| { |
| "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": 53.88819372213907, |
| "learning_rate": 7.843137254901962e-07, |
| "loss": 2.5558, |
| "mean_token_accuracy": 0.4949319437146187, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011730205278592375, |
| "grad_norm": 45.53813500273709, |
| "learning_rate": 1.5686274509803923e-06, |
| "loss": 2.6383, |
| "mean_token_accuracy": 0.4859154038131237, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.017595307917888565, |
| "grad_norm": 46.07293762408888, |
| "learning_rate": 2.3529411764705885e-06, |
| "loss": 2.5158, |
| "mean_token_accuracy": 0.48826197162270546, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.02346041055718475, |
| "grad_norm": 21.731930798046225, |
| "learning_rate": 3.1372549019607846e-06, |
| "loss": 2.4153, |
| "mean_token_accuracy": 0.507574986666441, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.02932551319648094, |
| "grad_norm": 13.719250081157423, |
| "learning_rate": 3.92156862745098e-06, |
| "loss": 2.1828, |
| "mean_token_accuracy": 0.5369513519108295, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03519061583577713, |
| "grad_norm": 11.296846771241944, |
| "learning_rate": 4.705882352941177e-06, |
| "loss": 2.0254, |
| "mean_token_accuracy": 0.5546183437108994, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.04105571847507331, |
| "grad_norm": 11.181546197747945, |
| "learning_rate": 5.4901960784313735e-06, |
| "loss": 2.0634, |
| "mean_token_accuracy": 0.5418906435370445, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0469208211143695, |
| "grad_norm": 9.95073085746692, |
| "learning_rate": 6.274509803921569e-06, |
| "loss": 1.909, |
| "mean_token_accuracy": 0.5698892250657082, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05278592375366569, |
| "grad_norm": 8.750145661654372, |
| "learning_rate": 7.058823529411766e-06, |
| "loss": 1.7282, |
| "mean_token_accuracy": 0.5925135612487793, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.05865102639296188, |
| "grad_norm": 6.881468868221019, |
| "learning_rate": 7.84313725490196e-06, |
| "loss": 1.6569, |
| "mean_token_accuracy": 0.6076302081346512, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06451612903225806, |
| "grad_norm": 8.253095142047671, |
| "learning_rate": 8.627450980392157e-06, |
| "loss": 1.5307, |
| "mean_token_accuracy": 0.6325564980506897, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07038123167155426, |
| "grad_norm": 7.4261225290773485, |
| "learning_rate": 9.411764705882354e-06, |
| "loss": 1.4483, |
| "mean_token_accuracy": 0.6526486948132515, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.07624633431085044, |
| "grad_norm": 6.779863395778969, |
| "learning_rate": 1.0196078431372549e-05, |
| "loss": 1.4433, |
| "mean_token_accuracy": 0.6399537846446037, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.08211143695014662, |
| "grad_norm": 6.268466773477867, |
| "learning_rate": 1.0980392156862747e-05, |
| "loss": 1.5392, |
| "mean_token_accuracy": 0.6327727138996124, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.08797653958944282, |
| "grad_norm": 6.160706527674582, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 1.4847, |
| "mean_token_accuracy": 0.6257975250482559, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.093841642228739, |
| "grad_norm": 5.222490978742135, |
| "learning_rate": 1.2549019607843138e-05, |
| "loss": 1.3997, |
| "mean_token_accuracy": 0.6548606380820274, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.09970674486803519, |
| "grad_norm": 4.975143902167062, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 1.2949, |
| "mean_token_accuracy": 0.6746953576803207, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.10557184750733138, |
| "grad_norm": 5.673987761988572, |
| "learning_rate": 1.4117647058823532e-05, |
| "loss": 1.2628, |
| "mean_token_accuracy": 0.6803952604532242, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.11143695014662756, |
| "grad_norm": 4.956998983619939, |
| "learning_rate": 1.4901960784313726e-05, |
| "loss": 1.4657, |
| "mean_token_accuracy": 0.6383700221776962, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.11730205278592376, |
| "grad_norm": 4.6674469767268665, |
| "learning_rate": 1.568627450980392e-05, |
| "loss": 1.3336, |
| "mean_token_accuracy": 0.6622527092695236, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12316715542521994, |
| "grad_norm": 4.56146568749882, |
| "learning_rate": 1.647058823529412e-05, |
| "loss": 1.2586, |
| "mean_token_accuracy": 0.6755763664841652, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.12903225806451613, |
| "grad_norm": 4.178539403683921, |
| "learning_rate": 1.7254901960784314e-05, |
| "loss": 1.2955, |
| "mean_token_accuracy": 0.6781341508030891, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.1348973607038123, |
| "grad_norm": 4.691795666447551, |
| "learning_rate": 1.8039215686274513e-05, |
| "loss": 1.2063, |
| "mean_token_accuracy": 0.7020066231489182, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.14076246334310852, |
| "grad_norm": 4.393626747850234, |
| "learning_rate": 1.8823529411764708e-05, |
| "loss": 1.2492, |
| "mean_token_accuracy": 0.6896483823657036, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.1466275659824047, |
| "grad_norm": 4.600031146460728, |
| "learning_rate": 1.9607843137254903e-05, |
| "loss": 1.2452, |
| "mean_token_accuracy": 0.6773535162210464, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15249266862170088, |
| "grad_norm": 4.750027023339882, |
| "learning_rate": 2.0392156862745097e-05, |
| "loss": 1.3096, |
| "mean_token_accuracy": 0.6744465455412865, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.15835777126099707, |
| "grad_norm": 5.016234982836503, |
| "learning_rate": 2.1176470588235296e-05, |
| "loss": 1.2253, |
| "mean_token_accuracy": 0.6968231871724129, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.16422287390029325, |
| "grad_norm": 4.1501723534181165, |
| "learning_rate": 2.1960784313725494e-05, |
| "loss": 1.0885, |
| "mean_token_accuracy": 0.7159736528992653, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.17008797653958943, |
| "grad_norm": 5.027518185476307, |
| "learning_rate": 2.274509803921569e-05, |
| "loss": 1.1875, |
| "mean_token_accuracy": 0.7006409764289856, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.17595307917888564, |
| "grad_norm": 4.695128131871855, |
| "learning_rate": 2.3529411764705884e-05, |
| "loss": 1.2233, |
| "mean_token_accuracy": 0.6893411129713058, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 4.444186099052533, |
| "learning_rate": 2.431372549019608e-05, |
| "loss": 1.3716, |
| "mean_token_accuracy": 0.6714634746313095, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.187683284457478, |
| "grad_norm": 4.594781832701057, |
| "learning_rate": 2.5098039215686277e-05, |
| "loss": 1.0986, |
| "mean_token_accuracy": 0.7190676406025887, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.1935483870967742, |
| "grad_norm": 5.074679164350963, |
| "learning_rate": 2.5882352941176475e-05, |
| "loss": 1.2351, |
| "mean_token_accuracy": 0.6866041272878647, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.19941348973607037, |
| "grad_norm": 3.9217364207838075, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 1.0962, |
| "mean_token_accuracy": 0.7126260623335838, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.20527859237536658, |
| "grad_norm": 4.24349529061146, |
| "learning_rate": 2.7450980392156865e-05, |
| "loss": 1.1477, |
| "mean_token_accuracy": 0.7069110572338104, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.21114369501466276, |
| "grad_norm": 4.236355982392962, |
| "learning_rate": 2.8235294117647063e-05, |
| "loss": 1.1657, |
| "mean_token_accuracy": 0.7083533778786659, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.21700879765395895, |
| "grad_norm": 4.056198751455204, |
| "learning_rate": 2.9019607843137258e-05, |
| "loss": 1.104, |
| "mean_token_accuracy": 0.7193247005343437, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.22287390029325513, |
| "grad_norm": 3.952005738151635, |
| "learning_rate": 2.9803921568627453e-05, |
| "loss": 1.0282, |
| "mean_token_accuracy": 0.7227280139923096, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2287390029325513, |
| "grad_norm": 4.268826077737683, |
| "learning_rate": 3.0588235294117644e-05, |
| "loss": 1.325, |
| "mean_token_accuracy": 0.6643695458769798, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.23460410557184752, |
| "grad_norm": 3.8742320180768868, |
| "learning_rate": 3.137254901960784e-05, |
| "loss": 1.0486, |
| "mean_token_accuracy": 0.7284644469618797, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2404692082111437, |
| "grad_norm": 3.5533315273234276, |
| "learning_rate": 3.215686274509804e-05, |
| "loss": 1.0222, |
| "mean_token_accuracy": 0.7333771288394928, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.24633431085043989, |
| "grad_norm": 3.9010486506007456, |
| "learning_rate": 3.294117647058824e-05, |
| "loss": 1.0616, |
| "mean_token_accuracy": 0.723753847181797, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.25219941348973607, |
| "grad_norm": 3.234591569823163, |
| "learning_rate": 3.372549019607844e-05, |
| "loss": 0.8581, |
| "mean_token_accuracy": 0.7685456275939941, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.25806451612903225, |
| "grad_norm": 3.743981662725678, |
| "learning_rate": 3.450980392156863e-05, |
| "loss": 1.037, |
| "mean_token_accuracy": 0.7245888039469719, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.26392961876832843, |
| "grad_norm": 3.7804639874968826, |
| "learning_rate": 3.529411764705883e-05, |
| "loss": 0.9217, |
| "mean_token_accuracy": 0.7485020831227303, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.2697947214076246, |
| "grad_norm": 3.716939922880826, |
| "learning_rate": 3.6078431372549025e-05, |
| "loss": 1.0878, |
| "mean_token_accuracy": 0.716446116566658, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.2756598240469208, |
| "grad_norm": 3.902425102382139, |
| "learning_rate": 3.686274509803922e-05, |
| "loss": 1.0478, |
| "mean_token_accuracy": 0.7267983332276344, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.28152492668621704, |
| "grad_norm": 3.4333368458738134, |
| "learning_rate": 3.7647058823529415e-05, |
| "loss": 0.9818, |
| "mean_token_accuracy": 0.7405076771974564, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.2873900293255132, |
| "grad_norm": 3.88647483745419, |
| "learning_rate": 3.8431372549019614e-05, |
| "loss": 0.9826, |
| "mean_token_accuracy": 0.766911968588829, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.2932551319648094, |
| "grad_norm": 3.98665632736657, |
| "learning_rate": 3.9215686274509805e-05, |
| "loss": 1.2055, |
| "mean_token_accuracy": 0.7004791498184204, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2991202346041056, |
| "grad_norm": 3.2689866643155785, |
| "learning_rate": 4e-05, |
| "loss": 0.9299, |
| "mean_token_accuracy": 0.7512985840439796, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.30498533724340177, |
| "grad_norm": 3.6566795475047242, |
| "learning_rate": 3.999996733363487e-05, |
| "loss": 1.055, |
| "mean_token_accuracy": 0.7290665507316589, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.31085043988269795, |
| "grad_norm": 3.5319474505893376, |
| "learning_rate": 3.9999869334658026e-05, |
| "loss": 0.9811, |
| "mean_token_accuracy": 0.7426001131534576, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.31671554252199413, |
| "grad_norm": 3.729947058428488, |
| "learning_rate": 3.9999706003425177e-05, |
| "loss": 1.0335, |
| "mean_token_accuracy": 0.731833204627037, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3225806451612903, |
| "grad_norm": 3.747352951199307, |
| "learning_rate": 3.999947734052915e-05, |
| "loss": 1.1685, |
| "mean_token_accuracy": 0.7056599855422974, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.3284457478005865, |
| "grad_norm": 3.1603059667205113, |
| "learning_rate": 3.999918334679989e-05, |
| "loss": 1.0283, |
| "mean_token_accuracy": 0.7293788716197014, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3343108504398827, |
| "grad_norm": 3.5593596872927393, |
| "learning_rate": 3.999882402330448e-05, |
| "loss": 0.9824, |
| "mean_token_accuracy": 0.7320685908198357, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.34017595307917886, |
| "grad_norm": 3.3758708442048717, |
| "learning_rate": 3.999839937134712e-05, |
| "loss": 0.9158, |
| "mean_token_accuracy": 0.7505558356642723, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.3460410557184751, |
| "grad_norm": 3.7326151053945926, |
| "learning_rate": 3.999790939246912e-05, |
| "loss": 1.1747, |
| "mean_token_accuracy": 0.7094109430909157, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3519061583577713, |
| "grad_norm": 3.528279867739533, |
| "learning_rate": 3.999735408844892e-05, |
| "loss": 0.9405, |
| "mean_token_accuracy": 0.7575809136033058, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.35777126099706746, |
| "grad_norm": 3.3839518740419026, |
| "learning_rate": 3.999673346130203e-05, |
| "loss": 1.0557, |
| "mean_token_accuracy": 0.7328348979353905, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 3.2633650772189298, |
| "learning_rate": 3.999604751328109e-05, |
| "loss": 0.8524, |
| "mean_token_accuracy": 0.7810637131333351, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.36950146627565983, |
| "grad_norm": 3.1490026716573074, |
| "learning_rate": 3.999529624687581e-05, |
| "loss": 0.8142, |
| "mean_token_accuracy": 0.7814765721559525, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.375366568914956, |
| "grad_norm": 3.2754413857067997, |
| "learning_rate": 3.999447966481298e-05, |
| "loss": 0.9898, |
| "mean_token_accuracy": 0.7611383348703384, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.3812316715542522, |
| "grad_norm": 3.660506367731786, |
| "learning_rate": 3.999359777005647e-05, |
| "loss": 1.0594, |
| "mean_token_accuracy": 0.7227808833122253, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.3870967741935484, |
| "grad_norm": 3.1676884856312792, |
| "learning_rate": 3.999265056580719e-05, |
| "loss": 0.7991, |
| "mean_token_accuracy": 0.7763359025120735, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.39296187683284456, |
| "grad_norm": 4.029643282419232, |
| "learning_rate": 3.999163805550313e-05, |
| "loss": 1.1659, |
| "mean_token_accuracy": 0.7266501784324646, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.39882697947214074, |
| "grad_norm": 3.7749079691303575, |
| "learning_rate": 3.9990560242819274e-05, |
| "loss": 1.0427, |
| "mean_token_accuracy": 0.742008738219738, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.4046920821114369, |
| "grad_norm": 2.847418175540077, |
| "learning_rate": 3.9989417131667647e-05, |
| "loss": 0.8382, |
| "mean_token_accuracy": 0.7917518392205238, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.41055718475073316, |
| "grad_norm": 3.000734305407189, |
| "learning_rate": 3.9988208726197293e-05, |
| "loss": 0.859, |
| "mean_token_accuracy": 0.7706286013126373, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.41642228739002934, |
| "grad_norm": 3.2494689736047166, |
| "learning_rate": 3.998693503079423e-05, |
| "loss": 1.0425, |
| "mean_token_accuracy": 0.748763732612133, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4222873900293255, |
| "grad_norm": 3.3185644568863504, |
| "learning_rate": 3.998559605008146e-05, |
| "loss": 0.911, |
| "mean_token_accuracy": 0.7488791346549988, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.4281524926686217, |
| "grad_norm": 3.308636181185568, |
| "learning_rate": 3.9984191788918936e-05, |
| "loss": 0.9626, |
| "mean_token_accuracy": 0.7521362155675888, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4340175953079179, |
| "grad_norm": 3.0388816030710157, |
| "learning_rate": 3.998272225240356e-05, |
| "loss": 1.0393, |
| "mean_token_accuracy": 0.7457354441285133, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4398826979472141, |
| "grad_norm": 2.9938798095118306, |
| "learning_rate": 3.9981187445869165e-05, |
| "loss": 0.8992, |
| "mean_token_accuracy": 0.7812586054205894, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.44574780058651026, |
| "grad_norm": 2.8252620826574075, |
| "learning_rate": 3.9979587374886466e-05, |
| "loss": 0.9967, |
| "mean_token_accuracy": 0.7389231100678444, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.45161290322580644, |
| "grad_norm": 3.186265590142511, |
| "learning_rate": 3.997792204526309e-05, |
| "loss": 0.9009, |
| "mean_token_accuracy": 0.7611340954899788, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.4574780058651026, |
| "grad_norm": 2.7414294876337193, |
| "learning_rate": 3.99761914630435e-05, |
| "loss": 0.8311, |
| "mean_token_accuracy": 0.7738662958145142, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.4633431085043988, |
| "grad_norm": 2.7941315506109317, |
| "learning_rate": 3.997439563450901e-05, |
| "loss": 0.795, |
| "mean_token_accuracy": 0.7797789797186852, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.46920821114369504, |
| "grad_norm": 3.5423646785271306, |
| "learning_rate": 3.997253456617775e-05, |
| "loss": 0.8952, |
| "mean_token_accuracy": 0.7717294245958328, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4750733137829912, |
| "grad_norm": 2.8793698731844946, |
| "learning_rate": 3.997060826480465e-05, |
| "loss": 0.7861, |
| "mean_token_accuracy": 0.7887553870677948, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.4809384164222874, |
| "grad_norm": 2.8342850937430124, |
| "learning_rate": 3.9968616737381414e-05, |
| "loss": 0.9051, |
| "mean_token_accuracy": 0.7746857702732086, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.4868035190615836, |
| "grad_norm": 2.765248067167797, |
| "learning_rate": 3.996655999113647e-05, |
| "loss": 0.7809, |
| "mean_token_accuracy": 0.7994513288140297, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.49266862170087977, |
| "grad_norm": 2.63444146182952, |
| "learning_rate": 3.9964438033534994e-05, |
| "loss": 0.6653, |
| "mean_token_accuracy": 0.8137254267930984, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.49853372434017595, |
| "grad_norm": 2.5758158024473894, |
| "learning_rate": 3.996225087227881e-05, |
| "loss": 0.8351, |
| "mean_token_accuracy": 0.7905571460723877, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5043988269794721, |
| "grad_norm": 2.679363954385569, |
| "learning_rate": 3.995999851530645e-05, |
| "loss": 0.7733, |
| "mean_token_accuracy": 0.8147490695118904, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.5102639296187683, |
| "grad_norm": 3.101877229990958, |
| "learning_rate": 3.995768097079305e-05, |
| "loss": 0.8257, |
| "mean_token_accuracy": 0.7912640422582626, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.5161290322580645, |
| "grad_norm": 3.2623148963738577, |
| "learning_rate": 3.9955298247150365e-05, |
| "loss": 0.9696, |
| "mean_token_accuracy": 0.7420180812478065, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.5219941348973607, |
| "grad_norm": 2.771096820053822, |
| "learning_rate": 3.9952850353026715e-05, |
| "loss": 0.7977, |
| "mean_token_accuracy": 0.7726879939436913, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.5278592375366569, |
| "grad_norm": 2.871934260005109, |
| "learning_rate": 3.9950337297306976e-05, |
| "loss": 0.8731, |
| "mean_token_accuracy": 0.7779897972941399, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.533724340175953, |
| "grad_norm": 3.2685752749904244, |
| "learning_rate": 3.994775908911251e-05, |
| "loss": 0.9586, |
| "mean_token_accuracy": 0.7562056183815002, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.5395894428152492, |
| "grad_norm": 2.969500327515322, |
| "learning_rate": 3.9945115737801183e-05, |
| "loss": 0.81, |
| "mean_token_accuracy": 0.7800324559211731, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 2.924171514995882, |
| "learning_rate": 3.99424072529673e-05, |
| "loss": 0.9543, |
| "mean_token_accuracy": 0.7631434127688408, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.5513196480938416, |
| "grad_norm": 2.793490417192969, |
| "learning_rate": 3.993963364444155e-05, |
| "loss": 0.8121, |
| "mean_token_accuracy": 0.7810578048229218, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.5571847507331378, |
| "grad_norm": 2.9166073057905835, |
| "learning_rate": 3.9936794922291015e-05, |
| "loss": 0.9339, |
| "mean_token_accuracy": 0.7549960389733315, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5630498533724341, |
| "grad_norm": 3.198161361235805, |
| "learning_rate": 3.993389109681912e-05, |
| "loss": 0.8918, |
| "mean_token_accuracy": 0.7610742226243019, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.5689149560117303, |
| "grad_norm": 2.9220063831682896, |
| "learning_rate": 3.993092217856557e-05, |
| "loss": 0.8076, |
| "mean_token_accuracy": 0.7827741503715515, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.5747800586510264, |
| "grad_norm": 3.27007124996685, |
| "learning_rate": 3.9927888178306346e-05, |
| "loss": 0.9276, |
| "mean_token_accuracy": 0.7676652446389198, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.5806451612903226, |
| "grad_norm": 3.1316564998983196, |
| "learning_rate": 3.992478910705364e-05, |
| "loss": 0.9, |
| "mean_token_accuracy": 0.7664341479539871, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.5865102639296188, |
| "grad_norm": 2.4604893204923655, |
| "learning_rate": 3.992162497605583e-05, |
| "loss": 0.7547, |
| "mean_token_accuracy": 0.81553765386343, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.592375366568915, |
| "grad_norm": 2.531774075426503, |
| "learning_rate": 3.991839579679742e-05, |
| "loss": 0.8143, |
| "mean_token_accuracy": 0.7856726944446564, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.5982404692082112, |
| "grad_norm": 2.8565788729879573, |
| "learning_rate": 3.991510158099905e-05, |
| "loss": 0.645, |
| "mean_token_accuracy": 0.8300929889082909, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.6041055718475073, |
| "grad_norm": 2.5799784187137043, |
| "learning_rate": 3.991174234061738e-05, |
| "loss": 0.6879, |
| "mean_token_accuracy": 0.8256210163235664, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.6099706744868035, |
| "grad_norm": 2.8988288323460547, |
| "learning_rate": 3.9908318087845104e-05, |
| "loss": 0.8477, |
| "mean_token_accuracy": 0.7800894677639008, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.6158357771260997, |
| "grad_norm": 2.652941902337806, |
| "learning_rate": 3.990482883511086e-05, |
| "loss": 0.628, |
| "mean_token_accuracy": 0.828456349670887, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.6217008797653959, |
| "grad_norm": 2.459546673804448, |
| "learning_rate": 3.990127459507924e-05, |
| "loss": 0.6674, |
| "mean_token_accuracy": 0.8069566413760185, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.6275659824046921, |
| "grad_norm": 5.737679812729463, |
| "learning_rate": 3.98976553806507e-05, |
| "loss": 0.6696, |
| "mean_token_accuracy": 0.8196565955877304, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.6334310850439883, |
| "grad_norm": 3.013498732232973, |
| "learning_rate": 3.989397120496152e-05, |
| "loss": 0.6028, |
| "mean_token_accuracy": 0.8420541435480118, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.6392961876832844, |
| "grad_norm": 2.546654879348618, |
| "learning_rate": 3.989022208138377e-05, |
| "loss": 0.6393, |
| "mean_token_accuracy": 0.8270744681358337, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "grad_norm": 3.20470392326585, |
| "learning_rate": 3.9886408023525256e-05, |
| "loss": 0.8824, |
| "mean_token_accuracy": 0.7817021533846855, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6510263929618768, |
| "grad_norm": 4.058205693055433, |
| "learning_rate": 3.9882529045229475e-05, |
| "loss": 0.9437, |
| "mean_token_accuracy": 0.7480623200535774, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.656891495601173, |
| "grad_norm": 2.943950340930463, |
| "learning_rate": 3.987858516057554e-05, |
| "loss": 0.6783, |
| "mean_token_accuracy": 0.8154667392373085, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.6627565982404692, |
| "grad_norm": 2.7735485267748383, |
| "learning_rate": 3.9874576383878165e-05, |
| "loss": 0.7185, |
| "mean_token_accuracy": 0.8148206546902657, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.6686217008797654, |
| "grad_norm": 2.846138915008106, |
| "learning_rate": 3.9870502729687594e-05, |
| "loss": 0.7421, |
