |
| "epoch": 4.633431085043989, |
| "grad_norm": 0.8102978461438669, |
| "learning_rate": 2.485137874146222e-05, |
| "loss": 0.1013, |
| "mean_token_accuracy": 0.9672133773565292, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.639296187683285, |
| "grad_norm": 0.9750006795393742, |
| "learning_rate": 2.4817513883107762e-05, |
| "loss": 0.1169, |
| "mean_token_accuracy": 0.963016502559185, |
| "step": 793 |
| }, |
| { |
| "epoch": 4.645161290322581, |
| "grad_norm": 0.6784007500449948, |
| "learning_rate": 2.4783638798315822e-05, |
| "loss": 0.0879, |
| "mean_token_accuracy": 0.9738304242491722, |
| "step": 794 |
| }, |
| { |
| "epoch": 4.651026392961877, |
| "grad_norm": 0.9884915387381938, |
| "learning_rate": 2.4749753610039288e-05, |
| "loss": 0.0928, |
| "mean_token_accuracy": 0.9698395952582359, |
| "step": 795 |
| }, |
| { |
| "epoch": 4.656891495601173, |
| "grad_norm": 0.804556017449245, |
| "learning_rate": 2.4715858441267706e-05, |
| "loss": 0.0949, |
| "mean_token_accuracy": 0.9707165434956551, |
| "step": 796 |
| }, |
| { |
| "epoch": 4.6627565982404695, |
| "grad_norm": 1.2020438772374247, |
| "learning_rate": 2.4681953415026845e-05, |
| "loss": 0.1252, |
| "mean_token_accuracy": 0.9631582796573639, |
| "step": 797 |
| }, |
| { |
| "epoch": 4.668621700879766, |
| "grad_norm": 0.8366726200311924, |
| "learning_rate": 2.464803865437826e-05, |
| "loss": 0.0954, |
| "mean_token_accuracy": 0.9677169546484947, |
| "step": 798 |
| }, |
| { |
| "epoch": 4.674486803519062, |
| "grad_norm": 1.0400561866526332, |
| "learning_rate": 2.461411428241883e-05, |
| "loss": 0.1256, |
| "mean_token_accuracy": 0.964072935283184, |
| "step": 799 |
| }, |
| { |
| "epoch": 4.680351906158358, |
| "grad_norm": 0.9623680214082836, |
| "learning_rate": 2.4580180422280325e-05, |
| "loss": 0.1042, |
| "mean_token_accuracy": 0.9697307646274567, |
| "step": 800 |
| }, |
| { |
| "epoch": 4.686217008797654, |
| "grad_norm": 0.9936707065124232, |
| "learning_rate": 2.4546237197128955e-05, |
| "loss": 0.1056, |
| "mean_token_accuracy": 0.9692076668143272, |
| "step": 801 |
| }, |
| { |
| "epoch": 4.69208211143695, |
| "grad_norm": 0.7547232442792623, |
| "learning_rate": 2.451228473016492e-05, |
| "loss": 0.1019, |
| "mean_token_accuracy": 0.9720749333500862, |
| "step": 802 |
| }, |
| { |
| "epoch": 4.697947214076247, |
| "grad_norm": 0.6539188611720734, |
| "learning_rate": 2.447832314462196e-05, |
| "loss": 0.0988, |
| "mean_token_accuracy": 0.9708434194326401, |
| "step": 803 |
| }, |
| { |
| "epoch": 4.703812316715543, |
| "grad_norm": 0.787149153305339, |
| "learning_rate": 2.444435256376692e-05, |
| "loss": 0.0969, |
| "mean_token_accuracy": 0.9698523208498955, |
| "step": 804 |
| }, |
| { |
| "epoch": 4.709677419354839, |
| "grad_norm": 0.9214253887479193, |
| "learning_rate": 2.4410373110899278e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9752322733402252, |
| "step": 805 |
| }, |
| { |
| "epoch": 4.715542521994135, |
| "grad_norm": 0.96985990470589, |
| "learning_rate": 2.4376384909350735e-05, |
| "loss": 0.1133, |
| "mean_token_accuracy": 0.9648006334900856, |
| "step": 806 |
| }, |
| { |
| "epoch": 4.721407624633431, |
| "grad_norm": 0.7705243515793144, |
| "learning_rate": 2.434238808248472e-05, |
| "loss": 0.0932, |
| "mean_token_accuracy": 0.9724510610103607, |
| "step": 807 |
| }, |
| { |
| "epoch": 4.7272727272727275, |
| "grad_norm": 0.8385330995599455, |
| "learning_rate": 2.4308382753696e-05, |
| "loss": 0.101, |
| "mean_token_accuracy": 0.9696679040789604, |
| "step": 808 |
| }, |
| { |
| "epoch": 4.733137829912024, |
| "grad_norm": 0.9962089643314436, |
| "learning_rate": 2.4274369046410183e-05, |
| "loss": 0.1164, |
| "mean_token_accuracy": 0.9683369919657707, |
| "step": 809 |
| }, |
| { |
| "epoch": 4.73900293255132, |
| "grad_norm": 0.7772156088138843, |
| "learning_rate": 2.4240347084083284e-05, |
| "loss": 0.096, |
| "mean_token_accuracy": 0.9717853516340256, |
| "step": 810 |
| }, |
| { |
| "epoch": 4.744868035190616, |
| "grad_norm": 3.9377209302415968, |
| "learning_rate": 2.4206316990201288e-05, |
| "loss": 0.1192, |
| "mean_token_accuracy": 0.9630280062556267, |
| "step": 811 |
| }, |
| { |
| "epoch": 4.750733137829912, |
| "grad_norm": 1.052866557087443, |
| "learning_rate": 2.4172278888279686e-05, |
| "loss": 0.1171, |
| "mean_token_accuracy": 0.9658652395009995, |
| "step": 812 |
| }, |
| { |
| "epoch": 4.756598240469208, |
| "grad_norm": 0.8332989638125091, |
| "learning_rate": 2.4138232901863053e-05, |
| "loss": 0.1067, |
| "mean_token_accuracy": 0.9677643477916718, |
| "step": 813 |
| }, |
| { |
| "epoch": 4.762463343108505, |
| "grad_norm": 0.7676532634589678, |
| "learning_rate": 2.4104179154524557e-05, |
| "loss": 0.0861, |
| "mean_token_accuracy": 0.9748517572879791, |
| "step": 814 |
| }, |
| { |
| "epoch": 4.768328445747801, |
| "grad_norm": 0.7491375439484187, |
| "learning_rate": 2.4070117769865554e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.9721824452280998, |
| "step": 815 |
| }, |
| { |
| "epoch": 4.774193548387097, |
| "grad_norm": 0.7082397718002087, |
| "learning_rate": 2.403604887151512e-05, |
| "loss": 0.0986, |
| "mean_token_accuracy": 0.9698486328125, |
| "step": 816 |
| }, |
| { |
| "epoch": 4.780058651026393, |
| "grad_norm": 0.8602958678227502, |
| "learning_rate": 2.400197258312959e-05, |
| "loss": 0.0968, |
| "mean_token_accuracy": 0.9724563658237457, |
| "step": 817 |
| }, |
| { |
| "epoch": 4.785923753665689, |
| "grad_norm": 0.7826309437388894, |
| "learning_rate": 2.3967889028392115e-05, |
| "loss": 0.0854, |
| "mean_token_accuracy": 0.9723799675703049, |
| "step": 818 |
| }, |
| { |
| "epoch": 4.7917888563049855, |
| "grad_norm": 0.8084978346561186, |
| "learning_rate": 2.3933798331012255e-05, |
| "loss": 0.1024, |
| "mean_token_accuracy": 0.9672785773873329, |
| "step": 819 |
| }, |
| { |
| "epoch": 4.797653958944282, |
| "grad_norm": 0.8416916669164977, |
| "learning_rate": 2.3899700614725458e-05, |
| "loss": 0.1021, |
| "mean_token_accuracy": 0.9661071300506592, |
| "step": 820 |
| }, |
| { |
| "epoch": 4.803519061583578, |
| "grad_norm": 0.8279382705506013, |
| "learning_rate": 2.3865596003292674e-05, |
| "loss": 0.101, |
| "mean_token_accuracy": 0.9684831723570824, |
| "step": 821 |
| }, |
| { |
| "epoch": 4.809384164222874, |
| "grad_norm": 0.8786095068042057, |
| "learning_rate": 2.3831484620499867e-05, |
| "loss": 0.1074, |
| "mean_token_accuracy": 0.9685612991452217, |
| "step": 822 |
| }, |
| { |
| "epoch": 4.81524926686217, |
| "grad_norm": 1.0040505276363547, |
| "learning_rate": 2.3797366590157565e-05, |
| "loss": 0.1195, |
| "mean_token_accuracy": 0.9612911120057106, |
| "step": 823 |
| }, |
| { |
| "epoch": 4.821114369501466, |
| "grad_norm": 0.8072349724088913, |
| "learning_rate": 2.3763242036100457e-05, |
| "loss": 0.0987, |
| "mean_token_accuracy": 0.9705159142613411, |
| "step": 824 |
| }, |
| { |
| "epoch": 4.826979472140763, |
| "grad_norm": 0.9064708195199968, |
| "learning_rate": 2.372911108218688e-05, |
| "loss": 0.1018, |
| "mean_token_accuracy": 0.9692626893520355, |
| "step": 825 |
| }, |
| { |
| "epoch": 4.832844574780059, |
| "grad_norm": 1.0817212148035031, |
| "learning_rate": 2.3694973852298425e-05, |
| "loss": 0.1185, |
| "mean_token_accuracy": 0.9651465937495232, |
| "step": 826 |
| }, |
| { |
| "epoch": 4.838709677419355, |
| "grad_norm": 0.8543951865046087, |
| "learning_rate": 2.3660830470339436e-05, |
| "loss": 0.1029, |
| "mean_token_accuracy": 0.9690027311444283, |
| "step": 827 |
| }, |
| { |
| "epoch": 4.844574780058651, |
| "grad_norm": 0.6162780385937312, |
| "learning_rate": 2.362668106023661e-05, |
| "loss": 0.0916, |
| "mean_token_accuracy": 0.9742050394415855, |
| "step": 828 |
| }, |
| { |
| "epoch": 4.850439882697947, |
| "grad_norm": 0.9398325918918323, |
| "learning_rate": 2.3592525745938515e-05, |
| "loss": 0.1007, |
| "mean_token_accuracy": 0.9716757461428642, |
| "step": 829 |
| }, |
| { |
| "epoch": 4.8563049853372435, |
| "grad_norm": 0.7602257778379286, |
| "learning_rate": 2.355836465141513e-05, |
| "loss": 0.0794, |
| "mean_token_accuracy": 0.9756976217031479, |
| "step": 830 |
| }, |
| { |
| "epoch": 4.86217008797654, |
| "grad_norm": 0.9022011629225589, |
| "learning_rate": 2.3524197900657447e-05, |
| "loss": 0.1169, |
| "mean_token_accuracy": 0.9684564545750618, |
| "step": 831 |
| }, |
| { |
| "epoch": 4.868035190615836, |
| "grad_norm": 0.650860880701899, |
| "learning_rate": 2.3490025617676966e-05, |
| "loss": 0.0837, |
| "mean_token_accuracy": 0.975691981613636, |
| "step": 832 |
| }, |
| { |
| "epoch": 4.873900293255132, |
| "grad_norm": 0.8971676331873251, |
| "learning_rate": 2.3455847926505283e-05, |
| "loss": 0.1129, |
| "mean_token_accuracy": 0.9650413244962692, |
| "step": 833 |
| }, |
| { |
| "epoch": 4.879765395894428, |
| "grad_norm": 0.937427582210325, |
| "learning_rate": 2.3421664951193596e-05, |
| "loss": 0.1098, |
| "mean_token_accuracy": 0.9684758335351944, |
| "step": 834 |
| }, |
| { |
| "epoch": 4.885630498533724, |
| "grad_norm": 0.8814505193033745, |
| "learning_rate": 2.3387476815812313e-05, |
| "loss": 0.1032, |
| "mean_token_accuracy": 0.9702811613678932, |
| "step": 835 |
| }, |
| { |
| "epoch": 4.891495601173021, |
| "grad_norm": 0.8136347217934341, |
| "learning_rate": 2.3353283644450556e-05, |
| "loss": 0.1049, |
| "mean_token_accuracy": 0.9681308940052986, |
| "step": 836 |
| }, |
| { |
| "epoch": 4.897360703812317, |
| "grad_norm": 1.0361749212065177, |
| "learning_rate": 2.3319085561215724e-05, |
| "loss": 0.1088, |
| "mean_token_accuracy": 0.9681940153241158, |
| "step": 837 |
| }, |
| { |
| "epoch": 4.903225806451613, |
| "grad_norm": 0.7246651123258426, |
| "learning_rate": 2.328488269023305e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.9740229845046997, |
| "step": 838 |
| }, |
| { |
| "epoch": 4.909090909090909, |
| "grad_norm": 0.9582355610327213, |
| "learning_rate": 2.3250675155645136e-05, |
| "loss": 0.0994, |
| "mean_token_accuracy": 0.9708064943552017, |
| "step": 839 |
| }, |
| { |
| "epoch": 4.914956011730205, |
| "grad_norm": 0.8597667767361529, |
| "learning_rate": 2.3216463081611525e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9721712917089462, |
| "step": 840 |
| }, |
| { |
| "epoch": 4.9208211143695015, |
| "grad_norm": 0.9203287999724475, |
| "learning_rate": 2.3182246592308235e-05, |
| "loss": 0.1134, |
| "mean_token_accuracy": 0.9678708836436272, |
| "step": 841 |
| }, |
| { |
| "epoch": 4.926686217008798, |
| "grad_norm": 0.7731015246866831, |
| "learning_rate": 2.314802581192728e-05, |
| "loss": 0.0909, |
| "mean_token_accuracy": 0.9706169962882996, |
| "step": 842 |
| }, |
| { |
| "epoch": 4.932551319648094, |
| "grad_norm": 0.9691449435397647, |
| "learning_rate": 2.311380086467629e-05, |
| "loss": 0.1138, |
| "mean_token_accuracy": 0.9661426022648811, |
| "step": 843 |
| }, |
| { |
| "epoch": 4.93841642228739, |
| "grad_norm": 0.72854018802925, |
| "learning_rate": 2.3079571874778e-05, |
| "loss": 0.1007, |
| "mean_token_accuracy": 0.9667091220617294, |
| "step": 844 |
| }, |
| { |
| "epoch": 4.944281524926686, |
| "grad_norm": 0.6600580029561475, |
| "learning_rate": 2.304533896646981e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9744493290781975, |
| "step": 845 |
| }, |
| { |
| "epoch": 4.9501466275659824, |
| "grad_norm": 0.8077377461501789, |
| "learning_rate": 2.3011102264003354e-05, |
| "loss": 0.0992, |
| "mean_token_accuracy": 0.9715530574321747, |
| "step": 846 |
| }, |
| { |
| "epoch": 4.956011730205279, |
| "grad_norm": 0.8026305302127565, |
| "learning_rate": 2.2976861891644045e-05, |
| "loss": 0.0941, |
| "mean_token_accuracy": 0.9704462736845016, |
| "step": 847 |
| }, |
| { |
| "epoch": 4.961876832844575, |
| "grad_norm": 0.839509361357775, |
| "learning_rate": 2.2942617973670596e-05, |
| "loss": 0.0955, |
| "mean_token_accuracy": 0.970968209207058, |
| "step": 848 |
| }, |
| { |
| "epoch": 4.967741935483871, |
| "grad_norm": 1.0376899814733738, |
| "learning_rate": 2.2908370634374603e-05, |
| "loss": 0.1387, |
| "mean_token_accuracy": 0.9611359685659409, |
| "step": 849 |
| }, |
| { |
| "epoch": 4.973607038123167, |
| "grad_norm": 0.9686754058096747, |
| "learning_rate": 2.287411999806007e-05, |
| "loss": 0.1103, |
| "mean_token_accuracy": 0.9722190052270889, |
| "step": 850 |
| }, |
| { |
| "epoch": 4.979472140762463, |
| "grad_norm": 0.8862617626596047, |
| "learning_rate": 2.2839866189042983e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.9709000736474991, |
| "step": 851 |
| }, |
| { |
| "epoch": 4.9853372434017595, |
| "grad_norm": 0.8477877839763255, |
| "learning_rate": 2.2805609331650826e-05, |
| "loss": 0.1113, |
| "mean_token_accuracy": 0.9674248471856117, |
| "step": 852 |
| }, |
| { |
| "epoch": 4.991202346041056, |
| "grad_norm": 0.8866585241499966, |
| "learning_rate": 2.2771349550222158e-05, |
| "loss": 0.1004, |
| "mean_token_accuracy": 0.9717306420207024, |
| "step": 853 |
| }, |
| { |
| "epoch": 4.997067448680352, |
| "grad_norm": 0.6095610289437057, |
| "learning_rate": 2.273708696910616e-05, |
| "loss": 0.0823, |
| "mean_token_accuracy": 0.9722500741481781, |
| "step": 854 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.6095610289437057, |
| "learning_rate": 2.2702821712662147e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9760673493146896, |
| "step": 855 |
| }, |
| { |
| "epoch": 5.005865102639296, |
| "grad_norm": 0.8433148437880541, |
| "learning_rate": 2.2668553905259168e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9737215414643288, |
| "step": 856 |
| }, |
| { |
| "epoch": 5.011730205278592, |
| "grad_norm": 0.5159271864203083, |
| "learning_rate": 2.2634283671275523e-05, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.977745771408081, |
| "step": 857 |
| }, |
| { |
| "epoch": 5.0175953079178885, |
| "grad_norm": 0.6773169070419274, |
| "learning_rate": 2.2600011135098323e-05, |
| "loss": 0.0807, |
| "mean_token_accuracy": 0.9754450246691704, |
| "step": 858 |
| }, |
| { |
| "epoch": 5.023460410557185, |
| "grad_norm": 0.6566845303303651, |
| "learning_rate": 2.2565736421123035e-05, |
| "loss": 0.0987, |
| "mean_token_accuracy": 0.973513200879097, |
| "step": 859 |
| }, |
| { |
| "epoch": 5.029325513196481, |
| "grad_norm": 1.0725755922059608, |
| "learning_rate": 2.253145965375302e-05, |
| "loss": 0.1049, |
| "mean_token_accuracy": 0.9684402048587799, |
| "step": 860 |
| }, |
| { |
| "epoch": 5.035190615835777, |
| "grad_norm": 0.7950554728335751, |
| "learning_rate": 2.2497180957399108e-05, |
| "loss": 0.1012, |
| "mean_token_accuracy": 0.9666916355490685, |
| "step": 861 |
| }, |
| { |
| "epoch": 5.041055718475073, |
| "grad_norm": 0.8569776292433064, |
| "learning_rate": 2.246290045647912e-05, |
| "loss": 0.0788, |
| "mean_token_accuracy": 0.97861647605896, |
| "step": 862 |
| }, |
| { |
| "epoch": 5.0469208211143695, |
| "grad_norm": 0.6247190584519964, |
| "learning_rate": 2.242861827541742e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9780908152461052, |
| "step": 863 |
| }, |
| { |
| "epoch": 5.052785923753666, |
| "grad_norm": 0.7794311246553162, |
| "learning_rate": 2.2394334538644494e-05, |
| "loss": 0.08, |
| "mean_token_accuracy": 0.9768287613987923, |
| "step": 864 |
| }, |
| { |
| "epoch": 5.058651026392962, |
| "grad_norm": 0.8297165299310638, |
| "learning_rate": 2.2360049370596454e-05, |
| "loss": 0.095, |
| "mean_token_accuracy": 0.9734896495938301, |
| "step": 865 |
| }, |
| { |
| "epoch": 5.064516129032258, |
| "grad_norm": 0.7979594762098186, |
| "learning_rate": 2.2325762895714616e-05, |
| "loss": 0.087, |
| "mean_token_accuracy": 0.9727722704410553, |
| "step": 866 |
| }, |
| { |
| "epoch": 5.070381231671554, |
| "grad_norm": 0.6589844664319869, |
| "learning_rate": 2.2291475238445033e-05, |
| "loss": 0.0901, |
| "mean_token_accuracy": 0.9736703634262085, |
| "step": 867 |
| }, |
| { |
| "epoch": 5.07624633431085, |
| "grad_norm": 2.042890482434605, |
| "learning_rate": 2.225718652323805e-05, |
| "loss": 0.0853, |
| "mean_token_accuracy": 0.9707973897457123, |
| "step": 868 |
| }, |
| { |
| "epoch": 5.0821114369501466, |
| "grad_norm": 0.9022788360958364, |
| "learning_rate": 2.2222896874547856e-05, |
| "loss": 0.1093, |
| "mean_token_accuracy": 0.97090233117342, |
| "step": 869 |
| }, |
| { |
| "epoch": 5.087976539589443, |
| "grad_norm": 0.773657493300953, |
| "learning_rate": 2.2188606416832035e-05, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9799191579222679, |
| "step": 870 |
| }, |
| { |
| "epoch": 5.093841642228739, |
| "grad_norm": 0.5823987344196742, |
| "learning_rate": 2.2154315274551093e-05, |
| "loss": 0.0934, |
| "mean_token_accuracy": 0.9723178669810295, |
| "step": 871 |
| }, |
| { |
| "epoch": 5.099706744868035, |
| "grad_norm": 0.6786086304917306, |
| "learning_rate": 2.2120023572168026e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9762729480862617, |
| "step": 872 |
| }, |
| { |
| "epoch": 5.105571847507331, |
| "grad_norm": 0.7089902588796277, |
| "learning_rate": 2.208573143414787e-05, |
| "loss": 0.079, |
| "mean_token_accuracy": 0.9801476299762726, |
| "step": 873 |
| }, |
| { |
| "epoch": 5.1114369501466275, |
| "grad_norm": 0.7326859159400232, |
| "learning_rate": 2.2051438984957234e-05, |
| "loss": 0.0888, |
| "mean_token_accuracy": 0.9746009409427643, |
| "step": 874 |
| }, |
| { |
| "epoch": 5.117302052785924, |
| "grad_norm": 0.6965082129251428, |
| "learning_rate": 2.2017146349063855e-05, |
| "loss": 0.0902, |
| "mean_token_accuracy": 0.9732745662331581, |
| "step": 875 |
| }, |
| { |
| "epoch": 5.12316715542522, |
| "grad_norm": 0.6205158598733057, |
| "learning_rate": 2.1982853650936154e-05, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.9761428236961365, |
| "step": 876 |
| }, |
| { |
| "epoch": 5.129032258064516, |
| "grad_norm": 0.6306034174676098, |
| "learning_rate": 2.1948561015042772e-05, |
| "loss": 0.089, |
| "mean_token_accuracy": 0.9759569987654686, |
| "step": 877 |
| }, |
| { |
| "epoch": 5.134897360703812, |
| "grad_norm": 0.7374044872193467, |
| "learning_rate": 2.1914268565852134e-05, |
| "loss": 0.1016, |
| "mean_token_accuracy": 0.9703678116202354, |
| "step": 878 |
| }, |
| { |
| "epoch": 5.140762463343108, |
| "grad_norm": 0.65191353602101, |
| "learning_rate": 2.1879976427831983e-05, |
| "loss": 0.0834, |
| "mean_token_accuracy": 0.9758019149303436, |
| "step": 879 |
| }, |
| { |
| "epoch": 5.146627565982405, |
| "grad_norm": 0.7506644384525571, |
| "learning_rate": 2.1845684725448916e-05, |
| "loss": 0.0956, |
| "mean_token_accuracy": 0.9727787226438522, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.152492668621701, |
| "grad_norm": 0.7900929308120329, |
| "learning_rate": 2.181139358316797e-05, |
| "loss": 0.0857, |
| "mean_token_accuracy": 0.9730308651924133, |
| "step": 881 |
| }, |
| { |
| "epoch": 5.158357771260997, |
| "grad_norm": 0.6620605131204909, |
| "learning_rate": 2.1777103125452146e-05, |
| "loss": 0.0848, |
| "mean_token_accuracy": 0.9756103083491325, |
| "step": 882 |
| }, |
| { |
| "epoch": 5.164222873900293, |
| "grad_norm": 0.8667893086755721, |
| "learning_rate": 2.1742813476761958e-05, |
| "loss": 0.1017, |
| "mean_token_accuracy": 0.9711831659078598, |
| "step": 883 |
| }, |
| { |
| "epoch": 5.170087976539589, |
| "grad_norm": 1.7675263240094965, |
| "learning_rate": 2.1708524761554973e-05, |
| "loss": 0.0837, |
| "mean_token_accuracy": 0.9736537113785744, |
| "step": 884 |
| }, |
| { |
| "epoch": 5.1759530791788855, |
| "grad_norm": 0.5726645519349775, |
| "learning_rate": 2.1674237104285393e-05, |
| "loss": 0.0827, |
| "mean_token_accuracy": 0.9737741276621819, |
| "step": 885 |
| }, |
| { |
| "epoch": 5.181818181818182, |
| "grad_norm": 0.7145760041095544, |
| "learning_rate": 2.1639950629403552e-05, |
| "loss": 0.0766, |
| "mean_token_accuracy": 0.9776047691702843, |
| "step": 886 |
| }, |
| { |
| "epoch": 5.187683284457478, |
| "grad_norm": 0.8323224710208923, |
| "learning_rate": 2.1605665461355515e-05, |
| "loss": 0.0865, |
| "mean_token_accuracy": 0.975310780107975, |
| "step": 887 |
| }, |
| { |
| "epoch": 5.193548387096774, |
| "grad_norm": 0.7231739554172291, |
| "learning_rate": 2.1571381724582588e-05, |
| "loss": 0.0929, |
| "mean_token_accuracy": 0.9715317115187645, |
| "step": 888 |
| }, |
| { |
| "epoch": 5.19941348973607, |
| "grad_norm": 0.909867276658091, |
| "learning_rate": 2.153709954352089e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9758851453661919, |
| "step": 889 |
| }, |
| { |
| "epoch": 5.205278592375366, |
| "grad_norm": 0.8188932670265725, |
| "learning_rate": 2.15028190426009e-05, |
| "loss": 0.0918, |
| "mean_token_accuracy": 0.9724317267537117, |
| "step": 890 |
| }, |
| { |
| "epoch": 5.211143695014663, |
| "grad_norm": 0.5670047382739889, |
| "learning_rate": 2.1468540346246986e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9727488458156586, |
| "step": 891 |
| }, |
| { |
| "epoch": 5.217008797653959, |
| "grad_norm": 0.9745874503233469, |
| "learning_rate": 2.143426357887697e-05, |
| "loss": 0.0982, |
| "mean_token_accuracy": 0.9717305302619934, |
| "step": 892 |
| }, |
| { |
| "epoch": 5.222873900293255, |
| "grad_norm": 0.7154601998505632, |
| "learning_rate": 2.139998886490169e-05, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9806524217128754, |
| "step": 893 |
| }, |
| { |
| "epoch": 5.228739002932551, |
| "grad_norm": 0.5296720463890491, |
| "learning_rate": 2.136571632872449e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.9748145341873169, |
| "step": 894 |
| }, |
| { |
| "epoch": 5.234604105571847, |
| "grad_norm": 0.8692292566562774, |
| "learning_rate": 2.1331446094740845e-05, |
| "loss": 0.1122, |
| "mean_token_accuracy": 0.9713733717799187, |
| "step": 895 |
| }, |
| { |
| "epoch": 5.2404692082111435, |
| "grad_norm": 0.9200261999499213, |
| "learning_rate": 2.1297178287337865e-05, |
| "loss": 0.1022, |
| "mean_token_accuracy": 0.9730254113674164, |
| "step": 896 |
| }, |
| { |
| "epoch": 5.24633431085044, |
| "grad_norm": 0.8792886399633073, |
| "learning_rate": 2.1262913030893855e-05, |
| "loss": 0.103, |
| "mean_token_accuracy": 0.9704674929380417, |
| "step": 897 |
| }, |
| { |
| "epoch": 5.252199413489736, |
| "grad_norm": 0.9771077901678256, |
| "learning_rate": 2.1228650449777848e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.972001887857914, |
| "step": 898 |
| }, |
| { |
| "epoch": 5.258064516129032, |
| "grad_norm": 0.7113805154464254, |
| "learning_rate": 2.1194390668349186e-05, |
| "loss": 0.0945, |
| "mean_token_accuracy": 0.9730637967586517, |
| "step": 899 |
| }, |
| { |
| "epoch": 5.263929618768328, |
| "grad_norm": 0.7719540492961735, |
| "learning_rate": 2.116013381095703e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9765499979257584, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.269794721407624, |
| "grad_norm": 0.5930886595639958, |
| "learning_rate": 2.112588000193994e-05, |
| "loss": 0.0775, |
| "mean_token_accuracy": 0.9765195026993752, |
| "step": 901 |
| }, |
| { |
| "epoch": 5.275659824046921, |
| "grad_norm": 0.823286226023431, |
| "learning_rate": 2.1091629365625403e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9732163697481155, |
| "step": 902 |
| }, |
| { |
| "epoch": 5.281524926686217, |
| "grad_norm": 0.9117273368025238, |
| "learning_rate": 2.105738202632941e-05, |
| "loss": 0.0965, |
| "mean_token_accuracy": 0.973268635571003, |
| "step": 903 |
| }, |
| { |
| "epoch": 5.287390029325513, |
| "grad_norm": 0.6499800912484074, |
| "learning_rate": 2.1023138108355957e-05, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9788585156202316, |
| "step": 904 |
| }, |
| { |
| "epoch": 5.293255131964809, |
| "grad_norm": 0.8350311296266436, |
| "learning_rate": 2.098889773599665e-05, |
| "loss": 0.1091, |
| "mean_token_accuracy": 0.9673629701137543, |
| "step": 905 |
| }, |
| { |
| "epoch": 5.299120234604105, |
| "grad_norm": 0.8758013377718885, |
| "learning_rate": 2.0954661033530193e-05, |