| "mean_token_accuracy": 0.8019789308309555, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.6744868035190615, |
| "grad_norm": 2.644169473625222, |
| "learning_rate": 3.986636421278954e-05, |
| "loss": 0.7782, |
| "mean_token_accuracy": 0.8042545765638351, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6803519061583577, |
| "grad_norm": 2.3392486448858927, |
| "learning_rate": 3.986216084820515e-05, |
| "loss": 0.5596, |
| "mean_token_accuracy": 0.8448091298341751, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.6862170087976539, |
| "grad_norm": 2.583813549613289, |
| "learning_rate": 3.985789265119095e-05, |
| "loss": 0.6485, |
| "mean_token_accuracy": 0.8111533001065254, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.6920821114369502, |
| "grad_norm": 2.4887332265478617, |
| "learning_rate": 3.985355963723875e-05, |
| "loss": 0.5541, |
| "mean_token_accuracy": 0.851133368909359, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.6979472140762464, |
| "grad_norm": 2.4799587573079513, |
| "learning_rate": 3.9849161822075655e-05, |
| "loss": 0.6044, |
| "mean_token_accuracy": 0.8356705754995346, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.7038123167155426, |
| "grad_norm": 2.530137167351601, |
| "learning_rate": 3.984469922166396e-05, |
| "loss": 0.7096, |
| "mean_token_accuracy": 0.8197364211082458, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7096774193548387, |
| "grad_norm": 2.824821340244295, |
| "learning_rate": 3.984017185220109e-05, |
| "loss": 0.8867, |
| "mean_token_accuracy": 0.7859450578689575, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.7155425219941349, |
| "grad_norm": 2.5599681132585617, |
| "learning_rate": 3.9835579730119576e-05, |
| "loss": 0.7616, |
| "mean_token_accuracy": 0.7998316809535027, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.7214076246334311, |
| "grad_norm": 2.3785812997234257, |
| "learning_rate": 3.9830922872086974e-05, |
| "loss": 0.743, |
| "mean_token_accuracy": 0.8207187280058861, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 2.585305660680504, |
| "learning_rate": 3.9826201295005784e-05, |
| "loss": 0.8467, |
| "mean_token_accuracy": 0.7912140190601349, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.7331378299120235, |
| "grad_norm": 2.8062519533225103, |
| "learning_rate": 3.982141501601343e-05, |
| "loss": 0.8176, |
| "mean_token_accuracy": 0.7884003445506096, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7390029325513197, |
| "grad_norm": 2.693775516289464, |
| "learning_rate": 3.9816564052482164e-05, |
| "loss": 0.7498, |
| "mean_token_accuracy": 0.799252338707447, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.7448680351906158, |
| "grad_norm": 2.9011965003727425, |
| "learning_rate": 3.981164842201904e-05, |
| "loss": 0.7827, |
| "mean_token_accuracy": 0.8069761171936989, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.750733137829912, |
| "grad_norm": 2.838289459808484, |
| "learning_rate": 3.9806668142465804e-05, |
| "loss": 0.8198, |
| "mean_token_accuracy": 0.7964724600315094, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.7565982404692082, |
| "grad_norm": 2.210570471941626, |
| "learning_rate": 3.9801623231898856e-05, |
| "loss": 0.607, |
| "mean_token_accuracy": 0.833724357187748, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.7624633431085044, |
| "grad_norm": 2.4332563355629326, |
| "learning_rate": 3.9796513708629186e-05, |
| "loss": 0.6395, |
| "mean_token_accuracy": 0.8242924064397812, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7683284457478006, |
| "grad_norm": 2.745783922339993, |
| "learning_rate": 3.979133959120229e-05, |
| "loss": 0.6428, |
| "mean_token_accuracy": 0.8359903246164322, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.7741935483870968, |
| "grad_norm": 2.446231449332525, |
| "learning_rate": 3.9786100898398145e-05, |
| "loss": 0.6281, |
| "mean_token_accuracy": 0.8326933979988098, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.7800586510263929, |
| "grad_norm": 2.2972578840395315, |
| "learning_rate": 3.9780797649231085e-05, |
| "loss": 0.6695, |
| "mean_token_accuracy": 0.8279871791601181, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.7859237536656891, |
| "grad_norm": 2.7410960234964894, |
| "learning_rate": 3.9775429862949745e-05, |
| "loss": 0.7781, |
| "mean_token_accuracy": 0.8053743913769722, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.7917888563049853, |
| "grad_norm": 2.5415583652058436, |
| "learning_rate": 3.976999755903704e-05, |
| "loss": 0.763, |
| "mean_token_accuracy": 0.7993438169360161, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7976539589442815, |
| "grad_norm": 2.270662512492905, |
| "learning_rate": 3.976450075721003e-05, |
| "loss": 0.6284, |
| "mean_token_accuracy": 0.8407260999083519, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.8035190615835777, |
| "grad_norm": 2.5929616858518676, |
| "learning_rate": 3.975893947741989e-05, |
| "loss": 0.5968, |
| "mean_token_accuracy": 0.845864936709404, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.8093841642228738, |
| "grad_norm": 2.3854479485716733, |
| "learning_rate": 3.9753313739851824e-05, |
| "loss": 0.7616, |
| "mean_token_accuracy": 0.7994790449738503, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.8152492668621701, |
| "grad_norm": 2.8723348402691906, |
| "learning_rate": 3.974762356492498e-05, |
| "loss": 0.8845, |
| "mean_token_accuracy": 0.7835755422711372, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.8211143695014663, |
| "grad_norm": 2.479196600373357, |
| "learning_rate": 3.974186897329239e-05, |
| "loss": 0.6029, |
| "mean_token_accuracy": 0.851497046649456, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8269794721407625, |
| "grad_norm": 2.504810711733226, |
| "learning_rate": 3.97360499858409e-05, |
| "loss": 0.6289, |
| "mean_token_accuracy": 0.8382159024477005, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.8328445747800587, |
| "grad_norm": 2.935237581676673, |
| "learning_rate": 3.9730166623691096e-05, |
| "loss": 0.8208, |
| "mean_token_accuracy": 0.7849750071763992, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.8387096774193549, |
| "grad_norm": 2.6436501176507603, |
| "learning_rate": 3.9724218908197194e-05, |
| "loss": 0.5852, |
| "mean_token_accuracy": 0.8367486670613289, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.844574780058651, |
| "grad_norm": 2.924448686602039, |
| "learning_rate": 3.971820686094701e-05, |
| "loss": 0.8792, |
| "mean_token_accuracy": 0.7791745141148567, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.8504398826979472, |
| "grad_norm": 2.7037525549378154, |
| "learning_rate": 3.971213050376183e-05, |
| "loss": 0.8009, |
| "mean_token_accuracy": 0.7840462699532509, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.8563049853372434, |
| "grad_norm": 2.023965935982458, |
| "learning_rate": 3.9705989858696387e-05, |
| "loss": 0.5849, |
| "mean_token_accuracy": 0.8464046567678452, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.8621700879765396, |
| "grad_norm": 2.2389680633489677, |
| "learning_rate": 3.969978494803876e-05, |
| "loss": 0.5711, |
| "mean_token_accuracy": 0.8433157354593277, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.8680351906158358, |
| "grad_norm": 2.278050804313283, |
| "learning_rate": 3.969351579431024e-05, |
| "loss": 0.5924, |
| "mean_token_accuracy": 0.8373497202992439, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.873900293255132, |
| "grad_norm": 2.402715693045193, |
| "learning_rate": 3.968718242026533e-05, |
| "loss": 0.5959, |
| "mean_token_accuracy": 0.840206079185009, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.8797653958944281, |
| "grad_norm": 2.2011155417677726, |
| "learning_rate": 3.968078484889163e-05, |
| "loss": 0.4494, |
| "mean_token_accuracy": 0.8684269115328789, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8856304985337243, |
| "grad_norm": 2.486921790559847, |
| "learning_rate": 3.9674323103409736e-05, |
| "loss": 0.6253, |
| "mean_token_accuracy": 0.8286841958761215, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.8914956011730205, |
| "grad_norm": 2.789517335456884, |
| "learning_rate": 3.966779720727317e-05, |
| "loss": 0.7794, |
| "mean_token_accuracy": 0.8061128631234169, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.8973607038123167, |
| "grad_norm": 2.510141045705032, |
| "learning_rate": 3.9661207184168305e-05, |
| "loss": 0.622, |
| "mean_token_accuracy": 0.8308300077915192, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.9032258064516129, |
| "grad_norm": 2.5109259078139936, |
| "learning_rate": 3.9654553058014265e-05, |
| "loss": 0.7255, |
| "mean_token_accuracy": 0.8097553253173828, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 2.186994234639019, |
| "learning_rate": 3.9647834852962825e-05, |
| "loss": 0.6056, |
| "mean_token_accuracy": 0.8426107689738274, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.9149560117302052, |
| "grad_norm": 2.690260479130677, |
| "learning_rate": 3.964105259339838e-05, |
| "loss": 0.8541, |
| "mean_token_accuracy": 0.7787467613816261, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.9208211143695014, |
| "grad_norm": 2.1337725885680925, |
| "learning_rate": 3.9634206303937773e-05, |
| "loss": 0.5244, |
| "mean_token_accuracy": 0.8537596613168716, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.9266862170087976, |
| "grad_norm": 1.9598919005300581, |
| "learning_rate": 3.962729600943028e-05, |
| "loss": 0.4997, |
| "mean_token_accuracy": 0.8664168417453766, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.9325513196480938, |
| "grad_norm": 2.325256374795688, |
| "learning_rate": 3.962032173495748e-05, |
| "loss": 0.5449, |
| "mean_token_accuracy": 0.8529787808656693, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.9384164222873901, |
| "grad_norm": 2.091552878169736, |
| "learning_rate": 3.961328350583316e-05, |
| "loss": 0.5242, |
| "mean_token_accuracy": 0.8521319106221199, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9442815249266863, |
| "grad_norm": 2.4200043074502355, |
| "learning_rate": 3.960618134760327e-05, |
| "loss": 0.6728, |
| "mean_token_accuracy": 0.832053430378437, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.9501466275659824, |
| "grad_norm": 1.9686791505112915, |
| "learning_rate": 3.959901528604575e-05, |
| "loss": 0.4286, |
| "mean_token_accuracy": 0.8681811094284058, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.9560117302052786, |
| "grad_norm": 2.599071858919526, |
| "learning_rate": 3.959178534717053e-05, |
| "loss": 0.7159, |
| "mean_token_accuracy": 0.8168910816311836, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.9618768328445748, |
| "grad_norm": 2.083295545704035, |
| "learning_rate": 3.9584491557219366e-05, |
| "loss": 0.6646, |
| "mean_token_accuracy": 0.8394544422626495, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.967741935483871, |
| "grad_norm": 2.240001768853048, |
| "learning_rate": 3.957713394266576e-05, |
| "loss": 0.5787, |
| "mean_token_accuracy": 0.836028702557087, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.9736070381231672, |
| "grad_norm": 2.575766108085151, |
| "learning_rate": 3.956971253021489e-05, |
| "loss": 0.5134, |
| "mean_token_accuracy": 0.8556343615055084, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.9794721407624634, |
| "grad_norm": 2.4405755915866165, |
| "learning_rate": 3.956222734680348e-05, |
| "loss": 0.6147, |
| "mean_token_accuracy": 0.8331816866993904, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.9853372434017595, |
| "grad_norm": 2.325820647224952, |
| "learning_rate": 3.955467841959972e-05, |
| "loss": 0.6321, |
| "mean_token_accuracy": 0.8455986753106117, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.9912023460410557, |
| "grad_norm": 2.178404407582914, |
| "learning_rate": 3.954706577600318e-05, |
| "loss": 0.5734, |
| "mean_token_accuracy": 0.8322867527604103, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.9970674486803519, |
| "grad_norm": 2.064610679796685, |
| "learning_rate": 3.953938944364467e-05, |
| "loss": 0.7105, |
| "mean_token_accuracy": 0.8211642429232597, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.064610679796685, |
| "learning_rate": 3.953164945038618e-05, |
| "loss": 0.6539, |
| "mean_token_accuracy": 0.8487359285354614, |
| "step": 171 |
| }, |
| { |
| "epoch": 1.0058651026392962, |
| "grad_norm": 3.388458997700093, |
| "learning_rate": 3.952384582432076e-05, |
| "loss": 0.4128, |
| "mean_token_accuracy": 0.8756323307752609, |
| "step": 172 |
| }, |
| { |
| "epoch": 1.0117302052785924, |
| "grad_norm": 1.946866153227053, |
| "learning_rate": 3.9515978593772426e-05, |
| "loss": 0.3487, |
| "mean_token_accuracy": 0.9017143920063972, |
| "step": 173 |
| }, |
| { |
| "epoch": 1.0175953079178885, |
| "grad_norm": 1.8895885148496738, |
| "learning_rate": 3.9508047787296034e-05, |
| "loss": 0.2699, |
| "mean_token_accuracy": 0.9154033064842224, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.0234604105571847, |
| "grad_norm": 1.61059572554682, |
| "learning_rate": 3.9500053433677226e-05, |
| "loss": 0.2817, |
| "mean_token_accuracy": 0.9106803834438324, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.029325513196481, |
| "grad_norm": 1.8435205509000987, |
| "learning_rate": 3.949199556193226e-05, |
| "loss": 0.3626, |
| "mean_token_accuracy": 0.8898500800132751, |
| "step": 176 |
| }, |
| { |
| "epoch": 1.035190615835777, |
| "grad_norm": 1.7339474636607546, |
| "learning_rate": 3.948387420130796e-05, |
| "loss": 0.2602, |
| "mean_token_accuracy": 0.9224452674388885, |
| "step": 177 |
| }, |
| { |
| "epoch": 1.0410557184750733, |
| "grad_norm": 1.7997907466178427, |
| "learning_rate": 3.94756893812816e-05, |
| "loss": 0.358, |
| "mean_token_accuracy": 0.8965035080909729, |
| "step": 178 |
| }, |
| { |
| "epoch": 1.0469208211143695, |
| "grad_norm": 2.258217493063847, |
| "learning_rate": 3.946744113156075e-05, |
| "loss": 0.3243, |
| "mean_token_accuracy": 0.8938365653157234, |
| "step": 179 |
| }, |
| { |
| "epoch": 1.0527859237536656, |
| "grad_norm": 2.593084420555114, |
| "learning_rate": 3.945912948208324e-05, |
| "loss": 0.4572, |
| "mean_token_accuracy": 0.8712584003806114, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.0586510263929618, |
| "grad_norm": 2.436465953164275, |
| "learning_rate": 3.9450754463016994e-05, |
| "loss": 0.4072, |
| "mean_token_accuracy": 0.8850173056125641, |
| "step": 181 |
| }, |
| { |
| "epoch": 1.064516129032258, |
| "grad_norm": 2.31061284700661, |
| "learning_rate": 3.9442316104759955e-05, |
| "loss": 0.3876, |
| "mean_token_accuracy": 0.8916988000273705, |
| "step": 182 |
| }, |
| { |
| "epoch": 1.0703812316715542, |
| "grad_norm": 1.8531473859414216, |
| "learning_rate": 3.943381443793994e-05, |
| "loss": 0.4046, |
| "mean_token_accuracy": 0.8912115767598152, |
| "step": 183 |
| }, |
| { |
| "epoch": 1.0762463343108504, |
| "grad_norm": 2.2566644664782145, |
| "learning_rate": 3.9425249493414585e-05, |
| "loss": 0.479, |
| "mean_token_accuracy": 0.8574677929282188, |
| "step": 184 |
| }, |
| { |
| "epoch": 1.0821114369501466, |
| "grad_norm": 2.0447795712362664, |
| "learning_rate": 3.941662130227118e-05, |
| "loss": 0.5012, |
| "mean_token_accuracy": 0.8605052158236504, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.0879765395894427, |
| "grad_norm": 2.0252956397987494, |
| "learning_rate": 3.940792989582654e-05, |
| "loss": 0.4011, |
| "mean_token_accuracy": 0.8870269060134888, |
| "step": 186 |
| }, |
| { |
| "epoch": 1.093841642228739, |
| "grad_norm": 2.1370096750662317, |
| "learning_rate": 3.939917530562701e-05, |
| "loss": 0.3308, |
| "mean_token_accuracy": 0.9050007611513138, |
| "step": 187 |
| }, |
| { |
| "epoch": 1.099706744868035, |
| "grad_norm": 2.0265811605099846, |
| "learning_rate": 3.939035756344818e-05, |
| "loss": 0.3665, |
| "mean_token_accuracy": 0.898661196231842, |
| "step": 188 |
| }, |
| { |
| "epoch": 1.1055718475073313, |
| "grad_norm": 1.952280542383211, |
| "learning_rate": 3.93814767012949e-05, |
| "loss": 0.3688, |
| "mean_token_accuracy": 0.8879161328077316, |
| "step": 189 |
| }, |
| { |
| "epoch": 1.1114369501466275, |
| "grad_norm": 1.7005130946868734, |
| "learning_rate": 3.937253275140113e-05, |
| "loss": 0.2879, |
| "mean_token_accuracy": 0.915998600423336, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.1173020527859236, |
| "grad_norm": 1.8692102303872629, |
| "learning_rate": 3.936352574622978e-05, |
| "loss": 0.2632, |
| "mean_token_accuracy": 0.9168166071176529, |
| "step": 191 |
| }, |
| { |
| "epoch": 1.1231671554252198, |
| "grad_norm": 1.4636789459840258, |
| "learning_rate": 3.9354455718472646e-05, |
| "loss": 0.3907, |
| "mean_token_accuracy": 0.890878938138485, |
| "step": 192 |
| }, |
| { |
| "epoch": 1.129032258064516, |
| "grad_norm": 2.221927967255573, |
| "learning_rate": 3.934532270105026e-05, |
| "loss": 0.4421, |
| "mean_token_accuracy": 0.8873759284615517, |
| "step": 193 |
| }, |
| { |
| "epoch": 1.1348973607038122, |
| "grad_norm": 2.370072341257091, |
| "learning_rate": 3.933612672711179e-05, |
| "loss": 0.3847, |
| "mean_token_accuracy": 0.8896044939756393, |
| "step": 194 |
| }, |
| { |
| "epoch": 1.1407624633431086, |
| "grad_norm": 1.857139188636865, |
| "learning_rate": 3.9326867830034915e-05, |
| "loss": 0.4143, |
| "mean_token_accuracy": 0.8805570974946022, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.1466275659824048, |
| "grad_norm": 1.8437744521798194, |
| "learning_rate": 3.931754604342568e-05, |
| "loss": 0.3271, |
| "mean_token_accuracy": 0.8968425765633583, |
| "step": 196 |
| }, |
| { |
| "epoch": 1.152492668621701, |
| "grad_norm": 1.8607108031680868, |
| "learning_rate": 3.930816140111842e-05, |
| "loss": 0.2857, |
| "mean_token_accuracy": 0.9045360758900642, |
| "step": 197 |
| }, |
| { |
| "epoch": 1.1583577712609971, |
| "grad_norm": 1.9508835791170454, |
| "learning_rate": 3.929871393717558e-05, |
| "loss": 0.3669, |
| "mean_token_accuracy": 0.9067378118634224, |
| "step": 198 |
| }, |
| { |
| "epoch": 1.1642228739002933, |
| "grad_norm": 2.0949010077945265, |
| "learning_rate": 3.9289203685887644e-05, |
| "loss": 0.4208, |
| "mean_token_accuracy": 0.8803550601005554, |
| "step": 199 |
| }, |
| { |
| "epoch": 1.1700879765395895, |
| "grad_norm": 2.085118395713445, |
| "learning_rate": 3.927963068177299e-05, |
| "loss": 0.4436, |
| "mean_token_accuracy": 0.8708969727158546, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1759530791788857, |
| "grad_norm": 2.1164241199376157, |
| "learning_rate": 3.926999495957775e-05, |
| "loss": 0.5082, |
| "mean_token_accuracy": 0.8535888493061066, |
| "step": 201 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 2.13206613518577, |
| "learning_rate": 3.9260296554275704e-05, |
| "loss": 0.5362, |
| "mean_token_accuracy": 0.8581036180257797, |
| "step": 202 |
| }, |
| { |
| "epoch": 1.187683284457478, |
| "grad_norm": 2.1096851845586047, |
| "learning_rate": 3.925053550106815e-05, |
| "loss": 0.3643, |
| "mean_token_accuracy": 0.894468292593956, |
| "step": 203 |
| }, |
| { |
| "epoch": 1.1935483870967742, |
| "grad_norm": 1.9205106894225823, |
| "learning_rate": 3.9240711835383766e-05, |
| "loss": 0.3395, |
| "mean_token_accuracy": 0.8946530520915985, |
| "step": 204 |
| }, |
| { |
| "epoch": 1.1994134897360704, |
| "grad_norm": 1.9233142739706681, |
| "learning_rate": 3.9230825592878494e-05, |
| "loss": 0.3717, |
| "mean_token_accuracy": 0.895426020026207, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.2052785923753666, |
| "grad_norm": 2.0226450173120747, |
| "learning_rate": 3.92208768094354e-05, |
| "loss": 0.3037, |
| "mean_token_accuracy": 0.9123189970850945, |
| "step": 206 |
| }, |
| { |
| "epoch": 1.2111436950146628, |
| "grad_norm": 1.8525205465171763, |
| "learning_rate": 3.921086552116455e-05, |
| "loss": 0.3298, |
| "mean_token_accuracy": 0.9004262015223503, |
| "step": 207 |
| }, |
| { |
| "epoch": 1.217008797653959, |
| "grad_norm": 2.01008712513797, |
| "learning_rate": 3.920079176440288e-05, |
| "loss": 0.3022, |
| "mean_token_accuracy": 0.9123654365539551, |
| "step": 208 |
| }, |
| { |
| "epoch": 1.2228739002932552, |
| "grad_norm": 2.085903024978829, |
| "learning_rate": 3.9190655575714045e-05, |
| "loss": 0.4884, |
| "mean_token_accuracy": 0.8751334249973297, |
| "step": 209 |
| }, |
| { |
| "epoch": 1.2287390029325513, |
| "grad_norm": 2.429563569008283, |
| "learning_rate": 3.918045699188833e-05, |
| "loss": 0.3692, |
| "mean_token_accuracy": 0.8923944160342216, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.2346041055718475, |
| "grad_norm": 2.0242830825921394, |
| "learning_rate": 3.9170196049942474e-05, |
| "loss": 0.3363, |
| "mean_token_accuracy": 0.9068214148283005, |
| "step": 211 |
| }, |
| { |
| "epoch": 1.2404692082111437, |
| "grad_norm": 1.7665849526519697, |
| "learning_rate": 3.915987278711954e-05, |
| "loss": 0.3032, |
| "mean_token_accuracy": 0.9094932749867439, |
| "step": 212 |
| }, |
| { |
| "epoch": 1.2463343108504399, |
| "grad_norm": 1.6859984756333792, |
| "learning_rate": 3.914948724088883e-05, |
| "loss": 0.4464, |
| "mean_token_accuracy": 0.8826745226979256, |
| "step": 213 |
| }, |
| { |
| "epoch": 1.252199413489736, |
| "grad_norm": 2.107291121286409, |
| "learning_rate": 3.913903944894565e-05, |
| "loss": 0.385, |
| "mean_token_accuracy": 0.8863528296351433, |
| "step": 214 |
| }, |
| { |
| "epoch": 1.2580645161290323, |
| "grad_norm": 1.731785903224652, |
| "learning_rate": 3.912852944921129e-05, |
| "loss": 0.3462, |
| "mean_token_accuracy": 0.9012412056326866, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.2639296187683284, |
| "grad_norm": 2.137318311123959, |
| "learning_rate": 3.911795727983279e-05, |
| "loss": 0.3789, |
| "mean_token_accuracy": 0.8955278024077415, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.2697947214076246, |
| "grad_norm": 2.056102679528605, |
| "learning_rate": 3.910732297918285e-05, |
| "loss": 0.4184, |
| "mean_token_accuracy": 0.8876356407999992, |
| "step": 217 |
| }, |
| { |
| "epoch": 1.2756598240469208, |
| "grad_norm": 2.1522822755480475, |
| "learning_rate": 3.90966265858597e-05, |
| "loss": 0.4578, |
| "mean_token_accuracy": 0.8790669366717339, |
| "step": 218 |
| }, |
| { |
| "epoch": 1.281524926686217, |
| "grad_norm": 2.2044287057502054, |
| "learning_rate": 3.908586813868693e-05, |
| "loss": 0.4495, |
| "mean_token_accuracy": 0.880668930709362, |
| "step": 219 |
| }, |
| { |
| "epoch": 1.2873900293255132, |
| "grad_norm": 2.1039486823285136, |
| "learning_rate": 3.9075047676713354e-05, |
| "loss": 0.4446, |
| "mean_token_accuracy": 0.8780560865998268, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.2932551319648093, |
| "grad_norm": 2.154180937578927, |
| "learning_rate": 3.9064165239212874e-05, |
| "loss": 0.3996, |
| "mean_token_accuracy": 0.8869764432311058, |
| "step": 221 |
| }, |
| { |
| "epoch": 1.2991202346041055, |
| "grad_norm": 1.924290765487603, |
| "learning_rate": 3.905322086568434e-05, |
| "loss": 0.4499, |
| "mean_token_accuracy": 0.883093573153019, |
| "step": 222 |
| }, |
| { |
| "epoch": 1.3049853372434017, |
| "grad_norm": 2.2702727232826745, |
| "learning_rate": 3.904221459585142e-05, |
| "loss": 0.3775, |
| "mean_token_accuracy": 0.889284610748291, |
| "step": 223 |
| }, |
| { |
| "epoch": 1.310850439882698, |
| "grad_norm": 2.4413459555324457, |
| "learning_rate": 3.903114646966242e-05, |
| "loss": 0.4279, |
| "mean_token_accuracy": 0.8820584490895271, |
| "step": 224 |
| }, |
| { |
| "epoch": 1.316715542521994, |
| "grad_norm": 1.6910433578113089, |
| "learning_rate": 3.9020016527290166e-05, |
| "loss": 0.3893, |
| "mean_token_accuracy": 0.8818121626973152, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.3225806451612903, |
| "grad_norm": 1.7243062281355852, |
| "learning_rate": 3.900882480913185e-05, |
| "loss": 0.2944, |
| "mean_token_accuracy": 0.9121311828494072, |
| "step": 226 |
| }, |
| { |
| "epoch": 1.3284457478005864, |
| "grad_norm": 2.090346610417419, |
| "learning_rate": 3.899757135580891e-05, |
| "loss": 0.4818, |
| "mean_token_accuracy": 0.8721955120563507, |
| "step": 227 |
| }, |
| { |
| "epoch": 1.3343108504398826, |
| "grad_norm": 1.988732267461751, |
| "learning_rate": 3.898625620816681e-05, |
| "loss": 0.3523, |
| "mean_token_accuracy": 0.8897998854517937, |
| "step": 228 |
| }, |
| { |
| "epoch": 1.3401759530791788, |
| "grad_norm": 2.061302818576063, |
| "learning_rate": 3.8974879407275e-05, |
| "loss": 0.5068, |
| "mean_token_accuracy": 0.8575932830572128, |
| "step": 229 |
| }, |
| { |
| "epoch": 1.3460410557184752, |
| "grad_norm": 2.242260225182611, |
| "learning_rate": 3.896344099442663e-05, |
| "loss": 0.3596, |