| "loss": 0.0832, |
| "mean_token_accuracy": 0.9746165573596954, |
| "step": 906 |
| }, |
| { |
| "epoch": 5.3049853372434015, |
| "grad_norm": 0.7318638597492443, |
| "learning_rate": 2.0920428125222004e-05, |
| "loss": 0.0881, |
| "mean_token_accuracy": 0.9729284644126892, |
| "step": 907 |
| }, |
| { |
| "epoch": 5.310850439882698, |
| "grad_norm": 0.5207542607039044, |
| "learning_rate": 2.0886199135323712e-05, |
| "loss": 0.0907, |
| "mean_token_accuracy": 0.9727116152644157, |
| "step": 908 |
| }, |
| { |
| "epoch": 5.316715542521994, |
| "grad_norm": 0.8002194745455268, |
| "learning_rate": 2.085197418807272e-05, |
| "loss": 0.0903, |
| "mean_token_accuracy": 0.9738972410559654, |
| "step": 909 |
| }, |
| { |
| "epoch": 5.32258064516129, |
| "grad_norm": 0.7003191473454057, |
| "learning_rate": 2.0817753407691774e-05, |
| "loss": 0.0904, |
| "mean_token_accuracy": 0.9728701040148735, |
| "step": 910 |
| }, |
| { |
| "epoch": 5.328445747800586, |
| "grad_norm": 0.6997923911492139, |
| "learning_rate": 2.0783536918388477e-05, |
| "loss": 0.1048, |
| "mean_token_accuracy": 0.9690842255949974, |
| "step": 911 |
| }, |
| { |
| "epoch": 5.334310850439882, |
| "grad_norm": 1.573742684312648, |
| "learning_rate": 2.0749324844354867e-05, |
| "loss": 0.091, |
| "mean_token_accuracy": 0.9728436172008514, |
| "step": 912 |
| }, |
| { |
| "epoch": 5.340175953079179, |
| "grad_norm": 0.6744667083171827, |
| "learning_rate": 2.0715117309766953e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9753686562180519, |
| "step": 913 |
| }, |
| { |
| "epoch": 5.346041055718475, |
| "grad_norm": 0.5591477289746339, |
| "learning_rate": 2.068091443878428e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9701094627380371, |
| "step": 914 |
| }, |
| { |
| "epoch": 5.351906158357771, |
| "grad_norm": 0.8062620386979885, |
| "learning_rate": 2.064671635554945e-05, |
| "loss": 0.104, |
| "mean_token_accuracy": 0.9726444035768509, |
| "step": 915 |
| }, |
| { |
| "epoch": 5.357771260997067, |
| "grad_norm": 0.7825370740045777, |
| "learning_rate": 2.0612523184187693e-05, |
| "loss": 0.0815, |
| "mean_token_accuracy": 0.9739454016089439, |
| "step": 916 |
| }, |
| { |
| "epoch": 5.363636363636363, |
| "grad_norm": 0.5988992551643588, |
| "learning_rate": 2.057833504880641e-05, |
| "loss": 0.0945, |
| "mean_token_accuracy": 0.9690568298101425, |
| "step": 917 |
| }, |
| { |
| "epoch": 5.3695014662756595, |
| "grad_norm": 0.8655470524535265, |
| "learning_rate": 2.054415207349473e-05, |
| "loss": 0.1016, |
| "mean_token_accuracy": 0.9704934805631638, |
| "step": 918 |
| }, |
| { |
| "epoch": 5.375366568914956, |
| "grad_norm": 0.6363959385625477, |
| "learning_rate": 2.0509974382323043e-05, |
| "loss": 0.0866, |
| "mean_token_accuracy": 0.9745766744017601, |
| "step": 919 |
| }, |
| { |
| "epoch": 5.381231671554252, |
| "grad_norm": 0.6258477209760515, |
| "learning_rate": 2.047580209934256e-05, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.9737055748701096, |
| "step": 920 |
| }, |
| { |
| "epoch": 5.387096774193548, |
| "grad_norm": 0.6613535414703848, |
| "learning_rate": 2.0441635348584876e-05, |
| "loss": 0.0881, |
| "mean_token_accuracy": 0.9749500304460526, |
| "step": 921 |
| }, |
| { |
| "epoch": 5.392961876832844, |
| "grad_norm": 0.7602735845477481, |
| "learning_rate": 2.0407474254061498e-05, |
| "loss": 0.1114, |
| "mean_token_accuracy": 0.9694864973425865, |
| "step": 922 |
| }, |
| { |
| "epoch": 5.39882697947214, |
| "grad_norm": 0.626037285164579, |
| "learning_rate": 2.0373318939763397e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.972472071647644, |
| "step": 923 |
| }, |
| { |
| "epoch": 5.404692082111437, |
| "grad_norm": 0.9112477803463636, |
| "learning_rate": 2.033916952966057e-05, |
| "loss": 0.0858, |
| "mean_token_accuracy": 0.9744387790560722, |
| "step": 924 |
| }, |
| { |
| "epoch": 5.410557184750733, |
| "grad_norm": 0.7421628592141191, |
| "learning_rate": 2.0305026147701584e-05, |
| "loss": 0.0863, |
| "mean_token_accuracy": 0.9712925776839256, |
| "step": 925 |
| }, |
| { |
| "epoch": 5.416422287390029, |
| "grad_norm": 0.6515695297727665, |
| "learning_rate": 2.0270888917813124e-05, |
| "loss": 0.0776, |
| "mean_token_accuracy": 0.9756393432617188, |
| "step": 926 |
| }, |
| { |
| "epoch": 5.422287390029325, |
| "grad_norm": 0.8628434185290488, |
| "learning_rate": 2.0236757963899548e-05, |
| "loss": 0.0984, |
| "mean_token_accuracy": 0.973811186850071, |
| "step": 927 |
| }, |
| { |
| "epoch": 5.428152492668621, |
| "grad_norm": 1.1299749301147368, |
| "learning_rate": 2.020263340984244e-05, |
| "loss": 0.0918, |
| "mean_token_accuracy": 0.9751879572868347, |
| "step": 928 |
| }, |
| { |
| "epoch": 5.4340175953079175, |
| "grad_norm": 0.6428804437106626, |
| "learning_rate": 2.0168515379500145e-05, |
| "loss": 0.0828, |
| "mean_token_accuracy": 0.9709775000810623, |
| "step": 929 |
| }, |
| { |
| "epoch": 5.439882697947214, |
| "grad_norm": 0.7470209883447461, |
| "learning_rate": 2.0134403996707338e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9749180600047112, |
| "step": 930 |
| }, |
| { |
| "epoch": 5.44574780058651, |
| "grad_norm": 0.4642855476533981, |
| "learning_rate": 2.0100299385274547e-05, |
| "loss": 0.0902, |
| "mean_token_accuracy": 0.9726503938436508, |
| "step": 931 |
| }, |
| { |
| "epoch": 5.451612903225806, |
| "grad_norm": 0.7606298055914933, |
| "learning_rate": 2.0066201668987757e-05, |
| "loss": 0.0923, |
| "mean_token_accuracy": 0.9702809303998947, |
| "step": 932 |
| }, |
| { |
| "epoch": 5.457478005865102, |
| "grad_norm": 0.6008762056162931, |
| "learning_rate": 2.0032110971607894e-05, |
| "loss": 0.0887, |
| "mean_token_accuracy": 0.9757914617657661, |
| "step": 933 |
| }, |
| { |
| "epoch": 5.463343108504398, |
| "grad_norm": 0.6078060941097535, |
| "learning_rate": 1.999802741687042e-05, |
| "loss": 0.0931, |
| "mean_token_accuracy": 0.9730753004550934, |
| "step": 934 |
| }, |
| { |
| "epoch": 5.469208211143695, |
| "grad_norm": 0.5758717205478393, |
| "learning_rate": 1.9963951128484886e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9766752049326897, |
| "step": 935 |
| }, |
| { |
| "epoch": 5.475073313782991, |
| "grad_norm": 0.6785426496703266, |
| "learning_rate": 1.9929882230134452e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.9692973420023918, |
| "step": 936 |
| }, |
| { |
| "epoch": 5.480938416422287, |
| "grad_norm": 0.728290541857711, |
| "learning_rate": 1.9895820845475445e-05, |
| "loss": 0.0969, |
| "mean_token_accuracy": 0.9711208865046501, |
| "step": 937 |
| }, |
| { |
| "epoch": 5.486803519061583, |
| "grad_norm": 0.6533361112946945, |
| "learning_rate": 1.9861767098136956e-05, |
| "loss": 0.0804, |
| "mean_token_accuracy": 0.9775801599025726, |
| "step": 938 |
| }, |
| { |
| "epoch": 5.492668621700879, |
| "grad_norm": 0.8201669009430897, |
| "learning_rate": 1.982772111172032e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.9733827859163284, |
| "step": 939 |
| }, |
| { |
| "epoch": 5.4985337243401755, |
| "grad_norm": 0.5158612094205587, |
| "learning_rate": 1.9793683009798718e-05, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9773239716887474, |
| "step": 940 |
| }, |
| { |
| "epoch": 5.504398826979472, |
| "grad_norm": 0.6241066832474991, |
| "learning_rate": 1.975965291591672e-05, |
| "loss": 0.0978, |
| "mean_token_accuracy": 0.9694525748491287, |
| "step": 941 |
| }, |
| { |
| "epoch": 5.510263929618768, |
| "grad_norm": 0.7158903642944286, |
| "learning_rate": 1.9725630953589823e-05, |
| "loss": 0.0896, |
| "mean_token_accuracy": 0.9751381054520607, |
| "step": 942 |
| }, |
| { |
| "epoch": 5.516129032258064, |
| "grad_norm": 0.6500428056572851, |
| "learning_rate": 1.9691617246304007e-05, |
| "loss": 0.0906, |
| "mean_token_accuracy": 0.9697719290852547, |
| "step": 943 |
| }, |
| { |
| "epoch": 5.52199413489736, |
| "grad_norm": 0.6757819265845151, |
| "learning_rate": 1.9657611917515287e-05, |
| "loss": 0.0946, |
| "mean_token_accuracy": 0.9740458875894547, |
| "step": 944 |
| }, |
| { |
| "epoch": 5.527859237536656, |
| "grad_norm": 0.6467851667757466, |
| "learning_rate": 1.962361509064928e-05, |
| "loss": 0.0779, |
| "mean_token_accuracy": 0.9767004624009132, |
| "step": 945 |
| }, |
| { |
| "epoch": 5.533724340175953, |
| "grad_norm": 0.6929353877478521, |
| "learning_rate": 1.958962688910073e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9737014174461365, |
| "step": 946 |
| }, |
| { |
| "epoch": 5.539589442815249, |
| "grad_norm": 0.554178700724065, |
| "learning_rate": 1.9555647436233093e-05, |
| "loss": 0.0833, |
| "mean_token_accuracy": 0.9781376793980598, |
| "step": 947 |
| }, |
| { |
| "epoch": 5.545454545454545, |
| "grad_norm": 0.731670261601833, |
| "learning_rate": 1.9521676855378045e-05, |
| "loss": 0.0813, |
| "mean_token_accuracy": 0.977122388780117, |
| "step": 948 |
| }, |
| { |
| "epoch": 5.551319648093841, |
| "grad_norm": 0.7428121682204718, |
| "learning_rate": 1.9487715269835082e-05, |
| "loss": 0.0821, |
| "mean_token_accuracy": 0.9735124111175537, |
| "step": 949 |
| }, |
| { |
| "epoch": 5.557184750733137, |
| "grad_norm": 0.5862393003846442, |
| "learning_rate": 1.945376280287105e-05, |
| "loss": 0.0907, |
| "mean_token_accuracy": 0.9709196835756302, |
| "step": 950 |
| }, |
| { |
| "epoch": 5.563049853372434, |
| "grad_norm": 0.7517377301766143, |
| "learning_rate": 1.9419819577719684e-05, |
| "loss": 0.0864, |
| "mean_token_accuracy": 0.9729499071836472, |
| "step": 951 |
| }, |
| { |
| "epoch": 5.568914956011731, |
| "grad_norm": 0.7630913812828717, |
| "learning_rate": 1.9385885717581182e-05, |
| "loss": 0.094, |
| "mean_token_accuracy": 0.9722026437520981, |
| "step": 952 |
| }, |
| { |
| "epoch": 5.574780058651027, |
| "grad_norm": 0.5631421776070452, |
| "learning_rate": 1.935196134562175e-05, |
| "loss": 0.0836, |
| "mean_token_accuracy": 0.9755956828594208, |
| "step": 953 |
| }, |
| { |
| "epoch": 5.580645161290323, |
| "grad_norm": 0.6601421450613268, |
| "learning_rate": 1.931804658497316e-05, |
| "loss": 0.086, |
| "mean_token_accuracy": 0.9734816625714302, |
| "step": 954 |
| }, |
| { |
| "epoch": 5.586510263929619, |
| "grad_norm": 0.7963802408293887, |
| "learning_rate": 1.9284141558732296e-05, |
| "loss": 0.0892, |
| "mean_token_accuracy": 0.9736581519246101, |
| "step": 955 |
| }, |
| { |
| "epoch": 5.592375366568915, |
| "grad_norm": 0.6925565662697808, |
| "learning_rate": 1.925024638996071e-05, |
| "loss": 0.0906, |
| "mean_token_accuracy": 0.9748614057898521, |
| "step": 956 |
| }, |
| { |
| "epoch": 5.5982404692082115, |
| "grad_norm": 0.4469096595424996, |
| "learning_rate": 1.9216361201684174e-05, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9786844179034233, |
| "step": 957 |
| }, |
| { |
| "epoch": 5.604105571847508, |
| "grad_norm": 0.6688127687388462, |
| "learning_rate": 1.918248611689224e-05, |
| "loss": 0.0805, |
| "mean_token_accuracy": 0.9765229448676109, |
| "step": 958 |
| }, |
| { |
| "epoch": 5.609970674486804, |
| "grad_norm": 0.6855039450437475, |
| "learning_rate": 1.9148621258537782e-05, |
| "loss": 0.0889, |
| "mean_token_accuracy": 0.9715561494231224, |
| "step": 959 |
| }, |
| { |
| "epoch": 5.6158357771261, |
| "grad_norm": 0.8037823314037765, |
| "learning_rate": 1.911476674953656e-05, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9763055369257927, |
| "step": 960 |
| }, |
| { |
| "epoch": 5.621700879765396, |
| "grad_norm": 0.5073819720734495, |
| "learning_rate": 1.9080922712766762e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9702242463827133, |
| "step": 961 |
| }, |
| { |
| "epoch": 5.627565982404692, |
| "grad_norm": 0.5329313662136718, |
| "learning_rate": 1.904708927106858e-05, |
| "loss": 0.0897, |
| "mean_token_accuracy": 0.9713274911046028, |
| "step": 962 |
| }, |
| { |
| "epoch": 5.633431085043989, |
| "grad_norm": 0.6822929726272469, |
| "learning_rate": 1.9013266547243742e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9777653217315674, |
| "step": 963 |
| }, |
| { |
| "epoch": 5.639296187683285, |
| "grad_norm": 0.5806622127690888, |
| "learning_rate": 1.8979454664055068e-05, |
| "loss": 0.0857, |
| "mean_token_accuracy": 0.9744703099131584, |
| "step": 964 |
| }, |
| { |
| "epoch": 5.645161290322581, |
| "grad_norm": 0.8665695970177962, |
| "learning_rate": 1.894565374422605e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9745295867323875, |
| "step": 965 |
| }, |
| { |
| "epoch": 5.651026392961877, |
| "grad_norm": 0.6266246362289842, |
| "learning_rate": 1.891186391044037e-05, |
| "loss": 0.0947, |
| "mean_token_accuracy": 0.9700672402977943, |
| "step": 966 |
| }, |
| { |
| "epoch": 5.656891495601173, |
| "grad_norm": 0.7989074355855846, |
| "learning_rate": 1.887808528534148e-05, |
| "loss": 0.0873, |
| "mean_token_accuracy": 0.9718985334038734, |
| "step": 967 |
| }, |
| { |
| "epoch": 5.6627565982404695, |
| "grad_norm": 0.4353989783282138, |
| "learning_rate": 1.884431799153214e-05, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.978706993162632, |
| "step": 968 |
| }, |
| { |
| "epoch": 5.668621700879766, |
| "grad_norm": 0.8266065947284112, |
| "learning_rate": 1.8810562151573993e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.972965806722641, |
| "step": 969 |
| }, |
| { |
| "epoch": 5.674486803519062, |
| "grad_norm": 0.6820629959510945, |
| "learning_rate": 1.8776817887987105e-05, |
| "loss": 0.0921, |
| "mean_token_accuracy": 0.9734281525015831, |
| "step": 970 |
| }, |
| { |
| "epoch": 5.680351906158358, |
| "grad_norm": 0.5623312424943822, |
| "learning_rate": 1.8743085323249527e-05, |
| "loss": 0.0889, |
| "mean_token_accuracy": 0.9733134210109711, |
| "step": 971 |
| }, |
| { |
| "epoch": 5.686217008797654, |
| "grad_norm": 0.5194482005569641, |
| "learning_rate": 1.870936457979684e-05, |
| "loss": 0.0908, |
| "mean_token_accuracy": 0.9747659862041473, |
| "step": 972 |
| }, |
| { |
| "epoch": 5.69208211143695, |
| "grad_norm": 0.5875433250388189, |
| "learning_rate": 1.8675655780021733e-05, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9777504205703735, |
| "step": 973 |
| }, |
| { |
| "epoch": 5.697947214076247, |
| "grad_norm": 0.5039670849995016, |
| "learning_rate": 1.8641959046273525e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9732639566063881, |
| "step": 974 |
| }, |
| { |
| "epoch": 5.703812316715543, |
| "grad_norm": 0.6502810650481761, |
| "learning_rate": 1.8608274500857756e-05, |
| "loss": 0.0916, |
| "mean_token_accuracy": 0.9737720489501953, |
| "step": 975 |
| }, |
| { |
| "epoch": 5.709677419354839, |
| "grad_norm": 0.7462538481750892, |
| "learning_rate": 1.8574602266035714e-05, |
| "loss": 0.0705, |
| "mean_token_accuracy": 0.9790600091218948, |
| "step": 976 |
| }, |
| { |
| "epoch": 5.715542521994135, |
| "grad_norm": 0.6951076012758072, |
| "learning_rate": 1.854094246402402e-05, |
| "loss": 0.1029, |
| "mean_token_accuracy": 0.9681782871484756, |
| "step": 977 |
| }, |
| { |
| "epoch": 5.721407624633431, |
| "grad_norm": 0.7289075041674313, |
| "learning_rate": 1.8507295216994162e-05, |
| "loss": 0.0745, |
| "mean_token_accuracy": 0.9782817512750626, |
| "step": 978 |
| }, |
| { |
| "epoch": 5.7272727272727275, |
| "grad_norm": 0.6170230938347478, |
| "learning_rate": 1.8473660647072053e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.9697033986449242, |
| "step": 979 |
| }, |
| { |
| "epoch": 5.733137829912024, |
| "grad_norm": 0.6286851176517133, |
| "learning_rate": 1.8440038876337597e-05, |
| "loss": 0.0738, |
| "mean_token_accuracy": 0.9746864810585976, |
| "step": 980 |
| }, |
| { |
| "epoch": 5.73900293255132, |
| "grad_norm": 0.6924654681455282, |
| "learning_rate": 1.8406430026824252e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.9719264730811119, |
| "step": 981 |
| }, |
| { |
| "epoch": 5.744868035190616, |
| "grad_norm": 0.6386975637341502, |
| "learning_rate": 1.837283422051855e-05, |
| "loss": 0.0824, |
| "mean_token_accuracy": 0.9745275229215622, |
| "step": 982 |
| }, |
| { |
| "epoch": 5.750733137829912, |
| "grad_norm": 0.7673873081774819, |
| "learning_rate": 1.8339251579359713e-05, |
| "loss": 0.0899, |
| "mean_token_accuracy": 0.9738566502928734, |
| "step": 983 |
| }, |
| { |
| "epoch": 5.756598240469208, |
| "grad_norm": 0.5320830282669105, |
| "learning_rate": 1.8305682225239167e-05, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9771842882037163, |
| "step": 984 |
| }, |
| { |
| "epoch": 5.762463343108505, |
| "grad_norm": 0.7839551637151186, |
| "learning_rate": 1.8272126280000102e-05, |
| "loss": 0.1027, |
| "mean_token_accuracy": 0.9691510125994682, |
| "step": 985 |
| }, |
| { |
| "epoch": 5.768328445747801, |
| "grad_norm": 0.659651301924526, |
| "learning_rate": 1.823858386543705e-05, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.9774763435125351, |
| "step": 986 |
| }, |
| { |
| "epoch": 5.774193548387097, |
| "grad_norm": 0.684337831256596, |
| "learning_rate": 1.8205055103295434e-05, |
| "loss": 0.0918, |
| "mean_token_accuracy": 0.9704063758254051, |
| "step": 987 |
| }, |
| { |
| "epoch": 5.780058651026393, |
| "grad_norm": 0.6780204534520761, |
| "learning_rate": 1.8171540115271108e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.9674130603671074, |
| "step": 988 |
| }, |
| { |
| "epoch": 5.785923753665689, |
| "grad_norm": 0.7688483149907289, |
| "learning_rate": 1.813803902300995e-05, |
| "loss": 0.0899, |
| "mean_token_accuracy": 0.9712028130888939, |
| "step": 989 |
| }, |
| { |
| "epoch": 5.7917888563049855, |
| "grad_norm": 0.5787977118824297, |
| "learning_rate": 1.8104551948107395e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.9761911928653717, |
| "step": 990 |
| }, |
| { |
| "epoch": 5.797653958944282, |
| "grad_norm": 0.7838858854358897, |
| "learning_rate": 1.8071079012107997e-05, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9778272584080696, |
| "step": 991 |
| }, |
| { |
| "epoch": 5.803519061583578, |
| "grad_norm": 0.5204651103182804, |
| "learning_rate": 1.8037620336504993e-05, |
| "loss": 0.0884, |
| "mean_token_accuracy": 0.9750376492738724, |
| "step": 992 |
| }, |
| { |
| "epoch": 5.809384164222874, |
| "grad_norm": 0.6959107859348317, |
| "learning_rate": 1.8004176042739877e-05, |
| "loss": 0.0812, |
| "mean_token_accuracy": 0.9772611781954765, |
| "step": 993 |
| }, |
| { |
| "epoch": 5.81524926686217, |
| "grad_norm": 0.5986772400066928, |
| "learning_rate": 1.797074625220191e-05, |
| "loss": 0.0842, |
| "mean_token_accuracy": 0.9771137833595276, |
| "step": 994 |
| }, |
| { |
| "epoch": 5.821114369501466, |
| "grad_norm": 0.4693360660469766, |
| "learning_rate": 1.7937331086227737e-05, |
| "loss": 0.0889, |
| "mean_token_accuracy": 0.9712493047118187, |
| "step": 995 |
| }, |
| { |
| "epoch": 5.826979472140763, |
| "grad_norm": 0.7490861103636983, |
| "learning_rate": 1.790393066610091e-05, |
| "loss": 0.0952, |
| "mean_token_accuracy": 0.971531830728054, |
| "step": 996 |
| }, |
| { |
| "epoch": 5.832844574780059, |
| "grad_norm": 0.6288451112815866, |
| "learning_rate": 1.787054511305148e-05, |
| "loss": 0.0893, |
| "mean_token_accuracy": 0.9741169288754463, |
| "step": 997 |
| }, |
| { |
| "epoch": 5.838709677419355, |
| "grad_norm": 0.7702435889994751, |
| "learning_rate": 1.7837174548255504e-05, |
| "loss": 0.0948, |
| "mean_token_accuracy": 0.9711467698216438, |
| "step": 998 |
| }, |
| { |
| "epoch": 5.844574780058651, |
| "grad_norm": 0.5823123249879522, |
| "learning_rate": 1.7803819092834668e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.975670225918293, |
| "step": 999 |
| }, |
| { |
| "epoch": 5.850439882697947, |
| "grad_norm": 0.6981130982253064, |
| "learning_rate": 1.7770478867855797e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9753496646881104, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.8563049853372435, |
| "grad_norm": 0.7372940110063448, |
| "learning_rate": 1.7737153994330437e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9673419818282127, |
| "step": 1001 |
| }, |
| { |
| "epoch": 5.86217008797654, |
| "grad_norm": 0.8006525910133377, |
| "learning_rate": 1.7703844593214427e-05, |
| "loss": 0.081, |
| "mean_token_accuracy": 0.974897563457489, |
| "step": 1002 |
| }, |
| { |
| "epoch": 5.868035190615836, |
| "grad_norm": 0.5561798341071992, |
| "learning_rate": 1.7670550785407444e-05, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9756550714373589, |
| "step": 1003 |
| }, |
| { |
| "epoch": 5.873900293255132, |
| "grad_norm": 0.5615991213783584, |
| "learning_rate": 1.7637272691752548e-05, |
| "loss": 0.0829, |
| "mean_token_accuracy": 0.97202467918396, |
| "step": 1004 |
| }, |
| { |
| "epoch": 5.879765395894428, |
| "grad_norm": 0.6399659767936104, |
| "learning_rate": 1.7604010433035793e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.9714025035500526, |
| "step": 1005 |
| }, |
| { |
| "epoch": 5.885630498533724, |
| "grad_norm": 0.6345682852590906, |
| "learning_rate": 1.7570764129985747e-05, |
| "loss": 0.0829, |
| "mean_token_accuracy": 0.9739578440785408, |
| "step": 1006 |
| }, |
| { |
| "epoch": 5.891495601173021, |
| "grad_norm": 0.8095757391274871, |
| "learning_rate": 1.7537533903273055e-05, |
| "loss": 0.1017, |
| "mean_token_accuracy": 0.9723379909992218, |
| "step": 1007 |
| }, |
| { |
| "epoch": 5.897360703812317, |
| "grad_norm": 0.829159717201638, |
| "learning_rate": 1.7504319873510014e-05, |
| "loss": 0.1032, |
| "mean_token_accuracy": 0.9734954759478569, |
| "step": 1008 |
| }, |
| { |
| "epoch": 5.903225806451613, |
| "grad_norm": 0.6932420286406421, |
| "learning_rate": 1.7471122161250153e-05, |
| "loss": 0.0863, |
| "mean_token_accuracy": 0.9713395535945892, |
| "step": 1009 |
| }, |
| { |
| "epoch": 5.909090909090909, |
| "grad_norm": 0.7242637421768542, |
| "learning_rate": 1.743794088698775e-05, |
| "loss": 0.1025, |
| "mean_token_accuracy": 0.9717629998922348, |
| "step": 1010 |
| }, |
| { |
| "epoch": 5.914956011730205, |
| "grad_norm": 0.6812715069301856, |
| "learning_rate": 1.7404776171157428e-05, |
| "loss": 0.0901, |
| "mean_token_accuracy": 0.9726547002792358, |
| "step": 1011 |
| }, |
| { |
| "epoch": 5.9208211143695015, |
| "grad_norm": 0.47494390794003294, |
| "learning_rate": 1.7371628134133716e-05, |
| "loss": 0.1006, |
| "mean_token_accuracy": 0.9703837037086487, |
| "step": 1012 |
| }, |
| { |
| "epoch": 5.926686217008798, |
| "grad_norm": 0.7988053128511963, |
| "learning_rate": 1.73384968962306e-05, |
| "loss": 0.087, |
| "mean_token_accuracy": 0.9710239991545677, |
| "step": 1013 |
| }, |
| { |
| "epoch": 5.932551319648094, |
| "grad_norm": 0.7048215584079881, |
| "learning_rate": 1.7305382577701088e-05, |
| "loss": 0.0912, |
| "mean_token_accuracy": 0.972258172929287, |
| "step": 1014 |
| }, |
| { |
| "epoch": 5.93841642228739, |
| "grad_norm": 0.5987039942872129, |
| "learning_rate": 1.7272285298736787e-05, |
| "loss": 0.0812, |
| "mean_token_accuracy": 0.9739760607481003, |
| "step": 1015 |
| }, |
| { |
| "epoch": 5.944281524926686, |
| "grad_norm": 0.7669426180702338, |
| "learning_rate": 1.7239205179467453e-05, |
| "loss": 0.0928, |
| "mean_token_accuracy": 0.9731807708740234, |
| "step": 1016 |
| }, |
| { |
| "epoch": 5.9501466275659824, |
| "grad_norm": 0.8816952587467959, |
| "learning_rate": 1.720614233996056e-05, |
| "loss": 0.1119, |
| "mean_token_accuracy": 0.9651398956775665, |
| "step": 1017 |
| }, |
| { |
| "epoch": 5.956011730205279, |
| "grad_norm": 0.7904778378822598, |
| "learning_rate": 1.7173096900220852e-05, |
| "loss": 0.0862, |
| "mean_token_accuracy": 0.9707507267594337, |
| "step": 1018 |
| }, |
| { |
| "epoch": 5.961876832844575, |
| "grad_norm": 0.5993372916237711, |
| "learning_rate": 1.7140068980189943e-05, |
| "loss": 0.1027, |
| "mean_token_accuracy": 0.9691429063677788, |
| "step": 1019 |
| }, |
| { |
| "epoch": 5.967741935483871, |
| "grad_norm": 0.7894401534507262, |
| "learning_rate": 1.710705869974583e-05, |
| "loss": 0.0878, |
| "mean_token_accuracy": 0.9715762436389923, |
| "step": 1020 |