| "mean_token_accuracy": 0.8998804241418839, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.3519061583577714, |
| "grad_norm": 1.847107530517423, |
| "learning_rate": 3.895194101113855e-05, |
| "loss": 0.3204, |
| "mean_token_accuracy": 0.885312870144844, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.3577712609970676, |
| "grad_norm": 1.844656842651701, |
| "learning_rate": 3.894037949915104e-05, |
| "loss": 0.3592, |
| "mean_token_accuracy": 0.9094949513673782, |
| "step": 232 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 1.653499557561736, |
| "learning_rate": 3.8928756500427735e-05, |
| "loss": 0.3537, |
| "mean_token_accuracy": 0.8922702744603157, |
| "step": 233 |
| }, |
| { |
| "epoch": 1.36950146627566, |
| "grad_norm": 1.8328249166634853, |
| "learning_rate": 3.89170720571554e-05, |
| "loss": 0.3317, |
| "mean_token_accuracy": 0.9058214798569679, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.3753665689149561, |
| "grad_norm": 1.8665975142042839, |
| "learning_rate": 3.890532621174387e-05, |
| "loss": 0.3413, |
| "mean_token_accuracy": 0.898667685687542, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.3812316715542523, |
| "grad_norm": 1.6996356173562472, |
| "learning_rate": 3.8893519006825806e-05, |
| "loss": 0.3258, |
| "mean_token_accuracy": 0.9047993496060371, |
| "step": 236 |
| }, |
| { |
| "epoch": 1.3870967741935485, |
| "grad_norm": 1.950666656245651, |
| "learning_rate": 3.88816504852566e-05, |
| "loss": 0.3437, |
| "mean_token_accuracy": 0.9000433012843132, |
| "step": 237 |
| }, |
| { |
| "epoch": 1.3929618768328447, |
| "grad_norm": 1.9752405137217386, |
| "learning_rate": 3.886972069011419e-05, |
| "loss": 0.5516, |
| "mean_token_accuracy": 0.8599549755454063, |
| "step": 238 |
| }, |
| { |
| "epoch": 1.3988269794721409, |
| "grad_norm": 2.4127549070414838, |
| "learning_rate": 3.885772966469891e-05, |
| "loss": 0.3559, |
| "mean_token_accuracy": 0.893404632806778, |
| "step": 239 |
| }, |
| { |
| "epoch": 1.404692082111437, |
| "grad_norm": 1.911059959976087, |
| "learning_rate": 3.884567745253335e-05, |
| "loss": 0.2826, |
| "mean_token_accuracy": 0.9134182780981064, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.4105571847507332, |
| "grad_norm": 1.7911171144834646, |
| "learning_rate": 3.8833564097362157e-05, |
| "loss": 0.4307, |
| "mean_token_accuracy": 0.8844648599624634, |
| "step": 241 |
| }, |
| { |
| "epoch": 1.4164222873900294, |
| "grad_norm": 1.6351845128869422, |
| "learning_rate": 3.8821389643151924e-05, |
| "loss": 0.2718, |
| "mean_token_accuracy": 0.9180882722139359, |
| "step": 242 |
| }, |
| { |
| "epoch": 1.4222873900293256, |
| "grad_norm": 1.8589530261198506, |
| "learning_rate": 3.880915413409102e-05, |
| "loss": 0.3403, |
| "mean_token_accuracy": 0.9056767523288727, |
| "step": 243 |
| }, |
| { |
| "epoch": 1.4281524926686218, |
| "grad_norm": 1.7521182715832206, |
| "learning_rate": 3.879685761458938e-05, |
| "loss": 0.4686, |
| "mean_token_accuracy": 0.8556941673159599, |
| "step": 244 |
| }, |
| { |
| "epoch": 1.434017595307918, |
| "grad_norm": 1.9719842940855452, |
| "learning_rate": 3.8784500129278405e-05, |
| "loss": 0.2848, |
| "mean_token_accuracy": 0.9201192110776901, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.4398826979472141, |
| "grad_norm": 1.8790574357314227, |
| "learning_rate": 3.877208172301079e-05, |
| "loss": 0.4605, |
| "mean_token_accuracy": 0.8656576499342918, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.4457478005865103, |
| "grad_norm": 1.8025911112786197, |
| "learning_rate": 3.875960244086032e-05, |
| "loss": 0.3391, |
| "mean_token_accuracy": 0.9012917503714561, |
| "step": 247 |
| }, |
| { |
| "epoch": 1.4516129032258065, |
| "grad_norm": 1.801300852253163, |
| "learning_rate": 3.8747062328121756e-05, |
| "loss": 0.378, |
| "mean_token_accuracy": 0.9069185331463814, |
| "step": 248 |
| }, |
| { |
| "epoch": 1.4574780058651027, |
| "grad_norm": 1.534353901888919, |
| "learning_rate": 3.873446143031064e-05, |
| "loss": 0.2786, |
| "mean_token_accuracy": 0.9182317852973938, |
| "step": 249 |
| }, |
| { |
| "epoch": 1.4633431085043989, |
| "grad_norm": 1.6153260323031022, |
| "learning_rate": 3.872179979316314e-05, |
| "loss": 0.2901, |
| "mean_token_accuracy": 0.9126993268728256, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.469208211143695, |
| "grad_norm": 1.4971841035217601, |
| "learning_rate": 3.870907746263589e-05, |
| "loss": 0.2543, |
| "mean_token_accuracy": 0.9198986664414406, |
| "step": 251 |
| }, |
| { |
| "epoch": 1.4750733137829912, |
| "grad_norm": 1.6526746946220452, |
| "learning_rate": 3.869629448490582e-05, |
| "loss": 0.3306, |
| "mean_token_accuracy": 0.9064493998885155, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.4809384164222874, |
| "grad_norm": 1.622995160750932, |
| "learning_rate": 3.868345090636995e-05, |
| "loss": 0.3715, |
| "mean_token_accuracy": 0.9039052128791809, |
| "step": 253 |
| }, |
| { |
| "epoch": 1.4868035190615836, |
| "grad_norm": 1.9020619860495158, |
| "learning_rate": 3.867054677364531e-05, |
| "loss": 0.3454, |
| "mean_token_accuracy": 0.8969385549426079, |
| "step": 254 |
| }, |
| { |
| "epoch": 1.4926686217008798, |
| "grad_norm": 1.6271978444969855, |
| "learning_rate": 3.865758213356868e-05, |
| "loss": 0.3595, |
| "mean_token_accuracy": 0.8911759555339813, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.498533724340176, |
| "grad_norm": 1.9095375703624875, |
| "learning_rate": 3.8644557033196456e-05, |
| "loss": 0.344, |
| "mean_token_accuracy": 0.8955858647823334, |
| "step": 256 |
| }, |
| { |
| "epoch": 1.5043988269794721, |
| "grad_norm": 1.7428359018038488, |
| "learning_rate": 3.8631471519804514e-05, |
| "loss": 0.3832, |
| "mean_token_accuracy": 0.8968099281191826, |
| "step": 257 |
| }, |
| { |
| "epoch": 1.5102639296187683, |
| "grad_norm": 1.862424323093678, |
| "learning_rate": 3.861832564088797e-05, |
| "loss": 0.414, |
| "mean_token_accuracy": 0.8887148573994637, |
| "step": 258 |
| }, |
| { |
| "epoch": 1.5161290322580645, |
| "grad_norm": 1.9872329397145905, |
| "learning_rate": 3.860511944416105e-05, |
| "loss": 0.2824, |
| "mean_token_accuracy": 0.9190465062856674, |
| "step": 259 |
| }, |
| { |
| "epoch": 1.5219941348973607, |
| "grad_norm": 1.7282818347301152, |
| "learning_rate": 3.859185297755693e-05, |
| "loss": 0.2932, |
| "mean_token_accuracy": 0.9137580618262291, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.5278592375366569, |
| "grad_norm": 1.5338018657108714, |
| "learning_rate": 3.857852628922751e-05, |
| "loss": 0.2535, |
| "mean_token_accuracy": 0.9256049245595932, |
| "step": 261 |
| }, |
| { |
| "epoch": 1.533724340175953, |
| "grad_norm": 1.9982996544252496, |
| "learning_rate": 3.856513942754329e-05, |
| "loss": 0.3044, |
| "mean_token_accuracy": 0.9065937474370003, |
| "step": 262 |
| }, |
| { |
| "epoch": 1.5395894428152492, |
| "grad_norm": 1.6882075733622859, |
| "learning_rate": 3.8551692441093183e-05, |
| "loss": 0.224, |
| "mean_token_accuracy": 0.9296763613820076, |
| "step": 263 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 1.6550207607165734, |
| "learning_rate": 3.85381853786843e-05, |
| "loss": 0.4096, |
| "mean_token_accuracy": 0.8737977668642998, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.5513196480938416, |
| "grad_norm": 1.9251868350275612, |
| "learning_rate": 3.852461828934184e-05, |
| "loss": 0.3813, |
| "mean_token_accuracy": 0.8981966599822044, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.5571847507331378, |
| "grad_norm": 1.8470903871443582, |
| "learning_rate": 3.851099122230885e-05, |
| "loss": 0.2921, |
| "mean_token_accuracy": 0.9101375266909599, |
| "step": 266 |
| }, |
| { |
| "epoch": 1.563049853372434, |
| "grad_norm": 1.399781309432104, |
| "learning_rate": 3.849730422704608e-05, |
| "loss": 0.4117, |
| "mean_token_accuracy": 0.8910598680377007, |
| "step": 267 |
| }, |
| { |
| "epoch": 1.5689149560117301, |
| "grad_norm": 1.9099984044071514, |
| "learning_rate": 3.84835573532318e-05, |
| "loss": 0.2574, |
| "mean_token_accuracy": 0.9176947250962257, |
| "step": 268 |
| }, |
| { |
| "epoch": 1.5747800586510263, |
| "grad_norm": 1.6517764815366145, |
| "learning_rate": 3.84697506507616e-05, |
| "loss": 0.3905, |
| "mean_token_accuracy": 0.8897673636674881, |
| "step": 269 |
| }, |
| { |
| "epoch": 1.5806451612903225, |
| "grad_norm": 2.119009041143675, |
| "learning_rate": 3.845588416974824e-05, |
| "loss": 0.4224, |
| "mean_token_accuracy": 0.8940696120262146, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.5865102639296187, |
| "grad_norm": 1.9339959130871265, |
| "learning_rate": 3.844195796052144e-05, |
| "loss": 0.3438, |
| "mean_token_accuracy": 0.9041855335235596, |
| "step": 271 |
| }, |
| { |
| "epoch": 1.5923753665689149, |
| "grad_norm": 1.640513540139655, |
| "learning_rate": 3.8427972073627724e-05, |
| "loss": 0.4909, |
| "mean_token_accuracy": 0.867702804505825, |
| "step": 272 |
| }, |
| { |
| "epoch": 1.598240469208211, |
| "grad_norm": 1.9285791207634029, |
| "learning_rate": 3.841392655983021e-05, |
| "loss": 0.2348, |
| "mean_token_accuracy": 0.9315564408898354, |
| "step": 273 |
| }, |
| { |
| "epoch": 1.6041055718475072, |
| "grad_norm": 1.3040809643177875, |
| "learning_rate": 3.8399821470108444e-05, |
| "loss": 0.1918, |
| "mean_token_accuracy": 0.9407966360449791, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.6099706744868034, |
| "grad_norm": 1.8717232958282308, |
| "learning_rate": 3.838565685565819e-05, |
| "loss": 0.4585, |
| "mean_token_accuracy": 0.878320649266243, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.6158357771260996, |
| "grad_norm": 1.9125488044957306, |
| "learning_rate": 3.8371432767891295e-05, |
| "loss": 0.3633, |
| "mean_token_accuracy": 0.9053328037261963, |
| "step": 276 |
| }, |
| { |
| "epoch": 1.6217008797653958, |
| "grad_norm": 1.7227423517526814, |
| "learning_rate": 3.8357149258435444e-05, |
| "loss": 0.2805, |
| "mean_token_accuracy": 0.919714592397213, |
| "step": 277 |
| }, |
| { |
| "epoch": 1.627565982404692, |
| "grad_norm": 1.6693426207067774, |
| "learning_rate": 3.8342806379134005e-05, |
| "loss": 0.4284, |
| "mean_token_accuracy": 0.8809763565659523, |
| "step": 278 |
| }, |
| { |
| "epoch": 1.6334310850439882, |
| "grad_norm": 1.8397487618596386, |
| "learning_rate": 3.8328404182045854e-05, |
| "loss": 0.3692, |
| "mean_token_accuracy": 0.9018078520894051, |
| "step": 279 |
| }, |
| { |
| "epoch": 1.6392961876832843, |
| "grad_norm": 2.0516798648476002, |
| "learning_rate": 3.831394271944512e-05, |
| "loss": 0.3575, |
| "mean_token_accuracy": 0.9079688414931297, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.6451612903225805, |
| "grad_norm": 1.7909788776442834, |
| "learning_rate": 3.82994220438211e-05, |
| "loss": 0.3413, |
| "mean_token_accuracy": 0.8984247669577599, |
| "step": 281 |
| }, |
| { |
| "epoch": 1.6510263929618767, |
| "grad_norm": 1.907207226886229, |
| "learning_rate": 3.828484220787797e-05, |
| "loss": 0.3581, |
| "mean_token_accuracy": 0.899262860417366, |
| "step": 282 |
| }, |
| { |
| "epoch": 1.6568914956011729, |
| "grad_norm": 1.9715579318688201, |
| "learning_rate": 3.8270203264534644e-05, |
| "loss": 0.4442, |
| "mean_token_accuracy": 0.8822287917137146, |
| "step": 283 |
| }, |
| { |
| "epoch": 1.662756598240469, |
| "grad_norm": 1.6457253264182927, |
| "learning_rate": 3.8255505266924585e-05, |
| "loss": 0.3476, |
| "mean_token_accuracy": 0.8972783535718918, |
| "step": 284 |
| }, |
| { |
| "epoch": 1.6686217008797652, |
| "grad_norm": 1.4827534514844065, |
| "learning_rate": 3.824074826839557e-05, |
| "loss": 0.276, |
| "mean_token_accuracy": 0.9249418452382088, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.6744868035190614, |
| "grad_norm": 2.175526808689669, |
| "learning_rate": 3.822593232250956e-05, |
| "loss": 0.4903, |
| "mean_token_accuracy": 0.8697306215763092, |
| "step": 286 |
| }, |
| { |
| "epoch": 1.6803519061583576, |
| "grad_norm": 2.021289404237392, |
| "learning_rate": 3.8211057483042446e-05, |
| "loss": 0.504, |
| "mean_token_accuracy": 0.8762414082884789, |
| "step": 287 |
| }, |
| { |
| "epoch": 1.6862170087976538, |
| "grad_norm": 1.7314992545258114, |
| "learning_rate": 3.8196123803983895e-05, |
| "loss": 0.3522, |
| "mean_token_accuracy": 0.8997413292527199, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.6920821114369502, |
| "grad_norm": 1.8603560940766846, |
| "learning_rate": 3.818113133953712e-05, |
| "loss": 0.3271, |
| "mean_token_accuracy": 0.9100041314959526, |
| "step": 289 |
| }, |
| { |
| "epoch": 1.6979472140762464, |
| "grad_norm": 1.4966872907556552, |
| "learning_rate": 3.816608014411872e-05, |
| "loss": 0.2537, |
| "mean_token_accuracy": 0.9245190322399139, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.7038123167155426, |
| "grad_norm": 1.603750263252283, |
| "learning_rate": 3.815097027235845e-05, |
| "loss": 0.3494, |
| "mean_token_accuracy": 0.8979176208376884, |
| "step": 291 |
| }, |
| { |
| "epoch": 1.7096774193548387, |
| "grad_norm": 1.8283044408892475, |
| "learning_rate": 3.813580177909906e-05, |
| "loss": 0.2734, |
| "mean_token_accuracy": 0.9121185839176178, |
| "step": 292 |
| }, |
| { |
| "epoch": 1.715542521994135, |
| "grad_norm": 1.3502432363899728, |
| "learning_rate": 3.8120574719396023e-05, |
| "loss": 0.2877, |
| "mean_token_accuracy": 0.9239327982068062, |
| "step": 293 |
| }, |
| { |
| "epoch": 1.721407624633431, |
| "grad_norm": 2.027539954165466, |
| "learning_rate": 3.810528914851745e-05, |
| "loss": 0.4155, |
| "mean_token_accuracy": 0.8827510923147202, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 1.7186579918501383, |
| "learning_rate": 3.808994512194376e-05, |
| "loss": 0.3796, |
| "mean_token_accuracy": 0.8875857517123222, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.7331378299120235, |
| "grad_norm": 1.813081462480938, |
| "learning_rate": 3.807454269536758e-05, |
| "loss": 0.3981, |
| "mean_token_accuracy": 0.8904116526246071, |
| "step": 296 |
| }, |
| { |
| "epoch": 1.7390029325513197, |
| "grad_norm": 1.703513451013957, |
| "learning_rate": 3.805908192469351e-05, |
| "loss": 0.2559, |
| "mean_token_accuracy": 0.9196176305413246, |
| "step": 297 |
| }, |
| { |
| "epoch": 1.7448680351906158, |
| "grad_norm": 1.5203584075310517, |
| "learning_rate": 3.80435628660379e-05, |
| "loss": 0.3658, |
| "mean_token_accuracy": 0.8972667753696442, |
| "step": 298 |
| }, |
| { |
| "epoch": 1.750733137829912, |
| "grad_norm": 1.4984555872298189, |
| "learning_rate": 3.802798557572867e-05, |
| "loss": 0.361, |
| "mean_token_accuracy": 0.8996458873152733, |
| "step": 299 |
| }, |
| { |
| "epoch": 1.7565982404692082, |
| "grad_norm": 1.7784418749764175, |
| "learning_rate": 3.801235011030506e-05, |
| "loss": 0.349, |
| "mean_token_accuracy": 0.9058357775211334, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.7624633431085044, |
| "grad_norm": 1.6134415362903494, |
| "learning_rate": 3.799665652651754e-05, |
| "loss": 0.2183, |
| "mean_token_accuracy": 0.9335889741778374, |
| "step": 301 |
| }, |
| { |
| "epoch": 1.7683284457478006, |
| "grad_norm": 1.41824274486332, |
| "learning_rate": 3.7980904881327446e-05, |
| "loss": 0.2875, |
| "mean_token_accuracy": 0.9194483831524849, |
| "step": 302 |
| }, |
| { |
| "epoch": 1.7741935483870968, |
| "grad_norm": 1.6306057175263466, |
| "learning_rate": 3.796509523190691e-05, |
| "loss": 0.3065, |
| "mean_token_accuracy": 0.9074099063873291, |
| "step": 303 |
| }, |
| { |
| "epoch": 1.780058651026393, |
| "grad_norm": 1.3490534339890907, |
| "learning_rate": 3.794922763563857e-05, |
| "loss": 0.249, |
| "mean_token_accuracy": 0.9284609705209732, |
| "step": 304 |
| }, |
| { |
| "epoch": 1.7859237536656891, |
| "grad_norm": 1.800371852919932, |
| "learning_rate": 3.793330215011538e-05, |
| "loss": 0.3353, |
| "mean_token_accuracy": 0.9221402704715729, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.7917888563049853, |
| "grad_norm": 1.6498676734395081, |
| "learning_rate": 3.791731883314043e-05, |
| "loss": 0.3088, |
| "mean_token_accuracy": 0.9110808372497559, |
| "step": 306 |
| }, |
| { |
| "epoch": 1.7976539589442815, |
| "grad_norm": 1.7165297415750906, |
| "learning_rate": 3.790127774272671e-05, |
| "loss": 0.2658, |
| "mean_token_accuracy": 0.9218085780739784, |
| "step": 307 |
| }, |
| { |
| "epoch": 1.8035190615835777, |
| "grad_norm": 1.5710559635899641, |
| "learning_rate": 3.7885178937096884e-05, |
| "loss": 0.4084, |
| "mean_token_accuracy": 0.8922935128211975, |
| "step": 308 |
| }, |
| { |
| "epoch": 1.8093841642228738, |
| "grad_norm": 1.7141003007560607, |
| "learning_rate": 3.7869022474683125e-05, |
| "loss": 0.4542, |
| "mean_token_accuracy": 0.8909810185432434, |
| "step": 309 |
| }, |
| { |
| "epoch": 1.8152492668621703, |
| "grad_norm": 2.1651975563574406, |
| "learning_rate": 3.7852808414126876e-05, |
| "loss": 0.401, |
| "mean_token_accuracy": 0.8917931020259857, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.8211143695014664, |
| "grad_norm": 1.5322855424185167, |
| "learning_rate": 3.783653681427861e-05, |
| "loss": 0.2438, |
| "mean_token_accuracy": 0.9244765937328339, |
| "step": 311 |
| }, |
| { |
| "epoch": 1.8269794721407626, |
| "grad_norm": 1.5846288322829667, |
| "learning_rate": 3.7820207734197676e-05, |
| "loss": 0.3526, |
| "mean_token_accuracy": 0.9049504473805428, |
| "step": 312 |
| }, |
| { |
| "epoch": 1.8328445747800588, |
| "grad_norm": 1.689626483443562, |
| "learning_rate": 3.780382123315203e-05, |
| "loss": 0.2199, |
| "mean_token_accuracy": 0.9369524195790291, |
| "step": 313 |
| }, |
| { |
| "epoch": 1.838709677419355, |
| "grad_norm": 1.5158081896163202, |
| "learning_rate": 3.778737737061807e-05, |
| "loss": 0.3378, |
| "mean_token_accuracy": 0.9043772518634796, |
| "step": 314 |
| }, |
| { |
| "epoch": 1.8445747800586512, |
| "grad_norm": 1.550058792883986, |
| "learning_rate": 3.777087620628035e-05, |
| "loss": 0.2673, |
| "mean_token_accuracy": 0.9279494360089302, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.8504398826979473, |
| "grad_norm": 1.6597960206898577, |
| "learning_rate": 3.775431780003145e-05, |
| "loss": 0.2462, |
| "mean_token_accuracy": 0.9318157806992531, |
| "step": 316 |
| }, |
| { |
| "epoch": 1.8563049853372435, |
| "grad_norm": 1.4622011187254726, |
| "learning_rate": 3.7737702211971684e-05, |
| "loss": 0.2772, |
| "mean_token_accuracy": 0.929963655769825, |
| "step": 317 |
| }, |
| { |
| "epoch": 1.8621700879765397, |
| "grad_norm": 1.5151732843103733, |
| "learning_rate": 3.772102950240895e-05, |
| "loss": 0.2679, |
| "mean_token_accuracy": 0.931287556886673, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.868035190615836, |
| "grad_norm": 1.5891712041281862, |
| "learning_rate": 3.770429973185842e-05, |
| "loss": 0.3341, |
| "mean_token_accuracy": 0.9078937619924545, |
| "step": 319 |
| }, |
| { |
| "epoch": 1.873900293255132, |
| "grad_norm": 1.8744855927836221, |
| "learning_rate": 3.768751296104243e-05, |
| "loss": 0.2325, |
| "mean_token_accuracy": 0.9263536930084229, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.8797653958944283, |
| "grad_norm": 1.2684553166509498, |
| "learning_rate": 3.767066925089017e-05, |
| "loss": 0.3273, |
| "mean_token_accuracy": 0.9072131887078285, |
| "step": 321 |
| }, |
| { |
| "epoch": 1.8856304985337244, |
| "grad_norm": 1.5776419156712478, |
| "learning_rate": 3.765376866253749e-05, |
| "loss": 0.2212, |
| "mean_token_accuracy": 0.9262972101569176, |
| "step": 322 |
| }, |
| { |
| "epoch": 1.8914956011730206, |
| "grad_norm": 1.5061879986087867, |
| "learning_rate": 3.763681125732672e-05, |
| "loss": 0.2883, |
| "mean_token_accuracy": 0.9100302383303642, |
| "step": 323 |
| }, |
| { |
| "epoch": 1.8973607038123168, |
| "grad_norm": 1.6131493853591912, |
| "learning_rate": 3.7619797096806386e-05, |
| "loss": 0.322, |
| "mean_token_accuracy": 0.9105613902211189, |
| "step": 324 |
| }, |
| { |
| "epoch": 1.903225806451613, |
| "grad_norm": 1.563416189435815, |
| "learning_rate": 3.7602726242731016e-05, |
| "loss": 0.3532, |
| "mean_token_accuracy": 0.9058608040213585, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 1.600675087277008, |
| "learning_rate": 3.758559875706092e-05, |
| "loss": 0.2515, |
| "mean_token_accuracy": 0.9262616038322449, |
| "step": 326 |
| }, |
| { |
| "epoch": 1.9149560117302054, |
| "grad_norm": 1.4397417416715703, |
| "learning_rate": 3.756841470196195e-05, |
| "loss": 0.3584, |
| "mean_token_accuracy": 0.9060768559575081, |
| "step": 327 |
| }, |
| { |
| "epoch": 1.9208211143695015, |
| "grad_norm": 1.6091207177650233, |
| "learning_rate": 3.7551174139805284e-05, |
| "loss": 0.3848, |
| "mean_token_accuracy": 0.8916498497128487, |
| "step": 328 |
| }, |
| { |
| "epoch": 1.9266862170087977, |
| "grad_norm": 1.8405019636747775, |
| "learning_rate": 3.75338771331672e-05, |
| "loss": 0.3563, |
| "mean_token_accuracy": 0.8986505270004272, |
| "step": 329 |
| }, |
| { |
| "epoch": 1.932551319648094, |
| "grad_norm": 1.6744591407188665, |
| "learning_rate": 3.7516523744828856e-05, |
| "loss": 0.4076, |
| "mean_token_accuracy": 0.8903002217411995, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.93841642228739, |
| "grad_norm": 1.7844176464926413, |
| "learning_rate": 3.7499114037776036e-05, |
| "loss": 0.3237, |
| "mean_token_accuracy": 0.8996743708848953, |
| "step": 331 |
| }, |
| { |
| "epoch": 1.9442815249266863, |
| "grad_norm": 1.892031074058152, |
| "learning_rate": 3.748164807519894e-05, |
| "loss": 0.4614, |
| "mean_token_accuracy": 0.8785504251718521, |
| "step": 332 |
| }, |
| { |
| "epoch": 1.9501466275659824, |
| "grad_norm": 1.9529591014745988, |
| "learning_rate": 3.746412592049197e-05, |
| "loss": 0.3317, |
| "mean_token_accuracy": 0.9095030203461647, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.9560117302052786, |
| "grad_norm": 1.3361876397839005, |
| "learning_rate": 3.7446547637253464e-05, |
| "loss": 0.2158, |
| "mean_token_accuracy": 0.9386293217539787, |
| "step": 334 |
| }, |
| { |
| "epoch": 1.9618768328445748, |
| "grad_norm": 1.5896606700284657, |
| "learning_rate": 3.742891328928549e-05, |
| "loss": 0.3072, |
| "mean_token_accuracy": 0.9178111851215363, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.967741935483871, |
| "grad_norm": 1.5606940372882383, |
| "learning_rate": 3.74112229405936e-05, |
| "loss": 0.316, |
| "mean_token_accuracy": 0.9071382880210876, |
| "step": 336 |
| }, |
| { |
| "epoch": 1.9736070381231672, |
| "grad_norm": 1.6245220422058784, |
| "learning_rate": 3.739347665538664e-05, |
| "loss": 0.3286, |
| "mean_token_accuracy": 0.9116719961166382, |
| "step": 337 |
| }, |
| { |
| "epoch": 1.9794721407624634, |
| "grad_norm": 1.8517780202665928, |
| "learning_rate": 3.7375674498076445e-05, |
| "loss": 0.3867, |
| "mean_token_accuracy": 0.8904563412070274, |
| "step": 338 |
| }, |
| { |
| "epoch": 1.9853372434017595, |
| "grad_norm": 1.7036447018124885, |
| "learning_rate": 3.7357816533277646e-05, |
| "loss": 0.3053, |
| "mean_token_accuracy": 0.9213255569338799, |
| "step": 339 |
| }, |
| { |
| "epoch": 1.9912023460410557, |
| "grad_norm": 1.404790254341481, |
| "learning_rate": 3.733990282580745e-05, |
| "loss": 0.3073, |
| "mean_token_accuracy": 0.90599025785923, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.997067448680352, |
| "grad_norm": 1.7871327162492117, |
| "learning_rate": 3.732193344068539e-05, |
| "loss": 0.3151, |
| "mean_token_accuracy": 0.9118079468607903, |
| "step": 341 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.4692118190159413, |
| "learning_rate": 3.7303908443133054e-05, |
| "loss": 0.2212, |
| "mean_token_accuracy": 0.9288553893566132, |
| "step": 342 |
| }, |
| { |
| "epoch": 2.005865102639296, |
| "grad_norm": 1.476624660273671, |
| "learning_rate": 3.728582789857393e-05, |
| "loss": 0.2001, |
| "mean_token_accuracy": 0.9483243823051453, |
| "step": 343 |
| }, |
| { |
| "epoch": 2.0117302052785924, |
| "grad_norm": 1.503761647923481, |
| "learning_rate": 3.726769187263308e-05, |
| "loss": 0.2274, |
| "mean_token_accuracy": 0.9308255985379219, |
| "step": 344 |
| }, |
| { |
| "epoch": 2.0175953079178885, |
| "grad_norm": 1.1442273526640767, |
| "learning_rate": 3.724950043113695e-05, |
| "loss": 0.1528, |
| "mean_token_accuracy": 0.9552865400910378, |
| "step": 345 |
| }, |
| { |
| "epoch": 2.0234604105571847, |
| "grad_norm": 1.1676585793324792, |
| "learning_rate": 3.723125364011313e-05, |
| "loss": 0.1401, |
| "mean_token_accuracy": 0.959092803299427, |
| "step": 346 |
| }, |
| { |
| "epoch": 2.029325513196481, |
| "grad_norm": 1.4179806604734995, |
| "learning_rate": 3.7212951565790094e-05, |
| "loss": 0.1724, |
| "mean_token_accuracy": 0.9462388530373573, |