| }, |
| { |
| "epoch": 5.973607038123167, |
| "grad_norm": 0.5007290522624128, |
| "learning_rate": 1.7074066178702512e-05, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9772191122174263, |
| "step": 1021 |
| }, |
| { |
| "epoch": 5.979472140762463, |
| "grad_norm": 1.0706418477291928, |
| "learning_rate": 1.7041091536809506e-05, |
| "loss": 0.0899, |
| "mean_token_accuracy": 0.9734712392091751, |
| "step": 1022 |
| }, |
| { |
| "epoch": 5.9853372434017595, |
| "grad_norm": 0.5132866545703823, |
| "learning_rate": 1.7008134893751446e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9778529033064842, |
| "step": 1023 |
| }, |
| { |
| "epoch": 5.991202346041056, |
| "grad_norm": 0.3934917191270626, |
| "learning_rate": 1.697519636914765e-05, |
| "loss": 0.0752, |
| "mean_token_accuracy": 0.976367898285389, |
| "step": 1024 |
| }, |
| { |
| "epoch": 5.997067448680352, |
| "grad_norm": 0.5893645990583302, |
| "learning_rate": 1.6942276082551634e-05, |
| "loss": 0.1045, |
| "mean_token_accuracy": 0.968669667840004, |
| "step": 1025 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.3504099609374147, |
| "learning_rate": 1.6909374153450762e-05, |
| "loss": 0.098, |
| "mean_token_accuracy": 0.9726896286010742, |
| "step": 1026 |
| }, |
| { |
| "epoch": 6.005865102639296, |
| "grad_norm": 0.598228971963004, |
| "learning_rate": 1.6876490701265736e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.979034774005413, |
| "step": 1027 |
| }, |
| { |
| "epoch": 6.011730205278592, |
| "grad_norm": 0.48280619668172964, |
| "learning_rate": 1.684362584535022e-05, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9782651886343956, |
| "step": 1028 |
| }, |
| { |
| "epoch": 6.0175953079178885, |
| "grad_norm": 0.466644575352627, |
| "learning_rate": 1.6810779704990358e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9769785478711128, |
| "step": 1029 |
| }, |
| { |
| "epoch": 6.023460410557185, |
| "grad_norm": 0.47183688005778257, |
| "learning_rate": 1.677795239940438e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9806296676397324, |
| "step": 1030 |
| }, |
| { |
| "epoch": 6.029325513196481, |
| "grad_norm": 0.5718220069789671, |
| "learning_rate": 1.674514404774214e-05, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9777848049998283, |
| "step": 1031 |
| }, |
| { |
| "epoch": 6.035190615835777, |
| "grad_norm": 0.5179785510961876, |
| "learning_rate": 1.671235476908471e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9780596271157265, |
| "step": 1032 |
| }, |
| { |
| "epoch": 6.041055718475073, |
| "grad_norm": 0.6142614536588886, |
| "learning_rate": 1.6679584682443924e-05, |
| "loss": 0.0792, |
| "mean_token_accuracy": 0.97633446007967, |
| "step": 1033 |
| }, |
| { |
| "epoch": 6.0469208211143695, |
| "grad_norm": 0.41142915451620954, |
| "learning_rate": 1.6646833906761965e-05, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9772084280848503, |
| "step": 1034 |
| }, |
| { |
| "epoch": 6.052785923753666, |
| "grad_norm": 0.4847833155252248, |
| "learning_rate": 1.661410256091092e-05, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9788917377591133, |
| "step": 1035 |
| }, |
| { |
| "epoch": 6.058651026392962, |
| "grad_norm": 0.6440065513831064, |
| "learning_rate": 1.658139076369236e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9781024977564812, |
| "step": 1036 |
| }, |
| { |
| "epoch": 6.064516129032258, |
| "grad_norm": 0.4806652284113589, |
| "learning_rate": 1.6548698633836893e-05, |
| "loss": 0.0711, |
| "mean_token_accuracy": 0.9742519408464432, |
| "step": 1037 |
| }, |
| { |
| "epoch": 6.070381231671554, |
| "grad_norm": 0.49812439107885775, |
| "learning_rate": 1.6516026290003746e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9813807904720306, |
| "step": 1038 |
| }, |
| { |
| "epoch": 6.07624633431085, |
| "grad_norm": 0.4946026191358958, |
| "learning_rate": 1.6483373850780328e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9776654466986656, |
| "step": 1039 |
| }, |
| { |
| "epoch": 6.0821114369501466, |
| "grad_norm": 0.38914184460055723, |
| "learning_rate": 1.645074143468181e-05, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9806255549192429, |
| "step": 1040 |
| }, |
| { |
| "epoch": 6.087976539589443, |
| "grad_norm": 0.6214256536736328, |
| "learning_rate": 1.6418129160150692e-05, |
| "loss": 0.078, |
| "mean_token_accuracy": 0.9744777455925941, |
| "step": 1041 |
| }, |
| { |
| "epoch": 6.093841642228739, |
| "grad_norm": 0.42727507511348983, |
| "learning_rate": 1.6385537145556346e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9816567301750183, |
| "step": 1042 |
| }, |
| { |
| "epoch": 6.099706744868035, |
| "grad_norm": 0.5862832205156056, |
| "learning_rate": 1.6352965509194634e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9801078513264656, |
| "step": 1043 |
| }, |
| { |
| "epoch": 6.105571847507331, |
| "grad_norm": 0.5540609521688267, |
| "learning_rate": 1.6320414369287427e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9785455390810966, |
| "step": 1044 |
| }, |
| { |
| "epoch": 6.1114369501466275, |
| "grad_norm": 0.5305278819763478, |
| "learning_rate": 1.6287883843982223e-05, |
| "loss": 0.0745, |
| "mean_token_accuracy": 0.9784517213702202, |
| "step": 1045 |
| }, |
| { |
| "epoch": 6.117302052785924, |
| "grad_norm": 0.5324605295420759, |
| "learning_rate": 1.625537405135169e-05, |
| "loss": 0.0883, |
| "mean_token_accuracy": 0.9728142842650414, |
| "step": 1046 |
| }, |
| { |
| "epoch": 6.12316715542522, |
| "grad_norm": 0.48156545050119387, |
| "learning_rate": 1.622288510939325e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.9753900468349457, |
| "step": 1047 |
| }, |
| { |
| "epoch": 6.129032258064516, |
| "grad_norm": 0.5403475317147802, |
| "learning_rate": 1.619041713602864e-05, |
| "loss": 0.086, |
| "mean_token_accuracy": 0.9756969884037971, |
| "step": 1048 |
| }, |
| { |
| "epoch": 6.134897360703812, |
| "grad_norm": 0.6164994865776425, |
| "learning_rate": 1.6157970249103484e-05, |
| "loss": 0.0822, |
| "mean_token_accuracy": 0.97352235019207, |
| "step": 1049 |
| }, |
| { |
| "epoch": 6.140762463343108, |
| "grad_norm": 0.5479826751146541, |
| "learning_rate": 1.612554456638688e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.9752313643693924, |
| "step": 1050 |
| }, |
| { |
| "epoch": 6.146627565982405, |
| "grad_norm": 0.8355035708152437, |
| "learning_rate": 1.6093140205570962e-05, |
| "loss": 0.1034, |
| "mean_token_accuracy": 0.9721332043409348, |
| "step": 1051 |
| }, |
| { |
| "epoch": 6.152492668621701, |
| "grad_norm": 0.5699260258595685, |
| "learning_rate": 1.6060757284270474e-05, |
| "loss": 0.088, |
| "mean_token_accuracy": 0.9704829677939415, |
| "step": 1052 |
| }, |
| { |
| "epoch": 6.158357771260997, |
| "grad_norm": 0.4016074967594273, |
| "learning_rate": 1.6028395920022336e-05, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9768156260251999, |
| "step": 1053 |
| }, |
| { |
| "epoch": 6.164222873900293, |
| "grad_norm": 0.6274851394247467, |
| "learning_rate": 1.5996056230285237e-05, |
| "loss": 0.0776, |
| "mean_token_accuracy": 0.9752253219485283, |
| "step": 1054 |
| }, |
| { |
| "epoch": 6.170087976539589, |
| "grad_norm": 0.41979905539903684, |
| "learning_rate": 1.596373833243918e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9752494245767593, |
| "step": 1055 |
| }, |
| { |
| "epoch": 6.1759530791788855, |
| "grad_norm": 0.5371249434282453, |
| "learning_rate": 1.593144234378509e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9740007221698761, |
| "step": 1056 |
| }, |
| { |
| "epoch": 6.181818181818182, |
| "grad_norm": 0.5958655099860268, |
| "learning_rate": 1.5899168381544362e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9766522198915482, |
| "step": 1057 |
| }, |
| { |
| "epoch": 6.187683284457478, |
| "grad_norm": 0.5620879511590664, |
| "learning_rate": 1.5866916562858444e-05, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9761717393994331, |
| "step": 1058 |
| }, |
| { |
| "epoch": 6.193548387096774, |
| "grad_norm": 0.41663290523753393, |
| "learning_rate": 1.5834687004788406e-05, |
| "loss": 0.0719, |
| "mean_token_accuracy": 0.9762328043580055, |
| "step": 1059 |
| }, |
| { |
| "epoch": 6.19941348973607, |
| "grad_norm": 0.45751013839163385, |
| "learning_rate": 1.5802479824314537e-05, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9730842038989067, |
| "step": 1060 |
| }, |
| { |
| "epoch": 6.205278592375366, |
| "grad_norm": 0.6061591524965043, |
| "learning_rate": 1.5770295138335896e-05, |
| "loss": 0.0675, |
| "mean_token_accuracy": 0.9795668348670006, |
| "step": 1061 |
| }, |
| { |
| "epoch": 6.211143695014663, |
| "grad_norm": 0.48653084806168795, |
| "learning_rate": 1.573813306366988e-05, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.9805929064750671, |
| "step": 1062 |
| }, |
| { |
| "epoch": 6.217008797653959, |
| "grad_norm": 0.7918965125848585, |
| "learning_rate": 1.5705993717051838e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.9726722538471222, |
| "step": 1063 |
| }, |
| { |
| "epoch": 6.222873900293255, |
| "grad_norm": 0.4360806881193703, |
| "learning_rate": 1.567387721513462e-05, |
| "loss": 0.0733, |
| "mean_token_accuracy": 0.9755243211984634, |
| "step": 1064 |
| }, |
| { |
| "epoch": 6.228739002932551, |
| "grad_norm": 0.4507922929333053, |
| "learning_rate": 1.5641783674488155e-05, |
| "loss": 0.0788, |
| "mean_token_accuracy": 0.9779406636953354, |
| "step": 1065 |
| }, |
| { |
| "epoch": 6.234604105571847, |
| "grad_norm": 0.524440368997054, |
| "learning_rate": 1.5609713211599035e-05, |
| "loss": 0.0886, |
| "mean_token_accuracy": 0.9735754728317261, |
| "step": 1066 |
| }, |
| { |
| "epoch": 6.2404692082111435, |
| "grad_norm": 0.4933573360395662, |
| "learning_rate": 1.557766594287009e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9745327085256577, |
| "step": 1067 |
| }, |
| { |
| "epoch": 6.24633431085044, |
| "grad_norm": 0.6374490569807274, |
| "learning_rate": 1.554564198461996e-05, |
| "loss": 0.1006, |
| "mean_token_accuracy": 0.9676776975393295, |
| "step": 1068 |
| }, |
| { |
| "epoch": 6.252199413489736, |
| "grad_norm": 0.503016875609656, |
| "learning_rate": 1.5513641453082672e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9755501598119736, |
| "step": 1069 |
| }, |
| { |
| "epoch": 6.258064516129032, |
| "grad_norm": 0.6725586143220211, |
| "learning_rate": 1.5481664464407246e-05, |
| "loss": 0.0786, |
| "mean_token_accuracy": 0.9803177490830421, |
| "step": 1070 |
| }, |
| { |
| "epoch": 6.263929618768328, |
| "grad_norm": 0.3845258686542439, |
| "learning_rate": 1.5449711134657224e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9737701192498207, |
| "step": 1071 |
| }, |
| { |
| "epoch": 6.269794721407624, |
| "grad_norm": 0.5801290016339792, |
| "learning_rate": 1.5417781579810296e-05, |
| "loss": 0.0854, |
| "mean_token_accuracy": 0.9750698879361153, |
| "step": 1072 |
| }, |
| { |
| "epoch": 6.275659824046921, |
| "grad_norm": 0.46851452988304226, |
| "learning_rate": 1.5385875915757846e-05, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.9781253635883331, |
| "step": 1073 |
| }, |
| { |
| "epoch": 6.281524926686217, |
| "grad_norm": 0.6003054181463484, |
| "learning_rate": 1.535399425830456e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9752677977085114, |
| "step": 1074 |
| }, |
| { |
| "epoch": 6.287390029325513, |
| "grad_norm": 0.4922352812959743, |
| "learning_rate": 1.5322136723167957e-05, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9730022326111794, |
| "step": 1075 |
| }, |
| { |
| "epoch": 6.293255131964809, |
| "grad_norm": 0.5503056897332197, |
| "learning_rate": 1.5290303425978036e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.978991761803627, |
| "step": 1076 |
| }, |
| { |
| "epoch": 6.299120234604105, |
| "grad_norm": 0.48722504997778493, |
| "learning_rate": 1.525849448227681e-05, |
| "loss": 0.0808, |
| "mean_token_accuracy": 0.9766300916671753, |
| "step": 1077 |
| }, |
| { |
| "epoch": 6.3049853372434015, |
| "grad_norm": 0.5168974806482571, |
| "learning_rate": 1.5226710007517894e-05, |
| "loss": 0.0912, |
| "mean_token_accuracy": 0.9702020585536957, |
| "step": 1078 |
| }, |
| { |
| "epoch": 6.310850439882698, |
| "grad_norm": 0.427948023862911, |
| "learning_rate": 1.5194950117066097e-05, |
| "loss": 0.0674, |
| "mean_token_accuracy": 0.9776515811681747, |
| "step": 1079 |
| }, |
| { |
| "epoch": 6.316715542521994, |
| "grad_norm": 0.5486267408576772, |
| "learning_rate": 1.5163214926196995e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.97169990837574, |
| "step": 1080 |
| }, |
| { |
| "epoch": 6.32258064516129, |
| "grad_norm": 0.4875960684561732, |
| "learning_rate": 1.5131504550096515e-05, |
| "loss": 0.079, |
| "mean_token_accuracy": 0.9735133945941925, |
| "step": 1081 |
| }, |
| { |
| "epoch": 6.328445747800586, |
| "grad_norm": 0.6244028161363354, |
| "learning_rate": 1.5099819103860504e-05, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9777925983071327, |
| "step": 1082 |
| }, |
| { |
| "epoch": 6.334310850439882, |
| "grad_norm": 0.5481634686271034, |
| "learning_rate": 1.5068158702494348e-05, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9792685136198997, |
| "step": 1083 |
| }, |
| { |
| "epoch": 6.340175953079179, |
| "grad_norm": 0.37298288716380845, |
| "learning_rate": 1.5036523460912511e-05, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9814745262265205, |
| "step": 1084 |
| }, |
| { |
| "epoch": 6.346041055718475, |
| "grad_norm": 0.36936094294826227, |
| "learning_rate": 1.5004913493938147e-05, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9765683263540268, |
| "step": 1085 |
| }, |
| { |
| "epoch": 6.351906158357771, |
| "grad_norm": 0.7399682764563025, |
| "learning_rate": 1.4973328916302667e-05, |
| "loss": 0.0947, |
| "mean_token_accuracy": 0.9703186228871346, |
| "step": 1086 |
| }, |
| { |
| "epoch": 6.357771260997067, |
| "grad_norm": 0.5453093945017612, |
| "learning_rate": 1.4941769842645335e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9727587401866913, |
| "step": 1087 |
| }, |
| { |
| "epoch": 6.363636363636363, |
| "grad_norm": 0.7601852801488714, |
| "learning_rate": 1.4910236387512837e-05, |
| "loss": 0.0773, |
| "mean_token_accuracy": 0.975163146853447, |
| "step": 1088 |
| }, |
| { |
| "epoch": 6.3695014662756595, |
| "grad_norm": 0.8980917715317281, |
| "learning_rate": 1.487872866535888e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9759137481451035, |
| "step": 1089 |
| }, |
| { |
| "epoch": 6.375366568914956, |
| "grad_norm": 0.5099633970627233, |
| "learning_rate": 1.4847246790543773e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9745916873216629, |
| "step": 1090 |
| }, |
| { |
| "epoch": 6.381231671554252, |
| "grad_norm": 0.6323169570307837, |
| "learning_rate": 1.4815790877334007e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9740422070026398, |
| "step": 1091 |
| }, |
| { |
| "epoch": 6.387096774193548, |
| "grad_norm": 0.6403999041432936, |
| "learning_rate": 1.4784361039901844e-05, |
| "loss": 0.0865, |
| "mean_token_accuracy": 0.9765808507800102, |
| "step": 1092 |
| }, |
| { |
| "epoch": 6.392961876832844, |
| "grad_norm": 0.7462715070778873, |
| "learning_rate": 1.47529573923249e-05, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.978026993572712, |
| "step": 1093 |
| }, |
| { |
| "epoch": 6.39882697947214, |
| "grad_norm": 0.5694658566557079, |
| "learning_rate": 1.472158004858573e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9749011695384979, |
| "step": 1094 |
| }, |
| { |
| "epoch": 6.404692082111437, |
| "grad_norm": 0.5450236136544335, |
| "learning_rate": 1.4690229122571419e-05, |
| "loss": 0.0929, |
| "mean_token_accuracy": 0.9710717871785164, |
| "step": 1095 |
| }, |
| { |
| "epoch": 6.410557184750733, |
| "grad_norm": 0.41354829760386663, |
| "learning_rate": 1.4658904728073169e-05, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9808862060308456, |
| "step": 1096 |
| }, |
| { |
| "epoch": 6.416422287390029, |
| "grad_norm": 0.5695348455497171, |
| "learning_rate": 1.4627606978785878e-05, |
| "loss": 0.0787, |
| "mean_token_accuracy": 0.9755074679851532, |
| "step": 1097 |
| }, |
| { |
| "epoch": 6.422287390029325, |
| "grad_norm": 0.6053385591283429, |
| "learning_rate": 1.4596335988307736e-05, |
| "loss": 0.0891, |
| "mean_token_accuracy": 0.9750615283846855, |
| "step": 1098 |
| }, |
| { |
| "epoch": 6.428152492668621, |
| "grad_norm": 0.43427458206289293, |
| "learning_rate": 1.4565091870139814e-05, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.978523463010788, |
| "step": 1099 |
| }, |
| { |
| "epoch": 6.4340175953079175, |
| "grad_norm": 0.7745882954070427, |
| "learning_rate": 1.4533874737685638e-05, |
| "loss": 0.1, |
| "mean_token_accuracy": 0.9720165580511093, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.439882697947214, |
| "grad_norm": 0.5568880003543828, |
| "learning_rate": 1.450268470425079e-05, |
| "loss": 0.0727, |
| "mean_token_accuracy": 0.9786621853709221, |
| "step": 1101 |
| }, |
| { |
| "epoch": 6.44574780058651, |
| "grad_norm": 0.6102606978496696, |
| "learning_rate": 1.4471521883042492e-05, |
| "loss": 0.0797, |
| "mean_token_accuracy": 0.9762641340494156, |
| "step": 1102 |
| }, |
| { |
| "epoch": 6.451612903225806, |
| "grad_norm": 0.5940527203426741, |
| "learning_rate": 1.4440386387169207e-05, |
| "loss": 0.0812, |
| "mean_token_accuracy": 0.9767268747091293, |
| "step": 1103 |
| }, |
| { |
| "epoch": 6.457478005865102, |
| "grad_norm": 0.45629024567204896, |
| "learning_rate": 1.4409278329640218e-05, |
| "loss": 0.0815, |
| "mean_token_accuracy": 0.9736464098095894, |
| "step": 1104 |
| }, |
| { |
| "epoch": 6.463343108504398, |
| "grad_norm": 0.5152284877743204, |
| "learning_rate": 1.4378197823365186e-05, |
| "loss": 0.0793, |
| "mean_token_accuracy": 0.9755809679627419, |
| "step": 1105 |
| }, |
| { |
| "epoch": 6.469208211143695, |
| "grad_norm": 0.5481643128231853, |
| "learning_rate": 1.4347144981153807e-05, |
| "loss": 0.0957, |
| "mean_token_accuracy": 0.9682923331856728, |
| "step": 1106 |
| }, |
| { |
| "epoch": 6.475073313782991, |
| "grad_norm": 0.38056702827336675, |
| "learning_rate": 1.4316119915715363e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9792584180831909, |
| "step": 1107 |
| }, |
| { |
| "epoch": 6.480938416422287, |
| "grad_norm": 0.6374492323620196, |
| "learning_rate": 1.42851227396583e-05, |
| "loss": 0.0848, |
| "mean_token_accuracy": 0.9738872051239014, |
| "step": 1108 |
| }, |
| { |
| "epoch": 6.486803519061583, |
| "grad_norm": 0.4774557252930596, |
| "learning_rate": 1.4254153565489861e-05, |
| "loss": 0.0847, |
| "mean_token_accuracy": 0.9743882343173027, |
| "step": 1109 |
| }, |
| { |
| "epoch": 6.492668621700879, |
| "grad_norm": 0.5011837903979812, |
| "learning_rate": 1.4223212505615634e-05, |
| "loss": 0.0729, |
| "mean_token_accuracy": 0.9778528362512589, |
| "step": 1110 |
| }, |
| { |
| "epoch": 6.4985337243401755, |
| "grad_norm": 0.33804780404464596, |
| "learning_rate": 1.4192299672339167e-05, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9776539281010628, |
| "step": 1111 |
| }, |
| { |
| "epoch": 6.504398826979472, |
| "grad_norm": 0.5528074933384356, |
| "learning_rate": 1.4161415177861568e-05, |
| "loss": 0.0812, |
| "mean_token_accuracy": 0.9744323939085007, |
| "step": 1112 |
| }, |
| { |
| "epoch": 6.510263929618768, |
| "grad_norm": 0.457506401160417, |
| "learning_rate": 1.4130559134281074e-05, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9784527495503426, |
| "step": 1113 |
| }, |
| { |
| "epoch": 6.516129032258064, |
| "grad_norm": 0.4355792645298778, |
| "learning_rate": 1.4099731653592668e-05, |
| "loss": 0.0714, |
| "mean_token_accuracy": 0.9768256545066833, |
| "step": 1114 |
| }, |
| { |
| "epoch": 6.52199413489736, |
| "grad_norm": 0.5847017963309225, |
| "learning_rate": 1.406893284768764e-05, |
| "loss": 0.0957, |
| "mean_token_accuracy": 0.9728905037045479, |
| "step": 1115 |
| }, |
| { |
| "epoch": 6.527859237536656, |
| "grad_norm": 0.4781949377668264, |
| "learning_rate": 1.4038162828353223e-05, |
| "loss": 0.0836, |
| "mean_token_accuracy": 0.9729764312505722, |
| "step": 1116 |
| }, |
| { |
| "epoch": 6.533724340175953, |
| "grad_norm": 0.39863238666699835, |
| "learning_rate": 1.4007421707272167e-05, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.9747898653149605, |
| "step": 1117 |
| }, |
| { |
| "epoch": 6.539589442815249, |
| "grad_norm": 0.42134641962040914, |
| "learning_rate": 1.3976709596022313e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9754165560007095, |
| "step": 1118 |
| }, |
| { |
| "epoch": 6.545454545454545, |
| "grad_norm": 0.55326137317192, |
| "learning_rate": 1.3946026606076232e-05, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.9780076220631599, |
| "step": 1119 |
| }, |
| { |
| "epoch": 6.551319648093841, |
| "grad_norm": 0.5124262743538484, |
| "learning_rate": 1.3915372848800784e-05, |
| "loss": 0.0813, |
| "mean_token_accuracy": 0.9773962423205376, |
| "step": 1120 |
| }, |
| { |
| "epoch": 6.557184750733137, |
| "grad_norm": 0.3791238325929412, |
| "learning_rate": 1.388474843545672e-05, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9768983200192451, |
| "step": 1121 |
| }, |
| { |
| "epoch": 6.563049853372434, |
| "grad_norm": 0.5267515124456588, |
| "learning_rate": 1.3854153477198305e-05, |
| "loss": 0.0975, |
| "mean_token_accuracy": 0.96617691218853, |
| "step": 1122 |
| }, |
| { |
| "epoch": 6.568914956011731, |
| "grad_norm": 0.43681836428663207, |
| "learning_rate": 1.3823588085072865e-05, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9760182648897171, |
| "step": 1123 |
| }, |
| { |
| "epoch": 6.574780058651027, |
| "grad_norm": 0.49103511141121264, |
| "learning_rate": 1.3793052370020441e-05, |
| "loss": 0.0855, |
| "mean_token_accuracy": 0.9750201031565666, |
| "step": 1124 |
| }, |
| { |
| "epoch": 6.580645161290323, |
| "grad_norm": 0.5269957140084237, |
| "learning_rate": 1.3762546442873343e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9769143760204315, |
| "step": 1125 |
| }, |
| { |
| "epoch": 6.586510263929619, |
| "grad_norm": 0.5181206552351602, |
| "learning_rate": 1.3732070414355766e-05, |
| "loss": 0.0787, |
| "mean_token_accuracy": 0.977984108030796, |
| "step": 1126 |
| }, |
| { |
| "epoch": 6.592375366568915, |
| "grad_norm": 0.5708151076864234, |
| "learning_rate": 1.370162439508339e-05, |
| "loss": 0.0693, |
| "mean_token_accuracy": 0.9770340025424957, |
| "step": 1127 |
| }, |
| { |
| "epoch": 6.5982404692082115, |
| "grad_norm": 0.5470399050655503, |
| "learning_rate": 1.367120849556296e-05, |
| "loss": 0.0777, |
| "mean_token_accuracy": 0.9765413254499435, |
| "step": 1128 |
| }, |
| { |
| "epoch": 6.604105571847508, |
| "grad_norm": 0.5386549797651184, |
| "learning_rate": 1.3640822826191907e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.981001041829586, |
| "step": 1129 |
| }, |
| { |
| "epoch": 6.609970674486804, |
| "grad_norm": 0.5851693910491862, |
| "learning_rate": 1.361046749725794e-05, |
| "loss": 0.0828, |
| "mean_token_accuracy": 0.9728478416800499, |
| "step": 1130 |
| }, |
| { |
| "epoch": 6.6158357771261, |
| "grad_norm": 0.43900153373855055, |
| "learning_rate": 1.3580142618938647e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9815235733985901, |
| "step": 1131 |
| }, |
| { |
| "epoch": 6.621700879765396, |
| "grad_norm": 0.49986443142734005, |
| "learning_rate": 1.354984830130109e-05, |
| "loss": 0.079, |
| "mean_token_accuracy": 0.972543366253376, |
| "step": 1132 |
| }, |
| { |
| "epoch": 6.627565982404692, |
| "grad_norm": 0.34788685161884764, |
| "learning_rate": 1.3519584654301401e-05, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9763465449213982, |
| "step": 1133 |
| }, |
| { |
| "epoch": 6.633431085043989, |
| "grad_norm": 0.4055813660781002, |
| "learning_rate": 1.3489351787784398e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9773242846131325, |
| "step": 1134 |
| }, |
| { |
| "epoch": 6.639296187683285, |
| "grad_norm": 0.5243402543409744, |
| "learning_rate": 1.3459149811483178e-05, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.9739445820450783, |
| "step": 1135 |
| }, |
| { |
| "epoch": 6.645161290322581, |
| "grad_norm": 0.5784909436096058, |
| "learning_rate": 1.342897883501872e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9781769141554832, |
| "step": 1136 |
| }, |
| { |
| "epoch": 6.651026392961877, |
| "grad_norm": 0.5642611585182853, |
| "learning_rate": 1.3398838967899477e-05, |
| "loss": 0.0757, |
| "mean_token_accuracy": 0.9764586612582207, |
| "step": 1137 |
| }, |
| { |
| "epoch": 6.656891495601173, |
| "grad_norm": 0.5776079482395293, |
| "learning_rate": 1.3368730319520992e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9767368286848068, |
| "step": 1138 |
| }, |
| { |
| "epoch": 6.6627565982404695, |
| "grad_norm": 0.5020885081440374, |
| "learning_rate": 1.3338652999165511e-05, |
| "loss": 0.0828, |
| "mean_token_accuracy": 0.9737912267446518, |
| "step": 1139 |
| }, |
| { |
| "epoch": 6.668621700879766, |
| "grad_norm": 0.4204132575953816, |
| "learning_rate": 1.3308607116001549e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9794393181800842, |
| "step": 1140 |
| }, |
| { |
| "epoch": 6.674486803519062, |
| "grad_norm": 0.33560567758456566, |
| "learning_rate": 1.3278592779083534e-05, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.982670783996582, |
| "step": 1141 |
| }, |
| { |
| "epoch": 6.680351906158358, |
| "grad_norm": 0.44043001628693984, |
| "learning_rate": 1.324861009735138e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.976046696305275, |
| "step": 1142 |
| }, |
| { |
| "epoch": 6.686217008797654, |
| "grad_norm": 0.4471342618318792, |
| "learning_rate": 1.3218659179630112e-05, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.9754833951592445, |
| "step": 1143 |
| }, |
| { |
| "epoch": 6.69208211143695, |
| "grad_norm": 0.4923308485055896, |
| "learning_rate": 1.3188740134629469e-05, |
| "loss": 0.0773, |
| "mean_token_accuracy": 0.9752767756581306, |
| "step": 1144 |
| }, |
| { |
| "epoch": 6.697947214076247, |
| "grad_norm": 0.38739961314807136, |
| "learning_rate": 1.3158853070943499e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9790047481656075, |
| "step": 1145 |
| }, |
| { |
| "epoch": 6.703812316715543, |
| "grad_norm": 0.5382902596883963, |
| "learning_rate": 1.3128998097050174e-05, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9773894026875496, |
| "step": 1146 |
| }, |
| { |
| "epoch": 6.709677419354839, |
| "grad_norm": 0.33644056058754507, |
| "learning_rate": 1.3099175321310993e-05, |
| "loss": 0.0731, |
| "mean_token_accuracy": 0.9767147675156593, |
| "step": 1147 |
| }, |
| { |
| "epoch": 6.715542521994135, |
| "grad_norm": 0.4103102513526391, |
| "learning_rate": 1.3069384851970584e-05, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9766853898763657, |
| "step": 1148 |
| }, |
| { |
| "epoch": 6.721407624633431, |
| "grad_norm": 0.4939880953827209, |
| "learning_rate": 1.3039626797156321e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.9746366888284683, |
| "step": 1149 |
| }, |
| { |
| "epoch": 6.7272727272727275, |
| "grad_norm": 0.5170797931844157, |
| "learning_rate": 1.3009901264877924e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.9808530285954475, |
| "step": 1150 |
| }, |
| { |
| "epoch": 6.733137829912024, |
| "grad_norm": 0.43733602892668694, |
| "learning_rate": 1.298020836302707e-05, |
| "loss": 0.0737, |
| "mean_token_accuracy": 0.9757565036416054, |
| "step": 1151 |
| }, |
| { |
| "epoch": 6.73900293255132, |
| "grad_norm": 0.4364034894757785, |
| "learning_rate": 1.2950548199376999e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9793206825852394, |
| "step": 1152 |
| }, |
| { |
| "epoch": 6.744868035190616, |
| "grad_norm": 0.46877766717768593, |
| "learning_rate": 1.292092088158213e-05, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.9757286831736565, |
| "step": 1153 |
| }, |
| { |
| "epoch": 6.750733137829912, |
| "grad_norm": 0.5253930018569454, |
| "learning_rate": 1.2891326517177663e-05, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9813364297151566, |
| "step": 1154 |
| }, |
| { |
| "epoch": 6.756598240469208, |
| "grad_norm": 0.7472840164089494, |
| "learning_rate": 1.2861765213579177e-05, |
| "loss": 0.0785, |
| "mean_token_accuracy": 0.9729948118329048, |
| "step": 1155 |
| }, |
| { |
| "epoch": 6.762463343108505, |
| "grad_norm": 0.4671253491191335, |
| "learning_rate": 1.2832237078082272e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.9766018316149712, |
| "step": 1156 |
| }, |
| { |
| "epoch": 6.768328445747801, |
| "grad_norm": 0.48121955835735647, |
| "learning_rate": 1.2802742217862156e-05, |
| "loss": 0.0789, |
| "mean_token_accuracy": 0.9764746427536011, |
| "step": 1157 |
| }, |
| { |
| "epoch": 6.774193548387097, |
| "grad_norm": 0.49066051899276214, |
| "learning_rate": 1.2773280739973255e-05, |
| "loss": 0.0763, |
| "mean_token_accuracy": 0.9759164974093437, |
| "step": 1158 |
| }, |
| { |
| "epoch": 6.780058651026393, |
| "grad_norm": 0.6208662162621278, |
| "learning_rate": 1.2743852751348833e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9792628586292267, |
| "step": 1159 |
| }, |
| { |
| "epoch": 6.785923753665689, |
| "grad_norm": 0.353932410029375, |
| "learning_rate": 1.2714458358800612e-05, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9837256073951721, |
| "step": 1160 |
| }, |
| { |
| "epoch": 6.7917888563049855, |
| "grad_norm": 0.49853873282358013, |
| "learning_rate": 1.2685097669018362e-05, |
| "loss": 0.0852, |
| "mean_token_accuracy": 0.9731195271015167, |
| "step": 1161 |
| }, |
| { |
| "epoch": 6.797653958944282, |
| "grad_norm": 0.44880495835263245, |
| "learning_rate": 1.265577078856953e-05, |
| "loss": 0.0828, |
| "mean_token_accuracy": 0.9722541272640228, |
| "step": 1162 |
| }, |
| { |
| "epoch": 6.803519061583578, |
| "grad_norm": 0.5569097040356273, |
| "learning_rate": 1.2626477823898843e-05, |
| "loss": 0.0859, |
| "mean_token_accuracy": 0.9755456000566483, |
| "step": 1163 |
| }, |
| { |
| "epoch": 6.809384164222874, |
| "grad_norm": 0.3498951131477967, |
| "learning_rate": 1.2597218881327944e-05, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9757883995771408, |
| "step": 1164 |
| }, |
| { |
| "epoch": 6.81524926686217, |
| "grad_norm": 0.5849400834625669, |
| "learning_rate": 1.2567994067054961e-05, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9759183302521706, |
| "step": 1165 |
| }, |
| { |
| "epoch": 6.821114369501466, |
| "grad_norm": 0.381799734503235, |
| "learning_rate": 1.2538803487154177e-05, |
| "loss": 0.0711, |
| "mean_token_accuracy": 0.9773522317409515, |
| "step": 1166 |
| }, |
| { |
| "epoch": 6.826979472140763, |
| "grad_norm": 0.7880188378909819, |
| "learning_rate": 1.25096472475756e-05, |
| "loss": 0.0826, |
| "mean_token_accuracy": 0.972911424934864, |
| "step": 1167 |
| }, |
| { |
| "epoch": 6.832844574780059, |
| "grad_norm": 0.3352929350228359, |
| "learning_rate": 1.248052545414461e-05, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9781019762158394, |
| "step": 1168 |
| }, |
| { |
| "epoch": 6.838709677419355, |
| "grad_norm": 0.4486648642428875, |
| "learning_rate": 1.2451438212561556e-05, |
| "loss": 0.086, |
| "mean_token_accuracy": 0.9684128165245056, |
| "step": 1169 |
| }, |
| { |
| "epoch": 6.844574780058651, |
| "grad_norm": 0.5337445397907, |
| "learning_rate": 1.2422385628401377e-05, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.975617341697216, |
| "step": 1170 |
| }, |
| { |
| "epoch": 6.850439882697947, |
| "grad_norm": 0.5023072492519426, |
| "learning_rate": 1.2393367807113217e-05, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9774403125047684, |
| "step": 1171 |
| }, |
| { |
| "epoch": 6.8563049853372435, |
| "grad_norm": 0.5478108519507331, |
| "learning_rate": 1.236438485402005e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9768877327442169, |
| "step": 1172 |
| }, |
| { |
| "epoch": 6.86217008797654, |
| "grad_norm": 0.34421809417617816, |
| "learning_rate": 1.2335436874318293e-05, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9794752076268196, |
| "step": 1173 |
| }, |
| { |
| "epoch": 6.868035190615836, |
| "grad_norm": 0.4818321119164012, |
| "learning_rate": 1.2306523973077416e-05, |
| "loss": 0.0854, |
| "mean_token_accuracy": 0.9749922305345535, |
| "step": 1174 |
| }, |
| { |
| "epoch": 6.873900293255132, |
| "grad_norm": 0.44140692461936487, |
| "learning_rate": 1.2277646255239572e-05, |
| "loss": 0.0822, |
| "mean_token_accuracy": 0.9771685898303986, |
| "step": 1175 |
| }, |
| { |
| "epoch": 6.879765395894428, |
| "grad_norm": 0.4122931627899861, |
| "learning_rate": 1.2248803825619224e-05, |
| "loss": 0.0777, |
| "mean_token_accuracy": 0.9765308573842049, |
| "step": 1176 |
| }, |
| { |
| "epoch": 6.885630498533724, |
| "grad_norm": 0.5185863368160872, |
| "learning_rate": 1.2219996788902734e-05, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9782401323318481, |
| "step": 1177 |
| }, |
| { |
| "epoch": 6.891495601173021, |
| "grad_norm": 0.4704417201653903, |
| "learning_rate": 1.2191225249648016e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9757214114069939, |
| "step": 1178 |
| }, |
| { |
| "epoch": 6.897360703812317, |
| "grad_norm": 0.4464835699482663, |
| "learning_rate": 1.216248931228413e-05, |
| "loss": 0.0816, |
| "mean_token_accuracy": 0.9743654951453209, |
| "step": 1179 |
| }, |
| { |
| "epoch": 6.903225806451613, |
| "grad_norm": 0.5291322182737432, |
| "learning_rate": 1.2133789081110927e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9801248833537102, |
| "step": 1180 |
| }, |
| { |
| "epoch": 6.909090909090909, |
| "grad_norm": 0.6972005324832886, |
| "learning_rate": 1.2105124660298655e-05, |
| "loss": 0.0744, |
| "mean_token_accuracy": 0.9761540293693542, |
| "step": 1181 |
| }, |
| { |
| "epoch": 6.914956011730205, |
| "grad_norm": 0.48751263996047123, |
| "learning_rate": 1.2076496153887587e-05, |
| "loss": 0.0707, |
| "mean_token_accuracy": 0.979655809700489, |
| "step": 1182 |
| }, |
| { |
| "epoch": 6.9208211143695015, |
| "grad_norm": 0.35181511064354204, |
| "learning_rate": 1.2047903665787633e-05, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9796392843127251, |
| "step": 1183 |
| }, |
| { |
| "epoch": 6.926686217008798, |
| "grad_norm": 0.4519666851787502, |
| "learning_rate": 1.2019347299777981e-05, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.980430044233799, |
| "step": 1184 |
| }, |
| { |
| "epoch": 6.932551319648094, |
| "grad_norm": 0.6175167131951601, |
| "learning_rate": 1.199082715950671e-05, |
| "loss": 0.0867, |
| "mean_token_accuracy": 0.9735838696360588, |
| "step": 1185 |
| }, |
| { |
| "epoch": 6.93841642228739, |
| "grad_norm": 0.5244767936392362, |
| "learning_rate": 1.1962343348490407e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9765205755829811, |
| "step": 1186 |
| }, |
| { |
| "epoch": 6.944281524926686, |
| "grad_norm": 0.5219220102479316, |
| "learning_rate": 1.1933895970113798e-05, |
| "loss": 0.0794, |
| "mean_token_accuracy": 0.9774181470274925, |
| "step": 1187 |
| }, |
| { |
| "epoch": 6.9501466275659824, |
| "grad_norm": 0.4556906562978321, |
| "learning_rate": 1.1905485127629387e-05, |
| "loss": 0.0818, |
| "mean_token_accuracy": 0.9761421829462051, |
| "step": 1188 |
| }, |
| { |
| "epoch": 6.956011730205279, |
| "grad_norm": 0.45508332549291347, |
| "learning_rate": 1.1877110924157046e-05, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.977460503578186, |
| "step": 1189 |
| }, |
| { |
| "epoch": 6.961876832844575, |
| "grad_norm": 0.4432193649311906, |
| "learning_rate": 1.1848773462683684e-05, |
| "loss": 0.0797, |
| "mean_token_accuracy": 0.9757311940193176, |
| "step": 1190 |
| }, |
| { |
| "epoch": 6.967741935483871, |
| "grad_norm": 0.48985886044639837, |
| "learning_rate": 1.1820472846062842e-05, |
| "loss": 0.0733, |
| "mean_token_accuracy": 0.976937510073185, |
| "step": 1191 |
| }, |
| { |
| "epoch": 6.973607038123167, |
| "grad_norm": 0.40019240637175396, |
| "learning_rate": 1.1792209177014317e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9791741147637367, |
| "step": 1192 |
| }, |
| { |
| "epoch": 6.979472140762463, |
| "grad_norm": 0.45859725535588075, |
| "learning_rate": 1.1763982558123823e-05, |
| "loss": 0.0786, |
| "mean_token_accuracy": 0.9758159667253494, |
| "step": 1193 |
| }, |
| { |
| "epoch": 6.9853372434017595, |
| "grad_norm": 0.6776544697191254, |
| "learning_rate": 1.1735793091842583e-05, |
| "loss": 0.0821, |
| "mean_token_accuracy": 0.974973164498806, |
| "step": 1194 |
| }, |
| { |
| "epoch": 6.991202346041056, |
| "grad_norm": 0.43821555095436865, |
| "learning_rate": 1.1707640880486975e-05, |
| "loss": 0.0894, |
| "mean_token_accuracy": 0.9700244292616844, |
| "step": 1195 |
| }, |
| { |
| "epoch": 6.997067448680352, |
| "grad_norm": 0.3282294489959217, |
| "learning_rate": 1.1679526026238155e-05, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9817990660667419, |
| "step": 1196 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.3282294489959217, |
| "learning_rate": 1.165144863114169e-05, |
| "loss": 0.0702, |
| "mean_token_accuracy": 0.9798854738473892, |
| "step": 1197 |
| }, |
| { |
| "epoch": 7.005865102639296, |
| "grad_norm": 0.6912206326178958, |
| "learning_rate": 1.1623408797107185e-05, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9741964638233185, |
| "step": 1198 |
| }, |
| { |
| "epoch": 7.011730205278592, |
| "grad_norm": 0.38262777975799617, |
| "learning_rate": 1.1595406625907914e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9813871160149574, |
| "step": 1199 |
| }, |
| { |
| "epoch": 7.0175953079178885, |
| "grad_norm": 0.3500785949484349, |
| "learning_rate": 1.1567442219180446e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9810681790113449, |
| "step": 1200 |
| }, |
| { |
| "epoch": 7.023460410557185, |
| "grad_norm": 0.23047356622297646, |
| "learning_rate": 1.153951567842429e-05, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9834885075688362, |
| "step": 1201 |
| }, |
| { |
| "epoch": 7.029325513196481, |
| "grad_norm": 0.3641697975570479, |
| "learning_rate": 1.1511627105001501e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9782865270972252, |
| "step": 1202 |
| }, |
| { |
| "epoch": 7.035190615835777, |
| "grad_norm": 0.4077718026992906, |
| "learning_rate": 1.1483776600136344e-05, |
| "loss": 0.0754, |
| "mean_token_accuracy": 0.975783459842205, |
| "step": 1203 |
| }, |
| { |
| "epoch": 7.041055718475073, |
| "grad_norm": 0.3328632538786026, |
| "learning_rate": 1.1455964264914906e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9806740134954453, |
| "step": 1204 |
| }, |
| { |
| "epoch": 7.0469208211143695, |
| "grad_norm": 0.3565482658377984, |
| "learning_rate": 1.142819020028472e-05, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9753721952438354, |
| "step": 1205 |
| }, |
| { |
| "epoch": 7.052785923753666, |
| "grad_norm": 0.513820218763689, |
| "learning_rate": 1.140045450705443e-05, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9776762798428535, |
| "step": 1206 |
| }, |
| { |
| "epoch": 7.058651026392962, |
| "grad_norm": 0.33746029088525126, |
| "learning_rate": 1.13727572858934e-05, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9811746403574944, |
| "step": 1207 |
| }, |
| { |
| "epoch": 7.064516129032258, |
| "grad_norm": 0.839529082956056, |
| "learning_rate": 1.1345098637331356e-05, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9804647564888, |
| "step": 1208 |
| }, |
| { |
| "epoch": 7.070381231671554, |
| "grad_norm": 0.4512949406596747, |
| "learning_rate": 1.1317478661758022e-05, |
| "loss": 0.0808, |
| "mean_token_accuracy": 0.9737851694226265, |
| "step": 1209 |
| }, |
| { |
| "epoch": 7.07624633431085, |
| "grad_norm": 0.3599939117700741, |
| "learning_rate": 1.1289897459422756e-05, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9815982356667519, |
| "step": 1210 |
| }, |
| { |
| "epoch": 7.0821114369501466, |
| "grad_norm": 0.45954124827480125, |
| "learning_rate": 1.126235513043418e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9773466065526009, |
| "step": 1211 |
| }, |
| { |
| "epoch": 7.087976539589443, |
| "grad_norm": 0.4170706025787579, |
| "learning_rate": 1.1234851774759828e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9824484139680862, |
| "step": 1212 |
| }, |
| { |
| "epoch": 7.093841642228739, |
| "grad_norm": 0.3152206043073185, |
| "learning_rate": 1.1207387492225772e-05, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.978251039981842, |
| "step": 1213 |
| }, |
| { |
| "epoch": 7.099706744868035, |
| "grad_norm": 0.34231567251230943, |
| "learning_rate": 1.1179962382516268e-05, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9778275638818741, |
| "step": 1214 |
| }, |
| { |
| "epoch": 7.105571847507331, |
| "grad_norm": 0.38154737914773634, |
| "learning_rate": 1.1152576545173388e-05, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9792356640100479, |
| "step": 1215 |
| }, |
| { |
| "epoch": 7.1114369501466275, |
| "grad_norm": 0.38506430145241727, |
| "learning_rate": 1.1125230079596654e-05, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9793743640184402, |
| "step": 1216 |
| }, |
| { |
| "epoch": 7.117302052785924, |
| "grad_norm": 0.29298285325763024, |
| "learning_rate": 1.10979230850427e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9798607155680656, |
| "step": 1217 |
| }, |
| { |
| "epoch": 7.12316715542522, |
| "grad_norm": 0.5131708622489167, |
| "learning_rate": 1.1070655660624876e-05, |
| "loss": 0.0762, |
| "mean_token_accuracy": 0.9752130582928658, |
| "step": 1218 |
| }, |
| { |
| "epoch": 7.129032258064516, |
| "grad_norm": 0.3530156134365258, |
| "learning_rate": 1.1043427905312933e-05, |
| "loss": 0.0764, |
| "mean_token_accuracy": 0.9781614691019058, |
| "step": 1219 |
| }, |
| { |
| "epoch": 7.134897360703812, |
| "grad_norm": 0.6047250936241889, |
| "learning_rate": 1.1016239917932618e-05, |
| "loss": 0.0705, |
| "mean_token_accuracy": 0.97938072681427, |
| "step": 1220 |
| }, |
| { |
| "epoch": 7.140762463343108, |
| "grad_norm": 0.43104388838903596, |
| "learning_rate": 1.098909179716535e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9750777781009674, |
| "step": 1221 |
| }, |
| { |
| "epoch": 7.146627565982405, |
| "grad_norm": 0.36410154505783404, |
| "learning_rate": 1.096198364154784e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9790825098752975, |
| "step": 1222 |
| }, |
| { |
| "epoch": 7.152492668621701, |
| "grad_norm": 0.34833475970741407, |
| "learning_rate": 1.0934915549471747e-05, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9804369062185287, |
| "step": 1223 |
| }, |
| { |
| "epoch": 7.158357771260997, |
| "grad_norm": 0.38353938112532193, |
| "learning_rate": 1.0907887619183308e-05, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9804348051548004, |
| "step": 1224 |
| }, |
| { |
| "epoch": 7.164222873900293, |
| "grad_norm": 0.3798952101192259, |
| "learning_rate": 1.0880899948783002e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9765540808439255, |
| "step": 1225 |
| }, |
| { |
| "epoch": 7.170087976539589, |
| "grad_norm": 0.3386618138568785, |
| "learning_rate": 1.0853952636225165e-05, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.9791587889194489, |
| "step": 1226 |
| }, |
| { |
| "epoch": 7.1759530791788855, |
| "grad_norm": 0.3955364270043223, |
| "learning_rate": 1.0827045779317662e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9806070253252983, |
| "step": 1227 |
| }, |
| { |
| "epoch": 7.181818181818182, |
| "grad_norm": 0.475027525545252, |
| "learning_rate": 1.080017947572152e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9796654880046844, |
| "step": 1228 |
| }, |
| { |
| "epoch": 7.187683284457478, |
| "grad_norm": 0.3715636804821357, |
| "learning_rate": 1.0773353822950563e-05, |
| "loss": 0.0778, |
| "mean_token_accuracy": 0.9782843813300133, |
| "step": 1229 |
| }, |
| { |
| "epoch": 7.193548387096774, |
| "grad_norm": 0.5439705897468128, |
| "learning_rate": 1.074656891837108e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9818157479166985, |
| "step": 1230 |
| }, |
| { |
| "epoch": 7.19941348973607, |
| "grad_norm": 0.2837476614356044, |
| "learning_rate": 1.0719824859201457e-05, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9786864891648293, |
| "step": 1231 |
| }, |
| { |
| "epoch": 7.205278592375366, |
| "grad_norm": 0.39130123442883724, |
| "learning_rate": 1.0693121742511828e-05, |
| "loss": 0.0819, |
| "mean_token_accuracy": 0.9728628844022751, |
| "step": 1232 |
| }, |
| { |
| "epoch": 7.211143695014663, |
| "grad_norm": 0.399415818262287, |
| "learning_rate": 1.0666459665223718e-05, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.97879458963871, |
| "step": 1233 |
| }, |
| { |
| "epoch": 7.217008797653959, |
| "grad_norm": 0.3830316696582617, |
| "learning_rate": 1.0639838724109708e-05, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9789978414773941, |
| "step": 1234 |
| }, |
| { |
| "epoch": 7.222873900293255, |
| "grad_norm": 0.28801687651420393, |
| "learning_rate": 1.0613259015793056e-05, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9807603433728218, |
| "step": 1235 |
| }, |
| { |
| "epoch": 7.228739002932551, |
| "grad_norm": 0.42958082726412133, |
| "learning_rate": 1.0586720636747368e-05, |
| "loss": 0.0762, |
| "mean_token_accuracy": 0.9768098592758179, |
| "step": 1236 |
| }, |
| { |
| "epoch": 7.234604105571847, |
| "grad_norm": 0.3079954178226424, |
| "learning_rate": 1.0560223683296244e-05, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9774455577135086, |
| "step": 1237 |
| }, |
| { |
| "epoch": 7.2404692082111435, |
| "grad_norm": 0.5264608888186644, |
| "learning_rate": 1.0533768251612924e-05, |
| "loss": 0.0729, |
| "mean_token_accuracy": 0.9767781645059586, |
| "step": 1238 |
| }, |
| { |
| "epoch": 7.24633431085044, |
| "grad_norm": 0.41160315181988266, |
| "learning_rate": 1.0507354437719938e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9828227832913399, |
| "step": 1239 |
| }, |
| { |
| "epoch": 7.252199413489736, |
| "grad_norm": 0.3872454574394867, |
| "learning_rate": 1.0480982337488768e-05, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9776423200964928, |
| "step": 1240 |
| }, |
| { |
| "epoch": 7.258064516129032, |
| "grad_norm": 0.45164649038274723, |
| "learning_rate": 1.0454652046639486e-05, |
| "loss": 0.077, |
| "mean_token_accuracy": 0.9758302047848701, |
| "step": 1241 |
| }, |
| { |
| "epoch": 7.263929618768328, |
| "grad_norm": 0.4139469705680152, |
| "learning_rate": 1.0428363660740407e-05, |
| "loss": 0.0708, |
| "mean_token_accuracy": 0.9761909395456314, |
| "step": 1242 |
| }, |
| { |
| "epoch": 7.269794721407624, |
| "grad_norm": 0.3840838494270553, |
| "learning_rate": 1.0402117275207757e-05, |
| "loss": 0.0754, |
| "mean_token_accuracy": 0.9756297990679741, |
| "step": 1243 |
| }, |
| { |
| "epoch": 7.275659824046921, |
| "grad_norm": 0.3808573639604821, |
| "learning_rate": 1.0375912985305319e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9781527444720268, |
| "step": 1244 |
| }, |
| { |
| "epoch": 7.281524926686217, |
| "grad_norm": 0.4206553824325304, |
| "learning_rate": 1.0349750886144077e-05, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.9749187454581261, |
| "step": 1245 |
| }, |
| { |
| "epoch": 7.287390029325513, |
| "grad_norm": 0.33265484291156516, |
| "learning_rate": 1.0323631072681888e-05, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.9795495644211769, |
| "step": 1246 |
| }, |
| { |
| "epoch": 7.293255131964809, |
| "grad_norm": 0.3178171971797074, |
| "learning_rate": 1.0297553639723123e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9814764708280563, |
| "step": 1247 |
| }, |
| { |