| "step": 347 |
| }, |
| { |
| "epoch": 2.035190615835777, |
| "grad_norm": 1.3565931025276359, |
| "learning_rate": 3.7194594274597e-05, |
| "loss": 0.1713, |
| "mean_token_accuracy": 0.9462545812129974, |
| "step": 348 |
| }, |
| { |
| "epoch": 2.0410557184750733, |
| "grad_norm": 2.0100162506170856, |
| "learning_rate": 3.7176181833163385e-05, |
| "loss": 0.214, |
| "mean_token_accuracy": 0.9363678023219109, |
| "step": 349 |
| }, |
| { |
| "epoch": 2.0469208211143695, |
| "grad_norm": 1.574439267468769, |
| "learning_rate": 3.7157714308318966e-05, |
| "loss": 0.1768, |
| "mean_token_accuracy": 0.9480359777808189, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.0527859237536656, |
| "grad_norm": 1.4723059029662238, |
| "learning_rate": 3.713919176709343e-05, |
| "loss": 0.2094, |
| "mean_token_accuracy": 0.942324809730053, |
| "step": 351 |
| }, |
| { |
| "epoch": 2.058651026392962, |
| "grad_norm": 1.5342137566871517, |
| "learning_rate": 3.712061427671609e-05, |
| "loss": 0.1612, |
| "mean_token_accuracy": 0.9546240866184235, |
| "step": 352 |
| }, |
| { |
| "epoch": 2.064516129032258, |
| "grad_norm": 1.468762510345496, |
| "learning_rate": 3.710198190461575e-05, |
| "loss": 0.1893, |
| "mean_token_accuracy": 0.9487204700708389, |
| "step": 353 |
| }, |
| { |
| "epoch": 2.070381231671554, |
| "grad_norm": 1.4106607901877921, |
| "learning_rate": 3.7083294718420394e-05, |
| "loss": 0.1829, |
| "mean_token_accuracy": 0.9452722370624542, |
| "step": 354 |
| }, |
| { |
| "epoch": 2.0762463343108504, |
| "grad_norm": 1.5971490830702397, |
| "learning_rate": 3.706455278595696e-05, |
| "loss": 0.1826, |
| "mean_token_accuracy": 0.9438930004835129, |
| "step": 355 |
| }, |
| { |
| "epoch": 2.0821114369501466, |
| "grad_norm": 1.4328050289867758, |
| "learning_rate": 3.7045756175251086e-05, |
| "loss": 0.1757, |
| "mean_token_accuracy": 0.9502169340848923, |
| "step": 356 |
| }, |
| { |
| "epoch": 2.0879765395894427, |
| "grad_norm": 1.3226133601725745, |
| "learning_rate": 3.7026904954526884e-05, |
| "loss": 0.1589, |
| "mean_token_accuracy": 0.949699193239212, |
| "step": 357 |
| }, |
| { |
| "epoch": 2.093841642228739, |
| "grad_norm": 1.302704971311971, |
| "learning_rate": 3.7007999192206676e-05, |
| "loss": 0.1498, |
| "mean_token_accuracy": 0.955219678580761, |
| "step": 358 |
| }, |
| { |
| "epoch": 2.099706744868035, |
| "grad_norm": 1.3221596689539326, |
| "learning_rate": 3.698903895691073e-05, |
| "loss": 0.1894, |
| "mean_token_accuracy": 0.9378139674663544, |
| "step": 359 |
| }, |
| { |
| "epoch": 2.1055718475073313, |
| "grad_norm": 1.5050554126622395, |
| "learning_rate": 3.697002431745706e-05, |
| "loss": 0.1808, |
| "mean_token_accuracy": 0.942346952855587, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.1114369501466275, |
| "grad_norm": 1.5953279006691845, |
| "learning_rate": 3.695095534286111e-05, |
| "loss": 0.2218, |
| "mean_token_accuracy": 0.9413799494504929, |
| "step": 361 |
| }, |
| { |
| "epoch": 2.1173020527859236, |
| "grad_norm": 1.4771134232796863, |
| "learning_rate": 3.693183210233557e-05, |
| "loss": 0.189, |
| "mean_token_accuracy": 0.9463675022125244, |
| "step": 362 |
| }, |
| { |
| "epoch": 2.12316715542522, |
| "grad_norm": 1.38647866538845, |
| "learning_rate": 3.691265466529007e-05, |
| "loss": 0.1821, |
| "mean_token_accuracy": 0.9421042799949646, |
| "step": 363 |
| }, |
| { |
| "epoch": 2.129032258064516, |
| "grad_norm": 1.362873233806283, |
| "learning_rate": 3.689342310133097e-05, |
| "loss": 0.1592, |
| "mean_token_accuracy": 0.9517010152339935, |
| "step": 364 |
| }, |
| { |
| "epoch": 2.134897360703812, |
| "grad_norm": 1.4294148599496252, |
| "learning_rate": 3.687413748026108e-05, |
| "loss": 0.1951, |
| "mean_token_accuracy": 0.9434895291924477, |
| "step": 365 |
| }, |
| { |
| "epoch": 2.1407624633431084, |
| "grad_norm": 1.3167525955804085, |
| "learning_rate": 3.68547978720794e-05, |
| "loss": 0.1779, |
| "mean_token_accuracy": 0.9462132379412651, |
| "step": 366 |
| }, |
| { |
| "epoch": 2.1466275659824046, |
| "grad_norm": 1.334685880079026, |
| "learning_rate": 3.683540434698093e-05, |
| "loss": 0.1653, |
| "mean_token_accuracy": 0.9485151618719101, |
| "step": 367 |
| }, |
| { |
| "epoch": 2.1524926686217007, |
| "grad_norm": 1.1362560129422759, |
| "learning_rate": 3.681595697535629e-05, |
| "loss": 0.1431, |
| "mean_token_accuracy": 0.9614577367901802, |
| "step": 368 |
| }, |
| { |
| "epoch": 2.158357771260997, |
| "grad_norm": 1.2719092502053326, |
| "learning_rate": 3.6796455827791614e-05, |
| "loss": 0.1641, |
| "mean_token_accuracy": 0.9526363462209702, |
| "step": 369 |
| }, |
| { |
| "epoch": 2.164222873900293, |
| "grad_norm": 1.4561156580126304, |
| "learning_rate": 3.677690097506819e-05, |
| "loss": 0.1771, |
| "mean_token_accuracy": 0.9508548080921173, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.1700879765395893, |
| "grad_norm": 1.355167178954715, |
| "learning_rate": 3.6757292488162224e-05, |
| "loss": 0.1812, |
| "mean_token_accuracy": 0.9459526911377907, |
| "step": 371 |
| }, |
| { |
| "epoch": 2.1759530791788855, |
| "grad_norm": 1.4755420760216644, |
| "learning_rate": 3.673763043824461e-05, |
| "loss": 0.2183, |
| "mean_token_accuracy": 0.9343624264001846, |
| "step": 372 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 1.4730527980876331, |
| "learning_rate": 3.671791489668065e-05, |
| "loss": 0.1958, |
| "mean_token_accuracy": 0.9429437816143036, |
| "step": 373 |
| }, |
| { |
| "epoch": 2.187683284457478, |
| "grad_norm": 1.1714314133219133, |
| "learning_rate": 3.6698145935029794e-05, |
| "loss": 0.1445, |
| "mean_token_accuracy": 0.9535733610391617, |
| "step": 374 |
| }, |
| { |
| "epoch": 2.193548387096774, |
| "grad_norm": 1.2427514759243454, |
| "learning_rate": 3.66783236250454e-05, |
| "loss": 0.1687, |
| "mean_token_accuracy": 0.946289099752903, |
| "step": 375 |
| }, |
| { |
| "epoch": 2.19941348973607, |
| "grad_norm": 1.475415652426242, |
| "learning_rate": 3.665844803867443e-05, |
| "loss": 0.2129, |
| "mean_token_accuracy": 0.9403799325227737, |
| "step": 376 |
| }, |
| { |
| "epoch": 2.2052785923753664, |
| "grad_norm": 1.428248135712194, |
| "learning_rate": 3.663851924805725e-05, |
| "loss": 0.1989, |
| "mean_token_accuracy": 0.9408678263425827, |
| "step": 377 |
| }, |
| { |
| "epoch": 2.2111436950146626, |
| "grad_norm": 1.4533859141194323, |
| "learning_rate": 3.66185373255273e-05, |
| "loss": 0.2005, |
| "mean_token_accuracy": 0.9400480091571808, |
| "step": 378 |
| }, |
| { |
| "epoch": 2.2170087976539588, |
| "grad_norm": 1.2568428196886394, |
| "learning_rate": 3.6598502343610906e-05, |
| "loss": 0.1588, |
| "mean_token_accuracy": 0.9535493031144142, |
| "step": 379 |
| }, |
| { |
| "epoch": 2.222873900293255, |
| "grad_norm": 1.7251468035919506, |
| "learning_rate": 3.657841437502697e-05, |
| "loss": 0.2436, |
| "mean_token_accuracy": 0.9211764186620712, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.228739002932551, |
| "grad_norm": 1.563747478750116, |
| "learning_rate": 3.6558273492686686e-05, |
| "loss": 0.1925, |
| "mean_token_accuracy": 0.9419304430484772, |
| "step": 381 |
| }, |
| { |
| "epoch": 2.2346041055718473, |
| "grad_norm": 1.3371515680969543, |
| "learning_rate": 3.6538079769693334e-05, |
| "loss": 0.1764, |
| "mean_token_accuracy": 0.9459211006760597, |
| "step": 382 |
| }, |
| { |
| "epoch": 2.2404692082111435, |
| "grad_norm": 1.1577027770973363, |
| "learning_rate": 3.6517833279341954e-05, |
| "loss": 0.144, |
| "mean_token_accuracy": 0.9560522958636284, |
| "step": 383 |
| }, |
| { |
| "epoch": 2.2463343108504397, |
| "grad_norm": 1.1804473461854166, |
| "learning_rate": 3.649753409511916e-05, |
| "loss": 0.1422, |
| "mean_token_accuracy": 0.9586736932396889, |
| "step": 384 |
| }, |
| { |
| "epoch": 2.252199413489736, |
| "grad_norm": 1.5316777495144922, |
| "learning_rate": 3.6477182290702766e-05, |
| "loss": 0.2218, |
| "mean_token_accuracy": 0.933185450732708, |
| "step": 385 |
| }, |
| { |
| "epoch": 2.258064516129032, |
| "grad_norm": 1.4337722711894096, |
| "learning_rate": 3.645677793996161e-05, |
| "loss": 0.1983, |
| "mean_token_accuracy": 0.9400441944599152, |
| "step": 386 |
| }, |
| { |
| "epoch": 2.263929618768328, |
| "grad_norm": 1.3355048384788264, |
| "learning_rate": 3.643632111695525e-05, |
| "loss": 0.1835, |
| "mean_token_accuracy": 0.9445948526263237, |
| "step": 387 |
| }, |
| { |
| "epoch": 2.2697947214076244, |
| "grad_norm": 1.4116132523940614, |
| "learning_rate": 3.6415811895933685e-05, |
| "loss": 0.1903, |
| "mean_token_accuracy": 0.9421262443065643, |
| "step": 388 |
| }, |
| { |
| "epoch": 2.2756598240469206, |
| "grad_norm": 1.1489874771022681, |
| "learning_rate": 3.639525035133712e-05, |
| "loss": 0.1434, |
| "mean_token_accuracy": 0.9581286609172821, |
| "step": 389 |
| }, |
| { |
| "epoch": 2.281524926686217, |
| "grad_norm": 1.5443270506707967, |
| "learning_rate": 3.637463655779563e-05, |
| "loss": 0.2251, |
| "mean_token_accuracy": 0.937995620071888, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.2873900293255134, |
| "grad_norm": 1.3016122311026777, |
| "learning_rate": 3.6353970590128975e-05, |
| "loss": 0.1619, |
| "mean_token_accuracy": 0.9526982828974724, |
| "step": 391 |
| }, |
| { |
| "epoch": 2.2932551319648096, |
| "grad_norm": 1.1825803045225631, |
| "learning_rate": 3.633325252334628e-05, |
| "loss": 0.1659, |
| "mean_token_accuracy": 0.9432104825973511, |
| "step": 392 |
| }, |
| { |
| "epoch": 2.2991202346041058, |
| "grad_norm": 1.4653068378575294, |
| "learning_rate": 3.6312482432645746e-05, |
| "loss": 0.2015, |
| "mean_token_accuracy": 0.9372165873646736, |
| "step": 393 |
| }, |
| { |
| "epoch": 2.304985337243402, |
| "grad_norm": 1.3865139735176901, |
| "learning_rate": 3.6291660393414414e-05, |
| "loss": 0.1633, |
| "mean_token_accuracy": 0.9534904658794403, |
| "step": 394 |
| }, |
| { |
| "epoch": 2.310850439882698, |
| "grad_norm": 1.332181176107831, |
| "learning_rate": 3.6270786481227885e-05, |
| "loss": 0.1759, |
| "mean_token_accuracy": 0.9474803134799004, |
| "step": 395 |
| }, |
| { |
| "epoch": 2.3167155425219943, |
| "grad_norm": 1.3868946979168462, |
| "learning_rate": 3.624986077185003e-05, |
| "loss": 0.1887, |
| "mean_token_accuracy": 0.9452441483736038, |
| "step": 396 |
| }, |
| { |
| "epoch": 2.3225806451612905, |
| "grad_norm": 1.1266308673977825, |
| "learning_rate": 3.622888334123272e-05, |
| "loss": 0.1576, |
| "mean_token_accuracy": 0.958634540438652, |
| "step": 397 |
| }, |
| { |
| "epoch": 2.3284457478005867, |
| "grad_norm": 1.1583104865991503, |
| "learning_rate": 3.620785426551555e-05, |
| "loss": 0.1652, |
| "mean_token_accuracy": 0.9511990696191788, |
| "step": 398 |
| }, |
| { |
| "epoch": 2.334310850439883, |
| "grad_norm": 1.290128290927979, |
| "learning_rate": 3.618677362102558e-05, |
| "loss": 0.1492, |
| "mean_token_accuracy": 0.9547437205910683, |
| "step": 399 |
| }, |
| { |
| "epoch": 2.340175953079179, |
| "grad_norm": 1.5975208805547034, |
| "learning_rate": 3.616564148427703e-05, |
| "loss": 0.1867, |
| "mean_token_accuracy": 0.9401877969503403, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.346041055718475, |
| "grad_norm": 1.4029390907999495, |
| "learning_rate": 3.614445793197103e-05, |
| "loss": 0.1675, |
| "mean_token_accuracy": 0.9511738941073418, |
| "step": 401 |
| }, |
| { |
| "epoch": 2.3519061583577714, |
| "grad_norm": 1.5974257452922849, |
| "learning_rate": 3.61232230409953e-05, |
| "loss": 0.176, |
| "mean_token_accuracy": 0.9497552961111069, |
| "step": 402 |
| }, |
| { |
| "epoch": 2.3577712609970676, |
| "grad_norm": 1.530210607178967, |
| "learning_rate": 3.6101936888423936e-05, |
| "loss": 0.1917, |
| "mean_token_accuracy": 0.9507608339190483, |
| "step": 403 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 2.509006214983105, |
| "learning_rate": 3.6080599551517076e-05, |
| "loss": 0.1982, |
| "mean_token_accuracy": 0.9404582604765892, |
| "step": 404 |
| }, |
| { |
| "epoch": 2.36950146627566, |
| "grad_norm": 1.5627934606392213, |
| "learning_rate": 3.605921110772063e-05, |
| "loss": 0.2118, |
| "mean_token_accuracy": 0.9388338625431061, |
| "step": 405 |
| }, |
| { |
| "epoch": 2.375366568914956, |
| "grad_norm": 1.3580342157157053, |
| "learning_rate": 3.603777163466601e-05, |
| "loss": 0.1774, |
| "mean_token_accuracy": 0.9472236335277557, |
| "step": 406 |
| }, |
| { |
| "epoch": 2.3812316715542523, |
| "grad_norm": 1.3490592728792703, |
| "learning_rate": 3.6016281210169844e-05, |
| "loss": 0.1825, |
| "mean_token_accuracy": 0.94171442091465, |
| "step": 407 |
| }, |
| { |
| "epoch": 2.3870967741935485, |
| "grad_norm": 1.3544855722262408, |
| "learning_rate": 3.599473991223369e-05, |
| "loss": 0.1729, |
| "mean_token_accuracy": 0.9484469667077065, |
| "step": 408 |
| }, |
| { |
| "epoch": 2.3929618768328447, |
| "grad_norm": 1.380080677011728, |
| "learning_rate": 3.5973147819043765e-05, |
| "loss": 0.1988, |
| "mean_token_accuracy": 0.9358495697379112, |
| "step": 409 |
| }, |
| { |
| "epoch": 2.398826979472141, |
| "grad_norm": 1.5440916647504026, |
| "learning_rate": 3.595150500897065e-05, |
| "loss": 0.215, |
| "mean_token_accuracy": 0.9350427612662315, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.404692082111437, |
| "grad_norm": 1.27541434637295, |
| "learning_rate": 3.5929811560569e-05, |
| "loss": 0.1812, |
| "mean_token_accuracy": 0.9499657303094864, |
| "step": 411 |
| }, |
| { |
| "epoch": 2.410557184750733, |
| "grad_norm": 1.198812240028181, |
| "learning_rate": 3.590806755257726e-05, |
| "loss": 0.1519, |
| "mean_token_accuracy": 0.9496930539608002, |
| "step": 412 |
| }, |
| { |
| "epoch": 2.4164222873900294, |
| "grad_norm": 1.1424990901176593, |
| "learning_rate": 3.5886273063917426e-05, |
| "loss": 0.161, |
| "mean_token_accuracy": 0.9473123177886009, |
| "step": 413 |
| }, |
| { |
| "epoch": 2.4222873900293256, |
| "grad_norm": 1.4649749934528322, |
| "learning_rate": 3.586442817369467e-05, |
| "loss": 0.2064, |
| "mean_token_accuracy": 0.9354598671197891, |
| "step": 414 |
| }, |
| { |
| "epoch": 2.4281524926686218, |
| "grad_norm": 1.1474037121371046, |
| "learning_rate": 3.5842532961197114e-05, |
| "loss": 0.1511, |
| "mean_token_accuracy": 0.9541265666484833, |
| "step": 415 |
| }, |
| { |
| "epoch": 2.434017595307918, |
| "grad_norm": 1.4617493541935012, |
| "learning_rate": 3.582058750589555e-05, |
| "loss": 0.1999, |
| "mean_token_accuracy": 0.9416180402040482, |
| "step": 416 |
| }, |
| { |
| "epoch": 2.439882697947214, |
| "grad_norm": 1.8454858948924562, |
| "learning_rate": 3.579859188744311e-05, |
| "loss": 0.2585, |
| "mean_token_accuracy": 0.918716236948967, |
| "step": 417 |
| }, |
| { |
| "epoch": 2.4457478005865103, |
| "grad_norm": 1.5332521836361521, |
| "learning_rate": 3.5776546185675014e-05, |
| "loss": 0.2124, |
| "mean_token_accuracy": 0.9358135014772415, |
| "step": 418 |
| }, |
| { |
| "epoch": 2.4516129032258065, |
| "grad_norm": 1.4555437762777426, |
| "learning_rate": 3.5754450480608244e-05, |
| "loss": 0.2104, |
| "mean_token_accuracy": 0.9368014857172966, |
| "step": 419 |
| }, |
| { |
| "epoch": 2.4574780058651027, |
| "grad_norm": 1.278448596075258, |
| "learning_rate": 3.5732304852441294e-05, |
| "loss": 0.2069, |
| "mean_token_accuracy": 0.9394045323133469, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.463343108504399, |
| "grad_norm": 1.781690690945349, |
| "learning_rate": 3.571010938155386e-05, |
| "loss": 0.2731, |
| "mean_token_accuracy": 0.9193499833345413, |
| "step": 421 |
| }, |
| { |
| "epoch": 2.469208211143695, |
| "grad_norm": 1.534397726266545, |
| "learning_rate": 3.5687864148506515e-05, |
| "loss": 0.2052, |
| "mean_token_accuracy": 0.9325775653123856, |
| "step": 422 |
| }, |
| { |
| "epoch": 2.4750733137829912, |
| "grad_norm": 1.2252911769053223, |
| "learning_rate": 3.566556923404048e-05, |
| "loss": 0.1613, |
| "mean_token_accuracy": 0.9514370709657669, |
| "step": 423 |
| }, |
| { |
| "epoch": 2.4809384164222874, |
| "grad_norm": 1.0729606974866042, |
| "learning_rate": 3.5643224719077294e-05, |
| "loss": 0.1496, |
| "mean_token_accuracy": 0.9551745429635048, |
| "step": 424 |
| }, |
| { |
| "epoch": 2.4868035190615836, |
| "grad_norm": 1.5221636427012317, |
| "learning_rate": 3.5620830684718515e-05, |
| "loss": 0.1774, |
| "mean_token_accuracy": 0.9464867487549782, |
| "step": 425 |
| }, |
| { |
| "epoch": 2.4926686217008798, |
| "grad_norm": 1.2041644713697683, |
| "learning_rate": 3.5598387212245456e-05, |
| "loss": 0.1726, |
| "mean_token_accuracy": 0.9489129334688187, |
| "step": 426 |
| }, |
| { |
| "epoch": 2.498533724340176, |
| "grad_norm": 1.3409374082416965, |
| "learning_rate": 3.5575894383118846e-05, |
| "loss": 0.1953, |
| "mean_token_accuracy": 0.9453120976686478, |
| "step": 427 |
| }, |
| { |
| "epoch": 2.504398826979472, |
| "grad_norm": 1.2648011317403038, |
| "learning_rate": 3.5553352278978574e-05, |
| "loss": 0.1652, |
| "mean_token_accuracy": 0.9458431974053383, |
| "step": 428 |
| }, |
| { |
| "epoch": 2.5102639296187683, |
| "grad_norm": 1.2941002110451578, |
| "learning_rate": 3.553076098164337e-05, |
| "loss": 0.1646, |
| "mean_token_accuracy": 0.9523252993822098, |
| "step": 429 |
| }, |
| { |
| "epoch": 2.5161290322580645, |
| "grad_norm": 1.2879718792056065, |
| "learning_rate": 3.5508120573110516e-05, |
| "loss": 0.1896, |
| "mean_token_accuracy": 0.9426534026861191, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.5219941348973607, |
| "grad_norm": 0.9901388180640722, |
| "learning_rate": 3.548543113555557e-05, |
| "loss": 0.1381, |
| "mean_token_accuracy": 0.9605349376797676, |
| "step": 431 |
| }, |
| { |
| "epoch": 2.527859237536657, |
| "grad_norm": 1.2535684304346122, |
| "learning_rate": 3.5462692751332014e-05, |
| "loss": 0.1853, |
| "mean_token_accuracy": 0.9452183693647385, |
| "step": 432 |
| }, |
| { |
| "epoch": 2.533724340175953, |
| "grad_norm": 1.019277872771832, |
| "learning_rate": 3.5439905502970996e-05, |
| "loss": 0.1145, |
| "mean_token_accuracy": 0.960605651140213, |
| "step": 433 |
| }, |
| { |
| "epoch": 2.5395894428152492, |
| "grad_norm": 1.183308994953806, |
| "learning_rate": 3.541706947318103e-05, |
| "loss": 0.1659, |
| "mean_token_accuracy": 0.9463500380516052, |
| "step": 434 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 1.7501106760732823, |
| "learning_rate": 3.539418474484768e-05, |
| "loss": 0.2173, |
| "mean_token_accuracy": 0.933612234890461, |
| "step": 435 |
| }, |
| { |
| "epoch": 2.5513196480938416, |
| "grad_norm": 1.3104294276861268, |
| "learning_rate": 3.537125140103327e-05, |
| "loss": 0.1884, |
| "mean_token_accuracy": 0.9485413134098053, |
| "step": 436 |
| }, |
| { |
| "epoch": 2.557184750733138, |
| "grad_norm": 1.2344802500119778, |
| "learning_rate": 3.534826952497657e-05, |
| "loss": 0.154, |
| "mean_token_accuracy": 0.954584963619709, |
| "step": 437 |
| }, |
| { |
| "epoch": 2.563049853372434, |
| "grad_norm": 1.2375074371168866, |
| "learning_rate": 3.5325239200092505e-05, |
| "loss": 0.1798, |
| "mean_token_accuracy": 0.9420296102762222, |
| "step": 438 |
| }, |
| { |
| "epoch": 2.56891495601173, |
| "grad_norm": 1.3498402815628565, |
| "learning_rate": 3.5302160509971866e-05, |
| "loss": 0.1931, |
| "mean_token_accuracy": 0.9404741451144218, |
| "step": 439 |
| }, |
| { |
| "epoch": 2.5747800586510263, |
| "grad_norm": 1.5153339396078678, |
| "learning_rate": 3.5279033538380974e-05, |
| "loss": 0.1971, |
| "mean_token_accuracy": 0.9389586672186852, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "grad_norm": 1.0927821569226148, |
| "learning_rate": 3.5255858369261385e-05, |
| "loss": 0.1293, |
| "mean_token_accuracy": 0.959166519343853, |
| "step": 441 |
| }, |
| { |
| "epoch": 2.5865102639296187, |
| "grad_norm": 1.573165687770213, |
| "learning_rate": 3.523263508672961e-05, |
| "loss": 0.227, |
| "mean_token_accuracy": 0.9359922930598259, |
| "step": 442 |
| }, |
| { |
| "epoch": 2.592375366568915, |
| "grad_norm": 1.31329236234176, |
| "learning_rate": 3.520936377507679e-05, |
| "loss": 0.1726, |
| "mean_token_accuracy": 0.9415776506066322, |
| "step": 443 |
| }, |
| { |
| "epoch": 2.598240469208211, |
| "grad_norm": 1.4360330933961905, |
| "learning_rate": 3.5186044518768376e-05, |
| "loss": 0.2235, |
| "mean_token_accuracy": 0.9257130026817322, |
| "step": 444 |
| }, |
| { |
| "epoch": 2.6041055718475072, |
| "grad_norm": 1.3874250860276218, |
| "learning_rate": 3.5162677402443864e-05, |
| "loss": 0.1962, |
| "mean_token_accuracy": 0.94052804261446, |
| "step": 445 |
| }, |
| { |
| "epoch": 2.6099706744868034, |
| "grad_norm": 1.3663549034269482, |
| "learning_rate": 3.513926251091644e-05, |
| "loss": 0.194, |
| "mean_token_accuracy": 0.9420884102582932, |
| "step": 446 |
| }, |
| { |
| "epoch": 2.6158357771260996, |
| "grad_norm": 1.2355875753890644, |
| "learning_rate": 3.51157999291727e-05, |
| "loss": 0.1883, |
| "mean_token_accuracy": 0.9405950680375099, |
| "step": 447 |
| }, |
| { |
| "epoch": 2.621700879765396, |
| "grad_norm": 1.4472757686119782, |
| "learning_rate": 3.509228974237235e-05, |
| "loss": 0.2317, |
| "mean_token_accuracy": 0.930273026227951, |
| "step": 448 |
| }, |
| { |
| "epoch": 2.627565982404692, |
| "grad_norm": 1.3499911027831195, |
| "learning_rate": 3.506873203584787e-05, |
| "loss": 0.1987, |
| "mean_token_accuracy": 0.9421002045273781, |
| "step": 449 |
| }, |
| { |
| "epoch": 2.633431085043988, |
| "grad_norm": 0.9022856812434747, |
| "learning_rate": 3.504512689510422e-05, |
| "loss": 0.1278, |
| "mean_token_accuracy": 0.9621746689081192, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.6392961876832843, |
| "grad_norm": 1.270860877585178, |
| "learning_rate": 3.5021474405818525e-05, |
| "loss": 0.1615, |
| "mean_token_accuracy": 0.9504728391766548, |
| "step": 451 |
| }, |
| { |
| "epoch": 2.6451612903225805, |
| "grad_norm": 1.3903665628243658, |
| "learning_rate": 3.499777465383977e-05, |
| "loss": 0.2059, |
| "mean_token_accuracy": 0.9414464309811592, |
| "step": 452 |
| }, |
| { |
| "epoch": 2.6510263929618767, |
| "grad_norm": 1.5121941542783566, |
| "learning_rate": 3.497402772518848e-05, |
| "loss": 0.2191, |
| "mean_token_accuracy": 0.930144228041172, |
| "step": 453 |
| }, |
| { |
| "epoch": 2.656891495601173, |
| "grad_norm": 1.2291299776343065, |
| "learning_rate": 3.4950233706056415e-05, |
| "loss": 0.1609, |
| "mean_token_accuracy": 0.9529666900634766, |
| "step": 454 |
| }, |
| { |
| "epoch": 2.662756598240469, |
| "grad_norm": 1.5178328136382258, |
| "learning_rate": 3.4926392682806265e-05, |
| "loss": 0.2178, |
| "mean_token_accuracy": 0.9358916729688644, |
| "step": 455 |
| }, |
| { |
| "epoch": 2.6686217008797652, |
| "grad_norm": 1.503800251837255, |
| "learning_rate": 3.490250474197131e-05, |
| "loss": 0.2129, |
| "mean_token_accuracy": 0.9409657120704651, |
| "step": 456 |
| }, |
| { |
| "epoch": 2.6744868035190614, |
| "grad_norm": 1.1699037972947557, |
| "learning_rate": 3.4878569970255116e-05, |
| "loss": 0.1664, |
| "mean_token_accuracy": 0.9472703188657761, |
| "step": 457 |
| }, |
| { |
| "epoch": 2.6803519061583576, |
| "grad_norm": 1.3730176544696786, |
| "learning_rate": 3.485458845453125e-05, |
| "loss": 0.1938, |
| "mean_token_accuracy": 0.943206362426281, |
| "step": 458 |
| }, |
| { |
| "epoch": 2.686217008797654, |
| "grad_norm": 1.142902961416544, |
| "learning_rate": 3.483056028184293e-05, |
| "loss": 0.1483, |
| "mean_token_accuracy": 0.9592099040746689, |
| "step": 459 |
| }, |
| { |
| "epoch": 2.6920821114369504, |
| "grad_norm": 1.4858353520299903, |
| "learning_rate": 3.4806485539402716e-05, |
| "loss": 0.2035, |
| "mean_token_accuracy": 0.9390188604593277, |
| "step": 460 |
| }, |
| { |
| "epoch": 2.6979472140762466, |
| "grad_norm": 1.094863918269323, |
| "learning_rate": 3.4782364314592186e-05, |
| "loss": 0.142, |
| "mean_token_accuracy": 0.9560906514525414, |
| "step": 461 |
| }, |
| { |
| "epoch": 2.703812316715543, |
| "grad_norm": 1.350848338520518, |
| "learning_rate": 3.475819669496167e-05, |
| "loss": 0.1668, |
| "mean_token_accuracy": 0.942637600004673, |
| "step": 462 |
| }, |
| { |
| "epoch": 2.709677419354839, |
| "grad_norm": 1.2655106986574725, |
| "learning_rate": 3.473398276822985e-05, |
| "loss": 0.1739, |
| "mean_token_accuracy": 0.9467576667666435, |
| "step": 463 |
| }, |
| { |
| "epoch": 2.715542521994135, |
| "grad_norm": 1.6239688129886054, |
| "learning_rate": 3.47097226222835e-05, |
| "loss": 0.2034, |
| "mean_token_accuracy": 0.9414631873369217, |
| "step": 464 |
| }, |
| { |
| "epoch": 2.7214076246334313, |
| "grad_norm": 1.3207640172284705, |
| "learning_rate": 3.468541634517716e-05, |
| "loss": 0.1682, |
| "mean_token_accuracy": 0.9518086910247803, |