| "epoch": 7.299120234604105, |
| "grad_norm": 0.3779867551878193, |
| "learning_rate": 1.027151868191834e-05, |
| "loss": 0.0745, |
| "mean_token_accuracy": 0.9745180755853653, |
| "step": 1248 |
| }, |
| { |
| "epoch": 7.3049853372434015, |
| "grad_norm": 0.4292350836002161, |
| "learning_rate": 1.0245526293763908e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.974598154425621, |
| "step": 1249 |
| }, |
| { |
| "epoch": 7.310850439882698, |
| "grad_norm": 0.35067941778112494, |
| "learning_rate": 1.0219576569601707e-05, |
| "loss": 0.0793, |
| "mean_token_accuracy": 0.9769597128033638, |
| "step": 1250 |
| }, |
| { |
| "epoch": 7.316715542521994, |
| "grad_norm": 0.39563806400869955, |
| "learning_rate": 1.0193669603618757e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.976021520793438, |
| "step": 1251 |
| }, |
| { |
| "epoch": 7.32258064516129, |
| "grad_norm": 0.46712769922706915, |
| "learning_rate": 1.0167805489846873e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9811434298753738, |
| "step": 1252 |
| }, |
| { |
| "epoch": 7.328445747800586, |
| "grad_norm": 0.37339627555491145, |
| "learning_rate": 1.0141984322162353e-05, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9801758378744125, |
| "step": 1253 |
| }, |
| { |
| "epoch": 7.334310850439882, |
| "grad_norm": 0.3044155287959229, |
| "learning_rate": 1.0116206194285598e-05, |
| "loss": 0.0719, |
| "mean_token_accuracy": 0.9779629483819008, |
| "step": 1254 |
| }, |
| { |
| "epoch": 7.340175953079179, |
| "grad_norm": 0.39714577819514213, |
| "learning_rate": 1.0090471199780812e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9755602031946182, |
| "step": 1255 |
| }, |
| { |
| "epoch": 7.346041055718475, |
| "grad_norm": 0.4570877974493308, |
| "learning_rate": 1.0064779432055616e-05, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9759530946612358, |
| "step": 1256 |
| }, |
| { |
| "epoch": 7.351906158357771, |
| "grad_norm": 0.4205327589510046, |
| "learning_rate": 1.0039130984360761e-05, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9774453565478325, |
| "step": 1257 |
| }, |
| { |
| "epoch": 7.357771260997067, |
| "grad_norm": 0.3684606740091315, |
| "learning_rate": 1.0013525949789745e-05, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9773312881588936, |
| "step": 1258 |
| }, |
| { |
| "epoch": 7.363636363636363, |
| "grad_norm": 0.3187355898488441, |
| "learning_rate": 9.987964421278512e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9804589822888374, |
| "step": 1259 |
| }, |
| { |
| "epoch": 7.3695014662756595, |
| "grad_norm": 0.4023244952241441, |
| "learning_rate": 9.962446491605084e-06, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.975837953388691, |
| "step": 1260 |
| }, |
| { |
| "epoch": 7.375366568914956, |
| "grad_norm": 0.5341557069269197, |
| "learning_rate": 9.936972253389235e-06, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9801123738288879, |
| "step": 1261 |
| }, |
| { |
| "epoch": 7.381231671554252, |
| "grad_norm": 0.3564112574933918, |
| "learning_rate": 9.911541799092162e-06, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9757182076573372, |
| "step": 1262 |
| }, |
| { |
| "epoch": 7.387096774193548, |
| "grad_norm": 0.2346449467553508, |
| "learning_rate": 9.88615522101615e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.978550560772419, |
| "step": 1263 |
| }, |
| { |
| "epoch": 7.392961876832844, |
| "grad_norm": 0.3271500195862692, |
| "learning_rate": 9.860812611304225e-06, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9800273403525352, |
| "step": 1264 |
| }, |
| { |
| "epoch": 7.39882697947214, |
| "grad_norm": 0.29052657488602945, |
| "learning_rate": 9.835514061939822e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9814219176769257, |
| "step": 1265 |
| }, |
| { |
| "epoch": 7.404692082111437, |
| "grad_norm": 0.32197042134754045, |
| "learning_rate": 9.810259664746454e-06, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9777977392077446, |
| "step": 1266 |
| }, |
| { |
| "epoch": 7.410557184750733, |
| "grad_norm": 0.48962506212270573, |
| "learning_rate": 9.785049511387383e-06, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.975383386015892, |
| "step": 1267 |
| }, |
| { |
| "epoch": 7.416422287390029, |
| "grad_norm": 0.42616315538478555, |
| "learning_rate": 9.759883693365287e-06, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.976491704583168, |
| "step": 1268 |
| }, |
| { |
| "epoch": 7.422287390029325, |
| "grad_norm": 0.5004041655379637, |
| "learning_rate": 9.734762302021923e-06, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9809972047805786, |
| "step": 1269 |
| }, |
| { |
| "epoch": 7.428152492668621, |
| "grad_norm": 0.41423957139830336, |
| "learning_rate": 9.709685428537794e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.982276625931263, |
| "step": 1270 |
| }, |
| { |
| "epoch": 7.4340175953079175, |
| "grad_norm": 0.4463820203523401, |
| "learning_rate": 9.684653163931823e-06, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9780172407627106, |
| "step": 1271 |
| }, |
| { |
| "epoch": 7.439882697947214, |
| "grad_norm": 0.32726953724707947, |
| "learning_rate": 9.659665599061019e-06, |
| "loss": 0.0785, |
| "mean_token_accuracy": 0.9734633192420006, |
| "step": 1272 |
| }, |
| { |
| "epoch": 7.44574780058651, |
| "grad_norm": 0.41686111725495745, |
| "learning_rate": 9.634722824620154e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9789967909455299, |
| "step": 1273 |
| }, |
| { |
| "epoch": 7.451612903225806, |
| "grad_norm": 0.25252483483957594, |
| "learning_rate": 9.609824931141423e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9781973287463188, |
| "step": 1274 |
| }, |
| { |
| "epoch": 7.457478005865102, |
| "grad_norm": 0.35317028243851656, |
| "learning_rate": 9.584972008994123e-06, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.980886660516262, |
| "step": 1275 |
| }, |
| { |
| "epoch": 7.463343108504398, |
| "grad_norm": 0.3588023504100938, |
| "learning_rate": 9.560164148384328e-06, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9760325774550438, |
| "step": 1276 |
| }, |
| { |
| "epoch": 7.469208211143695, |
| "grad_norm": 0.42465358965052863, |
| "learning_rate": 9.53540143935455e-06, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9772544130682945, |
| "step": 1277 |
| }, |
| { |
| "epoch": 7.475073313782991, |
| "grad_norm": 0.40089777234913554, |
| "learning_rate": 9.510683971783425e-06, |
| "loss": 0.0904, |
| "mean_token_accuracy": 0.9742084890604019, |
| "step": 1278 |
| }, |
| { |
| "epoch": 7.480938416422287, |
| "grad_norm": 0.5755039890987124, |
| "learning_rate": 9.486011835385372e-06, |
| "loss": 0.0484, |
| "mean_token_accuracy": 0.9854866787791252, |
| "step": 1279 |
| }, |
| { |
| "epoch": 7.486803519061583, |
| "grad_norm": 0.26318968566984136, |
| "learning_rate": 9.461385119710282e-06, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9743320271372795, |
| "step": 1280 |
| }, |
| { |
| "epoch": 7.492668621700879, |
| "grad_norm": 0.32345568363196076, |
| "learning_rate": 9.436803914143189e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9740675911307335, |
| "step": 1281 |
| }, |
| { |
| "epoch": 7.4985337243401755, |
| "grad_norm": 0.3359866371891183, |
| "learning_rate": 9.41226830790394e-06, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9786439761519432, |
| "step": 1282 |
| }, |
| { |
| "epoch": 7.504398826979472, |
| "grad_norm": 0.28449592977664995, |
| "learning_rate": 9.387778390046881e-06, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9785284176468849, |
| "step": 1283 |
| }, |
| { |
| "epoch": 7.510263929618768, |
| "grad_norm": 0.26900051978234174, |
| "learning_rate": 9.363334249460519e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9803383573889732, |
| "step": 1284 |
| }, |
| { |
| "epoch": 7.516129032258064, |
| "grad_norm": 0.32220420095575997, |
| "learning_rate": 9.338935974867213e-06, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9765875190496445, |
| "step": 1285 |
| }, |
| { |
| "epoch": 7.52199413489736, |
| "grad_norm": 0.5224308102926841, |
| "learning_rate": 9.314583654822844e-06, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9766501858830452, |
| "step": 1286 |
| }, |
| { |
| "epoch": 7.527859237536656, |
| "grad_norm": 0.5037316754055287, |
| "learning_rate": 9.290277377716503e-06, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9741085171699524, |
| "step": 1287 |
| }, |
| { |
| "epoch": 7.533724340175953, |
| "grad_norm": 0.42377305298738516, |
| "learning_rate": 9.266017231770155e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9798842146992683, |
| "step": 1288 |
| }, |
| { |
| "epoch": 7.539589442815249, |
| "grad_norm": 0.2573789224293022, |
| "learning_rate": 9.241803305038333e-06, |
| "loss": 0.0744, |
| "mean_token_accuracy": 0.9776958003640175, |
| "step": 1289 |
| }, |
| { |
| "epoch": 7.545454545454545, |
| "grad_norm": 0.2965363860970641, |
| "learning_rate": 9.217635685407813e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9799975752830505, |
| "step": 1290 |
| }, |
| { |
| "epoch": 7.551319648093841, |
| "grad_norm": 0.32631428816151475, |
| "learning_rate": 9.19351446059729e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9817659631371498, |
| "step": 1291 |
| }, |
| { |
| "epoch": 7.557184750733137, |
| "grad_norm": 0.3125871316017961, |
| "learning_rate": 9.16943971815708e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9800999537110329, |
| "step": 1292 |
| }, |
| { |
| "epoch": 7.563049853372434, |
| "grad_norm": 0.2734057475439993, |
| "learning_rate": 9.145411545468756e-06, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9795428663492203, |
| "step": 1293 |
| }, |
| { |
| "epoch": 7.568914956011731, |
| "grad_norm": 0.2604148879143986, |
| "learning_rate": 9.121430029744893e-06, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9805775061249733, |
| "step": 1294 |
| }, |
| { |
| "epoch": 7.574780058651027, |
| "grad_norm": 0.31702286505675215, |
| "learning_rate": 9.097495258028703e-06, |
| "loss": 0.0693, |
| "mean_token_accuracy": 0.9769936874508858, |
| "step": 1295 |
| }, |
| { |
| "epoch": 7.580645161290323, |
| "grad_norm": 0.3605926122000164, |
| "learning_rate": 9.073607317193742e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9788065627217293, |
| "step": 1296 |
| }, |
| { |
| "epoch": 7.586510263929619, |
| "grad_norm": 0.2535069897924097, |
| "learning_rate": 9.049766293943589e-06, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9772609323263168, |
| "step": 1297 |
| }, |
| { |
| "epoch": 7.592375366568915, |
| "grad_norm": 0.4109347943974271, |
| "learning_rate": 9.025972274811527e-06, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9789599850773811, |
| "step": 1298 |
| }, |
| { |
| "epoch": 7.5982404692082115, |
| "grad_norm": 0.2871829801660241, |
| "learning_rate": 9.002225346160238e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9778304621577263, |
| "step": 1299 |
| }, |
| { |
| "epoch": 7.604105571847508, |
| "grad_norm": 0.32674313911500424, |
| "learning_rate": 8.97852559418148e-06, |
| "loss": 0.0637, |
| "mean_token_accuracy": 0.9782585576176643, |
| "step": 1300 |
| }, |
| { |
| "epoch": 7.609970674486804, |
| "grad_norm": 0.34327052126908203, |
| "learning_rate": 8.954873104895787e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9815321713685989, |
| "step": 1301 |
| }, |
| { |
| "epoch": 7.6158357771261, |
| "grad_norm": 0.33708528837651625, |
| "learning_rate": 8.931267964152132e-06, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.9765809625387192, |
| "step": 1302 |
| }, |
| { |
| "epoch": 7.621700879765396, |
| "grad_norm": 0.5041195790884399, |
| "learning_rate": 8.907710257627651e-06, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9783420264720917, |
| "step": 1303 |
| }, |
| { |
| "epoch": 7.627565982404692, |
| "grad_norm": 0.2989590349789707, |
| "learning_rate": 8.884200070827303e-06, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9762579947710037, |
| "step": 1304 |
| }, |
| { |
| "epoch": 7.633431085043989, |
| "grad_norm": 0.4094635271370586, |
| "learning_rate": 8.86073748908357e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9789704233407974, |
| "step": 1305 |
| }, |
| { |
| "epoch": 7.639296187683285, |
| "grad_norm": 0.27117288447287735, |
| "learning_rate": 8.837322597556146e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9795557036995888, |
| "step": 1306 |
| }, |
| { |
| "epoch": 7.645161290322581, |
| "grad_norm": 0.4138735803384374, |
| "learning_rate": 8.813955481231633e-06, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9753428846597672, |
| "step": 1307 |
| }, |
| { |
| "epoch": 7.651026392961877, |
| "grad_norm": 0.30570757377595903, |
| "learning_rate": 8.790636224923221e-06, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9780451580882072, |
| "step": 1308 |
| }, |
| { |
| "epoch": 7.656891495601173, |
| "grad_norm": 0.3261846476792855, |
| "learning_rate": 8.767364913270399e-06, |
| "loss": 0.0768, |
| "mean_token_accuracy": 0.9772769138216972, |
| "step": 1309 |
| }, |
| { |
| "epoch": 7.6627565982404695, |
| "grad_norm": 0.45484472620842326, |
| "learning_rate": 8.744141630738624e-06, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9788528978824615, |
| "step": 1310 |
| }, |
| { |
| "epoch": 7.668621700879766, |
| "grad_norm": 0.274785803295409, |
| "learning_rate": 8.720966461619038e-06, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.9781883060932159, |
| "step": 1311 |
| }, |
| { |
| "epoch": 7.674486803519062, |
| "grad_norm": 0.5798168184695972, |
| "learning_rate": 8.69783949002814e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9807113409042358, |
| "step": 1312 |
| }, |
| { |
| "epoch": 7.680351906158358, |
| "grad_norm": 0.30491164949294325, |
| "learning_rate": 8.6747607999075e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9811301380395889, |
| "step": 1313 |
| }, |
| { |
| "epoch": 7.686217008797654, |
| "grad_norm": 0.38152749678409453, |
| "learning_rate": 8.651730475023435e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9776108860969543, |
| "step": 1314 |
| }, |
| { |
| "epoch": 7.69208211143695, |
| "grad_norm": 0.41854013127871614, |
| "learning_rate": 8.628748598966739e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9768750295042992, |
| "step": 1315 |
| }, |
| { |
| "epoch": 7.697947214076247, |
| "grad_norm": 0.45499424698989827, |
| "learning_rate": 8.605815255152323e-06, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.9720618352293968, |
| "step": 1316 |
| }, |
| { |
| "epoch": 7.703812316715543, |
| "grad_norm": 0.30913926089594507, |
| "learning_rate": 8.582930526818973e-06, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9765586853027344, |
| "step": 1317 |
| }, |
| { |
| "epoch": 7.709677419354839, |
| "grad_norm": 0.5304284265697857, |
| "learning_rate": 8.560094497029008e-06, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.9783492982387543, |
| "step": 1318 |
| }, |
| { |
| "epoch": 7.715542521994135, |
| "grad_norm": 0.44193236209697745, |
| "learning_rate": 8.537307248667992e-06, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9785650745034218, |
| "step": 1319 |
| }, |
| { |
| "epoch": 7.721407624633431, |
| "grad_norm": 0.3801324857485209, |
| "learning_rate": 8.514568864444432e-06, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9757534116506577, |
| "step": 1320 |
| }, |
| { |
| "epoch": 7.7272727272727275, |
| "grad_norm": 0.2924649756631599, |
| "learning_rate": 8.491879426889483e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9798558130860329, |
| "step": 1321 |
| }, |
| { |
| "epoch": 7.733137829912024, |
| "grad_norm": 0.46934446068300567, |
| "learning_rate": 8.469239018356636e-06, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9742545410990715, |
| "step": 1322 |
| }, |
| { |
| "epoch": 7.73900293255132, |
| "grad_norm": 0.42318394489101063, |
| "learning_rate": 8.446647721021435e-06, |
| "loss": 0.0852, |
| "mean_token_accuracy": 0.9734436348080635, |
| "step": 1323 |
| }, |
| { |
| "epoch": 7.744868035190616, |
| "grad_norm": 0.4709962099950871, |
| "learning_rate": 8.424105616881161e-06, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9796672537922859, |
| "step": 1324 |
| }, |
| { |
| "epoch": 7.750733137829912, |
| "grad_norm": 0.5052962775096801, |
| "learning_rate": 8.40161278775455e-06, |
| "loss": 0.079, |
| "mean_token_accuracy": 0.9778957739472389, |
| "step": 1325 |
| }, |
| { |
| "epoch": 7.756598240469208, |
| "grad_norm": 0.794953716358727, |
| "learning_rate": 8.379169315281485e-06, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.9770526960492134, |
| "step": 1326 |
| }, |
| { |
| "epoch": 7.762463343108505, |
| "grad_norm": 0.4708633571052823, |
| "learning_rate": 8.356775280922708e-06, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9773171544075012, |
| "step": 1327 |
| }, |
| { |
| "epoch": 7.768328445747801, |
| "grad_norm": 0.2977066686368222, |
| "learning_rate": 8.334430765959522e-06, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9756058230996132, |
| "step": 1328 |
| }, |
| { |
| "epoch": 7.774193548387097, |
| "grad_norm": 0.34688096761186954, |
| "learning_rate": 8.312135851493494e-06, |
| "loss": 0.0764, |
| "mean_token_accuracy": 0.9759645387530327, |
| "step": 1329 |
| }, |
| { |
| "epoch": 7.780058651026393, |
| "grad_norm": 0.37759510575185457, |
| "learning_rate": 8.28989061844615e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9825332537293434, |
| "step": 1330 |
| }, |
| { |
| "epoch": 7.785923753665689, |
| "grad_norm": 0.25548539074972576, |
| "learning_rate": 8.267695147558705e-06, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9778474643826485, |
| "step": 1331 |
| }, |
| { |
| "epoch": 7.7917888563049855, |
| "grad_norm": 0.3247899940629153, |
| "learning_rate": 8.245549519391758e-06, |
| "loss": 0.0763, |
| "mean_token_accuracy": 0.9769897162914276, |
| "step": 1332 |
| }, |
| { |
| "epoch": 7.797653958944282, |
| "grad_norm": 0.4165530275778508, |
| "learning_rate": 8.22345381432499e-06, |
| "loss": 0.0704, |
| "mean_token_accuracy": 0.9790071472525597, |
| "step": 1333 |
| }, |
| { |
| "epoch": 7.803519061583578, |
| "grad_norm": 0.3026205083529094, |
| "learning_rate": 8.201408112556893e-06, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.9787802696228027, |
| "step": 1334 |
| }, |
| { |
| "epoch": 7.809384164222874, |
| "grad_norm": 0.35726307580476363, |
| "learning_rate": 8.179412494104457e-06, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9751449227333069, |
| "step": 1335 |
| }, |
| { |
| "epoch": 7.81524926686217, |
| "grad_norm": 0.4509292195222995, |
| "learning_rate": 8.15746703880289e-06, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9777436852455139, |
| "step": 1336 |
| }, |
| { |
| "epoch": 7.821114369501466, |
| "grad_norm": 0.2686585360899267, |
| "learning_rate": 8.135571826305339e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9788657277822495, |
| "step": 1337 |
| }, |
| { |
| "epoch": 7.826979472140763, |
| "grad_norm": 0.4818930537808581, |
| "learning_rate": 8.113726936082576e-06, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9743361845612526, |
| "step": 1338 |
| }, |
| { |
| "epoch": 7.832844574780059, |
| "grad_norm": 0.49508100194206756, |
| "learning_rate": 8.091932447422737e-06, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9731877073645592, |
| "step": 1339 |
| }, |
| { |
| "epoch": 7.838709677419355, |
| "grad_norm": 0.29711247347821884, |
| "learning_rate": 8.070188439431005e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9789380878210068, |
| "step": 1340 |
| }, |
| { |
| "epoch": 7.844574780058651, |
| "grad_norm": 0.3397541983633956, |
| "learning_rate": 8.048494991029352e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9785341024398804, |
| "step": 1341 |
| }, |
| { |
| "epoch": 7.850439882697947, |
| "grad_norm": 0.480376564004997, |
| "learning_rate": 8.02685218095624e-06, |
| "loss": 0.0727, |
| "mean_token_accuracy": 0.9771670550107956, |
| "step": 1342 |
| }, |
| { |
| "epoch": 7.8563049853372435, |
| "grad_norm": 0.40889844988462554, |
| "learning_rate": 8.005260087766318e-06, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9762912541627884, |
| "step": 1343 |
| }, |
| { |
| "epoch": 7.86217008797654, |
| "grad_norm": 0.30638673540582606, |
| "learning_rate": 7.983718789830167e-06, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.9767410978674889, |
| "step": 1344 |
| }, |
| { |
| "epoch": 7.868035190615836, |
| "grad_norm": 0.3766404101128721, |
| "learning_rate": 7.962228365333999e-06, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9778221324086189, |
| "step": 1345 |
| }, |
| { |
| "epoch": 7.873900293255132, |
| "grad_norm": 0.3875864282647274, |
| "learning_rate": 7.940788892279375e-06, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9775504246354103, |
| "step": 1346 |
| }, |
| { |
| "epoch": 7.879765395894428, |
| "grad_norm": 0.3486193538218716, |
| "learning_rate": 7.919400448482928e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9794389456510544, |
| "step": 1347 |
| }, |
| { |
| "epoch": 7.885630498533724, |
| "grad_norm": 0.2955046780982513, |
| "learning_rate": 7.898063111576066e-06, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9779496192932129, |
| "step": 1348 |
| }, |
| { |
| "epoch": 7.891495601173021, |
| "grad_norm": 0.3234432215282191, |
| "learning_rate": 7.876776959004706e-06, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.9718790277838707, |
| "step": 1349 |
| }, |
| { |
| "epoch": 7.897360703812317, |
| "grad_norm": 0.35172886904487044, |
| "learning_rate": 7.855542068028981e-06, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9782620742917061, |
| "step": 1350 |
| }, |
| { |
| "epoch": 7.903225806451613, |
| "grad_norm": 0.2484032872765626, |
| "learning_rate": 7.834358515722977e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.9796766042709351, |
| "step": 1351 |
| }, |
| { |
| "epoch": 7.909090909090909, |
| "grad_norm": 0.3189929514946592, |
| "learning_rate": 7.813226378974427e-06, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.976318895816803, |
| "step": 1352 |
| }, |
| { |
| "epoch": 7.914956011730205, |
| "grad_norm": 0.32186645853668916, |
| "learning_rate": 7.792145734484455e-06, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9768570438027382, |
| "step": 1353 |
| }, |
| { |
| "epoch": 7.9208211143695015, |
| "grad_norm": 0.28509948839859406, |
| "learning_rate": 7.771116658767286e-06, |
| "loss": 0.0729, |
| "mean_token_accuracy": 0.9778455495834351, |
| "step": 1354 |
| }, |
| { |
| "epoch": 7.926686217008798, |
| "grad_norm": 0.31897252819873134, |
| "learning_rate": 7.750139228149978e-06, |
| "loss": 0.0782, |
| "mean_token_accuracy": 0.9735360145568848, |
| "step": 1355 |
| }, |
| { |
| "epoch": 7.932551319648094, |
| "grad_norm": 0.4594664457151054, |
| "learning_rate": 7.729213518772121e-06, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.980343259871006, |
| "step": 1356 |
| }, |
| { |
| "epoch": 7.93841642228739, |
| "grad_norm": 0.37424885169765215, |
| "learning_rate": 7.708339606585591e-06, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9746110588312149, |
| "step": 1357 |
| }, |
| { |
| "epoch": 7.944281524926686, |
| "grad_norm": 0.3355832207100877, |
| "learning_rate": 7.687517567354266e-06, |
| "loss": 0.0829, |
| "mean_token_accuracy": 0.9746036380529404, |
| "step": 1358 |
| }, |
| { |
| "epoch": 7.9501466275659824, |
| "grad_norm": 0.37310850047357214, |
| "learning_rate": 7.66674747665373e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9776176363229752, |
| "step": 1359 |
| }, |
| { |
| "epoch": 7.956011730205279, |
| "grad_norm": 0.34627662256254366, |
| "learning_rate": 7.646029409871029e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9754548743367195, |
| "step": 1360 |
| }, |
| { |
| "epoch": 7.961876832844575, |
| "grad_norm": 0.2924727330598229, |
| "learning_rate": 7.625363442204379e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9818178787827492, |
| "step": 1361 |
| }, |
| { |
| "epoch": 7.967741935483871, |
| "grad_norm": 0.37066267600800856, |
| "learning_rate": 7.604749648662892e-06, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9784936085343361, |
| "step": 1362 |
| }, |
| { |
| "epoch": 7.973607038123167, |
| "grad_norm": 0.2726562666079756, |
| "learning_rate": 7.584188104066317e-06, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.9794305935502052, |
| "step": 1363 |
| }, |
| { |
| "epoch": 7.979472140762463, |
| "grad_norm": 0.46100400117349094, |
| "learning_rate": 7.563678883044754e-06, |
| "loss": 0.0843, |
| "mean_token_accuracy": 0.9759550020098686, |
| "step": 1364 |
| }, |
| { |
| "epoch": 7.9853372434017595, |
| "grad_norm": 0.46096923720257865, |
| "learning_rate": 7.5432220600383935e-06, |
| "loss": 0.0832, |
| "mean_token_accuracy": 0.9736724197864532, |
| "step": 1365 |
| }, |
| { |
| "epoch": 7.991202346041056, |
| "grad_norm": 0.3537209449519693, |
| "learning_rate": 7.522817709297241e-06, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9790577068924904, |
| "step": 1366 |
| }, |
| { |
| "epoch": 7.997067448680352, |
| "grad_norm": 0.5417913017909552, |
| "learning_rate": 7.502465904880849e-06, |
| "loss": 0.0717, |
| "mean_token_accuracy": 0.9783544093370438, |
| "step": 1367 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.6652206583753479, |
| "learning_rate": 7.482166720658046e-06, |
| "loss": 0.0685, |
| "mean_token_accuracy": 0.980608344078064, |
| "step": 1368 |
| }, |
| { |
| "epoch": 8.005865102639296, |
| "grad_norm": 0.33294774705553826, |
| "learning_rate": 7.461920230306674e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9774910733103752, |
| "step": 1369 |
| }, |
| { |
| "epoch": 8.011730205278592, |
| "grad_norm": 0.4730798517874754, |
| "learning_rate": 7.441726507313318e-06, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.9798407405614853, |
| "step": 1370 |
| }, |
| { |
| "epoch": 8.017595307917889, |
| "grad_norm": 0.4072909224715183, |
| "learning_rate": 7.421585624973033e-06, |
| "loss": 0.0685, |
| "mean_token_accuracy": 0.9780117720365524, |
| "step": 1371 |
| }, |
| { |
| "epoch": 8.023460410557185, |
| "grad_norm": 0.23290629620105716, |
| "learning_rate": 7.4014976563890915e-06, |
| "loss": 0.0558, |
| "mean_token_accuracy": 0.9813942089676857, |
| "step": 1372 |
| }, |
| { |
| "epoch": 8.029325513196481, |
| "grad_norm": 0.23204586036189112, |
| "learning_rate": 7.381462674472702e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9837755858898163, |
| "step": 1373 |
| }, |
| { |
| "epoch": 8.035190615835777, |
| "grad_norm": 0.26570656097468354, |
| "learning_rate": 7.36148075194276e-06, |
| "loss": 0.0575, |
| "mean_token_accuracy": 0.9810594543814659, |
| "step": 1374 |
| }, |
| { |
| "epoch": 8.041055718475073, |
| "grad_norm": 0.2534234167607354, |
| "learning_rate": 7.341551961325574e-06, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.981083907186985, |
| "step": 1375 |
| }, |
| { |
| "epoch": 8.04692082111437, |
| "grad_norm": 0.22482533363895343, |
| "learning_rate": 7.3216763749546025e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9840012043714523, |
| "step": 1376 |
| }, |
| { |
| "epoch": 8.052785923753666, |
| "grad_norm": 0.3539307170644396, |
| "learning_rate": 7.301854064970202e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9816621989011765, |
| "step": 1377 |
| }, |
| { |
| "epoch": 8.058651026392962, |
| "grad_norm": 0.3133359023630968, |
| "learning_rate": 7.282085103319349e-06, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9810803234577179, |
| "step": 1378 |
| }, |
| { |
| "epoch": 8.064516129032258, |
| "grad_norm": 0.2856689566183232, |
| "learning_rate": 7.2623695617553934e-06, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9795011952519417, |
| "step": 1379 |
| }, |
| { |
| "epoch": 8.070381231671554, |
| "grad_norm": 0.32524667631472975, |
| "learning_rate": 7.242707511837781e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9811884611845016, |
| "step": 1380 |
| }, |
| { |
| "epoch": 8.07624633431085, |
| "grad_norm": 0.22155385666931476, |
| "learning_rate": 7.223099024931817e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9849221631884575, |
| "step": 1381 |
| }, |
| { |
| "epoch": 8.082111436950147, |
| "grad_norm": 0.2639512786516192, |
| "learning_rate": 7.203544172208387e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9811254888772964, |
| "step": 1382 |
| }, |
| { |
| "epoch": 8.087976539589443, |
| "grad_norm": 0.4099521690739927, |
| "learning_rate": 7.184043024643712e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.980625793337822, |
| "step": 1383 |
| }, |
| { |
| "epoch": 8.093841642228739, |
| "grad_norm": 0.2746270859860697, |
| "learning_rate": 7.16459565301908e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9808760434389114, |
| "step": 1384 |
| }, |
| { |
| "epoch": 8.099706744868035, |
| "grad_norm": 0.3336582722499348, |
| "learning_rate": 7.145202127920598e-06, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9770251661539078, |
| "step": 1385 |
| }, |
| { |
| "epoch": 8.105571847507331, |
| "grad_norm": 0.3159956433838349, |
| "learning_rate": 7.125862519738924e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9790099188685417, |
| "step": 1386 |
| }, |
| { |
| "epoch": 8.111436950146627, |
| "grad_norm": 0.27751907752313126, |
| "learning_rate": 7.106576898669031e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9811584055423737, |
| "step": 1387 |
| }, |
| { |
| "epoch": 8.117302052785924, |
| "grad_norm": 0.3229154865255592, |
| "learning_rate": 7.087345334709931e-06, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9760906621813774, |
| "step": 1388 |
| }, |
| { |
| "epoch": 8.12316715542522, |
| "grad_norm": 0.302786075924986, |
| "learning_rate": 7.068167897664433e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9771555885672569, |
| "step": 1389 |
| }, |
| { |
| "epoch": 8.129032258064516, |
| "grad_norm": 0.34533438808047695, |
| "learning_rate": 7.0490446571388925e-06, |
| "loss": 0.0714, |
| "mean_token_accuracy": 0.978884294629097, |
| "step": 1390 |
| }, |
| { |
| "epoch": 8.134897360703812, |
| "grad_norm": 0.27542127742914396, |
| "learning_rate": 7.0299756825429465e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9800280183553696, |
| "step": 1391 |
| }, |
| { |
| "epoch": 8.140762463343108, |
| "grad_norm": 0.2371774920683244, |
| "learning_rate": 7.010961043089277e-06, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9846341237425804, |
| "step": 1392 |
| }, |
| { |
| "epoch": 8.146627565982405, |
| "grad_norm": 0.24268229094962124, |
| "learning_rate": 6.992000807793333e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9803787469863892, |
| "step": 1393 |
| }, |
| { |
| "epoch": 8.1524926686217, |
| "grad_norm": 0.3643306900167006, |
| "learning_rate": 6.973095045473124e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9794165417551994, |
| "step": 1394 |
| }, |
| { |
| "epoch": 8.158357771260997, |
| "grad_norm": 0.2947855628136845, |
| "learning_rate": 6.954243824748922e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9798598140478134, |
| "step": 1395 |
| }, |
| { |
| "epoch": 8.164222873900293, |
| "grad_norm": 0.24965567868424024, |
| "learning_rate": 6.93544721404305e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.979515366256237, |
| "step": 1396 |
| }, |
| { |
| "epoch": 8.17008797653959, |
| "grad_norm": 0.33114852320813654, |
| "learning_rate": 6.916705281579612e-06, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9791374951601028, |
| "step": 1397 |
| }, |
| { |
| "epoch": 8.175953079178885, |
| "grad_norm": 0.29068631223410873, |
| "learning_rate": 6.898018095384252e-06, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.976100243628025, |
| "step": 1398 |
| }, |
| { |
| "epoch": 8.181818181818182, |
| "grad_norm": 0.3513269186709242, |
| "learning_rate": 6.879385723283913e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9797561913728714, |
| "step": 1399 |
| }, |
| { |
| "epoch": 8.187683284457478, |
| "grad_norm": 0.23415965488620152, |
| "learning_rate": 6.8608082329065775e-06, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9810163378715515, |
| "step": 1400 |
| }, |
| { |
| "epoch": 8.193548387096774, |
| "grad_norm": 0.2887897085336456, |
| "learning_rate": 6.842285691681032e-06, |
| "loss": 0.0702, |
| "mean_token_accuracy": 0.9803082495927811, |
| "step": 1401 |
| }, |
| { |
| "epoch": 8.19941348973607, |
| "grad_norm": 0.31338662556740365, |
| "learning_rate": 6.8238181668366244e-06, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.9798052236437798, |
| "step": 1402 |
| }, |
| { |
| "epoch": 8.205278592375366, |
| "grad_norm": 0.26118312597759613, |
| "learning_rate": 6.805405725403006e-06, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9780385494232178, |
| "step": 1403 |
| }, |
| { |
| "epoch": 8.211143695014663, |
| "grad_norm": 0.25966801207442913, |
| "learning_rate": 6.787048434209906e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9776748195290565, |
| "step": 1404 |
| }, |
| { |
| "epoch": 8.217008797653959, |
| "grad_norm": 0.2944460445098481, |
| "learning_rate": 6.768746359886882e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9799527376890182, |
| "step": 1405 |
| }, |
| { |
| "epoch": 8.222873900293255, |
| "grad_norm": 0.25208455985617567, |
| "learning_rate": 6.750499568863061e-06, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9808372110128403, |
| "step": 1406 |
| }, |
| { |
| "epoch": 8.228739002932551, |
| "grad_norm": 0.28741775439220846, |
| "learning_rate": 6.732308127366931e-06, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9774434566497803, |
| "step": 1407 |
| }, |
| { |
| "epoch": 8.234604105571847, |
| "grad_norm": 0.3289864539935258, |
| "learning_rate": 6.714172101426077e-06, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9762885868549347, |
| "step": 1408 |
| }, |
| { |
| "epoch": 8.240469208211143, |
| "grad_norm": 0.23736345312152154, |
| "learning_rate": 6.696091556866948e-06, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9827252328395844, |
| "step": 1409 |
| }, |
| { |
| "epoch": 8.24633431085044, |
| "grad_norm": 0.2977687940939231, |
| "learning_rate": 6.678066559314622e-06, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9760833904147148, |
| "step": 1410 |
| }, |
| { |
| "epoch": 8.252199413489736, |
| "grad_norm": 0.3982183165411704, |
| "learning_rate": 6.660097174192556e-06, |
| "loss": 0.0674, |
| "mean_token_accuracy": 0.9767892211675644, |
| "step": 1411 |
| }, |
| { |
| "epoch": 8.258064516129032, |
| "grad_norm": 0.24845009306240756, |
| "learning_rate": 6.642183466722363e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9782160073518753, |
| "step": 1412 |
| }, |
| { |
| "epoch": 8.263929618768328, |
| "grad_norm": 0.25047139942879637, |
| "learning_rate": 6.624325501923565e-06, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9789937734603882, |
| "step": 1413 |
| }, |
| { |
| "epoch": 8.269794721407624, |
| "grad_norm": 0.3582552285931662, |
| "learning_rate": 6.606523344613362e-06, |
| "loss": 0.0728, |
| "mean_token_accuracy": 0.974414773285389, |
| "step": 1414 |
| }, |
| { |
| "epoch": 8.27565982404692, |
| "grad_norm": 0.23281831399691813, |
| "learning_rate": 6.588777059406397e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9821778386831284, |
| "step": 1415 |
| }, |
| { |
| "epoch": 8.281524926686217, |
| "grad_norm": 0.21783610764412928, |
| "learning_rate": 6.571086710714516e-06, |
| "loss": 0.0523, |
| "mean_token_accuracy": 0.9819829240441322, |
| "step": 1416 |
| }, |
| { |
| "epoch": 8.287390029325513, |
| "grad_norm": 0.26618761667003027, |
| "learning_rate": 6.553452362746543e-06, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.9776479974389076, |
| "step": 1417 |
| }, |
| { |
| "epoch": 8.29325513196481, |
| "grad_norm": 0.3307461688951337, |
| "learning_rate": 6.5358740795080335e-06, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9744124263525009, |
| "step": 1418 |
| }, |
| { |
| "epoch": 8.299120234604105, |
| "grad_norm": 0.3877945336373047, |
| "learning_rate": 6.518351924801061e-06, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.9782202020287514, |
| "step": 1419 |
| }, |
| { |
| "epoch": 8.304985337243401, |
| "grad_norm": 0.21829692333074224, |
| "learning_rate": 6.500885962223969e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9835516288876534, |
| "step": 1420 |
| }, |
| { |
| "epoch": 8.310850439882698, |
| "grad_norm": 0.2737695133055407, |
| "learning_rate": 6.483476255171146e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9777635931968689, |
| "step": 1421 |
| }, |
| { |
| "epoch": 8.316715542521994, |
| "grad_norm": 0.3156742313219525, |
| "learning_rate": 6.4661228668328015e-06, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9810267016291618, |
| "step": 1422 |
| }, |
| { |
| "epoch": 8.32258064516129, |
| "grad_norm": 0.29043044693215986, |
| "learning_rate": 6.448825860194722e-06, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9785061553120613, |
| "step": 1423 |
| }, |
| { |
| "epoch": 8.328445747800586, |
| "grad_norm": 0.20232305876185708, |
| "learning_rate": 6.431585298038057e-06, |
| "loss": 0.0474, |
| "mean_token_accuracy": 0.9857818335294724, |
| "step": 1424 |
| }, |
| { |
| "epoch": 8.334310850439882, |
| "grad_norm": 0.2604739184613935, |
| "learning_rate": 6.414401242939087e-06, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9787532687187195, |
| "step": 1425 |
| }, |
| { |
| "epoch": 8.340175953079179, |
| "grad_norm": 0.28996723077653824, |
| "learning_rate": 6.397273757268987e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.981784000992775, |
| "step": 1426 |
| }, |
| { |
| "epoch": 8.346041055718475, |
| "grad_norm": 0.2826379503854459, |
| "learning_rate": 6.380202903193616e-06, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9775265082716942, |
| "step": 1427 |
| }, |
| { |
| "epoch": 8.351906158357771, |
| "grad_norm": 0.3247668563192037, |
| "learning_rate": 6.363188742673281e-06, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.978668600320816, |
| "step": 1428 |
| }, |
| { |
| "epoch": 8.357771260997067, |
| "grad_norm": 0.2769284132122931, |
| "learning_rate": 6.346231337462513e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9785289466381073, |
| "step": 1429 |
| }, |
| { |
| "epoch": 8.363636363636363, |
| "grad_norm": 0.35215981895710224, |
| "learning_rate": 6.329330749109839e-06, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9739778935909271, |
| "step": 1430 |
| }, |
| { |
| "epoch": 8.36950146627566, |
| "grad_norm": 0.2895199872166017, |
| "learning_rate": 6.312487038957573e-06, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9788866117596626, |
| "step": 1431 |
| }, |
| { |
| "epoch": 8.375366568914956, |
| "grad_norm": 0.30231800425923677, |
| "learning_rate": 6.295700268141579e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.981073260307312, |
| "step": 1432 |
| }, |
| { |
| "epoch": 8.381231671554252, |
| "grad_norm": 0.2861524694796837, |
| "learning_rate": 6.2789704975910574e-06, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9809359386563301, |
| "step": 1433 |
| }, |
| { |
| "epoch": 8.387096774193548, |
| "grad_norm": 0.27965800064820345, |
| "learning_rate": 6.262297788028316e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9791011437773705, |
| "step": 1434 |
| }, |
| { |
| "epoch": 8.392961876832844, |
| "grad_norm": 0.2567178381963598, |
| "learning_rate": 6.245682199968556e-06, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.977754257619381, |
| "step": 1435 |
| }, |
| { |
| "epoch": 8.39882697947214, |
| "grad_norm": 0.252089258921102, |
| "learning_rate": 6.229123793719656e-06, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9788324162364006, |
| "step": 1436 |
| }, |
| { |
| "epoch": 8.404692082111437, |
| "grad_norm": 0.2498020291209392, |
| "learning_rate": 6.21262262938194e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9818584844470024, |
| "step": 1437 |
| }, |
| { |
| "epoch": 8.410557184750733, |
| "grad_norm": 0.3067068353713511, |
| "learning_rate": 6.196178766847969e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.977524109184742, |
| "step": 1438 |
| }, |
| { |
| "epoch": 8.416422287390029, |
| "grad_norm": 0.279049594579598, |
| "learning_rate": 6.1797922658023264e-06, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9750313237309456, |
| "step": 1439 |
| }, |
| { |
| "epoch": 8.422287390029325, |
| "grad_norm": 0.2428016087284499, |
| "learning_rate": 6.16346318572139e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9801136925816536, |
| "step": 1440 |
| }, |
| { |
| "epoch": 8.428152492668621, |
| "grad_norm": 0.3642333111467534, |
| "learning_rate": 6.147191585873128e-06, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9765574038028717, |
| "step": 1441 |
| }, |
| { |
| "epoch": 8.434017595307918, |
| "grad_norm": 0.2452302120598073, |
| "learning_rate": 6.130977525316878e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9802148938179016, |
| "step": 1442 |
| }, |
| { |
| "epoch": 8.439882697947214, |
| "grad_norm": 0.23546548291503536, |
| "learning_rate": 6.114821062903125e-06, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9796994179487228, |
| "step": 1443 |
| }, |
| { |
| "epoch": 8.44574780058651, |
| "grad_norm": 0.34248040168779487, |
| "learning_rate": 6.098722257273303e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9773654565215111, |
| "step": 1444 |
| }, |
| { |
| "epoch": 8.451612903225806, |
| "grad_norm": 0.3267948785376941, |
| "learning_rate": 6.082681166859579e-06, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9782762229442596, |
| "step": 1445 |
| }, |
| { |
| "epoch": 8.457478005865102, |
| "grad_norm": 0.24944133665569335, |
| "learning_rate": 6.066697849884629e-06, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9791956692934036, |
| "step": 1446 |
| }, |
| { |
| "epoch": 8.463343108504398, |
| "grad_norm": 0.22140226528324586, |
| "learning_rate": 6.0507723643614415e-06, |
| "loss": 0.0484, |
| "mean_token_accuracy": 0.9839403405785561, |
| "step": 1447 |
| }, |
| { |
| "epoch": 8.469208211143695, |
| "grad_norm": 0.3931794295766522, |
| "learning_rate": 6.034904768093095e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9783346280455589, |
| "step": 1448 |
| }, |
| { |
| "epoch": 8.47507331378299, |
| "grad_norm": 0.28221103656025875, |
| "learning_rate": 6.019095118672557e-06, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9760680794715881, |
| "step": 1449 |
| }, |
| { |
| "epoch": 8.480938416422287, |
| "grad_norm": 0.35500720339693564, |
| "learning_rate": 6.003343473482469e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9795534163713455, |
| "step": 1450 |
| }, |
| { |
| "epoch": 8.486803519061583, |
| "grad_norm": 0.44206392730367217, |
| "learning_rate": 5.98764988969494e-06, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.9759310409426689, |
| "step": 1451 |
| }, |
| { |
| "epoch": 8.49266862170088, |
| "grad_norm": 0.2884122822560015, |
| "learning_rate": 5.972014424271344e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9818243160843849, |
| "step": 1452 |
| }, |
| { |
| "epoch": 8.498533724340176, |
| "grad_norm": 0.24169715217818574, |
| "learning_rate": 5.956437133962103e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9796706140041351, |
| "step": 1453 |
| }, |
| { |
| "epoch": 8.504398826979472, |
| "grad_norm": 0.3567541736942327, |
| "learning_rate": 5.94091807530649e-06, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.976375125348568, |
| "step": 1454 |
| }, |
| { |
| "epoch": 8.510263929618768, |
| "grad_norm": 0.2660628076236119, |
| "learning_rate": 5.925457304632421e-06, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9772655889391899, |
| "step": 1455 |
| }, |
| { |
| "epoch": 8.516129032258064, |
| "grad_norm": 0.3586723680013531, |
| "learning_rate": 5.91005487805625e-06, |
| "loss": 0.0781, |
| "mean_token_accuracy": 0.975320614874363, |
| "step": 1456 |
| }, |
| { |
| "epoch": 8.52199413489736, |
| "grad_norm": 0.2531027806770582, |
| "learning_rate": 5.894710851482563e-06, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9815174117684364, |
| "step": 1457 |
| }, |
| { |
| "epoch": 8.527859237536656, |
| "grad_norm": 0.25474047304957326, |
| "learning_rate": 5.879425280603981e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9790660366415977, |
| "step": 1458 |
| }, |
| { |
| "epoch": 8.533724340175953, |
| "grad_norm": 0.29693469905798703, |
| "learning_rate": 5.864198220900952e-06, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9797492399811745, |
| "step": 1459 |
| }, |
| { |
| "epoch": 8.539589442815249, |
| "grad_norm": 0.28442650282700044, |
| "learning_rate": 5.849029727641552e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9790033251047134, |
| "step": 1460 |
| }, |
| { |
| "epoch": 8.545454545454545, |
| "grad_norm": 0.29862524636179977, |
| "learning_rate": 5.833919855881286e-06, |
| "loss": 0.0687, |
| "mean_token_accuracy": 0.9779817909002304, |
| "step": 1461 |
| }, |
| { |
| "epoch": 8.551319648093841, |
| "grad_norm": 0.2766831332028397, |
| "learning_rate": 5.818868660462886e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9803951904177666, |
| "step": 1462 |
| }, |
| { |
| "epoch": 8.557184750733137, |
| "grad_norm": 0.23218479374158082, |
| "learning_rate": 5.803876196016114e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9823366180062294, |
| "step": 1463 |
| }, |
| { |
| "epoch": 8.563049853372434, |
| "grad_norm": 0.2464367593263216, |
| "learning_rate": 5.788942516957561e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9808334708213806, |
| "step": 1464 |
| }, |
| { |
| "epoch": 8.56891495601173, |
| "grad_norm": 0.30192138899810556, |
| "learning_rate": 5.774067677490448e-06, |
| "loss": 0.0719, |
| "mean_token_accuracy": 0.9759406819939613, |
| "step": 1465 |
| }, |
| { |
| "epoch": 8.574780058651026, |
| "grad_norm": 0.3158998321878276, |
| "learning_rate": 5.759251731604435e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9803323373198509, |
| "step": 1466 |
| }, |
| { |
| "epoch": 8.580645161290322, |
| "grad_norm": 0.31413085082208875, |
| "learning_rate": 5.744494733075424e-06, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9777957648038864, |
| "step": 1467 |
| }, |
| { |
| "epoch": 8.586510263929618, |
| "grad_norm": 0.2555349585045622, |
| "learning_rate": 5.729796735465359e-06, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9778914302587509, |
| "step": 1468 |
| }, |
| { |
| "epoch": 8.592375366568914, |
| "grad_norm": 0.26756135754205695, |
| "learning_rate": 5.7151577921220356e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9788284227252007, |
| "step": 1469 |
| }, |
| { |
| "epoch": 8.59824046920821, |
| "grad_norm": 0.244072542005457, |
| "learning_rate": 5.7005779561789046e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9816020429134369, |
| "step": 1470 |
| }, |
| { |
| "epoch": 8.604105571847507, |
| "grad_norm": 0.23753259941339863, |
| "learning_rate": 5.686057280554882e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9804639518260956, |
| "step": 1471 |
| }, |
| { |
| "epoch": 8.609970674486803, |
| "grad_norm": 0.2801786700225434, |
| "learning_rate": 5.671595817954157e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9800218939781189, |
| "step": 1472 |
| }, |
| { |
| "epoch": 8.6158357771261, |
| "grad_norm": 0.2970190736822563, |
| "learning_rate": 5.657193620865997e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9817324727773666, |
| "step": 1473 |
| }, |
| { |
| "epoch": 8.621700879765395, |
| "grad_norm": 0.36583022561839285, |
| "learning_rate": 5.642850741564562e-06, |
| "loss": 0.0714, |
| "mean_token_accuracy": 0.9777909740805626, |
| "step": 1474 |
| }, |
| { |
| "epoch": 8.627565982404692, |