| "step": 465 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 1.0812855439860434, |
| "learning_rate": 3.4661064025132796e-05, |
| "loss": 0.1393, |
| "mean_token_accuracy": 0.9551347717642784, |
| "step": 466 |
| }, |
| { |
| "epoch": 2.7331378299120237, |
| "grad_norm": 1.669554956385613, |
| "learning_rate": 3.463666575053949e-05, |
| "loss": 0.2302, |
| "mean_token_accuracy": 0.9358491003513336, |
| "step": 467 |
| }, |
| { |
| "epoch": 2.73900293255132, |
| "grad_norm": 1.2117870250039342, |
| "learning_rate": 3.4612221609953126e-05, |
| "loss": 0.152, |
| "mean_token_accuracy": 0.9533187001943588, |
| "step": 468 |
| }, |
| { |
| "epoch": 2.744868035190616, |
| "grad_norm": 1.4016919628458295, |
| "learning_rate": 3.4587731692096065e-05, |
| "loss": 0.1832, |
| "mean_token_accuracy": 0.9502892270684242, |
| "step": 469 |
| }, |
| { |
| "epoch": 2.7507331378299122, |
| "grad_norm": 1.4977960432623156, |
| "learning_rate": 3.4563196085856815e-05, |
| "loss": 0.1984, |
| "mean_token_accuracy": 0.9398622885346413, |
| "step": 470 |
| }, |
| { |
| "epoch": 2.7565982404692084, |
| "grad_norm": 1.2989435104540572, |
| "learning_rate": 3.4538614880289724e-05, |
| "loss": 0.1833, |
| "mean_token_accuracy": 0.9461094737052917, |
| "step": 471 |
| }, |
| { |
| "epoch": 2.7624633431085046, |
| "grad_norm": 1.2689972508312564, |
| "learning_rate": 3.4513988164614635e-05, |
| "loss": 0.1604, |
| "mean_token_accuracy": 0.955364815890789, |
| "step": 472 |
| }, |
| { |
| "epoch": 2.768328445747801, |
| "grad_norm": 1.213681034144693, |
| "learning_rate": 3.4489316028216584e-05, |
| "loss": 0.1532, |
| "mean_token_accuracy": 0.9536414071917534, |
| "step": 473 |
| }, |
| { |
| "epoch": 2.774193548387097, |
| "grad_norm": 1.1162415342567564, |
| "learning_rate": 3.446459856064545e-05, |
| "loss": 0.1442, |
| "mean_token_accuracy": 0.9580774754285812, |
| "step": 474 |
| }, |
| { |
| "epoch": 2.780058651026393, |
| "grad_norm": 1.562832189465237, |
| "learning_rate": 3.443983585161568e-05, |
| "loss": 0.2024, |
| "mean_token_accuracy": 0.9375625848770142, |
| "step": 475 |
| }, |
| { |
| "epoch": 2.7859237536656893, |
| "grad_norm": 1.3440963011489055, |
| "learning_rate": 3.441502799100588e-05, |
| "loss": 0.168, |
| "mean_token_accuracy": 0.9529064446687698, |
| "step": 476 |
| }, |
| { |
| "epoch": 2.7917888563049855, |
| "grad_norm": 1.3875913315793824, |
| "learning_rate": 3.439017506885858e-05, |
| "loss": 0.1833, |
| "mean_token_accuracy": 0.9444696083664894, |
| "step": 477 |
| }, |
| { |
| "epoch": 2.7976539589442817, |
| "grad_norm": 1.3437212381186996, |
| "learning_rate": 3.436527717537985e-05, |
| "loss": 0.1814, |
| "mean_token_accuracy": 0.9524684324860573, |
| "step": 478 |
| }, |
| { |
| "epoch": 2.803519061583578, |
| "grad_norm": 1.13616471103987, |
| "learning_rate": 3.434033440093899e-05, |
| "loss": 0.1767, |
| "mean_token_accuracy": 0.9441180974245071, |
| "step": 479 |
| }, |
| { |
| "epoch": 2.809384164222874, |
| "grad_norm": 1.5699460979346578, |
| "learning_rate": 3.431534683606818e-05, |
| "loss": 0.2116, |
| "mean_token_accuracy": 0.9400829449295998, |
| "step": 480 |
| }, |
| { |
| "epoch": 2.8152492668621703, |
| "grad_norm": 1.2890357354824495, |
| "learning_rate": 3.4290314571462214e-05, |
| "loss": 0.1749, |
| "mean_token_accuracy": 0.9491599574685097, |
| "step": 481 |
| }, |
| { |
| "epoch": 2.8211143695014664, |
| "grad_norm": 1.180927092541653, |
| "learning_rate": 3.426523769797808e-05, |
| "loss": 0.1524, |
| "mean_token_accuracy": 0.951946809887886, |
| "step": 482 |
| }, |
| { |
| "epoch": 2.8269794721407626, |
| "grad_norm": 2.0281247027871636, |
| "learning_rate": 3.424011630663472e-05, |
| "loss": 0.1849, |
| "mean_token_accuracy": 0.9392823651432991, |
| "step": 483 |
| }, |
| { |
| "epoch": 2.832844574780059, |
| "grad_norm": 1.445272870309301, |
| "learning_rate": 3.421495048861262e-05, |
| "loss": 0.2067, |
| "mean_token_accuracy": 0.9413087740540504, |
| "step": 484 |
| }, |
| { |
| "epoch": 2.838709677419355, |
| "grad_norm": 1.207685907104084, |
| "learning_rate": 3.418974033525355e-05, |
| "loss": 0.155, |
| "mean_token_accuracy": 0.953525498509407, |
| "step": 485 |
| }, |
| { |
| "epoch": 2.844574780058651, |
| "grad_norm": 1.423801110337816, |
| "learning_rate": 3.416448593806019e-05, |
| "loss": 0.2128, |
| "mean_token_accuracy": 0.9368026629090309, |
| "step": 486 |
| }, |
| { |
| "epoch": 2.8504398826979473, |
| "grad_norm": 1.3447638850919599, |
| "learning_rate": 3.4139187388695774e-05, |
| "loss": 0.1898, |
| "mean_token_accuracy": 0.9403852596879005, |
| "step": 487 |
| }, |
| { |
| "epoch": 2.8563049853372435, |
| "grad_norm": 1.7242878324194963, |
| "learning_rate": 3.411384477898385e-05, |
| "loss": 0.1922, |
| "mean_token_accuracy": 0.9478732720017433, |
| "step": 488 |
| }, |
| { |
| "epoch": 2.8621700879765397, |
| "grad_norm": 1.213083493046893, |
| "learning_rate": 3.408845820090784e-05, |
| "loss": 0.1655, |
| "mean_token_accuracy": 0.9495300799608231, |
| "step": 489 |
| }, |
| { |
| "epoch": 2.868035190615836, |
| "grad_norm": 1.3410093896289859, |
| "learning_rate": 3.406302774661077e-05, |
| "loss": 0.2188, |
| "mean_token_accuracy": 0.9278420805931091, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.873900293255132, |
| "grad_norm": 1.4983997591436693, |
| "learning_rate": 3.403755350839492e-05, |
| "loss": 0.2239, |
| "mean_token_accuracy": 0.9401474595069885, |
| "step": 491 |
| }, |
| { |
| "epoch": 2.8797653958944283, |
| "grad_norm": 1.0320683861366073, |
| "learning_rate": 3.401203557872149e-05, |
| "loss": 0.1208, |
| "mean_token_accuracy": 0.9612024202942848, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.8856304985337244, |
| "grad_norm": 1.17865515123761, |
| "learning_rate": 3.398647405021026e-05, |
| "loss": 0.1716, |
| "mean_token_accuracy": 0.9516402930021286, |
| "step": 493 |
| }, |
| { |
| "epoch": 2.8914956011730206, |
| "grad_norm": 1.4957974553498135, |
| "learning_rate": 3.396086901563925e-05, |
| "loss": 0.2196, |
| "mean_token_accuracy": 0.9332915842533112, |
| "step": 494 |
| }, |
| { |
| "epoch": 2.897360703812317, |
| "grad_norm": 1.1314739606086441, |
| "learning_rate": 3.3935220567944395e-05, |
| "loss": 0.1607, |
| "mean_token_accuracy": 0.9516676366329193, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.903225806451613, |
| "grad_norm": 1.3198388233629983, |
| "learning_rate": 3.39095288002192e-05, |
| "loss": 0.1988, |
| "mean_token_accuracy": 0.9403504058718681, |
| "step": 496 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 1.1729074523420793, |
| "learning_rate": 3.3883793805714406e-05, |
| "loss": 0.1679, |
| "mean_token_accuracy": 0.94942307472229, |
| "step": 497 |
| }, |
| { |
| "epoch": 2.9149560117302054, |
| "grad_norm": 1.5546458022132672, |
| "learning_rate": 3.3858015677837656e-05, |
| "loss": 0.206, |
| "mean_token_accuracy": 0.9396896436810493, |
| "step": 498 |
| }, |
| { |
| "epoch": 2.9208211143695015, |
| "grad_norm": 1.3193613560349773, |
| "learning_rate": 3.3832194510153126e-05, |
| "loss": 0.2074, |
| "mean_token_accuracy": 0.9424831047654152, |
| "step": 499 |
| }, |
| { |
| "epoch": 2.9266862170087977, |
| "grad_norm": 1.5103842145967505, |
| "learning_rate": 3.380633039638125e-05, |
| "loss": 0.1967, |
| "mean_token_accuracy": 0.9491210356354713, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.932551319648094, |
| "grad_norm": 1.3899787104350685, |
| "learning_rate": 3.37804234303983e-05, |
| "loss": 0.1853, |
| "mean_token_accuracy": 0.9460192769765854, |
| "step": 501 |
| }, |
| { |
| "epoch": 2.93841642228739, |
| "grad_norm": 1.6042983579274848, |
| "learning_rate": 3.37544737062361e-05, |
| "loss": 0.2159, |
| "mean_token_accuracy": 0.9384797960519791, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.9442815249266863, |
| "grad_norm": 1.1857829239019415, |
| "learning_rate": 3.372848131808167e-05, |
| "loss": 0.1663, |
| "mean_token_accuracy": 0.9543160423636436, |
| "step": 503 |
| }, |
| { |
| "epoch": 2.9501466275659824, |
| "grad_norm": 1.2895444159726623, |
| "learning_rate": 3.370244636027688e-05, |
| "loss": 0.1724, |
| "mean_token_accuracy": 0.9467265158891678, |
| "step": 504 |
| }, |
| { |
| "epoch": 2.9560117302052786, |
| "grad_norm": 1.1995300770374142, |
| "learning_rate": 3.367636892731812e-05, |
| "loss": 0.1627, |
| "mean_token_accuracy": 0.9443233907222748, |
| "step": 505 |
| }, |
| { |
| "epoch": 2.961876832844575, |
| "grad_norm": 1.3286742396306415, |
| "learning_rate": 3.365024911385593e-05, |
| "loss": 0.1605, |
| "mean_token_accuracy": 0.9559065476059914, |
| "step": 506 |
| }, |
| { |
| "epoch": 2.967741935483871, |
| "grad_norm": 1.2272292303747936, |
| "learning_rate": 3.362408701469469e-05, |
| "loss": 0.1735, |
| "mean_token_accuracy": 0.9431959837675095, |
| "step": 507 |
| }, |
| { |
| "epoch": 2.973607038123167, |
| "grad_norm": 1.3932587517490482, |
| "learning_rate": 3.359788272479225e-05, |
| "loss": 0.1973, |
| "mean_token_accuracy": 0.9413277730345726, |
| "step": 508 |
| }, |
| { |
| "epoch": 2.9794721407624634, |
| "grad_norm": 1.2786049269699822, |
| "learning_rate": 3.35716363392596e-05, |
| "loss": 0.1816, |
| "mean_token_accuracy": 0.9395741447806358, |
| "step": 509 |
| }, |
| { |
| "epoch": 2.9853372434017595, |
| "grad_norm": 1.6116723531914925, |
| "learning_rate": 3.354534795336052e-05, |
| "loss": 0.2391, |
| "mean_token_accuracy": 0.9272446259856224, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.9912023460410557, |
| "grad_norm": 1.2075082144961329, |
| "learning_rate": 3.351901766251123e-05, |
| "loss": 0.1909, |
| "mean_token_accuracy": 0.9406610727310181, |
| "step": 511 |
| }, |
| { |
| "epoch": 2.997067448680352, |
| "grad_norm": 1.7026589757148236, |
| "learning_rate": 3.349264556228006e-05, |
| "loss": 0.2441, |
| "mean_token_accuracy": 0.9360670745372772, |
| "step": 512 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.7026589757148236, |
| "learning_rate": 3.3466231748387077e-05, |
| "loss": 0.2243, |
| "mean_token_accuracy": 0.9212906956672668, |
| "step": 513 |
| }, |
| { |
| "epoch": 3.005865102639296, |
| "grad_norm": 1.9172525119833599, |
| "learning_rate": 3.343977631670376e-05, |
| "loss": 0.1102, |
| "mean_token_accuracy": 0.9692064374685287, |
| "step": 514 |
| }, |
| { |
| "epoch": 3.0117302052785924, |
| "grad_norm": 1.1847851063603438, |
| "learning_rate": 3.341327936325264e-05, |
| "loss": 0.1318, |
| "mean_token_accuracy": 0.9639127478003502, |
| "step": 515 |
| }, |
| { |
| "epoch": 3.0175953079178885, |
| "grad_norm": 0.9061334284550635, |
| "learning_rate": 3.338674098420695e-05, |
| "loss": 0.1028, |
| "mean_token_accuracy": 0.9676964953541756, |
| "step": 516 |
| }, |
| { |
| "epoch": 3.0234604105571847, |
| "grad_norm": 0.9102322647938016, |
| "learning_rate": 3.33601612758903e-05, |
| "loss": 0.1144, |
| "mean_token_accuracy": 0.9649685248732567, |
| "step": 517 |
| }, |
| { |
| "epoch": 3.029325513196481, |
| "grad_norm": 0.9042900152145036, |
| "learning_rate": 3.3333540334776286e-05, |
| "loss": 0.132, |
| "mean_token_accuracy": 0.9574764594435692, |
| "step": 518 |
| }, |
| { |
| "epoch": 3.035190615835777, |
| "grad_norm": 1.1385844279042818, |
| "learning_rate": 3.330687825748818e-05, |
| "loss": 0.1194, |
| "mean_token_accuracy": 0.9642714560031891, |
| "step": 519 |
| }, |
| { |
| "epoch": 3.0410557184750733, |
| "grad_norm": 1.0653366992695055, |
| "learning_rate": 3.328017514079855e-05, |
| "loss": 0.1209, |
| "mean_token_accuracy": 0.9662440121173859, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.0469208211143695, |
| "grad_norm": 0.9944121868967081, |
| "learning_rate": 3.325343108162893e-05, |
| "loss": 0.1072, |
| "mean_token_accuracy": 0.9639370143413544, |
| "step": 521 |
| }, |
| { |
| "epoch": 3.0527859237536656, |
| "grad_norm": 1.1494314839298039, |
| "learning_rate": 3.3226646177049446e-05, |
| "loss": 0.131, |
| "mean_token_accuracy": 0.9620062932372093, |
| "step": 522 |
| }, |
| { |
| "epoch": 3.058651026392962, |
| "grad_norm": 1.1758302687993867, |
| "learning_rate": 3.3199820524278485e-05, |
| "loss": 0.1349, |
| "mean_token_accuracy": 0.9607839807868004, |
| "step": 523 |
| }, |
| { |
| "epoch": 3.064516129032258, |
| "grad_norm": 1.2242461859748268, |
| "learning_rate": 3.317295422068234e-05, |
| "loss": 0.1269, |
| "mean_token_accuracy": 0.96031753718853, |
| "step": 524 |
| }, |
| { |
| "epoch": 3.070381231671554, |
| "grad_norm": 1.0331010016728317, |
| "learning_rate": 3.314604736377484e-05, |
| "loss": 0.0969, |
| "mean_token_accuracy": 0.9681897535920143, |
| "step": 525 |
| }, |
| { |
| "epoch": 3.0762463343108504, |
| "grad_norm": 0.7781497219146758, |
| "learning_rate": 3.3119100051217005e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.9731072410941124, |
| "step": 526 |
| }, |
| { |
| "epoch": 3.0821114369501466, |
| "grad_norm": 1.2166577904207496, |
| "learning_rate": 3.3092112380816696e-05, |
| "loss": 0.1324, |
| "mean_token_accuracy": 0.962135910987854, |
| "step": 527 |
| }, |
| { |
| "epoch": 3.0879765395894427, |
| "grad_norm": 1.0974981165151148, |
| "learning_rate": 3.306508445052826e-05, |
| "loss": 0.1425, |
| "mean_token_accuracy": 0.9630181938409805, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.093841642228739, |
| "grad_norm": 1.4099756052774848, |
| "learning_rate": 3.303801635845216e-05, |
| "loss": 0.1214, |
| "mean_token_accuracy": 0.9584023430943489, |
| "step": 529 |
| }, |
| { |
| "epoch": 3.099706744868035, |
| "grad_norm": 1.201123082840797, |
| "learning_rate": 3.301090820283465e-05, |
| "loss": 0.136, |
| "mean_token_accuracy": 0.9598643630743027, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.1055718475073313, |
| "grad_norm": 1.176553540140124, |
| "learning_rate": 3.298376008206739e-05, |
| "loss": 0.1157, |
| "mean_token_accuracy": 0.9649958238005638, |
| "step": 531 |
| }, |
| { |
| "epoch": 3.1114369501466275, |
| "grad_norm": 0.9279228524428683, |
| "learning_rate": 3.295657209468707e-05, |
| "loss": 0.1091, |
| "mean_token_accuracy": 0.9710751473903656, |
| "step": 532 |
| }, |
| { |
| "epoch": 3.1173020527859236, |
| "grad_norm": 1.0571051553285986, |
| "learning_rate": 3.2929344339375125e-05, |
| "loss": 0.1245, |
| "mean_token_accuracy": 0.9605824053287506, |
| "step": 533 |
| }, |
| { |
| "epoch": 3.12316715542522, |
| "grad_norm": 1.1404392855763104, |
| "learning_rate": 3.290207691495731e-05, |
| "loss": 0.1486, |
| "mean_token_accuracy": 0.9611983299255371, |
| "step": 534 |
| }, |
| { |
| "epoch": 3.129032258064516, |
| "grad_norm": 1.1108140744094672, |
| "learning_rate": 3.2874769920403355e-05, |
| "loss": 0.1309, |
| "mean_token_accuracy": 0.9562818929553032, |
| "step": 535 |
| }, |
| { |
| "epoch": 3.134897360703812, |
| "grad_norm": 1.0394406562184513, |
| "learning_rate": 3.2847423454826616e-05, |
| "loss": 0.1072, |
| "mean_token_accuracy": 0.9680725708603859, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.1407624633431084, |
| "grad_norm": 0.9161537395043307, |
| "learning_rate": 3.2820037617483734e-05, |
| "loss": 0.141, |
| "mean_token_accuracy": 0.9604132622480392, |
| "step": 537 |
| }, |
| { |
| "epoch": 3.1466275659824046, |
| "grad_norm": 1.3707774590187438, |
| "learning_rate": 3.2792612507774224e-05, |
| "loss": 0.1339, |
| "mean_token_accuracy": 0.9593137428164482, |
| "step": 538 |
| }, |
| { |
| "epoch": 3.1524926686217007, |
| "grad_norm": 1.012147704956255, |
| "learning_rate": 3.2765148225240176e-05, |
| "loss": 0.1246, |
| "mean_token_accuracy": 0.9646853432059288, |
| "step": 539 |
| }, |
| { |
| "epoch": 3.158357771260997, |
| "grad_norm": 1.0725542099127343, |
| "learning_rate": 3.273764486956583e-05, |
| "loss": 0.135, |
| "mean_token_accuracy": 0.96214210242033, |
| "step": 540 |
| }, |
| { |
| "epoch": 3.164222873900293, |
| "grad_norm": 1.12481951852536, |
| "learning_rate": 3.2710102540577256e-05, |
| "loss": 0.1182, |
| "mean_token_accuracy": 0.9636344686150551, |
| "step": 541 |
| }, |
| { |
| "epoch": 3.1700879765395893, |
| "grad_norm": 1.2737900941858715, |
| "learning_rate": 3.268252133824198e-05, |
| "loss": 0.1625, |
| "mean_token_accuracy": 0.9540104120969772, |
| "step": 542 |
| }, |
| { |
| "epoch": 3.1759530791788855, |
| "grad_norm": 1.212108019559075, |
| "learning_rate": 3.2654901362668656e-05, |
| "loss": 0.1258, |
| "mean_token_accuracy": 0.9660171419382095, |
| "step": 543 |
| }, |
| { |
| "epoch": 3.1818181818181817, |
| "grad_norm": 1.127815767716653, |
| "learning_rate": 3.262724271410661e-05, |
| "loss": 0.1404, |
| "mean_token_accuracy": 0.9578510448336601, |
| "step": 544 |
| }, |
| { |
| "epoch": 3.187683284457478, |
| "grad_norm": 1.2610603469789805, |
| "learning_rate": 3.2599545492945584e-05, |
| "loss": 0.1342, |
| "mean_token_accuracy": 0.9645530432462692, |
| "step": 545 |
| }, |
| { |
| "epoch": 3.193548387096774, |
| "grad_norm": 1.2319746864500574, |
| "learning_rate": 3.257180979971529e-05, |
| "loss": 0.1333, |
| "mean_token_accuracy": 0.9600680395960808, |
| "step": 546 |
| }, |
| { |
| "epoch": 3.19941348973607, |
| "grad_norm": 0.9570365722404466, |
| "learning_rate": 3.25440357350851e-05, |
| "loss": 0.1371, |
| "mean_token_accuracy": 0.9588101580739021, |
| "step": 547 |
| }, |
| { |
| "epoch": 3.2052785923753664, |
| "grad_norm": 1.1555892585291052, |
| "learning_rate": 3.251622339986366e-05, |
| "loss": 0.133, |
| "mean_token_accuracy": 0.9624381512403488, |
| "step": 548 |
| }, |
| { |
| "epoch": 3.2111436950146626, |
| "grad_norm": 1.1220972442323853, |
| "learning_rate": 3.24883728949985e-05, |
| "loss": 0.1353, |
| "mean_token_accuracy": 0.9607517868280411, |
| "step": 549 |
| }, |
| { |
| "epoch": 3.2170087976539588, |
| "grad_norm": 1.1180353918248547, |
| "learning_rate": 3.2460484321575714e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.9660913869738579, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.222873900293255, |
| "grad_norm": 1.1272669000126658, |
| "learning_rate": 3.2432557780819556e-05, |
| "loss": 0.1249, |
| "mean_token_accuracy": 0.9630195274949074, |
| "step": 551 |
| }, |
| { |
| "epoch": 3.228739002932551, |
| "grad_norm": 1.2021106524091134, |
| "learning_rate": 3.240459337409209e-05, |
| "loss": 0.1232, |
| "mean_token_accuracy": 0.9603384956717491, |
| "step": 552 |
| }, |
| { |
| "epoch": 3.2346041055718473, |
| "grad_norm": 1.0242118203263009, |
| "learning_rate": 3.237659120289282e-05, |
| "loss": 0.1291, |
| "mean_token_accuracy": 0.9633880257606506, |
| "step": 553 |
| }, |
| { |
| "epoch": 3.2404692082111435, |
| "grad_norm": 1.3147750355772578, |
| "learning_rate": 3.2348551368858315e-05, |
| "loss": 0.1281, |
| "mean_token_accuracy": 0.9652110934257507, |
| "step": 554 |
| }, |
| { |
| "epoch": 3.2463343108504397, |
| "grad_norm": 1.0420733903333175, |
| "learning_rate": 3.2320473973761845e-05, |
| "loss": 0.1275, |
| "mean_token_accuracy": 0.9632606133818626, |
| "step": 555 |
| }, |
| { |
| "epoch": 3.252199413489736, |
| "grad_norm": 1.1681134194309897, |
| "learning_rate": 3.229235911951303e-05, |
| "loss": 0.1327, |
| "mean_token_accuracy": 0.9661369696259499, |
| "step": 556 |
| }, |
| { |
| "epoch": 3.258064516129032, |
| "grad_norm": 1.1385374917446593, |
| "learning_rate": 3.2264206908157425e-05, |
| "loss": 0.1064, |
| "mean_token_accuracy": 0.9682695493102074, |
| "step": 557 |
| }, |
| { |
| "epoch": 3.263929618768328, |
| "grad_norm": 1.2397464547533545, |
| "learning_rate": 3.2236017441876185e-05, |
| "loss": 0.1317, |
| "mean_token_accuracy": 0.9587446004152298, |
| "step": 558 |
| }, |
| { |
| "epoch": 3.2697947214076244, |
| "grad_norm": 1.2747233600312535, |
| "learning_rate": 3.220779082298569e-05, |
| "loss": 0.1422, |
| "mean_token_accuracy": 0.9570489674806595, |
| "step": 559 |
| }, |
| { |
| "epoch": 3.2756598240469206, |
| "grad_norm": 1.263930404888225, |
| "learning_rate": 3.2179527153937165e-05, |
| "loss": 0.1325, |
| "mean_token_accuracy": 0.9581855908036232, |
| "step": 560 |
| }, |
| { |
| "epoch": 3.281524926686217, |
| "grad_norm": 1.07405022031719, |
| "learning_rate": 3.2151226537316315e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9662249088287354, |
| "step": 561 |
| }, |
| { |
| "epoch": 3.2873900293255134, |
| "grad_norm": 1.012781657621151, |
| "learning_rate": 3.212288907584296e-05, |
| "loss": 0.1173, |
| "mean_token_accuracy": 0.9624657481908798, |
| "step": 562 |
| }, |
| { |
| "epoch": 3.2932551319648096, |
| "grad_norm": 1.1273423111917455, |
| "learning_rate": 3.209451487237062e-05, |
| "loss": 0.1558, |
| "mean_token_accuracy": 0.9555483162403107, |
| "step": 563 |
| }, |
| { |
| "epoch": 3.2991202346041058, |
| "grad_norm": 1.0772108863186236, |
| "learning_rate": 3.206610402988621e-05, |
| "loss": 0.1246, |
| "mean_token_accuracy": 0.9665045291185379, |
| "step": 564 |
| }, |
| { |
| "epoch": 3.304985337243402, |
| "grad_norm": 1.283465674599968, |
| "learning_rate": 3.20376566515096e-05, |
| "loss": 0.1484, |
| "mean_token_accuracy": 0.9613608345389366, |
| "step": 565 |
| }, |
| { |
| "epoch": 3.310850439882698, |
| "grad_norm": 3.083503730186153, |
| "learning_rate": 3.20091728404933e-05, |
| "loss": 0.1046, |
| "mean_token_accuracy": 0.9690384045243263, |
| "step": 566 |
| }, |
| { |
| "epoch": 3.3167155425219943, |
| "grad_norm": 0.9347036594770055, |
| "learning_rate": 3.1980652700222024e-05, |
| "loss": 0.128, |
| "mean_token_accuracy": 0.9639571607112885, |
| "step": 567 |
| }, |
| { |
| "epoch": 3.3225806451612905, |
| "grad_norm": 0.9910476896451094, |
| "learning_rate": 3.195209633421237e-05, |
| "loss": 0.1214, |
| "mean_token_accuracy": 0.956595666706562, |
| "step": 568 |
| }, |
| { |
| "epoch": 3.3284457478005867, |
| "grad_norm": 1.063945331096459, |
| "learning_rate": 3.192350384611242e-05, |
| "loss": 0.15, |
| "mean_token_accuracy": 0.9561426416039467, |
| "step": 569 |
| }, |
| { |
| "epoch": 3.334310850439883, |
| "grad_norm": 1.0615452381591053, |
| "learning_rate": 3.1894875339701354e-05, |
| "loss": 0.125, |
| "mean_token_accuracy": 0.9663048535585403, |
| "step": 570 |
| }, |
| { |
| "epoch": 3.340175953079179, |
| "grad_norm": 1.2629558448763267, |
| "learning_rate": 3.186621091888909e-05, |
| "loss": 0.1461, |
| "mean_token_accuracy": 0.957501508295536, |
| "step": 571 |
| }, |
| { |
| "epoch": 3.346041055718475, |
| "grad_norm": 1.0679814269736243, |
| "learning_rate": 3.183751068771588e-05, |
| "loss": 0.144, |
| "mean_token_accuracy": 0.9582978636026382, |
| "step": 572 |
| }, |
| { |
| "epoch": 3.3519061583577714, |
| "grad_norm": 1.0690636455835296, |
| "learning_rate": 3.180877475035199e-05, |
| "loss": 0.1204, |
| "mean_token_accuracy": 0.9598318859934807, |
| "step": 573 |
| }, |
| { |
| "epoch": 3.3577712609970676, |
| "grad_norm": 0.9369182682129731, |
| "learning_rate": 3.178000321109727e-05, |
| "loss": 0.138, |
| "mean_token_accuracy": 0.961778499186039, |
| "step": 574 |
| }, |
| { |
| "epoch": 3.3636363636363638, |
| "grad_norm": 1.1682551194640143, |
| "learning_rate": 3.175119617438078e-05, |
| "loss": 0.145, |
| "mean_token_accuracy": 0.9567500725388527, |
| "step": 575 |
| }, |
| { |
| "epoch": 3.36950146627566, |
| "grad_norm": 1.216383932443075, |
| "learning_rate": 3.172235374476043e-05, |
| "loss": 0.1237, |
| "mean_token_accuracy": 0.961734727025032, |
| "step": 576 |
| }, |
| { |
| "epoch": 3.375366568914956, |
| "grad_norm": 1.018664041230987, |
| "learning_rate": 3.169347602692259e-05, |
| "loss": 0.1442, |
| "mean_token_accuracy": 0.9599500149488449, |
| "step": 577 |
| }, |
| { |
| "epoch": 3.3812316715542523, |
| "grad_norm": 1.4739777903748597, |
| "learning_rate": 3.166456312568171e-05, |
| "loss": 0.1295, |
| "mean_token_accuracy": 0.9598701372742653, |
| "step": 578 |
| }, |
| { |
| "epoch": 3.3870967741935485, |
| "grad_norm": 1.1249165312933065, |
| "learning_rate": 3.1635615145979955e-05, |
| "loss": 0.1456, |
| "mean_token_accuracy": 0.9606313407421112, |
| "step": 579 |
| }, |
| { |
| "epoch": 3.3929618768328447, |
| "grad_norm": 1.0071746295455668, |
| "learning_rate": 3.160663219288679e-05, |
| "loss": 0.1192, |
| "mean_token_accuracy": 0.9617794305086136, |
| "step": 580 |
| }, |
| { |
| "epoch": 3.398826979472141, |
| "grad_norm": 1.0993797961538627, |
| "learning_rate": 3.157761437159863e-05, |
| "loss": 0.1422, |
| "mean_token_accuracy": 0.9568778499960899, |
| "step": 581 |
| }, |
| { |
| "epoch": 3.404692082111437, |
| "grad_norm": 1.1322199004325646, |
| "learning_rate": 3.1548561787438445e-05, |
| "loss": 0.1162, |
| "mean_token_accuracy": 0.9666043370962143, |
| "step": 582 |
| }, |
| { |
| "epoch": 3.410557184750733, |
| "grad_norm": 0.9257710808652309, |
| "learning_rate": 3.15194745458554e-05, |
| "loss": 0.1177, |
| "mean_token_accuracy": 0.9651551991701126, |
| "step": 583 |
| }, |
| { |
| "epoch": 3.4164222873900294, |
| "grad_norm": 0.8967042705762746, |
| "learning_rate": 3.149035275242441e-05, |
| "loss": 0.1056, |
| "mean_token_accuracy": 0.9653290957212448, |
| "step": 584 |
| }, |
| { |
| "epoch": 3.4222873900293256, |
| "grad_norm": 0.9946395497540884, |
| "learning_rate": 3.1461196512845834e-05, |
| "loss": 0.1422, |
| "mean_token_accuracy": 0.9611693695187569, |
| "step": 585 |
| }, |
| { |
| "epoch": 3.4281524926686218, |
| "grad_norm": 1.1659931848306362, |
| "learning_rate": 3.143200593294504e-05, |
| "loss": 0.1321, |
| "mean_token_accuracy": 0.9641125351190567, |
| "step": 586 |
| }, |
| { |
| "epoch": 3.434017595307918, |
| "grad_norm": 1.1333867615599893, |
| "learning_rate": 3.1402781118672065e-05, |
| "loss": 0.1339, |
| "mean_token_accuracy": 0.9595314189791679, |
| "step": 587 |
| }, |
| { |
| "epoch": 3.439882697947214, |
| "grad_norm": 0.9935811808065257, |
| "learning_rate": 3.137352217610115e-05, |
| "loss": 0.1355, |
| "mean_token_accuracy": 0.959190770983696, |
| "step": 588 |
| }, |
| { |
| "epoch": 3.4457478005865103, |
| "grad_norm": 1.3506457586579745, |
| "learning_rate": 3.1344229211430465e-05, |
| "loss": 0.1322, |
| "mean_token_accuracy": 0.9644437432289124, |
| "step": 589 |
| }, |
| { |
| "epoch": 3.4516129032258065, |
| "grad_norm": 0.8601614930196996, |
| "learning_rate": 3.131490233098164e-05, |
| "loss": 0.0998, |
| "mean_token_accuracy": 0.9721217975020409, |
| "step": 590 |
| }, |
| { |
| "epoch": 3.4574780058651027, |
| "grad_norm": 1.1429108686960525, |
| "learning_rate": 3.1285541641199383e-05, |
| "loss": 0.136, |
| "mean_token_accuracy": 0.9600744768977165, |
| "step": 591 |
| }, |
| { |
| "epoch": 3.463343108504399, |
| "grad_norm": 1.1562641886722125, |
| "learning_rate": 3.1256147248651166e-05, |
| "loss": 0.1167, |
| "mean_token_accuracy": 0.9670383408665657, |
| "step": 592 |
| }, |
| { |
| "epoch": 3.469208211143695, |
| "grad_norm": 1.140404363160057, |
| "learning_rate": 3.122671926002675e-05, |
| "loss": 0.1379, |
| "mean_token_accuracy": 0.9537649974226952, |
| "step": 593 |
| }, |
| { |
| "epoch": 3.4750733137829912, |
| "grad_norm": 1.0494864326031599, |
| "learning_rate": 3.119725778213785e-05, |
| "loss": 0.1272, |
| "mean_token_accuracy": 0.9602258205413818, |
| "step": 594 |
| }, |
| { |
| "epoch": 3.4809384164222874, |
| "grad_norm": 1.3319663312850152, |
| "learning_rate": 3.116776292191774e-05, |
| "loss": 0.1475, |
| "mean_token_accuracy": 0.9561516419053078, |
| "step": 595 |
| }, |
| { |
| "epoch": 3.4868035190615836, |
| "grad_norm": 1.097406612158555, |
| "learning_rate": 3.1138234786420834e-05, |
| "loss": 0.1126, |
| "mean_token_accuracy": 0.9662728533148766, |
| "step": 596 |
| }, |
| { |
| "epoch": 3.4926686217008798, |
| "grad_norm": 0.9710678312472462, |
| "learning_rate": 3.110867348282235e-05, |
| "loss": 0.125, |
| "mean_token_accuracy": 0.959438756108284, |
| "step": 597 |
| }, |
| { |
| "epoch": 3.498533724340176, |
| "grad_norm": 1.144735358404297, |
| "learning_rate": 3.107907911841787e-05, |
| "loss": 0.1207, |
| "mean_token_accuracy": 0.9607328251004219, |
| "step": 598 |
| }, |
| { |
| "epoch": 3.504398826979472, |
| "grad_norm": 1.0324245303515245, |
| "learning_rate": 3.104945180062301e-05, |
| "loss": 0.1202, |
| "mean_token_accuracy": 0.9630052521824837, |
| "step": 599 |
| }, |
| { |
| "epoch": 3.5102639296187683, |
| "grad_norm": 0.9863915422704965, |
| "learning_rate": 3.1019791636972936e-05, |
| "loss": 0.1176, |
| "mean_token_accuracy": 0.960706502199173, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.5161290322580645, |
| "grad_norm": 1.1729388689241018, |
| "learning_rate": 3.099009873512208e-05, |
| "loss": 0.13, |
| "mean_token_accuracy": 0.9642725735902786, |
| "step": 601 |
| }, |
| { |
| "epoch": 3.5219941348973607, |
| "grad_norm": 1.047671209762438, |
| "learning_rate": 3.0960373202843685e-05, |
| "loss": 0.1171, |
| "mean_token_accuracy": 0.9662189558148384, |
| "step": 602 |
| }, |
| { |
| "epoch": 3.527859237536657, |
| "grad_norm": 1.2279707434064486, |
| "learning_rate": 3.093061514802943e-05, |
| "loss": 0.1361, |
| "mean_token_accuracy": 0.9595428928732872, |
| "step": 603 |
| }, |
| { |
| "epoch": 3.533724340175953, |
| "grad_norm": 1.0214846172440661, |
| "learning_rate": 3.090082467868901e-05, |
| "loss": 0.1096, |
| "mean_token_accuracy": 0.9664286971092224, |
| "step": 604 |
| }, |
| { |
| "epoch": 3.5395894428152492, |
| "grad_norm": 1.0733131073175353, |
| "learning_rate": 3.087100190294983e-05, |
| "loss": 0.135, |
| "mean_token_accuracy": 0.961511418223381, |
| "step": 605 |
| }, |
| { |
| "epoch": 3.5454545454545454, |
| "grad_norm": 1.1130636637804585, |
| "learning_rate": 3.0841146929056505e-05, |
| "loss": 0.1385, |
| "mean_token_accuracy": 0.9636392369866371, |
| "step": 606 |
| }, |
| { |
| "epoch": 3.5513196480938416, |
| "grad_norm": 1.2231653555608124, |
| "learning_rate": 3.0811259865370535e-05, |
| "loss": 0.1185, |
| "mean_token_accuracy": 0.9636795818805695, |
| "step": 607 |
| }, |
| { |
| "epoch": 3.557184750733138, |
| "grad_norm": 1.0296766827227837, |
| "learning_rate": 3.07813408203699e-05, |
| "loss": 0.1138, |
| "mean_token_accuracy": 0.966869942843914, |
| "step": 608 |
| }, |
| { |
| "epoch": 3.563049853372434, |
| "grad_norm": 0.8726518475985359, |
| "learning_rate": 3.075138990264863e-05, |
| "loss": 0.1345, |
| "mean_token_accuracy": 0.9573319032788277, |
| "step": 609 |
| }, |
| { |
| "epoch": 3.56891495601173, |
| "grad_norm": 0.982040690626221, |
| "learning_rate": 3.072140722091648e-05, |
| "loss": 0.1098, |
| "mean_token_accuracy": 0.9681224301457405, |
| "step": 610 |
| }, |
| { |
| "epoch": 3.5747800586510263, |
| "grad_norm": 1.0451643330650482, |
| "learning_rate": 3.0691392883998455e-05, |
| "loss": 0.1462, |
| "mean_token_accuracy": 0.9576861411333084, |
| "step": 611 |
| }, |
| { |
| "epoch": 3.5806451612903225, |
| "grad_norm": 1.1110176689312552, |
| "learning_rate": 3.0661347000834496e-05, |
| "loss": 0.1205, |
| "mean_token_accuracy": 0.9639183133840561, |
| "step": 612 |
| }, |
| { |
| "epoch": 3.5865102639296187, |
| "grad_norm": 1.0329228692943557, |
| "learning_rate": 3.063126968047901e-05, |
| "loss": 0.1209, |
| "mean_token_accuracy": 0.9623586907982826, |
| "step": 613 |
| }, |
| { |
| "epoch": 3.592375366568915, |
| "grad_norm": 1.0468458895005488, |
| "learning_rate": 3.060116103210053e-05, |
| "loss": 0.1091, |
| "mean_token_accuracy": 0.9651313573122025, |
| "step": 614 |
| }, |
| { |
| "epoch": 3.598240469208211, |
| "grad_norm": 0.8132398233992888, |
| "learning_rate": 3.057102116498129e-05, |
| "loss": 0.1174, |
| "mean_token_accuracy": 0.9631007760763168, |
| "step": 615 |
| }, |
| { |
| "epoch": 3.6041055718475072, |
| "grad_norm": 1.242549002424926, |
| "learning_rate": 3.0540850188516826e-05, |
| "loss": 0.1425, |
| "mean_token_accuracy": 0.959061473608017, |
| "step": 616 |
| }, |
| { |
| "epoch": 3.6099706744868034, |
| "grad_norm": 1.0993514477355864, |
| "learning_rate": 3.051064821221561e-05, |
| "loss": 0.1031, |
| "mean_token_accuracy": 0.9673552736639977, |
| "step": 617 |
| }, |
| { |
| "epoch": 3.6158357771260996, |
| "grad_norm": 1.1657904332320168, |
| "learning_rate": 3.0480415345698606e-05, |
| "loss": 0.1552, |
| "mean_token_accuracy": 0.9506959840655327, |
| "step": 618 |
| }, |
| { |
| "epoch": 3.621700879765396, |
| "grad_norm": 1.150960665843493, |
| "learning_rate": 3.045015169869892e-05, |
| "loss": 0.1195, |
| "mean_token_accuracy": 0.9686484485864639, |
| "step": 619 |
| }, |
| { |
| "epoch": 3.627565982404692, |
| "grad_norm": 1.1076750183604511, |
| "learning_rate": 3.0419857381061355e-05, |
| "loss": 0.1421, |
| "mean_token_accuracy": 0.9578369930386543, |
| "step": 620 |
| }, |
| { |
| "epoch": 3.633431085043988, |
| "grad_norm": 0.9829376148207803, |
| "learning_rate": 3.0389532502742066e-05, |
| "loss": 0.1176, |
| "mean_token_accuracy": 0.9635881930589676, |
| "step": 621 |
| }, |
| { |
| "epoch": 3.6392961876832843, |
| "grad_norm": 1.0113335224798026, |
| "learning_rate": 3.0359177173808104e-05, |
| "loss": 0.1323, |
| "mean_token_accuracy": 0.9630266651511192, |
| "step": 622 |
| }, |
| { |
| "epoch": 3.6451612903225805, |
| "grad_norm": 0.9697653312050357, |
| "learning_rate": 3.032879150443705e-05, |
| "loss": 0.122, |
| "mean_token_accuracy": 0.9638355746865273, |
| "step": 623 |
| }, |
| { |
| "epoch": 3.6510263929618767, |
| "grad_norm": 1.024466551155938, |
| "learning_rate": 3.029837560491662e-05, |
| "loss": 0.124, |
| "mean_token_accuracy": 0.9646790847182274, |
| "step": 624 |
| }, |
| { |
| "epoch": 3.656891495601173, |
| "grad_norm": 1.124859894371915, |
| "learning_rate": 3.0267929585644236e-05, |
| "loss": 0.1337, |
| "mean_token_accuracy": 0.9610456451773643, |
| "step": 625 |
| }, |
| { |
| "epoch": 3.662756598240469, |
| "grad_norm": 0.9189572296363571, |
| "learning_rate": 3.0237453557126656e-05, |
| "loss": 0.1206, |
| "mean_token_accuracy": 0.9620600938796997, |
| "step": 626 |
| }, |
| { |
| "epoch": 3.6686217008797652, |
| "grad_norm": 0.9491940147888425, |
| "learning_rate": 3.020694762997956e-05, |
| "loss": 0.1331, |
| "mean_token_accuracy": 0.9604885205626488, |
| "step": 627 |
| }, |
| { |
| "epoch": 3.6744868035190614, |
| "grad_norm": 0.9537881007771453, |
| "learning_rate": 3.017641191492714e-05, |
| "loss": 0.1008, |
| "mean_token_accuracy": 0.9705606251955032, |
| "step": 628 |
| }, |
| { |
| "epoch": 3.6803519061583576, |
| "grad_norm": 0.9318456905477659, |
| "learning_rate": 3.0145846522801703e-05, |
| "loss": 0.104, |
| "mean_token_accuracy": 0.9685833752155304, |
| "step": 629 |
| }, |
| { |
| "epoch": 3.686217008797654, |
| "grad_norm": 1.1342752028945045, |
| "learning_rate": 3.0115251564543287e-05, |
| "loss": 0.1529, |
| "mean_token_accuracy": 0.9536353126168251, |
| "step": 630 |
| }, |
| { |
| "epoch": 3.6920821114369504, |
| "grad_norm": 1.26477365670727, |
| "learning_rate": 3.008462715119922e-05, |
| "loss": 0.1819, |
| "mean_token_accuracy": 0.9487387984991074, |
| "step": 631 |
| }, |
| { |
| "epoch": 3.6979472140762466, |
| "grad_norm": 1.1689930066757435, |
| "learning_rate": 3.0053973393923768e-05, |
| "loss": 0.1121, |
| "mean_token_accuracy": 0.9648066237568855, |
| "step": 632 |
| }, |
| { |
| "epoch": 3.703812316715543, |
| "grad_norm": 1.1899537022041637, |
| "learning_rate": 3.0023290403977694e-05, |
| "loss": 0.1543, |
| "mean_token_accuracy": 0.9553825706243515, |
| "step": 633 |
| }, |
| { |
| "epoch": 3.709677419354839, |
| "grad_norm": 1.1940929525894617, |
| "learning_rate": 2.9992578292727842e-05, |
| "loss": 0.133, |
| "mean_token_accuracy": 0.9566139429807663, |
| "step": 634 |
| }, |
| { |
| "epoch": 3.715542521994135, |
| "grad_norm": 1.021003772912016, |
| "learning_rate": 2.9961837171646778e-05, |
| "loss": 0.1224, |
| "mean_token_accuracy": 0.9648139327764511, |
| "step": 635 |
| }, |
| { |
| "epoch": 3.7214076246334313, |
| "grad_norm": 1.0968439934399599, |
| "learning_rate": 2.993106715231237e-05, |
| "loss": 0.1365, |
| "mean_token_accuracy": 0.9622660800814629, |
| "step": 636 |
| }, |
| { |
| "epoch": 3.7272727272727275, |
| "grad_norm": 1.284149147587276, |
| "learning_rate": 2.9900268346407336e-05, |
| "loss": 0.1491, |
| "mean_token_accuracy": 0.9584473669528961, |
| "step": 637 |
| }, |
| { |
| "epoch": 3.7331378299120237, |
| "grad_norm": 1.0442806693508573, |
| "learning_rate": 2.986944086571893e-05, |
| "loss": 0.1655, |
| "mean_token_accuracy": 0.9546647220849991, |
| "step": 638 |
| }, |
| { |
| "epoch": 3.73900293255132, |
| "grad_norm": 1.0873198584921593, |
| "learning_rate": 2.983858482213843e-05, |
| "loss": 0.1073, |
| "mean_token_accuracy": 0.9703760594129562, |
| "step": 639 |
| }, |
| { |
| "epoch": 3.744868035190616, |
| "grad_norm": 0.8172269296217749, |
| "learning_rate": 2.9807700327660834e-05, |
| "loss": 0.1367, |
| "mean_token_accuracy": 0.9637920260429382, |
| "step": 640 |
| }, |
| { |
| "epoch": 3.7507331378299122, |
| "grad_norm": 1.0256265023187172, |
| "learning_rate": 2.977678749438437e-05, |
| "loss": 0.1342, |
| "mean_token_accuracy": 0.9610049724578857, |
| "step": 641 |
| }, |
| { |
| "epoch": 3.7565982404692084, |
| "grad_norm": 0.9516278233131595, |
| "learning_rate": 2.9745846434510146e-05, |
| "loss": 0.1213, |
| "mean_token_accuracy": 0.9634719267487526, |
| "step": 642 |
| }, |
| { |
| "epoch": 3.7624633431085046, |
| "grad_norm": 1.1595407462435696, |
| "learning_rate": 2.9714877260341705e-05, |
| "loss": 0.1302, |
| "mean_token_accuracy": 0.9575833827257156, |
| "step": 643 |
| }, |
| { |
| "epoch": 3.768328445747801, |
| "grad_norm": 0.8386228216414092, |
| "learning_rate": 2.9683880084284648e-05, |
| "loss": 0.0906, |
| "mean_token_accuracy": 0.9728109389543533, |
| "step": 644 |
| }, |
| { |
| "epoch": 3.774193548387097, |
| "grad_norm": 0.9416321297213441, |
| "learning_rate": 2.96528550188462e-05, |
| "loss": 0.1395, |
| "mean_token_accuracy": 0.9599805325269699, |
| "step": 645 |
| }, |
| { |
| "epoch": 3.780058651026393, |
| "grad_norm": 0.96183773603705, |
| "learning_rate": 2.962180217663483e-05, |
| "loss": 0.1439, |
| "mean_token_accuracy": 0.9582567065954208, |
| "step": 646 |
| }, |
| { |
| "epoch": 3.7859237536656893, |
| "grad_norm": 1.131360501733182, |
| "learning_rate": 2.95907216703598e-05, |
| "loss": 0.1289, |
| "mean_token_accuracy": 0.9588178247213364, |
| "step": 647 |
| }, |
| { |
| "epoch": 3.7917888563049855, |
| "grad_norm": 1.1889300836649888, |
| "learning_rate": 2.9559613612830797e-05, |
| "loss": 0.1405, |
| "mean_token_accuracy": 0.9560826346278191, |
| "step": 648 |
| }, |
| { |
| "epoch": 3.7976539589442817, |
| "grad_norm": 0.9285715986177883, |
| "learning_rate": 2.952847811695751e-05, |
| "loss": 0.1138, |
| "mean_token_accuracy": 0.9683981463313103, |
| "step": 649 |
| }, |
| { |
| "epoch": 3.803519061583578, |
| "grad_norm": 0.903376412534086, |
| "learning_rate": 2.9497315295749218e-05, |
| "loss": 0.1312, |
| "mean_token_accuracy": 0.9626697823405266, |
| "step": 650 |
| }, |
| { |
| "epoch": 3.809384164222874, |
| "grad_norm": 1.4224710911985958, |
| "learning_rate": 2.9466125262314368e-05, |
| "loss": 0.1845, |
| "mean_token_accuracy": 0.9472808763384819, |
| "step": 651 |
| }, |
| { |
| "epoch": 3.8152492668621703, |
| "grad_norm": 1.1203349050086433, |
| "learning_rate": 2.9434908129860193e-05, |
| "loss": 0.1162, |
| "mean_token_accuracy": 0.9646425694227219, |
| "step": 652 |
| }, |
| { |
| "epoch": 3.8211143695014664, |
| "grad_norm": 1.039353270090754, |
| "learning_rate": 2.9403664011692276e-05, |
| "loss": 0.1513, |
| "mean_token_accuracy": 0.954769104719162, |
| "step": 653 |
| }, |
| { |
| "epoch": 3.8269794721407626, |
| "grad_norm": 1.0214390534355535, |
| "learning_rate": 2.9372393021214134e-05, |
| "loss": 0.1527, |
| "mean_token_accuracy": 0.9548315033316612, |
| "step": 654 |
| }, |
| { |
| "epoch": 3.832844574780059, |
| "grad_norm": 1.096985857955185, |
| "learning_rate": 2.9341095271926842e-05, |
| "loss": 0.1328, |
| "mean_token_accuracy": 0.9606662914156914, |
| "step": 655 |
| }, |
| { |
| "epoch": 3.838709677419355, |
| "grad_norm": 1.0291726390166944, |
| "learning_rate": 2.930977087742859e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9647061824798584, |
| "step": 656 |
| }, |
| { |
| "epoch": 3.844574780058651, |
| "grad_norm": 0.9808743642711901, |
| "learning_rate": 2.9278419951414277e-05, |
| "loss": 0.1268, |
| "mean_token_accuracy": 0.9629314094781876, |
| "step": 657 |
| }, |
| { |
| "epoch": 3.8504398826979473, |
| "grad_norm": 0.8692894059522167, |
| "learning_rate": 2.9247042607675105e-05, |
| "loss": 0.1229, |
| "mean_token_accuracy": 0.9611641019582748, |
| "step": 658 |
| }, |
| { |
| "epoch": 3.8563049853372435, |
| "grad_norm": 0.8870762370430467, |
| "learning_rate": 2.9215638960098164e-05, |
| "loss": 0.0913, |
| "mean_token_accuracy": 0.9687012657523155, |
| "step": 659 |
| }, |
| { |
| "epoch": 3.8621700879765397, |
| "grad_norm": 0.8587891520353423, |
| "learning_rate": 2.9184209122665996e-05, |
| "loss": 0.129, |
| "mean_token_accuracy": 0.9611743912100792, |
| "step": 660 |
| }, |
| { |
| "epoch": 3.868035190615836, |
| "grad_norm": 1.0641124073179626, |
| "learning_rate": 2.915275320945623e-05, |
| "loss": 0.1436, |
| "mean_token_accuracy": 0.9597739949822426, |
| "step": 661 |
| }, |
| { |
| "epoch": 3.873900293255132, |
| "grad_norm": 1.238895601397053, |
| "learning_rate": 2.9121271334641127e-05, |
| "loss": 0.1393, |
| "mean_token_accuracy": 0.9588789939880371, |
| "step": 662 |
| }, |
| { |
| "epoch": 3.8797653958944283, |
| "grad_norm": 1.0953247983118455, |
| "learning_rate": 2.908976361248717e-05, |
| "loss": 0.1197, |
| "mean_token_accuracy": 0.9674094244837761, |
| "step": 663 |
| }, |
| { |
| "epoch": 3.8856304985337244, |
| "grad_norm": 0.9234924370356041, |
| "learning_rate": 2.9058230157354674e-05, |
| "loss": 0.1458, |
| "mean_token_accuracy": 0.9566569328308105, |
| "step": 664 |
| }, |
| { |
| "epoch": 3.8914956011730206, |
| "grad_norm": 1.243221731581411, |
| "learning_rate": 2.902667108369734e-05, |
| "loss": 0.1562, |
| "mean_token_accuracy": 0.9574529975652695, |
| "step": 665 |
| }, |
| { |
| "epoch": 3.897360703812317, |
| "grad_norm": 1.1983136333100237, |
| "learning_rate": 2.8995086506061862e-05, |
| "loss": 0.1253, |
| "mean_token_accuracy": 0.9618943110108376, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.903225806451613, |
| "grad_norm": 1.0812316125608272, |
| "learning_rate": 2.896347653908749e-05, |
| "loss": 0.1164, |
| "mean_token_accuracy": 0.9669682160019875, |
| "step": 667 |
| }, |
| { |
| "epoch": 3.909090909090909, |
| "grad_norm": 0.8182003202052918, |
| "learning_rate": 2.8931841297505657e-05, |
| "loss": 0.1224, |
| "mean_token_accuracy": 0.9632921889424324, |
| "step": 668 |
| }, |
| { |
| "epoch": 3.9149560117302054, |
| "grad_norm": 0.8941991483105637, |
| "learning_rate": 2.8900180896139503e-05, |
| "loss": 0.1024, |
| "mean_token_accuracy": 0.9696899205446243, |
| "step": 669 |
| }, |
| { |
| "epoch": 3.9208211143695015, |
| "grad_norm": 0.9809121287934861, |
| "learning_rate": 2.8868495449903498e-05, |
| "loss": 0.0985, |
| "mean_token_accuracy": 0.9719806686043739, |
| "step": 670 |
| }, |
| { |
| "epoch": 3.9266862170087977, |
| "grad_norm": 0.8417864765905216, |
| "learning_rate": 2.8836785073803014e-05, |
| "loss": 0.1086, |
| "mean_token_accuracy": 0.9669199660420418, |
| "step": 671 |
| }, |
| { |
| "epoch": 3.932551319648094, |
| "grad_norm": 0.8345877730462873, |
| "learning_rate": 2.880504988293391e-05, |
| "loss": 0.1313, |
| "mean_token_accuracy": 0.9613889157772064, |
| "step": 672 |
| }, |
| { |
| "epoch": 3.93841642228739, |
| "grad_norm": 0.9129539631264306, |
| "learning_rate": 2.8773289992482115e-05, |
| "loss": 0.1131, |
| "mean_token_accuracy": 0.9657901525497437, |
| "step": 673 |
| }, |
| { |
| "epoch": 3.9442815249266863, |
| "grad_norm": 0.9668219103314973, |
| "learning_rate": 2.87415055177232e-05, |
| "loss": 0.1194, |
| "mean_token_accuracy": 0.9630595743656158, |
| "step": 674 |
| }, |
| { |
| "epoch": 3.9501466275659824, |
| "grad_norm": 0.825214625411393, |
| "learning_rate": 2.870969657402197e-05, |
| "loss": 0.1303, |
| "mean_token_accuracy": 0.9587484747171402, |
| "step": 675 |
| }, |
| { |
| "epoch": 3.9560117302052786, |
| "grad_norm": 1.2778726879319384, |
| "learning_rate": 2.867786327683205e-05, |
| "loss": 0.1641, |
| "mean_token_accuracy": 0.9540645256638527, |
| "step": 676 |
| }, |
| { |
| "epoch": 3.961876832844575, |
| "grad_norm": 1.2095162631576735, |
| "learning_rate": 2.864600574169545e-05, |
| "loss": 0.1297, |
| "mean_token_accuracy": 0.9639428108930588, |
| "step": 677 |
| }, |
| { |
| "epoch": 3.967741935483871, |
| "grad_norm": 1.2245034866624815, |
| "learning_rate": 2.861412408424216e-05, |
| "loss": 0.1298, |
| "mean_token_accuracy": 0.961310125887394, |
| "step": 678 |
| }, |
| { |
| "epoch": 3.973607038123167, |
| "grad_norm": 1.0900181972818253, |
| "learning_rate": 2.8582218420189706e-05, |
| "loss": 0.1234, |
| "mean_token_accuracy": 0.9650765135884285, |
| "step": 679 |
| }, |
| { |
| "epoch": 3.9794721407624634, |
| "grad_norm": 0.995318870496006, |
| "learning_rate": 2.855028886534278e-05, |
| "loss": 0.149, |
| "mean_token_accuracy": 0.9595285654067993, |
| "step": 680 |
| }, |
| { |
| "epoch": 3.9853372434017595, |
| "grad_norm": 1.2425322980130953, |
| "learning_rate": 2.851833553559276e-05, |
| "loss": 0.1267, |
| "mean_token_accuracy": 0.963188923895359, |
| "step": 681 |
| }, |
| { |
| "epoch": 3.9912023460410557, |
| "grad_norm": 0.9820863081556225, |
| "learning_rate": 2.848635854691733e-05, |
| "loss": 0.1348, |
| "mean_token_accuracy": 0.9570389837026596, |
| "step": 682 |
| }, |
| { |
| "epoch": 3.997067448680352, |
| "grad_norm": 0.9569301662769316, |
| "learning_rate": 2.8454358015380046e-05, |
| "loss": 0.107, |
| "mean_token_accuracy": 0.9685926288366318, |
| "step": 683 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.4219372689116887, |
| "learning_rate": 2.8422334057129913e-05, |
| "loss": 0.1163, |
| "mean_token_accuracy": 0.9649382084608078, |
| "step": 684 |
| }, |
| { |
| "epoch": 4.005865102639296, |
| "grad_norm": 0.709241476686682, |
| "learning_rate": 2.8390286788400967e-05, |
| "loss": 0.0887, |
| "mean_token_accuracy": 0.9674655348062515, |
| "step": 685 |
| }, |
| { |
| "epoch": 4.011730205278592, |
| "grad_norm": 0.6173979664464195, |
| "learning_rate": 2.8358216325511847e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9766078963875771, |
| "step": 686 |
| }, |
| { |
| "epoch": 4.0175953079178885, |
| "grad_norm": 0.9128727805263251, |
| "learning_rate": 2.832612278486538e-05, |
| "loss": 0.1148, |
| "mean_token_accuracy": 0.9675131067633629, |
| "step": 687 |
| }, |
| { |
| "epoch": 4.023460410557185, |
| "grad_norm": 0.9010122632573339, |
| "learning_rate": 2.8294006282948165e-05, |
| "loss": 0.1047, |
| "mean_token_accuracy": 0.9745191410183907, |
| "step": 688 |
| }, |
| { |
| "epoch": 4.029325513196481, |
| "grad_norm": 0.7585836610895886, |
| "learning_rate": 2.8261866936330123e-05, |
| "loss": 0.0892, |
| "mean_token_accuracy": 0.9691687375307083, |
| "step": 689 |
| }, |
| { |
| "epoch": 4.035190615835777, |
| "grad_norm": 0.7878473822842609, |
| "learning_rate": 2.8229704861664113e-05, |
| "loss": 0.0876, |
| "mean_token_accuracy": 0.974379763007164, |
| "step": 690 |
| }, |
| { |
| "epoch": 4.041055718475073, |
| "grad_norm": 0.7821495099972663, |
| "learning_rate": 2.8197520175685462e-05, |
| "loss": 0.0847, |
| "mean_token_accuracy": 0.975913368165493, |
| "step": 691 |
| }, |
| { |
| "epoch": 4.0469208211143695, |
| "grad_norm": 0.7293539456978901, |
| "learning_rate": 2.8165312995211596e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9754629284143448, |
| "step": 692 |
| }, |
| { |
| "epoch": 4.052785923753666, |
| "grad_norm": 0.8275396448134474, |
| "learning_rate": 2.813308343714156e-05, |
| "loss": 0.0917, |
| "mean_token_accuracy": 0.9701932370662689, |
| "step": 693 |
| }, |
| { |
| "epoch": 4.058651026392962, |
| "grad_norm": 1.0230174194614936, |
| "learning_rate": 2.810083161845564e-05, |
| "loss": 0.1045, |
| "mean_token_accuracy": 0.9693364053964615, |
| "step": 694 |
| }, |
| { |
| "epoch": 4.064516129032258, |
| "grad_norm": 0.9057093506395073, |
| "learning_rate": 2.8068557656214913e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.96998730301857, |
| "step": 695 |
| }, |
| { |
| "epoch": 4.070381231671554, |
| "grad_norm": 0.6599318416871625, |
| "learning_rate": 2.8036261667560826e-05, |
| "loss": 0.088, |
| "mean_token_accuracy": 0.9751304760575294, |
| "step": 696 |
| }, |
| { |
| "epoch": 4.07624633431085, |
| "grad_norm": 1.0436927596250734, |
| "learning_rate": 2.8003943769714776e-05, |
| "loss": 0.1212, |
| "mean_token_accuracy": 0.9670998901128769, |
| "step": 697 |
| }, |
| { |
| "epoch": 4.0821114369501466, |
| "grad_norm": 1.1198652536954283, |
| "learning_rate": 2.7971604079977673e-05, |
| "loss": 0.1195, |
| "mean_token_accuracy": 0.9634276106953621, |
| "step": 698 |
| }, |
| { |
| "epoch": 4.087976539589443, |
| "grad_norm": 1.2320403179620185, |
| "learning_rate": 2.793924271572954e-05, |
| "loss": 0.1039, |
| "mean_token_accuracy": 0.9721868559718132, |
| "step": 699 |
| }, |
| { |
| "epoch": 4.093841642228739, |
| "grad_norm": 1.3210237101709343, |
| "learning_rate": 2.7906859794429047e-05, |
| "loss": 0.1096, |
| "mean_token_accuracy": 0.9650368392467499, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.099706744868035, |
| "grad_norm": 0.8181651139051924, |
| "learning_rate": 2.787445543361313e-05, |
| "loss": 0.0839, |
| "mean_token_accuracy": 0.9707164391875267, |