| "grad_norm": 0.2688933336929723, |
| "learning_rate": 5.62856723210871e-06, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.9783223196864128, |
| "step": 1475 |
| }, |
| { |
| "epoch": 8.633431085043988, |
| "grad_norm": 0.3036719866897421, |
| "learning_rate": 5.614343144341814e-06, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9752448201179504, |
| "step": 1476 |
| }, |
| { |
| "epoch": 8.639296187683284, |
| "grad_norm": 0.2737493833380235, |
| "learning_rate": 5.600178529891564e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9796081408858299, |
| "step": 1477 |
| }, |
| { |
| "epoch": 8.64516129032258, |
| "grad_norm": 0.3011765116046612, |
| "learning_rate": 5.58607344016979e-06, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9739836007356644, |
| "step": 1478 |
| }, |
| { |
| "epoch": 8.651026392961876, |
| "grad_norm": 0.26931220609417367, |
| "learning_rate": 5.5720279263722795e-06, |
| "loss": 0.0613, |
| "mean_token_accuracy": 0.9778261408209801, |
| "step": 1479 |
| }, |
| { |
| "epoch": 8.656891495601172, |
| "grad_norm": 0.28849384987997934, |
| "learning_rate": 5.558042039478564e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.979794979095459, |
| "step": 1480 |
| }, |
| { |
| "epoch": 8.662756598240469, |
| "grad_norm": 0.4481433032150989, |
| "learning_rate": 5.544115830251769e-06, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.9757302552461624, |
| "step": 1481 |
| }, |
| { |
| "epoch": 8.668621700879765, |
| "grad_norm": 0.24979918369391133, |
| "learning_rate": 5.530249349238407e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9798487946391106, |
| "step": 1482 |
| }, |
| { |
| "epoch": 8.674486803519061, |
| "grad_norm": 0.41387409378504497, |
| "learning_rate": 5.516442646768207e-06, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.973071850836277, |
| "step": 1483 |
| }, |
| { |
| "epoch": 8.680351906158357, |
| "grad_norm": 0.25828185399248105, |
| "learning_rate": 5.502695772953922e-06, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9765612930059433, |
| "step": 1484 |
| }, |
| { |
| "epoch": 8.686217008797653, |
| "grad_norm": 0.26377515536943485, |
| "learning_rate": 5.489008777691151e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9816120192408562, |
| "step": 1485 |
| }, |
| { |
| "epoch": 8.69208211143695, |
| "grad_norm": 0.33227377501750116, |
| "learning_rate": 5.475381710658161e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9787192866206169, |
| "step": 1486 |
| }, |
| { |
| "epoch": 8.697947214076246, |
| "grad_norm": 0.2817841011781313, |
| "learning_rate": 5.4618146213157e-06, |
| "loss": 0.0738, |
| "mean_token_accuracy": 0.9738593846559525, |
| "step": 1487 |
| }, |
| { |
| "epoch": 8.703812316715542, |
| "grad_norm": 0.35285024202029736, |
| "learning_rate": 5.448307558906822e-06, |
| "loss": 0.0704, |
| "mean_token_accuracy": 0.9770059287548065, |
| "step": 1488 |
| }, |
| { |
| "epoch": 8.709677419354838, |
| "grad_norm": 0.2562314555826694, |
| "learning_rate": 5.434860572456711e-06, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9778687655925751, |
| "step": 1489 |
| }, |
| { |
| "epoch": 8.715542521994134, |
| "grad_norm": 0.2685199038032354, |
| "learning_rate": 5.421473710772496e-06, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9799297451972961, |
| "step": 1490 |
| }, |
| { |
| "epoch": 8.72140762463343, |
| "grad_norm": 0.23958679172858152, |
| "learning_rate": 5.408147022443077e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9788787066936493, |
| "step": 1491 |
| }, |
| { |
| "epoch": 8.727272727272727, |
| "grad_norm": 0.37532852839555414, |
| "learning_rate": 5.39488055583895e-06, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9793713614344597, |
| "step": 1492 |
| }, |
| { |
| "epoch": 8.733137829912023, |
| "grad_norm": 0.30168346493046544, |
| "learning_rate": 5.3816743591120365e-06, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9784124940633774, |
| "step": 1493 |
| }, |
| { |
| "epoch": 8.739002932551319, |
| "grad_norm": 0.32283133480358384, |
| "learning_rate": 5.368528480195492e-06, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9787509068846703, |
| "step": 1494 |
| }, |
| { |
| "epoch": 8.744868035190615, |
| "grad_norm": 0.18242889955187325, |
| "learning_rate": 5.355442966803544e-06, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9821577444672585, |
| "step": 1495 |
| }, |
| { |
| "epoch": 8.750733137829911, |
| "grad_norm": 0.3571788534447416, |
| "learning_rate": 5.342417866431326e-06, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9728782624006271, |
| "step": 1496 |
| }, |
| { |
| "epoch": 8.756598240469208, |
| "grad_norm": 0.32907123108892783, |
| "learning_rate": 5.329453226354692e-06, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9787439778447151, |
| "step": 1497 |
| }, |
| { |
| "epoch": 8.762463343108504, |
| "grad_norm": 0.23510121292718625, |
| "learning_rate": 5.31654909363005e-06, |
| "loss": 0.0637, |
| "mean_token_accuracy": 0.98048335313797, |
| "step": 1498 |
| }, |
| { |
| "epoch": 8.7683284457478, |
| "grad_norm": 0.3292238101609866, |
| "learning_rate": 5.303705515094187e-06, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9763019159436226, |
| "step": 1499 |
| }, |
| { |
| "epoch": 8.774193548387096, |
| "grad_norm": 0.31772186010158904, |
| "learning_rate": 5.290922537364109e-06, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.9719724953174591, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.780058651026392, |
| "grad_norm": 0.43601699445852304, |
| "learning_rate": 5.278200206836861e-06, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9765214696526527, |
| "step": 1501 |
| }, |
| { |
| "epoch": 8.785923753665688, |
| "grad_norm": 0.24631726988703956, |
| "learning_rate": 5.265538569689365e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9786100387573242, |
| "step": 1502 |
| }, |
| { |
| "epoch": 8.791788856304985, |
| "grad_norm": 0.23348947782863988, |
| "learning_rate": 5.25293767187825e-06, |
| "loss": 0.0599, |
| "mean_token_accuracy": 0.9810864999890327, |
| "step": 1503 |
| }, |
| { |
| "epoch": 8.79765395894428, |
| "grad_norm": 0.3059628956328224, |
| "learning_rate": 5.240397559139685e-06, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9774987623095512, |
| "step": 1504 |
| }, |
| { |
| "epoch": 8.803519061583577, |
| "grad_norm": 0.2271743851090028, |
| "learning_rate": 5.227918276989215e-06, |
| "loss": 0.0613, |
| "mean_token_accuracy": 0.9777540266513824, |
| "step": 1505 |
| }, |
| { |
| "epoch": 8.809384164222873, |
| "grad_norm": 0.24351844409606843, |
| "learning_rate": 5.2154998707215976e-06, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9778146594762802, |
| "step": 1506 |
| }, |
| { |
| "epoch": 8.81524926686217, |
| "grad_norm": 0.32814994186809865, |
| "learning_rate": 5.203142385410628e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9819656610488892, |
| "step": 1507 |
| }, |
| { |
| "epoch": 8.821114369501466, |
| "grad_norm": 0.24451284850690339, |
| "learning_rate": 5.190845865908987e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9768688082695007, |
| "step": 1508 |
| }, |
| { |
| "epoch": 8.826979472140762, |
| "grad_norm": 0.35278726245532943, |
| "learning_rate": 5.178610356848075e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.977623425424099, |
| "step": 1509 |
| }, |
| { |
| "epoch": 8.832844574780058, |
| "grad_norm": 0.26703275114310665, |
| "learning_rate": 5.166435902637848e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9784714952111244, |
| "step": 1510 |
| }, |
| { |
| "epoch": 8.838709677419354, |
| "grad_norm": 0.248994392474072, |
| "learning_rate": 5.154322547466658e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9805686995387077, |
| "step": 1511 |
| }, |
| { |
| "epoch": 8.84457478005865, |
| "grad_norm": 0.2515813584107477, |
| "learning_rate": 5.142270335301095e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9793656393885612, |
| "step": 1512 |
| }, |
| { |
| "epoch": 8.850439882697946, |
| "grad_norm": 0.2800317772193338, |
| "learning_rate": 5.130279309885817e-06, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9782811179757118, |
| "step": 1513 |
| }, |
| { |
| "epoch": 8.856304985337243, |
| "grad_norm": 0.3103625834439301, |
| "learning_rate": 5.118349514743404e-06, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9753215909004211, |
| "step": 1514 |
| }, |
| { |
| "epoch": 8.862170087976539, |
| "grad_norm": 0.3526394713823649, |
| "learning_rate": 5.1064809931741975e-06, |
| "loss": 0.08, |
| "mean_token_accuracy": 0.9744403213262558, |
| "step": 1515 |
| }, |
| { |
| "epoch": 8.868035190615835, |
| "grad_norm": 0.2560684899292793, |
| "learning_rate": 5.094673788256137e-06, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9820585176348686, |
| "step": 1516 |
| }, |
| { |
| "epoch": 8.873900293255131, |
| "grad_norm": 0.29971977388113474, |
| "learning_rate": 5.082927942844603e-06, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9782021939754486, |
| "step": 1517 |
| }, |
| { |
| "epoch": 8.879765395894427, |
| "grad_norm": 0.2637842941875261, |
| "learning_rate": 5.0712434995722734e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9771728515625, |
| "step": 1518 |
| }, |
| { |
| "epoch": 8.885630498533724, |
| "grad_norm": 0.314860671900927, |
| "learning_rate": 5.059620500848964e-06, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9802365675568581, |
| "step": 1519 |
| }, |
| { |
| "epoch": 8.89149560117302, |
| "grad_norm": 0.2764897492165904, |
| "learning_rate": 5.048058988861455e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9786038100719452, |
| "step": 1520 |
| }, |
| { |
| "epoch": 8.897360703812316, |
| "grad_norm": 0.22492681630529185, |
| "learning_rate": 5.0365590055733715e-06, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9813904538750648, |
| "step": 1521 |
| }, |
| { |
| "epoch": 8.903225806451612, |
| "grad_norm": 0.3147598263869332, |
| "learning_rate": 5.025120592725009e-06, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9776310920715332, |
| "step": 1522 |
| }, |
| { |
| "epoch": 8.909090909090908, |
| "grad_norm": 0.34074469808815616, |
| "learning_rate": 5.013743791833187e-06, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.979078084230423, |
| "step": 1523 |
| }, |
| { |
| "epoch": 8.914956011730204, |
| "grad_norm": 0.26152297778605377, |
| "learning_rate": 5.002428644191094e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9802012667059898, |
| "step": 1524 |
| }, |
| { |
| "epoch": 8.9208211143695, |
| "grad_norm": 0.2578124682100099, |
| "learning_rate": 4.991175190868148e-06, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9790066555142403, |
| "step": 1525 |
| }, |
| { |
| "epoch": 8.926686217008797, |
| "grad_norm": 0.2376683233781485, |
| "learning_rate": 4.9799834727098415e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9810256138443947, |
| "step": 1526 |
| }, |
| { |
| "epoch": 8.932551319648093, |
| "grad_norm": 0.28798216028853235, |
| "learning_rate": 4.968853530337587e-06, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9783130586147308, |
| "step": 1527 |
| }, |
| { |
| "epoch": 8.93841642228739, |
| "grad_norm": 0.21284234625947226, |
| "learning_rate": 4.957785404148585e-06, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9768381863832474, |
| "step": 1528 |
| }, |
| { |
| "epoch": 8.944281524926687, |
| "grad_norm": 0.28902188952693547, |
| "learning_rate": 4.946779134315662e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9778866022825241, |
| "step": 1529 |
| }, |
| { |
| "epoch": 8.950146627565982, |
| "grad_norm": 0.24256775933774233, |
| "learning_rate": 4.935834760787133e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9800405576825142, |
| "step": 1530 |
| }, |
| { |
| "epoch": 8.95601173020528, |
| "grad_norm": 0.2761848112737178, |
| "learning_rate": 4.924952323286651e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9786167815327644, |
| "step": 1531 |
| }, |
| { |
| "epoch": 8.961876832844574, |
| "grad_norm": 0.29420548049004036, |
| "learning_rate": 4.91413186131307e-06, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.979533426463604, |
| "step": 1532 |
| }, |
| { |
| "epoch": 8.967741935483872, |
| "grad_norm": 0.26436955721941907, |
| "learning_rate": 4.9033734141402964e-06, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9764868766069412, |
| "step": 1533 |
| }, |
| { |
| "epoch": 8.973607038123166, |
| "grad_norm": 0.2454668416645823, |
| "learning_rate": 4.892677020817151e-06, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9776885583996773, |
| "step": 1534 |
| }, |
| { |
| "epoch": 8.979472140762464, |
| "grad_norm": 0.274662605031312, |
| "learning_rate": 4.8820427201672195e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9772161841392517, |
| "step": 1535 |
| }, |
| { |
| "epoch": 8.985337243401759, |
| "grad_norm": 0.46063707991159386, |
| "learning_rate": 4.871470550788717e-06, |
| "loss": 0.0773, |
| "mean_token_accuracy": 0.9726253524422646, |
| "step": 1536 |
| }, |
| { |
| "epoch": 8.991202346041057, |
| "grad_norm": 0.2598327356469058, |
| "learning_rate": 4.860960551054352e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9794004708528519, |
| "step": 1537 |
| }, |
| { |
| "epoch": 8.997067448680351, |
| "grad_norm": 0.22718132289500315, |
| "learning_rate": 4.850512759111177e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9775163903832436, |
| "step": 1538 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.22718132289500315, |
| "learning_rate": 4.840127212880457e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9819877296686172, |
| "step": 1539 |
| }, |
| { |
| "epoch": 9.005865102639296, |
| "grad_norm": 0.3373449133841611, |
| "learning_rate": 4.82980395005753e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9807324483990669, |
| "step": 1540 |
| }, |
| { |
| "epoch": 9.011730205278592, |
| "grad_norm": 0.2660171293852756, |
| "learning_rate": 4.8195430081116715e-06, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9796838536858559, |
| "step": 1541 |
| }, |
| { |
| "epoch": 9.017595307917889, |
| "grad_norm": 0.22636028477722886, |
| "learning_rate": 4.809344424285959e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9821007177233696, |
| "step": 1542 |
| }, |
| { |
| "epoch": 9.023460410557185, |
| "grad_norm": 0.26586548560149015, |
| "learning_rate": 4.799208235597129e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9777081608772278, |
| "step": 1543 |
| }, |
| { |
| "epoch": 9.029325513196481, |
| "grad_norm": 0.2777149628567429, |
| "learning_rate": 4.7891344788354535e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9795635268092155, |
| "step": 1544 |
| }, |
| { |
| "epoch": 9.035190615835777, |
| "grad_norm": 0.3049973622375955, |
| "learning_rate": 4.779123190564601e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9791153743863106, |
| "step": 1545 |
| }, |
| { |
| "epoch": 9.041055718475073, |
| "grad_norm": 0.2593981713494098, |
| "learning_rate": 4.769174407121508e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9796656146645546, |
| "step": 1546 |
| }, |
| { |
| "epoch": 9.04692082111437, |
| "grad_norm": 0.2288825869864337, |
| "learning_rate": 4.7592881646162336e-06, |
| "loss": 0.0728, |
| "mean_token_accuracy": 0.9769270122051239, |
| "step": 1547 |
| }, |
| { |
| "epoch": 9.052785923753666, |
| "grad_norm": 0.28065390101886106, |
| "learning_rate": 4.749464498931852e-06, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9819205701351166, |
| "step": 1548 |
| }, |
| { |
| "epoch": 9.058651026392962, |
| "grad_norm": 0.23404322036009262, |
| "learning_rate": 4.739703445724296e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9835373759269714, |
| "step": 1549 |
| }, |
| { |
| "epoch": 9.064516129032258, |
| "grad_norm": 0.2359254198323517, |
| "learning_rate": 4.730005040422253e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9820079058408737, |
| "step": 1550 |
| }, |
| { |
| "epoch": 9.070381231671554, |
| "grad_norm": 0.251373443947105, |
| "learning_rate": 4.720369318227014e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9808452799916267, |
| "step": 1551 |
| }, |
| { |
| "epoch": 9.07624633431085, |
| "grad_norm": 0.28719476489184603, |
| "learning_rate": 4.710796314112358e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9796859174966812, |
| "step": 1552 |
| }, |
| { |
| "epoch": 9.082111436950147, |
| "grad_norm": 0.2642294407118322, |
| "learning_rate": 4.701286062824425e-06, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9804991409182549, |
| "step": 1553 |
| }, |
| { |
| "epoch": 9.087976539589443, |
| "grad_norm": 0.2775262974710003, |
| "learning_rate": 4.691838598881587e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9793780148029327, |
| "step": 1554 |
| }, |
| { |
| "epoch": 9.093841642228739, |
| "grad_norm": 0.2170466478297633, |
| "learning_rate": 4.68245395657432e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9822722375392914, |
| "step": 1555 |
| }, |
| { |
| "epoch": 9.099706744868035, |
| "grad_norm": 0.22836245350689496, |
| "learning_rate": 4.673132169965089e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9818886816501617, |
| "step": 1556 |
| }, |
| { |
| "epoch": 9.105571847507331, |
| "grad_norm": 0.20963749864182238, |
| "learning_rate": 4.663873272888212e-06, |
| "loss": 0.0539, |
| "mean_token_accuracy": 0.9836770445108414, |
| "step": 1557 |
| }, |
| { |
| "epoch": 9.111436950146627, |
| "grad_norm": 0.21765369676261487, |
| "learning_rate": 4.654677298949746e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9772438853979111, |
| "step": 1558 |
| }, |
| { |
| "epoch": 9.117302052785924, |
| "grad_norm": 0.22920276916129523, |
| "learning_rate": 4.645544281527362e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9798052459955215, |
| "step": 1559 |
| }, |
| { |
| "epoch": 9.12316715542522, |
| "grad_norm": 0.2248070439208056, |
| "learning_rate": 4.636474253770226e-06, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9813929721713066, |
| "step": 1560 |
| }, |
| { |
| "epoch": 9.129032258064516, |
| "grad_norm": 0.23392902750221167, |
| "learning_rate": 4.627467248598876e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9810582026839256, |
| "step": 1561 |
| }, |
| { |
| "epoch": 9.134897360703812, |
| "grad_norm": 0.35068933786793133, |
| "learning_rate": 4.618523298705101e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9805464595556259, |
| "step": 1562 |
| }, |
| { |
| "epoch": 9.140762463343108, |
| "grad_norm": 0.2639000982065526, |
| "learning_rate": 4.609642436551828e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9803919643163681, |
| "step": 1563 |
| }, |
| { |
| "epoch": 9.146627565982405, |
| "grad_norm": 0.23878300312488335, |
| "learning_rate": 4.600824694373e-06, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.983349584043026, |
| "step": 1564 |
| }, |
| { |
| "epoch": 9.1524926686217, |
| "grad_norm": 0.245763989099376, |
| "learning_rate": 4.592070104173461e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9818849116563797, |
| "step": 1565 |
| }, |
| { |
| "epoch": 9.158357771260997, |
| "grad_norm": 0.23279489695026834, |
| "learning_rate": 4.583378697728835e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.979814425110817, |
| "step": 1566 |
| }, |
| { |
| "epoch": 9.164222873900293, |
| "grad_norm": 0.2356722070822205, |
| "learning_rate": 4.574750506585419e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9795899465680122, |
| "step": 1567 |
| }, |
| { |
| "epoch": 9.17008797653959, |
| "grad_norm": 0.3100951878952791, |
| "learning_rate": 4.566185562060062e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9785728603601456, |
| "step": 1568 |
| }, |
| { |
| "epoch": 9.175953079178885, |
| "grad_norm": 0.23758456109764423, |
| "learning_rate": 4.557683895240052e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9810535088181496, |
| "step": 1569 |
| }, |
| { |
| "epoch": 9.181818181818182, |
| "grad_norm": 0.397590962919886, |
| "learning_rate": 4.549245536983009e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9803250953555107, |
| "step": 1570 |
| }, |
| { |
| "epoch": 9.187683284457478, |
| "grad_norm": 0.2709295526230137, |
| "learning_rate": 4.540870517916765e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9819755181670189, |
| "step": 1571 |
| }, |
| { |
| "epoch": 9.193548387096774, |
| "grad_norm": 0.26365206186856915, |
| "learning_rate": 4.532558868439249e-06, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9806329160928726, |
| "step": 1572 |
| }, |
| { |
| "epoch": 9.19941348973607, |
| "grad_norm": 0.23180936574802335, |
| "learning_rate": 4.524310618718403e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9812423959374428, |
| "step": 1573 |
| }, |
| { |
| "epoch": 9.205278592375366, |
| "grad_norm": 0.2479537384786009, |
| "learning_rate": 4.516125798692037e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9807397574186325, |
| "step": 1574 |
| }, |
| { |
| "epoch": 9.211143695014663, |
| "grad_norm": 0.2703042461210012, |
| "learning_rate": 4.508004438067742e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9777510985732079, |
| "step": 1575 |
| }, |
| { |
| "epoch": 9.217008797653959, |
| "grad_norm": 0.24641143582704136, |
| "learning_rate": 4.4999465663227785e-06, |
| "loss": 0.055, |
| "mean_token_accuracy": 0.9833300933241844, |
| "step": 1576 |
| }, |
| { |
| "epoch": 9.222873900293255, |
| "grad_norm": 0.3188227218692964, |
| "learning_rate": 4.491952212703964e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9781920313835144, |
| "step": 1577 |
| }, |
| { |
| "epoch": 9.228739002932551, |
| "grad_norm": 0.24287084230549283, |
| "learning_rate": 4.484021406227576e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9793609604239464, |
| "step": 1578 |
| }, |
| { |
| "epoch": 9.234604105571847, |
| "grad_norm": 0.5712888100286926, |
| "learning_rate": 4.476154175679239e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9787584096193314, |
| "step": 1579 |
| }, |
| { |
| "epoch": 9.240469208211143, |
| "grad_norm": 0.24728813746312206, |
| "learning_rate": 4.468350549613822e-06, |
| "loss": 0.0518, |
| "mean_token_accuracy": 0.9819226488471031, |
| "step": 1580 |
| }, |
| { |
| "epoch": 9.24633431085044, |
| "grad_norm": 0.31373054201391787, |
| "learning_rate": 4.460610556355333e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.9764752313494682, |
| "step": 1581 |
| }, |
| { |
| "epoch": 9.252199413489736, |
| "grad_norm": 0.2385955767542648, |
| "learning_rate": 4.452934223996824e-06, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.982081227004528, |
| "step": 1582 |
| }, |
| { |
| "epoch": 9.258064516129032, |
| "grad_norm": 0.22005978869984863, |
| "learning_rate": 4.445321580400281e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9792909696698189, |
| "step": 1583 |
| }, |
| { |
| "epoch": 9.263929618768328, |
| "grad_norm": 0.24484280057621527, |
| "learning_rate": 4.437772653196527e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9810920730233192, |
| "step": 1584 |
| }, |
| { |
| "epoch": 9.269794721407624, |
| "grad_norm": 0.2744886690898688, |
| "learning_rate": 4.430287469785118e-06, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9745521992444992, |
| "step": 1585 |
| }, |
| { |
| "epoch": 9.27565982404692, |
| "grad_norm": 0.30860823590247866, |
| "learning_rate": 4.422866057334246e-06, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9808021262288094, |
| "step": 1586 |
| }, |
| { |
| "epoch": 9.281524926686217, |
| "grad_norm": 0.2704520421355319, |
| "learning_rate": 4.415508442780642e-06, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.9760096520185471, |
| "step": 1587 |
| }, |
| { |
| "epoch": 9.287390029325513, |
| "grad_norm": 0.424541508090357, |
| "learning_rate": 4.408214652829473e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9811082854866982, |
| "step": 1588 |
| }, |