| "step": 701 |
| }, |
| { |
| "epoch": 4.105571847507331, |
| "grad_norm": 0.8473790019730275, |
| "learning_rate": 2.7842029750896525e-05, |
| "loss": 0.1009, |
| "mean_token_accuracy": 0.9700881019234657, |
| "step": 702 |
| }, |
| { |
| "epoch": 4.1114369501466275, |
| "grad_norm": 0.9904668060663937, |
| "learning_rate": 2.7809582863971373e-05, |
| "loss": 0.1043, |
| "mean_token_accuracy": 0.9687797203660011, |
| "step": 703 |
| }, |
| { |
| "epoch": 4.117302052785924, |
| "grad_norm": 0.9380936164168817, |
| "learning_rate": 2.777711489060676e-05, |
| "loss": 0.1144, |
| "mean_token_accuracy": 0.9675206765532494, |
| "step": 704 |
| }, |
| { |
| "epoch": 4.12316715542522, |
| "grad_norm": 0.9031920501562392, |
| "learning_rate": 2.7744625948648316e-05, |
| "loss": 0.1035, |
| "mean_token_accuracy": 0.9714310243725777, |
| "step": 705 |
| }, |
| { |
| "epoch": 4.129032258064516, |
| "grad_norm": 0.8428938896716028, |
| "learning_rate": 2.7712116156017783e-05, |
| "loss": 0.097, |
| "mean_token_accuracy": 0.9733357578516006, |
| "step": 706 |
| }, |
| { |
| "epoch": 4.134897360703812, |
| "grad_norm": 0.9412808030019473, |
| "learning_rate": 2.7679585630712585e-05, |
| "loss": 0.1113, |
| "mean_token_accuracy": 0.9657137170433998, |
| "step": 707 |
| }, |
| { |
| "epoch": 4.140762463343108, |
| "grad_norm": 0.7779470899780662, |
| "learning_rate": 2.764703449080538e-05, |
| "loss": 0.0978, |
| "mean_token_accuracy": 0.97261843085289, |
| "step": 708 |
| }, |
| { |
| "epoch": 4.146627565982405, |
| "grad_norm": 0.8327366946019571, |
| "learning_rate": 2.761446285444366e-05, |
| "loss": 0.099, |
| "mean_token_accuracy": 0.9688172861933708, |
| "step": 709 |
| }, |
| { |
| "epoch": 4.152492668621701, |
| "grad_norm": 0.6166216833854606, |
| "learning_rate": 2.758187083984931e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9770351052284241, |
| "step": 710 |
| }, |
| { |
| "epoch": 4.158357771260997, |
| "grad_norm": 0.981652746856198, |
| "learning_rate": 2.754925856531819e-05, |
| "loss": 0.1155, |
| "mean_token_accuracy": 0.9650738835334778, |
| "step": 711 |
| }, |
| { |
| "epoch": 4.164222873900293, |
| "grad_norm": 0.8621583383424518, |
| "learning_rate": 2.7516626149219678e-05, |
| "loss": 0.094, |
| "mean_token_accuracy": 0.9712882563471794, |
| "step": 712 |
| }, |
| { |
| "epoch": 4.170087976539589, |
| "grad_norm": 0.8715573279290548, |
| "learning_rate": 2.7483973709996267e-05, |
| "loss": 0.1067, |
| "mean_token_accuracy": 0.9686557427048683, |
| "step": 713 |
| }, |
| { |
| "epoch": 4.1759530791788855, |
| "grad_norm": 0.9830720772685587, |
| "learning_rate": 2.7451301366163116e-05, |
| "loss": 0.1157, |
| "mean_token_accuracy": 0.9641370326280594, |
| "step": 714 |
| }, |
| { |
| "epoch": 4.181818181818182, |
| "grad_norm": 0.614999654305874, |
| "learning_rate": 2.741860923630765e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.97749213129282, |
| "step": 715 |
| }, |
| { |
| "epoch": 4.187683284457478, |
| "grad_norm": 0.8528408299395791, |
| "learning_rate": 2.7385897439089086e-05, |
| "loss": 0.1054, |
| "mean_token_accuracy": 0.9677549675107002, |
| "step": 716 |
| }, |
| { |
| "epoch": 4.193548387096774, |
| "grad_norm": 0.9483311566184626, |
| "learning_rate": 2.735316609323804e-05, |
| "loss": 0.1161, |
| "mean_token_accuracy": 0.9652642160654068, |
| "step": 717 |
| }, |
| { |
| "epoch": 4.19941348973607, |
| "grad_norm": 0.9247175808359333, |
| "learning_rate": 2.7320415317556085e-05, |
| "loss": 0.1038, |
| "mean_token_accuracy": 0.9713630378246307, |
| "step": 718 |
| }, |
| { |
| "epoch": 4.205278592375366, |
| "grad_norm": 0.7419985712721145, |
| "learning_rate": 2.72876452309153e-05, |
| "loss": 0.0766, |
| "mean_token_accuracy": 0.9739850908517838, |
| "step": 719 |
| }, |
| { |
| "epoch": 4.211143695014663, |
| "grad_norm": 1.0296466250591831, |
| "learning_rate": 2.7254855952257867e-05, |
| "loss": 0.1103, |
| "mean_token_accuracy": 0.9655221551656723, |
| "step": 720 |
| }, |
| { |
| "epoch": 4.217008797653959, |
| "grad_norm": 1.1384543982681885, |
| "learning_rate": 2.7222047600595626e-05, |
| "loss": 0.1285, |
| "mean_token_accuracy": 0.9629199728369713, |
| "step": 721 |
| }, |
| { |
| "epoch": 4.222873900293255, |
| "grad_norm": 0.8447805103003336, |
| "learning_rate": 2.718922029500965e-05, |
| "loss": 0.1048, |
| "mean_token_accuracy": 0.9712353870272636, |
| "step": 722 |
| }, |
| { |
| "epoch": 4.228739002932551, |
| "grad_norm": 0.7431719179679741, |
| "learning_rate": 2.7156374154649787e-05, |
| "loss": 0.0924, |
| "mean_token_accuracy": 0.9682846069335938, |
| "step": 723 |
| }, |
| { |
| "epoch": 4.234604105571847, |
| "grad_norm": 0.7009163129349052, |
| "learning_rate": 2.7123509298734267e-05, |
| "loss": 0.0918, |
| "mean_token_accuracy": 0.9705768898129463, |
| "step": 724 |
| }, |
| { |
| "epoch": 4.2404692082111435, |
| "grad_norm": 0.931316392486653, |
| "learning_rate": 2.7090625846549247e-05, |
| "loss": 0.103, |
| "mean_token_accuracy": 0.9691152274608612, |
| "step": 725 |
| }, |
| { |
| "epoch": 4.24633431085044, |
| "grad_norm": 0.8894668079937573, |
| "learning_rate": 2.705772391744837e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.9710854515433311, |
| "step": 726 |
| }, |
| { |
| "epoch": 4.252199413489736, |
| "grad_norm": 0.886947309997863, |
| "learning_rate": 2.7024803630852362e-05, |
| "loss": 0.1117, |
| "mean_token_accuracy": 0.9700823053717613, |
| "step": 727 |
| }, |
| { |
| "epoch": 4.258064516129032, |
| "grad_norm": 0.9113850424773436, |
| "learning_rate": 2.699186510624856e-05, |
| "loss": 0.1251, |
| "mean_token_accuracy": 0.9644127413630486, |
| "step": 728 |
| }, |
| { |
| "epoch": 4.263929618768328, |
| "grad_norm": 0.849019273066941, |
| "learning_rate": 2.6958908463190506e-05, |
| "loss": 0.1051, |
| "mean_token_accuracy": 0.9653807803988457, |
| "step": 729 |
| }, |
| { |
| "epoch": 4.269794721407624, |
| "grad_norm": 0.8066154131479902, |
| "learning_rate": 2.6925933821297497e-05, |
| "loss": 0.1044, |
| "mean_token_accuracy": 0.9673965945839882, |
| "step": 730 |
| }, |
| { |
| "epoch": 4.275659824046921, |
| "grad_norm": 0.9500006710768306, |
| "learning_rate": 2.6892941300254176e-05, |
| "loss": 0.1043, |
| "mean_token_accuracy": 0.9693391621112823, |
| "step": 731 |
| }, |
| { |
| "epoch": 4.281524926686217, |
| "grad_norm": 0.8393073675779207, |
| "learning_rate": 2.685993101981007e-05, |
| "loss": 0.0986, |
| "mean_token_accuracy": 0.9713418409228325, |
| "step": 732 |
| }, |
| { |
| "epoch": 4.287390029325513, |
| "grad_norm": 0.7433667011265701, |
| "learning_rate": 2.6826903099779157e-05, |
| "loss": 0.0919, |
| "mean_token_accuracy": 0.9730396121740341, |
| "step": 733 |
| }, |
| { |
| "epoch": 4.293255131964809, |
| "grad_norm": 1.040976292438877, |
| "learning_rate": 2.679385766003945e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9655982628464699, |
| "step": 734 |
| }, |
| { |
| "epoch": 4.299120234604105, |
| "grad_norm": 0.7644680704316061, |
| "learning_rate": 2.676079482053255e-05, |
| "loss": 0.1094, |
| "mean_token_accuracy": 0.9659839272499084, |
| "step": 735 |
| }, |
| { |
| "epoch": 4.3049853372434015, |
| "grad_norm": 0.864902634731277, |
| "learning_rate": 2.6727714701263212e-05, |
| "loss": 0.1011, |
| "mean_token_accuracy": 0.9684811905026436, |
| "step": 736 |
| }, |
| { |
| "epoch": 4.310850439882698, |
| "grad_norm": 0.9630405184292459, |
| "learning_rate": 2.669461742229891e-05, |
| "loss": 0.1145, |
| "mean_token_accuracy": 0.9672865197062492, |
| "step": 737 |
| }, |
| { |
| "epoch": 4.316715542521994, |
| "grad_norm": 0.870823765290408, |
| "learning_rate": 2.6661503103769404e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.9726337790489197, |
| "step": 738 |
| }, |
| { |
| "epoch": 4.32258064516129, |
| "grad_norm": 0.9663765543260392, |
| "learning_rate": 2.6628371865866286e-05, |
| "loss": 0.1185, |
| "mean_token_accuracy": 0.965896911919117, |
| "step": 739 |
| }, |
| { |
| "epoch": 4.328445747800586, |
| "grad_norm": 0.8933323190339318, |
| "learning_rate": 2.6595223828842578e-05, |
| "loss": 0.1087, |
| "mean_token_accuracy": 0.9675631076097488, |
| "step": 740 |
| }, |
| { |
| "epoch": 4.334310850439882, |
| "grad_norm": 0.8062191969539717, |
| "learning_rate": 2.6562059113012253e-05, |
| "loss": 0.1017, |
| "mean_token_accuracy": 0.9707746133208275, |
| "step": 741 |
| }, |
| { |
| "epoch": 4.340175953079179, |
| "grad_norm": 0.7386260737331057, |
| "learning_rate": 2.6528877838749853e-05, |
| "loss": 0.0901, |
| "mean_token_accuracy": 0.9732140600681305, |
| "step": 742 |
| }, |
| { |
| "epoch": 4.346041055718475, |
| "grad_norm": 0.9540370649859513, |
| "learning_rate": 2.6495680126489984e-05, |
| "loss": 0.0996, |
| "mean_token_accuracy": 0.9677102938294411, |
| "step": 743 |
| }, |
| { |
| "epoch": 4.351906158357771, |
| "grad_norm": 0.9249637570107009, |
| "learning_rate": 2.6462466096726954e-05, |
| "loss": 0.1219, |
| "mean_token_accuracy": 0.9667763486504555, |
| "step": 744 |
| }, |
| { |
| "epoch": 4.357771260997067, |
| "grad_norm": 0.7792653229818829, |
| "learning_rate": 2.6429235870014256e-05, |
| "loss": 0.0903, |
| "mean_token_accuracy": 0.9705804735422134, |
| "step": 745 |
| }, |
| { |
| "epoch": 4.363636363636363, |
| "grad_norm": 0.8140317445393424, |
| "learning_rate": 2.639598956696421e-05, |
| "loss": 0.1107, |
| "mean_token_accuracy": 0.9697221592068672, |
| "step": 746 |
| }, |
| { |
| "epoch": 4.3695014662756595, |
| "grad_norm": 0.6129404128094667, |
| "learning_rate": 2.6362727308247458e-05, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.9690393060445786, |
| "step": 747 |
| }, |
| { |
| "epoch": 4.375366568914956, |
| "grad_norm": 0.8363655869915996, |
| "learning_rate": 2.6329449214592568e-05, |
| "loss": 0.11, |
| "mean_token_accuracy": 0.9687171280384064, |
| "step": 748 |
| }, |
| { |
| "epoch": 4.381231671554252, |
| "grad_norm": 0.8829130626858406, |
| "learning_rate": 2.6296155406785578e-05, |
| "loss": 0.1064, |
| "mean_token_accuracy": 0.9672866985201836, |
| "step": 749 |
| }, |
| { |
| "epoch": 4.387096774193548, |
| "grad_norm": 0.8266185050112379, |
| "learning_rate": 2.6262846005669572e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.968304455280304, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.392961876832844, |
| "grad_norm": 0.7916713310234549, |
| "learning_rate": 2.6229521132144212e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9701255336403847, |
| "step": 751 |
| }, |
| { |
| "epoch": 4.39882697947214, |
| "grad_norm": 0.7701614711517824, |
| "learning_rate": 2.619618090716534e-05, |
| "loss": 0.0943, |
| "mean_token_accuracy": 0.9703449010848999, |
| "step": 752 |
| }, |
| { |
| "epoch": 4.404692082111437, |
| "grad_norm": 0.6968343695166375, |
| "learning_rate": 2.61628254517445e-05, |
| "loss": 0.0843, |
| "mean_token_accuracy": 0.971925251185894, |
| "step": 753 |
| }, |
| { |
| "epoch": 4.410557184750733, |
| "grad_norm": 0.9629492868220234, |
| "learning_rate": 2.612945488694853e-05, |
| "loss": 0.1134, |
| "mean_token_accuracy": 0.9676346555352211, |
| "step": 754 |
| }, |
| { |
| "epoch": 4.416422287390029, |
| "grad_norm": 0.854167238685368, |
| "learning_rate": 2.6096069333899094e-05, |
| "loss": 0.0898, |
| "mean_token_accuracy": 0.9729126617312431, |
| "step": 755 |
| }, |
| { |
| "epoch": 4.422287390029325, |
| "grad_norm": 1.1094574088373235, |
| "learning_rate": 2.6062668913772275e-05, |
| "loss": 0.1299, |
| "mean_token_accuracy": 0.9626433402299881, |
| "step": 756 |
| }, |
| { |
| "epoch": 4.428152492668621, |
| "grad_norm": 0.9014170089707675, |
| "learning_rate": 2.60292537477981e-05, |
| "loss": 0.1019, |
| "mean_token_accuracy": 0.9680602997541428, |
| "step": 757 |
| }, |
| { |
| "epoch": 4.4340175953079175, |
| "grad_norm": 0.9810775727763513, |
| "learning_rate": 2.5995823957260132e-05, |
| "loss": 0.1279, |
| "mean_token_accuracy": 0.9605071842670441, |
| "step": 758 |
| }, |
| { |
| "epoch": 4.439882697947214, |
| "grad_norm": 0.7869832998345235, |
| "learning_rate": 2.596237966349501e-05, |
| "loss": 0.0985, |
| "mean_token_accuracy": 0.9684450924396515, |
| "step": 759 |
| }, |
| { |
| "epoch": 4.44574780058651, |
| "grad_norm": 0.7758876264350651, |
| "learning_rate": 2.592892098789201e-05, |
| "loss": 0.0865, |
| "mean_token_accuracy": 0.9744958430528641, |
| "step": 760 |
| }, |
| { |
| "epoch": 4.451612903225806, |
| "grad_norm": 0.8860224269922468, |
| "learning_rate": 2.589544805189261e-05, |
| "loss": 0.1083, |
| "mean_token_accuracy": 0.9676248952746391, |
| "step": 761 |
| }, |
| { |
| "epoch": 4.457478005865102, |
| "grad_norm": 0.7409093088530903, |
| "learning_rate": 2.5861960976990056e-05, |
| "loss": 0.093, |
| "mean_token_accuracy": 0.9732578694820404, |
| "step": 762 |
| }, |
| { |
| "epoch": 4.463343108504398, |
| "grad_norm": 1.1676717217139776, |
| "learning_rate": 2.5828459884728898e-05, |
| "loss": 0.1169, |
| "mean_token_accuracy": 0.9647529572248459, |
| "step": 763 |
| }, |
| { |
| "epoch": 4.469208211143695, |
| "grad_norm": 0.6625765738343412, |
| "learning_rate": 2.5794944896704572e-05, |
| "loss": 0.0819, |
| "mean_token_accuracy": 0.9757863134145737, |
| "step": 764 |
| }, |
| { |
| "epoch": 4.475073313782991, |
| "grad_norm": 0.6874296342022658, |
| "learning_rate": 2.5761416134562955e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9720703139901161, |
| "step": 765 |
| }, |
| { |
| "epoch": 4.480938416422287, |
| "grad_norm": 0.7247716827978176, |
| "learning_rate": 2.5727873719999904e-05, |
| "loss": 0.093, |
| "mean_token_accuracy": 0.9728222563862801, |
| "step": 766 |
| }, |
| { |
| "epoch": 4.486803519061583, |
| "grad_norm": 0.8452909187598238, |
| "learning_rate": 2.569431777476084e-05, |
| "loss": 0.1102, |
| "mean_token_accuracy": 0.9691123142838478, |
| "step": 767 |
| }, |
| { |
| "epoch": 4.492668621700879, |
| "grad_norm": 0.6269007242451082, |
| "learning_rate": 2.566074842064029e-05, |
| "loss": 0.0825, |
| "mean_token_accuracy": 0.9736087173223495, |
| "step": 768 |
| }, |
| { |
| "epoch": 4.4985337243401755, |
| "grad_norm": 0.6833634732485709, |
| "learning_rate": 2.562716577948145e-05, |
| "loss": 0.0894, |
| "mean_token_accuracy": 0.9721810445189476, |
| "step": 769 |
| }, |
| { |
| "epoch": 4.504398826979472, |
| "grad_norm": 0.9016470000451788, |
| "learning_rate": 2.5593569973175757e-05, |
| "loss": 0.099, |
| "mean_token_accuracy": 0.9684557020664215, |
| "step": 770 |
| }, |
| { |
| "epoch": 4.510263929618768, |
| "grad_norm": 0.8214283949891577, |
| "learning_rate": 2.5559961123662405e-05, |
| "loss": 0.09, |
| "mean_token_accuracy": 0.9735552668571472, |
| "step": 771 |
| }, |
| { |
| "epoch": 4.516129032258064, |
| "grad_norm": 0.8539772217032783, |
| "learning_rate": 2.5526339352927956e-05, |
| "loss": 0.0985, |
| "mean_token_accuracy": 0.9696103483438492, |
| "step": 772 |
| }, |
| { |
| "epoch": 4.52199413489736, |
| "grad_norm": 0.7730054145378401, |
| "learning_rate": 2.5492704783005847e-05, |
| "loss": 0.0979, |
| "mean_token_accuracy": 0.9686698243021965, |
| "step": 773 |
| }, |
| { |
| "epoch": 4.527859237536656, |
| "grad_norm": 1.2854864103824832, |
| "learning_rate": 2.5459057535975985e-05, |
| "loss": 0.127, |
| "mean_token_accuracy": 0.9684014022350311, |
| "step": 774 |
| }, |
| { |
| "epoch": 4.533724340175953, |
| "grad_norm": 1.0322132404220972, |
| "learning_rate": 2.542539773396429e-05, |
| "loss": 0.1147, |
| "mean_token_accuracy": 0.9624549448490143, |
| "step": 775 |
| }, |
| { |
| "epoch": 4.539589442815249, |
| "grad_norm": 1.0925929672195411, |
| "learning_rate": 2.5391725499142253e-05, |
| "loss": 0.1274, |
| "mean_token_accuracy": 0.9652435928583145, |
| "step": 776 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 0.7645119510316551, |
| "learning_rate": 2.535804095372648e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.9722094312310219, |
| "step": 777 |
| }, |
| { |
| "epoch": 4.551319648093841, |
| "grad_norm": 0.8311326236464569, |
| "learning_rate": 2.5324344219978273e-05, |
| "loss": 0.1036, |
| "mean_token_accuracy": 0.9671364203095436, |
| "step": 778 |
| }, |
| { |
| "epoch": 4.557184750733137, |
| "grad_norm": 0.8292493397463394, |
| "learning_rate": 2.5290635420203162e-05, |
| "loss": 0.1043, |
| "mean_token_accuracy": 0.9715534523129463, |
| "step": 779 |
| }, |
| { |
| "epoch": 4.563049853372434, |
| "grad_norm": 0.8608211600298957, |
| "learning_rate": 2.525691467675048e-05, |
| "loss": 0.1093, |
| "mean_token_accuracy": 0.9706666171550751, |
| "step": 780 |
| }, |
| { |
| "epoch": 4.568914956011731, |
| "grad_norm": 0.6784230146610292, |
| "learning_rate": 2.5223182112012897e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9699116349220276, |
| "step": 781 |
| }, |
| { |
| "epoch": 4.574780058651027, |
| "grad_norm": 0.7343542604693692, |
| "learning_rate": 2.5189437848426016e-05, |
| "loss": 0.0839, |
| "mean_token_accuracy": 0.9741816371679306, |
| "step": 782 |
| }, |
| { |
| "epoch": 4.580645161290323, |
| "grad_norm": 0.8193787549551812, |
| "learning_rate": 2.515568200846787e-05, |
| "loss": 0.1126, |
| "mean_token_accuracy": 0.965341791510582, |
| "step": 783 |
| }, |
| { |
| "epoch": 4.586510263929619, |
| "grad_norm": 0.7686994711379227, |
| "learning_rate": 2.5121914714658526e-05, |
| "loss": 0.1026, |
| "mean_token_accuracy": 0.9705801084637642, |
| "step": 784 |
| }, |
| { |
| "epoch": 4.592375366568915, |
| "grad_norm": 0.6846639175891126, |
| "learning_rate": 2.5088136089559636e-05, |
| "loss": 0.0881, |
| "mean_token_accuracy": 0.9729414209723473, |
| "step": 785 |
| }, |
| { |
| "epoch": 4.5982404692082115, |
| "grad_norm": 0.6457900343034328, |
| "learning_rate": 2.5054346255773952e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9756535366177559, |
| "step": 786 |
| }, |
| { |
| "epoch": 4.604105571847508, |
| "grad_norm": 0.8155908776106904, |
| "learning_rate": 2.502054533594493e-05, |
| "loss": 0.0949, |
| "mean_token_accuracy": 0.9718875661492348, |
| "step": 787 |
| }, |
| { |
| "epoch": 4.609970674486804, |
| "grad_norm": 0.7295520284793742, |
| "learning_rate": 2.4986733452756264e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9746653810143471, |
| "step": 788 |
| }, |
| { |
| "epoch": 4.6158357771261, |
| "grad_norm": 0.7882592432293024, |
| "learning_rate": 2.495291072893142e-05, |
| "loss": 0.1069, |
| "mean_token_accuracy": 0.9730554893612862, |
| "step": 789 |
| }, |
| { |
| "epoch": 4.621700879765396, |
| "grad_norm": 0.7762536144917583, |
| "learning_rate": 2.4919077287233237e-05, |
| "loss": 0.1011, |
| "mean_token_accuracy": 0.9697251468896866, |
| "step": 790 |
| }, |
| { |
| "epoch": 4.627565982404692, |
| "grad_norm": 0.7501153105236112, |
| "learning_rate": 2.4885233250463445e-05, |
| "loss": 0.0981, |
| "mean_token_accuracy": 0.971202477812767, |
| "step": 791 |
| }, |
| { |
| "epoch": 4.633431085043989, |
| "grad_norm": 0.7971158503889687, |
| "learning_rate": 2.485137874146222e-05, |
| "loss": 0.1001, |
| "mean_token_accuracy": 0.9674383029341698, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.639296187683285, |
| "grad_norm": 0.7887660045681235, |
| "learning_rate": 2.4817513883107762e-05, |
| "loss": 0.1037, |
| "mean_token_accuracy": 0.9634637236595154, |
| "step": 793 |
| }, |
| { |
| "epoch": 4.645161290322581, |
| "grad_norm": 0.8063096426550572, |
| "learning_rate": 2.4783638798315822e-05, |
| "loss": 0.0992, |
| "mean_token_accuracy": 0.9716535285115242, |
| "step": 794 |
| }, |
| { |
| "epoch": 4.651026392961877, |
| "grad_norm": 0.8102967123391493, |
| "learning_rate": 2.4749753610039288e-05, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.9733820334076881, |
| "step": 795 |
| }, |
| { |
| "epoch": 4.656891495601173, |
| "grad_norm": 0.734265742655663, |
| "learning_rate": 2.4715858441267706e-05, |
| "loss": 0.0932, |
| "mean_token_accuracy": 0.9707584381103516, |
| "step": 796 |
| }, |
| { |
| "epoch": 4.6627565982404695, |
| "grad_norm": 1.0708816496376599, |
| "learning_rate": 2.4681953415026845e-05, |
| "loss": 0.1151, |
| "mean_token_accuracy": 0.9674431756138802, |
| "step": 797 |
| }, |
| { |
| "epoch": 4.668621700879766, |
| "grad_norm": 0.7632236114224711, |
| "learning_rate": 2.464803865437826e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.96937146037817, |
| "step": 798 |
| }, |
| { |
| "epoch": 4.674486803519062, |
| "grad_norm": 1.0123704280545058, |
| "learning_rate": 2.461411428241883e-05, |
| "loss": 0.1211, |
| "mean_token_accuracy": 0.9677753895521164, |
| "step": 799 |
| }, |
| { |
| "epoch": 4.680351906158358, |
| "grad_norm": 0.7585877502897928, |
| "learning_rate": 2.4580180422280325e-05, |
| "loss": 0.0974, |
| "mean_token_accuracy": 0.9710182920098305, |
| "step": 800 |
| }, |
| { |
| "epoch": 4.686217008797654, |
| "grad_norm": 0.7599802618930964, |
| "learning_rate": 2.4546237197128955e-05, |
| "loss": 0.0964, |
| "mean_token_accuracy": 0.9718500971794128, |
| "step": 801 |
| }, |
| { |
| "epoch": 4.69208211143695, |
| "grad_norm": 0.8785070865398006, |
| "learning_rate": 2.451228473016492e-05, |
| "loss": 0.0983, |
| "mean_token_accuracy": 0.9714755862951279, |
| "step": 802 |
| }, |
| { |
| "epoch": 4.697947214076247, |
| "grad_norm": 0.7923717791867461, |
| "learning_rate": 2.447832314462196e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.9698025360703468, |
| "step": 803 |
| }, |
| { |
| "epoch": 4.703812316715543, |
| "grad_norm": 0.6198673256208855, |
| "learning_rate": 2.444435256376692e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.9722053855657578, |
| "step": 804 |
| }, |
| { |
| "epoch": 4.709677419354839, |
| "grad_norm": 0.7258817559918743, |
| "learning_rate": 2.4410373110899278e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9761781170964241, |
| "step": 805 |
| }, |
| { |
| "epoch": 4.715542521994135, |
| "grad_norm": 0.9172924248024136, |
| "learning_rate": 2.4376384909350735e-05, |
| "loss": 0.1043, |
| "mean_token_accuracy": 0.9676323756575584, |
| "step": 806 |
| }, |
| { |
| "epoch": 4.721407624633431, |
| "grad_norm": 0.7471141708163742, |
| "learning_rate": 2.434238808248472e-05, |
| "loss": 0.0947, |
| "mean_token_accuracy": 0.9704129174351692, |
| "step": 807 |
| }, |
| { |
| "epoch": 4.7272727272727275, |
| "grad_norm": 0.9028932892020963, |
| "learning_rate": 2.4308382753696e-05, |
| "loss": 0.1092, |
| "mean_token_accuracy": 0.9671567976474762, |
| "step": 808 |
| }, |
| { |
| "epoch": 4.733137829912024, |
| "grad_norm": 0.9404310972887582, |
| "learning_rate": 2.4274369046410183e-05, |
| "loss": 0.1148, |
| "mean_token_accuracy": 0.969983272254467, |
| "step": 809 |
| }, |
| { |
| "epoch": 4.73900293255132, |
| "grad_norm": 0.7335061132763945, |
| "learning_rate": 2.4240347084083284e-05, |
| "loss": 0.0909, |
| "mean_token_accuracy": 0.9720699489116669, |
| "step": 810 |
| }, |
| { |
| "epoch": 4.744868035190616, |
| "grad_norm": 0.8135650291115837, |
| "learning_rate": 2.4206316990201288e-05, |
| "loss": 0.1011, |
| "mean_token_accuracy": 0.9665744081139565, |
| "step": 811 |
| }, |
| { |
| "epoch": 4.750733137829912, |
| "grad_norm": 1.006450006617362, |
| "learning_rate": 2.4172278888279686e-05, |
| "loss": 0.1203, |
| "mean_token_accuracy": 0.9652376249432564, |
| "step": 812 |
| }, |
| { |
| "epoch": 4.756598240469208, |
| "grad_norm": 0.8383972213721953, |
| "learning_rate": 2.4138232901863053e-05, |
| "loss": 0.0988, |
| "mean_token_accuracy": 0.9674033001065254, |
| "step": 813 |
| }, |
| { |
| "epoch": 4.762463343108505, |
| "grad_norm": 0.7477269136479021, |
| "learning_rate": 2.4104179154524557e-05, |
| "loss": 0.0794, |
| "mean_token_accuracy": 0.9763186648488045, |
| "step": 814 |
| }, |
| { |
| "epoch": 4.768328445747801, |
| "grad_norm": 0.7443883106412051, |
| "learning_rate": 2.4070117769865554e-05, |
| "loss": 0.0948, |
| "mean_token_accuracy": 0.9707931205630302, |
| "step": 815 |
| }, |
| { |
| "epoch": 4.774193548387097, |
| "grad_norm": 0.764340980807826, |
| "learning_rate": 2.403604887151512e-05, |
| "loss": 0.0972, |
| "mean_token_accuracy": 0.9693472981452942, |
| "step": 816 |
| }, |
| { |
| "epoch": 4.780058651026393, |
| "grad_norm": 0.9296757955451029, |
| "learning_rate": 2.400197258312959e-05, |
| "loss": 0.085, |
| "mean_token_accuracy": 0.9715523645281792, |
| "step": 817 |
| }, |
| { |
| "epoch": 4.785923753665689, |
| "grad_norm": 0.757736033011415, |
| "learning_rate": 2.3967889028392115e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9713739231228828, |
| "step": 818 |
| }, |
| { |
| "epoch": 4.7917888563049855, |
| "grad_norm": 0.8872201408127831, |
| "learning_rate": 2.3933798331012255e-05, |
| "loss": 0.1071, |
| "mean_token_accuracy": 0.9671370834112167, |
| "step": 819 |
| }, |
| { |