| { |
| "epoch": 9.29325513196481, |
| "grad_norm": 0.2165123109041628, |
| "learning_rate": 4.400984713954253e-06, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.9843787923455238, |
| "step": 1589 |
| }, |
| { |
| "epoch": 9.299120234604105, |
| "grad_norm": 0.2700478826426142, |
| "learning_rate": 4.39381865239674e-06, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.9778083339333534, |
| "step": 1590 |
| }, |
| { |
| "epoch": 9.304985337243401, |
| "grad_norm": 0.2938143417822229, |
| "learning_rate": 4.386716494166842e-06, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9770649150013924, |
| "step": 1591 |
| }, |
| { |
| "epoch": 9.310850439882698, |
| "grad_norm": 0.3118340992348746, |
| "learning_rate": 4.379678265042529e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9765070602297783, |
| "step": 1592 |
| }, |
| { |
| "epoch": 9.316715542521994, |
| "grad_norm": 0.2695776935953318, |
| "learning_rate": 4.372703990569725e-06, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9807394593954086, |
| "step": 1593 |
| }, |
| { |
| "epoch": 9.32258064516129, |
| "grad_norm": 0.32864370703275114, |
| "learning_rate": 4.365793696062231e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9772561341524124, |
| "step": 1594 |
| }, |
| { |
| "epoch": 9.328445747800586, |
| "grad_norm": 0.2561966735650709, |
| "learning_rate": 4.358947406601626e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9803736731410027, |
| "step": 1595 |
| }, |
| { |
| "epoch": 9.334310850439882, |
| "grad_norm": 0.21566529835698572, |
| "learning_rate": 4.352165147037177e-06, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9788841158151627, |
| "step": 1596 |
| }, |
| { |
| "epoch": 9.340175953079179, |
| "grad_norm": 0.2560030399776893, |
| "learning_rate": 4.345446941985741e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9801218211650848, |
| "step": 1597 |
| }, |
| { |
| "epoch": 9.346041055718475, |
| "grad_norm": 0.23202327830121788, |
| "learning_rate": 4.338792815831698e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9768727198243141, |
| "step": 1598 |
| }, |
| { |
| "epoch": 9.351906158357771, |
| "grad_norm": 0.28701737565493496, |
| "learning_rate": 4.332202792726832e-06, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9776144996285439, |
| "step": 1599 |
| }, |
| { |
| "epoch": 9.357771260997067, |
| "grad_norm": 0.26539530331958283, |
| "learning_rate": 4.3256768965902684e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.977261483669281, |
| "step": 1600 |
| }, |
| { |
| "epoch": 9.363636363636363, |
| "grad_norm": 0.28930665981214404, |
| "learning_rate": 4.319215151108373e-06, |
| "loss": 0.0768, |
| "mean_token_accuracy": 0.9744983091950417, |
| "step": 1601 |
| }, |
| { |
| "epoch": 9.36950146627566, |
| "grad_norm": 0.26360393051635667, |
| "learning_rate": 4.312817579734673e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9822754934430122, |
| "step": 1602 |
| }, |
| { |
| "epoch": 9.375366568914956, |
| "grad_norm": 0.26032508841711777, |
| "learning_rate": 4.306484205689768e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9772569611668587, |
| "step": 1603 |
| }, |
| { |
| "epoch": 9.381231671554252, |
| "grad_norm": 0.2589814486685344, |
| "learning_rate": 4.300215051961248e-06, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9801448434591293, |
| "step": 1604 |
| }, |
| { |
| "epoch": 9.387096774193548, |
| "grad_norm": 0.25436834908109707, |
| "learning_rate": 4.2940101413036115e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9820843636989594, |
| "step": 1605 |
| }, |
| { |
| "epoch": 9.392961876832844, |
| "grad_norm": 0.2864933202075239, |
| "learning_rate": 4.287869496238174e-06, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9779408723115921, |
| "step": 1606 |
| }, |
| { |
| "epoch": 9.39882697947214, |
| "grad_norm": 0.24064124268536968, |
| "learning_rate": 4.281793139053001e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9796174690127373, |
| "step": 1607 |
| }, |
| { |
| "epoch": 9.404692082111437, |
| "grad_norm": 0.26540587503625385, |
| "learning_rate": 4.275781091802811e-06, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.9738316759467125, |
| "step": 1608 |
| }, |
| { |
| "epoch": 9.410557184750733, |
| "grad_norm": 0.32309718949209215, |
| "learning_rate": 4.26983337630891e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9797775819897652, |
| "step": 1609 |
| }, |
| { |
| "epoch": 9.416422287390029, |
| "grad_norm": 0.3022671879036554, |
| "learning_rate": 4.263950014159103e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9769906178116798, |
| "step": 1610 |
| }, |
| { |
| "epoch": 9.422287390029325, |
| "grad_norm": 0.25312838489835093, |
| "learning_rate": 4.258131026707618e-06, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9816729798913002, |
| "step": 1611 |
| }, |
| { |
| "epoch": 9.428152492668621, |
| "grad_norm": 0.24041663444550618, |
| "learning_rate": 4.2523764350750305e-06, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9787357822060585, |
| "step": 1612 |
| }, |
| { |
| "epoch": 9.434017595307918, |
| "grad_norm": 0.24088936329489447, |
| "learning_rate": 4.246686260148179e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9813699051737785, |
| "step": 1613 |
| }, |
| { |
| "epoch": 9.439882697947214, |
| "grad_norm": 0.2902013485039333, |
| "learning_rate": 4.241060522580108e-06, |
| "loss": 0.0752, |
| "mean_token_accuracy": 0.9762661457061768, |
| "step": 1614 |
| }, |
| { |
| "epoch": 9.44574780058651, |
| "grad_norm": 0.26593653778779147, |
| "learning_rate": 4.2354992427899674e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9807288646697998, |
| "step": 1615 |
| }, |
| { |
| "epoch": 9.451612903225806, |
| "grad_norm": 0.27473853653381974, |
| "learning_rate": 4.23000244096296e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9793464988470078, |
| "step": 1616 |
| }, |
| { |
| "epoch": 9.457478005865102, |
| "grad_norm": 0.23339911568703745, |
| "learning_rate": 4.224570137050254e-06, |
| "loss": 0.0492, |
| "mean_token_accuracy": 0.9841224849224091, |
| "step": 1617 |
| }, |
| { |
| "epoch": 9.463343108504398, |
| "grad_norm": 0.22630713206222056, |
| "learning_rate": 4.219202350768919e-06, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9775300472974777, |
| "step": 1618 |
| }, |
| { |
| "epoch": 9.469208211143695, |
| "grad_norm": 0.23955620707093253, |
| "learning_rate": 4.213899101601853e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9794919416308403, |
| "step": 1619 |
| }, |
| { |
| "epoch": 9.47507331378299, |
| "grad_norm": 0.2457762790452542, |
| "learning_rate": 4.208660408797708e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9798106178641319, |
| "step": 1620 |
| }, |
| { |
| "epoch": 9.480938416422287, |
| "grad_norm": 0.2431662748020246, |
| "learning_rate": 4.203486291370821e-06, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9812995418906212, |
| "step": 1621 |
| }, |
| { |
| "epoch": 9.486803519061583, |
| "grad_norm": 0.2723357831813373, |
| "learning_rate": 4.198376768101149e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9783790037035942, |
| "step": 1622 |
| }, |
| { |
| "epoch": 9.49266862170088, |
| "grad_norm": 0.3520178956023517, |
| "learning_rate": 4.193331857534198e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.980711355805397, |
| "step": 1623 |
| }, |
| { |
| "epoch": 9.498533724340176, |
| "grad_norm": 0.22927005303270442, |
| "learning_rate": 4.188351577980961e-06, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9831141978502274, |
| "step": 1624 |
| }, |
| { |
| "epoch": 9.504398826979472, |
| "grad_norm": 0.238973278958498, |
| "learning_rate": 4.183435947517836e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.979368269443512, |
| "step": 1625 |
| }, |
| { |
| "epoch": 9.510263929618768, |
| "grad_norm": 0.22548713924712482, |
| "learning_rate": 4.178584983986575e-06, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.9827914386987686, |
| "step": 1626 |
| }, |
| { |
| "epoch": 9.516129032258064, |
| "grad_norm": 0.2155318232305598, |
| "learning_rate": 4.173798704994221e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9815772697329521, |
| "step": 1627 |
| }, |
| { |
| "epoch": 9.52199413489736, |
| "grad_norm": 0.2525525304429569, |
| "learning_rate": 4.169077127913031e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9765826910734177, |
| "step": 1628 |
| }, |
| { |
| "epoch": 9.527859237536656, |
| "grad_norm": 0.22780826504919216, |
| "learning_rate": 4.164420269880422e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9760891944169998, |
| "step": 1629 |
| }, |
| { |
| "epoch": 9.533724340175953, |
| "grad_norm": 0.2531272072086709, |
| "learning_rate": 4.159828147798914e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9820951670408249, |
| "step": 1630 |
| }, |
| { |
| "epoch": 9.539589442815249, |
| "grad_norm": 0.24380644152767034, |
| "learning_rate": 4.155300778336047e-06, |
| "loss": 0.0617, |
| "mean_token_accuracy": 0.9779926687479019, |
| "step": 1631 |
| }, |
| { |
| "epoch": 9.545454545454545, |
| "grad_norm": 0.28384668257122436, |
| "learning_rate": 4.150838177924349e-06, |
| "loss": 0.0599, |
| "mean_token_accuracy": 0.9832035973668098, |
| "step": 1632 |
| }, |
| { |
| "epoch": 9.551319648093841, |
| "grad_norm": 0.22414889555068185, |
| "learning_rate": 4.146440362761256e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9802982956171036, |
| "step": 1633 |
| }, |
| { |
| "epoch": 9.557184750733137, |
| "grad_norm": 0.23750844736936616, |
| "learning_rate": 4.142107348809058e-06, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9758076518774033, |
| "step": 1634 |
| }, |
| { |
| "epoch": 9.563049853372434, |
| "grad_norm": 0.25194978074346364, |
| "learning_rate": 4.1378391517948505e-06, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9831016063690186, |
| "step": 1635 |
| }, |
| { |
| "epoch": 9.56891495601173, |
| "grad_norm": 0.24188617681913702, |
| "learning_rate": 4.1336357872104614e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9811783134937286, |
| "step": 1636 |
| }, |
| { |
| "epoch": 9.574780058651026, |
| "grad_norm": 0.24307965914320542, |
| "learning_rate": 4.12949727031241e-06, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9804549887776375, |
| "step": 1637 |
| }, |
| { |
| "epoch": 9.580645161290322, |
| "grad_norm": 0.2209724909626426, |
| "learning_rate": 4.125423616121837e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9810581132769585, |
| "step": 1638 |
| }, |
| { |
| "epoch": 9.586510263929618, |
| "grad_norm": 0.19695458594988682, |
| "learning_rate": 4.121414839424464e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9823091104626656, |
| "step": 1639 |
| }, |
| { |
| "epoch": 9.592375366568914, |
| "grad_norm": 0.25761669321110686, |
| "learning_rate": 4.117470954770529e-06, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9789463207125664, |
| "step": 1640 |
| }, |
| { |
| "epoch": 9.59824046920821, |
| "grad_norm": 0.19877925033471974, |
| "learning_rate": 4.1135919764747454e-06, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.9804951846599579, |
| "step": 1641 |
| }, |
| { |
| "epoch": 9.604105571847507, |
| "grad_norm": 0.22402798094527665, |
| "learning_rate": 4.109777918616235e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9828111082315445, |
| "step": 1642 |
| }, |
| { |
| "epoch": 9.609970674486803, |
| "grad_norm": 0.2454189049005734, |
| "learning_rate": 4.106028795038487e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.977626658976078, |
| "step": 1643 |
| }, |
| { |
| "epoch": 9.6158357771261, |
| "grad_norm": 0.3023925092807269, |
| "learning_rate": 4.102344619349307e-06, |
| "loss": 0.0759, |
| "mean_token_accuracy": 0.9734556525945663, |
| "step": 1644 |
| }, |
| { |
| "epoch": 9.621700879765395, |
| "grad_norm": 0.2774980485563469, |
| "learning_rate": 4.098725404920763e-06, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9775623232126236, |
| "step": 1645 |
| }, |
| { |
| "epoch": 9.627565982404692, |
| "grad_norm": 0.30333570428748763, |
| "learning_rate": 4.095171164889143e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9795369878411293, |
| "step": 1646 |
| }, |
| { |
| "epoch": 9.633431085043988, |
| "grad_norm": 0.2356131369923837, |
| "learning_rate": 4.091681912154903e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9773572832345963, |
| "step": 1647 |
| }, |
| { |
| "epoch": 9.639296187683284, |
| "grad_norm": 0.3972197577494257, |
| "learning_rate": 4.088257659382619e-06, |
| "loss": 0.085, |
| "mean_token_accuracy": 0.972993515431881, |
| "step": 1648 |
| }, |
| { |
| "epoch": 9.64516129032258, |
| "grad_norm": 0.2869208785212869, |
| "learning_rate": 4.0848984190009495e-06, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9753344133496284, |
| "step": 1649 |
| }, |
| { |
| "epoch": 9.651026392961876, |
| "grad_norm": 0.21142625693572772, |
| "learning_rate": 4.081604203202577e-06, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.983475349843502, |
| "step": 1650 |
| }, |
| { |
| "epoch": 9.656891495601172, |
| "grad_norm": 0.21591702452821918, |
| "learning_rate": 4.078375023944175e-06, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9807283952832222, |
| "step": 1651 |
| }, |
| { |
| "epoch": 9.662756598240469, |
| "grad_norm": 0.2510568273569073, |
| "learning_rate": 4.0752108929463625e-06, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.9732875376939774, |
| "step": 1652 |
| }, |
| { |
| "epoch": 9.668621700879765, |
| "grad_norm": 0.2863797336182336, |
| "learning_rate": 4.072111821693655e-06, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9797648787498474, |
| "step": 1653 |
| }, |
| { |
| "epoch": 9.674486803519061, |
| "grad_norm": 0.38771617138049674, |
| "learning_rate": 4.069077821434429e-06, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9792503714561462, |
| "step": 1654 |
| }, |
| { |
| "epoch": 9.680351906158357, |
| "grad_norm": 0.2900452759214232, |
| "learning_rate": 4.06610890318088e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9800984635949135, |
| "step": 1655 |
| }, |
| { |
| "epoch": 9.686217008797653, |
| "grad_norm": 0.20255555978860618, |
| "learning_rate": 4.063205077708986e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9810278192162514, |
| "step": 1656 |
| }, |
| { |
| "epoch": 9.69208211143695, |
| "grad_norm": 0.29768882425093995, |
| "learning_rate": 4.060366355558456e-06, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.976965144276619, |
| "step": 1657 |
| }, |
| { |
| "epoch": 9.697947214076246, |
| "grad_norm": 0.279989351630936, |
| "learning_rate": 4.057592747032707e-06, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.9744569063186646, |
| "step": 1658 |
| }, |
| { |
| "epoch": 9.703812316715542, |
| "grad_norm": 0.264998673954461, |
| "learning_rate": 4.054884262198816e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.980218268930912, |
| "step": 1659 |
| }, |
| { |
| "epoch": 9.709677419354838, |
| "grad_norm": 0.2122981558643174, |
| "learning_rate": 4.052240910887493e-06, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9808973520994186, |
| "step": 1660 |
| }, |
| { |
| "epoch": 9.715542521994134, |
| "grad_norm": 0.23351588515140767, |
| "learning_rate": 4.049662702693031e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9794720560312271, |
| "step": 1661 |
| }, |
| { |
| "epoch": 9.72140762463343, |
| "grad_norm": 0.23921226195250828, |
| "learning_rate": 4.047149646973288e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9779072403907776, |
| "step": 1662 |
| }, |
| { |
| "epoch": 9.727272727272727, |
| "grad_norm": 0.2719726622731542, |
| "learning_rate": 4.044701752849639e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9809428751468658, |
| "step": 1663 |
| }, |
| { |
| "epoch": 9.733137829912023, |
| "grad_norm": 0.22023511820730315, |
| "learning_rate": 4.042319029206954e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9804383143782616, |
| "step": 1664 |
| }, |
| { |
| "epoch": 9.739002932551319, |
| "grad_norm": 0.2645304598593257, |
| "learning_rate": 4.040001484693553e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9822018891572952, |
| "step": 1665 |
| }, |
| { |
| "epoch": 9.744868035190615, |
| "grad_norm": 0.26898083015274943, |
| "learning_rate": 4.037749127721191e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9816476553678513, |
| "step": 1666 |
| }, |
| { |
| "epoch": 9.750733137829911, |
| "grad_norm": 0.2148855087589927, |
| "learning_rate": 4.03556196646501e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9825252592563629, |
| "step": 1667 |
| }, |
| { |
| "epoch": 9.756598240469208, |
| "grad_norm": 0.258599519645029, |
| "learning_rate": 4.033440008863528e-06, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9784804806113243, |
| "step": 1668 |
| }, |
| { |
| "epoch": 9.762463343108504, |
| "grad_norm": 0.2561946434849189, |
| "learning_rate": 4.031383262618588e-06, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9773758798837662, |
| "step": 1669 |
| }, |
| { |
| "epoch": 9.7683284457478, |
| "grad_norm": 0.2762399259206808, |
| "learning_rate": 4.0293917351953505e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9803431034088135, |
| "step": 1670 |
| }, |
| { |
| "epoch": 9.774193548387096, |
| "grad_norm": 0.355930013011736, |
| "learning_rate": 4.027465433822255e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9785107672214508, |
| "step": 1671 |
| }, |
| { |
| "epoch": 9.780058651026392, |
| "grad_norm": 0.24895531218985303, |
| "learning_rate": 4.025604365490999e-06, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9814844280481339, |
| "step": 1672 |
| }, |
| { |
| "epoch": 9.785923753665688, |
| "grad_norm": 0.2340877368955121, |
| "learning_rate": 4.0238085369565085e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9819305539131165, |
| "step": 1673 |
| }, |
| { |
| "epoch": 9.791788856304985, |
| "grad_norm": 0.21828086268261218, |
| "learning_rate": 4.022077954736916e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9818969219923019, |
| "step": 1674 |
| }, |
| { |
| "epoch": 9.79765395894428, |
| "grad_norm": 0.2658598614336904, |
| "learning_rate": 4.020412625113535e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9813483133912086, |
| "step": 1675 |
| }, |
| { |
| "epoch": 9.803519061583577, |
| "grad_norm": 0.2602573672355344, |
| "learning_rate": 4.018812554130839e-06, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9781445488333702, |
| "step": 1676 |
| }, |
| { |
| "epoch": 9.809384164222873, |
| "grad_norm": 0.2801981767369684, |
| "learning_rate": 4.01727774759644e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.9778248742222786, |
| "step": 1677 |
| }, |
| { |
| "epoch": 9.81524926686217, |
| "grad_norm": 0.2703585276782977, |
| "learning_rate": 4.0158082110810695e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9797122403979301, |
| "step": 1678 |
| }, |
| { |
| "epoch": 9.821114369501466, |
| "grad_norm": 0.31803486063306685, |
| "learning_rate": 4.014403949918545e-06, |
| "loss": 0.0599, |
| "mean_token_accuracy": 0.9799430221319199, |
| "step": 1679 |
| }, |
| { |
| "epoch": 9.826979472140762, |
| "grad_norm": 0.2820420179958132, |
| "learning_rate": 4.0130649692057715e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9790126010775566, |
| "step": 1680 |
| }, |
| { |
| "epoch": 9.832844574780058, |
| "grad_norm": 0.25148689534618957, |
| "learning_rate": 4.01179127380271e-06, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9769551530480385, |
| "step": 1681 |
| }, |
| { |
| "epoch": 9.838709677419354, |
| "grad_norm": 0.2379631065406326, |
| "learning_rate": 4.010582868332353e-06, |
| "loss": 0.0538, |
| "mean_token_accuracy": 0.9826568216085434, |
| "step": 1682 |
| }, |
| { |
| "epoch": 9.84457478005865, |
| "grad_norm": 0.27305533671205534, |
| "learning_rate": 4.009439757180732e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9774700924754143, |
| "step": 1683 |
| }, |
| { |
| "epoch": 9.850439882697946, |
| "grad_norm": 0.2964998847163188, |
| "learning_rate": 4.008361944496875e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9798463135957718, |
| "step": 1684 |
| }, |
| { |
| "epoch": 9.856304985337243, |
| "grad_norm": 0.2965938750339812, |
| "learning_rate": 4.00734943419281e-06, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.9754137769341469, |
| "step": 1685 |
| }, |
| { |
| "epoch": 9.862170087976539, |
| "grad_norm": 0.28260924704377915, |
| "learning_rate": 4.006402229943534e-06, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9779395908117294, |
| "step": 1686 |
| }, |
| { |
| "epoch": 9.868035190615835, |
| "grad_norm": 0.23371054288209903, |
| "learning_rate": 4.005520335187023e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9794416725635529, |
| "step": 1687 |
| }, |
| { |
| "epoch": 9.873900293255131, |
| "grad_norm": 0.2612525488005821, |
| "learning_rate": 4.004703753124195e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9788842275738716, |
| "step": 1688 |
| }, |
| { |
| "epoch": 9.879765395894427, |
| "grad_norm": 0.215311765680089, |
| "learning_rate": 4.003952486718913e-06, |
| "loss": 0.0552, |
| "mean_token_accuracy": 0.9810579568147659, |
| "step": 1689 |
| }, |
| { |
| "epoch": 9.885630498533724, |
| "grad_norm": 0.2504746637761669, |
| "learning_rate": 4.003266538697973e-06, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.978359691798687, |
| "step": 1690 |
| }, |
| { |
| "epoch": 9.89149560117302, |
| "grad_norm": 0.3033572404106571, |
| "learning_rate": 4.002645911551086e-06, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9803460240364075, |
| "step": 1691 |
| }, |
| { |
| "epoch": 9.897360703812316, |
| "grad_norm": 0.2266595329570515, |
| "learning_rate": 4.002090607530882e-06, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9790749177336693, |
| "step": 1692 |
| }, |
| { |
| "epoch": 9.903225806451612, |
| "grad_norm": 0.25758436439961796, |
| "learning_rate": 4.001600628652887e-06, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9739339500665665, |
| "step": 1693 |
| }, |
| { |
| "epoch": 9.909090909090908, |
| "grad_norm": 0.2730797336241935, |
| "learning_rate": 4.001175976695527e-06, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9755261316895485, |
| "step": 1694 |
| }, |
| { |
| "epoch": 9.914956011730204, |
| "grad_norm": 0.24102622763373174, |
| "learning_rate": 4.000816653200117e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9845007807016373, |
| "step": 1695 |
| }, |
| { |
| "epoch": 9.9208211143695, |
| "grad_norm": 0.2813958161148632, |
| "learning_rate": 4.000522659470857e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9797054156661034, |
| "step": 1696 |
| }, |
| { |
| "epoch": 9.926686217008797, |
| "grad_norm": 0.3285137376648042, |
| "learning_rate": 4.000293996574826e-06, |
| "loss": 0.0799, |
| "mean_token_accuracy": 0.9748532995581627, |
| "step": 1697 |
| }, |
| { |
| "epoch": 9.932551319648093, |
| "grad_norm": 0.28907914247281624, |
| "learning_rate": 4.000130665341977e-06, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9762020409107208, |
| "step": 1698 |
| }, |
| { |
| "epoch": 9.93841642228739, |
| "grad_norm": 0.2506289774234882, |
| "learning_rate": 4.000032666365136e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9811992347240448, |
| "step": 1699 |
| }, |
| { |
| "epoch": 9.944281524926687, |
| "grad_norm": 0.23581196926582984, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9796453937888145, |
| "step": 1700 |
| }, |
| { |
| "epoch": 9.944281524926687, |
| "step": 1700, |
| "total_flos": 13396901806080.0, |
| "train_loss": 0.21142534818062012, |
| "train_runtime": 61693.825, |
| "train_samples_per_second": 0.884, |
| "train_steps_per_second": 0.028 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1700, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 13396901806080.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