| "epoch": 4.797653958944282, |
| "grad_norm": 0.7207454265279954, |
| "learning_rate": 2.3899700614725458e-05, |
| "loss": 0.097, |
| "mean_token_accuracy": 0.9650105834007263, |
| "step": 820 |
| }, |
| { |
| "epoch": 4.803519061583578, |
| "grad_norm": 0.7908055653055925, |
| "learning_rate": 2.3865596003292674e-05, |
| "loss": 0.1028, |
| "mean_token_accuracy": 0.9701355323195457, |
| "step": 821 |
| }, |
| { |
| "epoch": 4.809384164222874, |
| "grad_norm": 0.6486808078141573, |
| "learning_rate": 2.3831484620499867e-05, |
| "loss": 0.0952, |
| "mean_token_accuracy": 0.9729474484920502, |
| "step": 822 |
| }, |
| { |
| "epoch": 4.81524926686217, |
| "grad_norm": 0.9229266535389385, |
| "learning_rate": 2.3797366590157565e-05, |
| "loss": 0.1095, |
| "mean_token_accuracy": 0.9646266847848892, |
| "step": 823 |
| }, |
| { |
| "epoch": 4.821114369501466, |
| "grad_norm": 0.9127539327987895, |
| "learning_rate": 2.3763242036100457e-05, |
| "loss": 0.0988, |
| "mean_token_accuracy": 0.9674626067280769, |
| "step": 824 |
| }, |
| { |
| "epoch": 4.826979472140763, |
| "grad_norm": 0.8258037643370993, |
| "learning_rate": 2.372911108218688e-05, |
| "loss": 0.0933, |
| "mean_token_accuracy": 0.9713954329490662, |
| "step": 825 |
| }, |
| { |
| "epoch": 4.832844574780059, |
| "grad_norm": 0.9162371634383302, |
| "learning_rate": 2.3694973852298425e-05, |
| "loss": 0.1043, |
| "mean_token_accuracy": 0.9656035676598549, |
| "step": 826 |
| }, |
| { |
| "epoch": 4.838709677419355, |
| "grad_norm": 0.684629551090319, |
| "learning_rate": 2.3660830470339436e-05, |
| "loss": 0.0896, |
| "mean_token_accuracy": 0.9730357006192207, |
| "step": 827 |
| }, |
| { |
| "epoch": 4.844574780058651, |
| "grad_norm": 0.8047131016250728, |
| "learning_rate": 2.362668106023661e-05, |
| "loss": 0.0991, |
| "mean_token_accuracy": 0.9705889150500298, |
| "step": 828 |
| }, |
| { |
| "epoch": 4.850439882697947, |
| "grad_norm": 0.8042236766203159, |
| "learning_rate": 2.3592525745938515e-05, |
| "loss": 0.0932, |
| "mean_token_accuracy": 0.9739318490028381, |
| "step": 829 |
| }, |
| { |
| "epoch": 4.8563049853372435, |
| "grad_norm": 0.6823089370978507, |
| "learning_rate": 2.355836465141513e-05, |
| "loss": 0.0809, |
| "mean_token_accuracy": 0.975515104830265, |
| "step": 830 |
| }, |
| { |
| "epoch": 4.86217008797654, |
| "grad_norm": 1.056676551862205, |
| "learning_rate": 2.3524197900657447e-05, |
| "loss": 0.1181, |
| "mean_token_accuracy": 0.9661965668201447, |
| "step": 831 |
| }, |
| { |
| "epoch": 4.868035190615836, |
| "grad_norm": 0.6719408329574679, |
| "learning_rate": 2.3490025617676966e-05, |
| "loss": 0.0788, |
| "mean_token_accuracy": 0.9769859835505486, |
| "step": 832 |
| }, |
| { |
| "epoch": 4.873900293255132, |
| "grad_norm": 0.9361482521021528, |
| "learning_rate": 2.3455847926505283e-05, |
| "loss": 0.1215, |
| "mean_token_accuracy": 0.9638217911124229, |
| "step": 833 |
| }, |
| { |
| "epoch": 4.879765395894428, |
| "grad_norm": 0.9148451630035029, |
| "learning_rate": 2.3421664951193596e-05, |
| "loss": 0.1082, |
| "mean_token_accuracy": 0.9696593731641769, |
| "step": 834 |
| }, |
| { |
| "epoch": 4.885630498533724, |
| "grad_norm": 0.7778350466276233, |
| "learning_rate": 2.3387476815812313e-05, |
| "loss": 0.1035, |
| "mean_token_accuracy": 0.9713735282421112, |
| "step": 835 |
| }, |
| { |
| "epoch": 4.891495601173021, |
| "grad_norm": 0.861960176959738, |
| "learning_rate": 2.3353283644450556e-05, |
| "loss": 0.1102, |
| "mean_token_accuracy": 0.9678222835063934, |
| "step": 836 |
| }, |
| { |
| "epoch": 4.897360703812317, |
| "grad_norm": 0.8318096305591833, |
| "learning_rate": 2.3319085561215724e-05, |
| "loss": 0.1018, |
| "mean_token_accuracy": 0.9691039249300957, |
| "step": 837 |
| }, |
| { |
| "epoch": 4.903225806451613, |
| "grad_norm": 0.7242772575603745, |
| "learning_rate": 2.328488269023305e-05, |
| "loss": 0.0913, |
| "mean_token_accuracy": 0.9706755951046944, |
| "step": 838 |
| }, |
| { |
| "epoch": 4.909090909090909, |
| "grad_norm": 0.6533623048792406, |
| "learning_rate": 2.3250675155645136e-05, |
| "loss": 0.0822, |
| "mean_token_accuracy": 0.9732807353138924, |
| "step": 839 |
| }, |
| { |
| "epoch": 4.914956011730205, |
| "grad_norm": 0.6998592106148985, |
| "learning_rate": 2.3216463081611525e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9738926067948341, |
| "step": 840 |
| }, |
| { |
| "epoch": 4.9208211143695015, |
| "grad_norm": 0.8997130023440117, |
| "learning_rate": 2.3182246592308235e-05, |
| "loss": 0.1088, |
| "mean_token_accuracy": 0.9683014452457428, |
| "step": 841 |
| }, |
| { |
| "epoch": 4.926686217008798, |
| "grad_norm": 0.8073979598994243, |
| "learning_rate": 2.314802581192728e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.96952273696661, |
| "step": 842 |
| }, |
| { |
| "epoch": 4.932551319648094, |
| "grad_norm": 0.9604499998077138, |
| "learning_rate": 2.311380086467629e-05, |
| "loss": 0.1168, |
| "mean_token_accuracy": 0.9669440165162086, |
| "step": 843 |
| }, |
| { |
| "epoch": 4.93841642228739, |
| "grad_norm": 0.70913935151314, |
| "learning_rate": 2.3079571874778e-05, |
| "loss": 0.0996, |
| "mean_token_accuracy": 0.9702354818582535, |
| "step": 844 |
| }, |
| { |
| "epoch": 4.944281524926686, |
| "grad_norm": 0.8614283401684019, |
| "learning_rate": 2.304533896646981e-05, |
| "loss": 0.0965, |
| "mean_token_accuracy": 0.9706253558397293, |
| "step": 845 |
| }, |
| { |
| "epoch": 4.9501466275659824, |
| "grad_norm": 0.6715033958091532, |
| "learning_rate": 2.3011102264003354e-05, |
| "loss": 0.0902, |
| "mean_token_accuracy": 0.9727234393358231, |
| "step": 846 |
| }, |
| { |
| "epoch": 4.956011730205279, |
| "grad_norm": 0.8437834609592847, |
| "learning_rate": 2.2976861891644045e-05, |
| "loss": 0.0899, |
| "mean_token_accuracy": 0.9689526185393333, |
| "step": 847 |
| }, |
| { |
| "epoch": 4.961876832844575, |
| "grad_norm": 0.7677466012630041, |
| "learning_rate": 2.2942617973670596e-05, |
| "loss": 0.091, |
| "mean_token_accuracy": 0.9746912643313408, |
| "step": 848 |
| }, |
| { |
| "epoch": 4.967741935483871, |
| "grad_norm": 1.3044373985496345, |
| "learning_rate": 2.2908370634374603e-05, |
| "loss": 0.1369, |
| "mean_token_accuracy": 0.9604402333498001, |
| "step": 849 |
| }, |
| { |
| "epoch": 4.973607038123167, |
| "grad_norm": 0.6899750785431267, |
| "learning_rate": 2.287411999806007e-05, |
| "loss": 0.0886, |
| "mean_token_accuracy": 0.9728878736495972, |
| "step": 850 |
| }, |
| { |
| "epoch": 4.979472140762463, |
| "grad_norm": 0.8347658349866184, |
| "learning_rate": 2.2839866189042983e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.9728017598390579, |
| "step": 851 |
| }, |
| { |
| "epoch": 4.9853372434017595, |
| "grad_norm": 0.7517247253149162, |
| "learning_rate": 2.2805609331650826e-05, |
| "loss": 0.1027, |
| "mean_token_accuracy": 0.9682365879416466, |
| "step": 852 |
| }, |
| { |
| "epoch": 4.991202346041056, |
| "grad_norm": 0.7521709150117921, |
| "learning_rate": 2.2771349550222158e-05, |
| "loss": 0.0906, |
| "mean_token_accuracy": 0.9731875956058502, |
| "step": 853 |
| }, |
| { |
| "epoch": 4.997067448680352, |
| "grad_norm": 0.7112238021631059, |
| "learning_rate": 2.273708696910616e-05, |
| "loss": 0.0862, |
| "mean_token_accuracy": 0.973906010389328, |
| "step": 854 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.7112238021631059, |
| "learning_rate": 2.2702821712662147e-05, |
| "loss": 0.0764, |
| "mean_token_accuracy": 0.9778192937374115, |
| "step": 855 |
| }, |
| { |
| "epoch": 5.005865102639296, |
| "grad_norm": 1.0128576576804946, |
| "learning_rate": 2.2668553905259168e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.974254384636879, |
| "step": 856 |
| }, |
| { |
| "epoch": 5.011730205278592, |
| "grad_norm": 0.608267020682671, |
| "learning_rate": 2.2634283671275523e-05, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9795678928494453, |
| "step": 857 |
| }, |
| { |
| "epoch": 5.0175953079178885, |
| "grad_norm": 0.5622048670870978, |
| "learning_rate": 2.2600011135098323e-05, |
| "loss": 0.0744, |
| "mean_token_accuracy": 0.9774943068623543, |
| "step": 858 |
| }, |
| { |
| "epoch": 5.023460410557185, |
| "grad_norm": 0.5921735306162148, |
| "learning_rate": 2.2565736421123035e-05, |
| "loss": 0.0853, |
| "mean_token_accuracy": 0.97476976364851, |
| "step": 859 |
| }, |
| { |
| "epoch": 5.029325513196481, |
| "grad_norm": 0.7814112686967922, |
| "learning_rate": 2.253145965375302e-05, |
| "loss": 0.1095, |
| "mean_token_accuracy": 0.9669553339481354, |
| "step": 860 |
| }, |
| { |
| "epoch": 5.035190615835777, |
| "grad_norm": 0.7427252443009537, |
| "learning_rate": 2.2497180957399108e-05, |
| "loss": 0.0905, |
| "mean_token_accuracy": 0.9688437804579735, |
| "step": 861 |
| }, |
| { |
| "epoch": 5.041055718475073, |
| "grad_norm": 0.7799570398100676, |
| "learning_rate": 2.246290045647912e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9773503243923187, |
| "step": 862 |
| }, |
| { |
| "epoch": 5.0469208211143695, |
| "grad_norm": 0.5605487780130354, |
| "learning_rate": 2.242861827541742e-05, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9778739288449287, |
| "step": 863 |
| }, |
| { |
| "epoch": 5.052785923753666, |
| "grad_norm": 0.5680136427773851, |
| "learning_rate": 2.2394334538644494e-05, |
| "loss": 0.0842, |
| "mean_token_accuracy": 0.9757679551839828, |
| "step": 864 |
| }, |
| { |
| "epoch": 5.058651026392962, |
| "grad_norm": 0.8673912297345526, |
| "learning_rate": 2.2360049370596454e-05, |
| "loss": 0.0867, |
| "mean_token_accuracy": 0.9756646528840065, |
| "step": 865 |
| }, |
| { |
| "epoch": 5.064516129032258, |
| "grad_norm": 0.7257313253397972, |
| "learning_rate": 2.2325762895714616e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.9739532098174095, |
| "step": 866 |
| }, |
| { |
| "epoch": 5.070381231671554, |
| "grad_norm": 0.7275380843304412, |
| "learning_rate": 2.2291475238445033e-05, |
| "loss": 0.0906, |
| "mean_token_accuracy": 0.9731993973255157, |
| "step": 867 |
| }, |
| { |
| "epoch": 5.07624633431085, |
| "grad_norm": 0.7539545393297449, |
| "learning_rate": 2.225718652323805e-05, |
| "loss": 0.0816, |
| "mean_token_accuracy": 0.9701853692531586, |
| "step": 868 |
| }, |
| { |
| "epoch": 5.0821114369501466, |
| "grad_norm": 0.8405685160148454, |
| "learning_rate": 2.2222896874547856e-05, |
| "loss": 0.0983, |
| "mean_token_accuracy": 0.9731288999319077, |
| "step": 869 |
| }, |
| { |
| "epoch": 5.087976539589443, |
| "grad_norm": 0.7993482343128961, |
| "learning_rate": 2.2188606416832035e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.977057509124279, |
| "step": 870 |
| }, |
| { |
| "epoch": 5.093841642228739, |
| "grad_norm": 0.8172411599541392, |
| "learning_rate": 2.2154315274551093e-05, |
| "loss": 0.0889, |
| "mean_token_accuracy": 0.9734968990087509, |
| "step": 871 |
| }, |
| { |
| "epoch": 5.099706744868035, |
| "grad_norm": 0.6520924706945902, |
| "learning_rate": 2.2120023572168026e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.97675970941782, |
| "step": 872 |
| }, |
| { |
| "epoch": 5.105571847507331, |
| "grad_norm": 0.6628656863287348, |
| "learning_rate": 2.208573143414787e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9797274470329285, |
| "step": 873 |
| }, |
| { |
| "epoch": 5.1114369501466275, |
| "grad_norm": 0.5465670696067368, |
| "learning_rate": 2.2051438984957234e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9757656827569008, |
| "step": 874 |
| }, |
| { |
| "epoch": 5.117302052785924, |
| "grad_norm": 0.7747976458168354, |
| "learning_rate": 2.2017146349063855e-05, |
| "loss": 0.0903, |
| "mean_token_accuracy": 0.9750406444072723, |
| "step": 875 |
| }, |
| { |
| "epoch": 5.12316715542522, |
| "grad_norm": 0.6154236649307834, |
| "learning_rate": 2.1982853650936154e-05, |
| "loss": 0.0835, |
| "mean_token_accuracy": 0.9757610484957695, |
| "step": 876 |
| }, |
| { |
| "epoch": 5.129032258064516, |
| "grad_norm": 0.6386021245757174, |
| "learning_rate": 2.1948561015042772e-05, |
| "loss": 0.0849, |
| "mean_token_accuracy": 0.9769806042313576, |
| "step": 877 |
| }, |
| { |
| "epoch": 5.134897360703812, |
| "grad_norm": 0.8485634110906592, |
| "learning_rate": 2.1914268565852134e-05, |
| "loss": 0.1005, |
| "mean_token_accuracy": 0.9702042117714882, |
| "step": 878 |
| }, |
| { |
| "epoch": 5.140762463343108, |
| "grad_norm": 0.6417040051521462, |
| "learning_rate": 2.1879976427831983e-05, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.9777021408081055, |
| "step": 879 |
| }, |
| { |
| "epoch": 5.146627565982405, |
| "grad_norm": 0.9496873079801262, |
| "learning_rate": 2.1845684725448916e-05, |
| "loss": 0.0986, |
| "mean_token_accuracy": 0.9698187112808228, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.152492668621701, |
| "grad_norm": 0.7318435813184204, |
| "learning_rate": 2.181139358316797e-05, |
| "loss": 0.0819, |
| "mean_token_accuracy": 0.9735628068447113, |
| "step": 881 |
| }, |
| { |
| "epoch": 5.158357771260997, |
| "grad_norm": 0.7132143176614368, |
| "learning_rate": 2.1777103125452146e-05, |
| "loss": 0.0858, |
| "mean_token_accuracy": 0.9724550470709801, |
| "step": 882 |
| }, |
| { |
| "epoch": 5.164222873900293, |
| "grad_norm": 0.8291763986470454, |
| "learning_rate": 2.1742813476761958e-05, |
| "loss": 0.0995, |
| "mean_token_accuracy": 0.9693228304386139, |
| "step": 883 |
| }, |
| { |
| "epoch": 5.170087976539589, |
| "grad_norm": 0.7365191888977923, |
| "learning_rate": 2.1708524761554973e-05, |
| "loss": 0.0858, |
| "mean_token_accuracy": 0.9737670198082924, |
| "step": 884 |
| }, |
| { |
| "epoch": 5.1759530791788855, |
| "grad_norm": 0.6229037109477557, |
| "learning_rate": 2.1674237104285393e-05, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.975468099117279, |
| "step": 885 |
| }, |
| { |
| "epoch": 5.181818181818182, |
| "grad_norm": 0.5698465859203371, |
| "learning_rate": 2.1639950629403552e-05, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9791614338755608, |
| "step": 886 |
| }, |
| { |
| "epoch": 5.187683284457478, |
| "grad_norm": 0.5736934209439896, |
| "learning_rate": 2.1605665461355515e-05, |
| "loss": 0.0799, |
| "mean_token_accuracy": 0.975306861102581, |
| "step": 887 |
| }, |
| { |
| "epoch": 5.193548387096774, |
| "grad_norm": 0.642707306614463, |
| "learning_rate": 2.1571381724582588e-05, |
| "loss": 0.0951, |
| "mean_token_accuracy": 0.9715821146965027, |
| "step": 888 |
| }, |
| { |
| "epoch": 5.19941348973607, |
| "grad_norm": 0.9214123192091717, |
| "learning_rate": 2.153709954352089e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.973389632999897, |
| "step": 889 |
| }, |
| { |
| "epoch": 5.205278592375366, |
| "grad_norm": 0.754059027278609, |
| "learning_rate": 2.15028190426009e-05, |
| "loss": 0.0902, |
| "mean_token_accuracy": 0.9721227064728737, |
| "step": 890 |
| }, |
| { |
| "epoch": 5.211143695014663, |
| "grad_norm": 0.6893716853875429, |
| "learning_rate": 2.1468540346246986e-05, |
| "loss": 0.0804, |
| "mean_token_accuracy": 0.9698435142636299, |
| "step": 891 |
| }, |
| { |
| "epoch": 5.217008797653959, |
| "grad_norm": 0.6795703629568569, |
| "learning_rate": 2.143426357887697e-05, |
| "loss": 0.0915, |
| "mean_token_accuracy": 0.9739984050393105, |
| "step": 892 |
| }, |
| { |
| "epoch": 5.222873900293255, |
| "grad_norm": 0.7702418917677822, |
| "learning_rate": 2.139998886490169e-05, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.9761215299367905, |
| "step": 893 |
| }, |
| { |
| "epoch": 5.228739002932551, |
| "grad_norm": 0.6046235507122676, |
| "learning_rate": 2.136571632872449e-05, |
| "loss": 0.0889, |
| "mean_token_accuracy": 0.9733590260148048, |
| "step": 894 |
| }, |
| { |
| "epoch": 5.234604105571847, |
| "grad_norm": 0.8257469175456973, |
| "learning_rate": 2.1331446094740845e-05, |
| "loss": 0.1044, |
| "mean_token_accuracy": 0.9706998839974403, |
| "step": 895 |
| }, |
| { |
| "epoch": 5.2404692082111435, |
| "grad_norm": 0.9294165820978288, |
| "learning_rate": 2.1297178287337865e-05, |
| "loss": 0.0878, |
| "mean_token_accuracy": 0.972227543592453, |
| "step": 896 |
| }, |
| { |
| "epoch": 5.24633431085044, |
| "grad_norm": 0.6893445425870071, |
| "learning_rate": 2.1262913030893855e-05, |
| "loss": 0.1045, |
| "mean_token_accuracy": 0.9695899188518524, |
| "step": 897 |
| }, |
| { |
| "epoch": 5.252199413489736, |
| "grad_norm": 1.104947276779602, |
| "learning_rate": 2.1228650449777848e-05, |
| "loss": 0.0982, |
| "mean_token_accuracy": 0.9720256999135017, |
| "step": 898 |
| }, |
| { |
| "epoch": 5.258064516129032, |
| "grad_norm": 0.7524610114511344, |
| "learning_rate": 2.1194390668349186e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.9729163721203804, |
| "step": 899 |
| }, |
| { |
| "epoch": 5.263929618768328, |
| "grad_norm": 0.7362606630635441, |
| "learning_rate": 2.116013381095703e-05, |
| "loss": 0.0777, |
| "mean_token_accuracy": 0.9786986038088799, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.269794721407624, |
| "grad_norm": 0.5211179939843894, |
| "learning_rate": 2.112588000193994e-05, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.9741416275501251, |
| "step": 901 |
| }, |
| { |
| "epoch": 5.275659824046921, |
| "grad_norm": 0.7209693940538987, |
| "learning_rate": 2.1091629365625403e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9762564152479172, |
| "step": 902 |
| }, |
| { |
| "epoch": 5.281524926686217, |
| "grad_norm": 0.7741807909355801, |
| "learning_rate": 2.105738202632941e-05, |
| "loss": 0.0993, |
| "mean_token_accuracy": 0.9709812626242638, |
| "step": 903 |
| }, |
| { |
| "epoch": 5.287390029325513, |
| "grad_norm": 0.6747396182625481, |
| "learning_rate": 2.1023138108355957e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9794772490859032, |
| "step": 904 |
| }, |
| { |
| "epoch": 5.293255131964809, |
| "grad_norm": 0.5803581197055916, |
| "learning_rate": 2.098889773599665e-05, |
| "loss": 0.0934, |
| "mean_token_accuracy": 0.9710723906755447, |
| "step": 905 |
| }, |
| { |
| "epoch": 5.299120234604105, |
| "grad_norm": 0.7312865747989487, |
| "learning_rate": 2.0954661033530193e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9799710288643837, |
| "step": 906 |
| }, |
| { |
| "epoch": 5.3049853372434015, |
| "grad_norm": 0.6023379146658334, |
| "learning_rate": 2.0920428125222004e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9746310263872147, |
| "step": 907 |
| }, |
| { |
| "epoch": 5.310850439882698, |
| "grad_norm": 0.6922686013988262, |
| "learning_rate": 2.0886199135323712e-05, |
| "loss": 0.0901, |
| "mean_token_accuracy": 0.9730349406599998, |
| "step": 908 |
| }, |
| { |
| "epoch": 5.316715542521994, |
| "grad_norm": 0.8095953938881245, |
| "learning_rate": 2.085197418807272e-05, |
| "loss": 0.0839, |
| "mean_token_accuracy": 0.9751959219574928, |
| "step": 909 |
| }, |
| { |
| "epoch": 5.32258064516129, |
| "grad_norm": 0.7756873814279036, |
| "learning_rate": 2.0817753407691774e-05, |
| "loss": 0.0843, |
| "mean_token_accuracy": 0.9740110486745834, |
| "step": 910 |
| }, |
| { |
| "epoch": 5.328445747800586, |
| "grad_norm": 0.6614025346901433, |
| "learning_rate": 2.0783536918388477e-05, |
| "loss": 0.1002, |
| "mean_token_accuracy": 0.9684435129165649, |
| "step": 911 |
| }, |
| { |
| "epoch": 5.334310850439882, |
| "grad_norm": 0.9972663221317221, |
| "learning_rate": 2.0749324844354867e-05, |
| "loss": 0.0856, |
| "mean_token_accuracy": 0.9751722291111946, |
| "step": 912 |
| }, |
| { |
| "epoch": 5.340175953079179, |
| "grad_norm": 0.6195183258111225, |
| "learning_rate": 2.0715117309766953e-05, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9773119017481804, |
| "step": 913 |
| }, |
| { |
| "epoch": 5.346041055718475, |
| "grad_norm": 0.5891900151530527, |
| "learning_rate": 2.068091443878428e-05, |
| "loss": 0.0924, |
| "mean_token_accuracy": 0.9727002307772636, |
| "step": 914 |
| }, |
| { |
| "epoch": 5.351906158357771, |
| "grad_norm": 0.6577743321968366, |
| "learning_rate": 2.064671635554945e-05, |
| "loss": 0.1042, |
| "mean_token_accuracy": 0.973984107375145, |
| "step": 915 |
| }, |
| { |
| "epoch": 5.357771260997067, |
| "grad_norm": 0.6432081149097092, |
| "learning_rate": 2.0612523184187693e-05, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9766345173120499, |
| "step": 916 |
| }, |
| { |
| "epoch": 5.363636363636363, |
| "grad_norm": 0.5940654858986845, |
| "learning_rate": 2.057833504880641e-05, |
| "loss": 0.0907, |
| "mean_token_accuracy": 0.970424547791481, |
| "step": 917 |
| }, |
| { |
| "epoch": 5.3695014662756595, |
| "grad_norm": 0.7978700792585309, |
| "learning_rate": 2.054415207349473e-05, |
| "loss": 0.0986, |
| "mean_token_accuracy": 0.9700106978416443, |
| "step": 918 |
| }, |
| { |
| "epoch": 5.375366568914956, |
| "grad_norm": 0.7734624846466107, |
| "learning_rate": 2.0509974382323043e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9722676649689674, |
| "step": 919 |
| }, |
| { |
| "epoch": 5.381231671554252, |
| "grad_norm": 0.6025196729714031, |
| "learning_rate": 2.047580209934256e-05, |
| "loss": 0.0819, |
| "mean_token_accuracy": 0.9750821068882942, |
| "step": 920 |
| }, |
| { |
| "epoch": 5.387096774193548, |
| "grad_norm": 0.8058624103581123, |
| "learning_rate": 2.0441635348584876e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9749607369303703, |
| "step": 921 |
| }, |
| { |
| "epoch": 5.392961876832844, |
| "grad_norm": 0.5601275527868476, |
| "learning_rate": 2.0407474254061498e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.9728451818227768, |
| "step": 922 |
| }, |
| { |
| "epoch": 5.39882697947214, |
| "grad_norm": 0.6533125937693671, |
| "learning_rate": 2.0373318939763397e-05, |
| "loss": 0.0819, |
| "mean_token_accuracy": 0.9742006808519363, |
| "step": 923 |
| }, |
| { |
| "epoch": 5.404692082111437, |
| "grad_norm": 0.5319127388615715, |
| "learning_rate": 2.033916952966057e-05, |
| "loss": 0.0821, |
| "mean_token_accuracy": 0.9746419414877892, |
| "step": 924 |
| }, |
| { |
| "epoch": 5.410557184750733, |
| "grad_norm": 0.8970156927927059, |
| "learning_rate": 2.0305026147701584e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.9721054211258888, |
| "step": 925 |
| }, |
| { |
| "epoch": 5.416422287390029, |
| "grad_norm": 0.7073601134598491, |
| "learning_rate": 2.0270888917813124e-05, |
| "loss": 0.0826, |
| "mean_token_accuracy": 0.9741240218281746, |
| "step": 926 |
| }, |
| { |
| "epoch": 5.422287390029325, |
| "grad_norm": 0.6846811877738305, |
| "learning_rate": 2.0236757963899548e-05, |
| "loss": 0.0867, |
| "mean_token_accuracy": 0.9731223210692406, |
| "step": 927 |
| }, |
| { |
| "epoch": 5.428152492668621, |
| "grad_norm": 0.6728499001788334, |
| "learning_rate": 2.020263340984244e-05, |
| "loss": 0.111, |
| "mean_token_accuracy": 0.9723155945539474, |
| "step": 928 |
| }, |
| { |
| "epoch": 5.4340175953079175, |
| "grad_norm": 4.80499137254916, |
| "learning_rate": 2.0168515379500145e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9738029539585114, |
| "step": 929 |
| }, |
| { |
| "epoch": 5.439882697947214, |
| "grad_norm": 0.5659705242146589, |
| "learning_rate": 2.0134403996707338e-05, |
| "loss": 0.082, |
| "mean_token_accuracy": 0.9739853367209435, |
| "step": 930 |
| }, |
| { |
| "epoch": 5.44574780058651, |
| "grad_norm": 0.5441226945035449, |
| "learning_rate": 2.0100299385274547e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9742333069443703, |
| "step": 931 |
| }, |
| { |
| "epoch": 5.451612903225806, |
| "grad_norm": 0.7050420063651641, |
| "learning_rate": 2.0066201668987757e-05, |
| "loss": 0.0916, |
| "mean_token_accuracy": 0.9706050902605057, |
| "step": 932 |
| }, |
| { |
| "epoch": 5.457478005865102, |
| "grad_norm": 0.6357536693584852, |
| "learning_rate": 2.0032110971607894e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9762316793203354, |
| "step": 933 |
| }, |
| { |
| "epoch": 5.463343108504398, |
| "grad_norm": 0.704077597095192, |
| "learning_rate": 1.999802741687042e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9715845510363579, |
| "step": 934 |
| }, |
| { |
| "epoch": 5.469208211143695, |
| "grad_norm": 0.6093082482082577, |
| "learning_rate": 1.9963951128484886e-05, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9773004725575447, |
| "step": 935 |
| }, |
| { |
| "epoch": 5.475073313782991, |
| "grad_norm": 0.6051590416188609, |
| "learning_rate": 1.9929882230134452e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.971544623374939, |
| "step": 936 |
| }, |
| { |
| "epoch": 5.480938416422287, |
| "grad_norm": 0.5593716193262593, |
| "learning_rate": 1.9895820845475445e-05, |
| "loss": 0.0861, |
| "mean_token_accuracy": 0.974859744310379, |
| "step": 937 |
| }, |
| { |
| "epoch": 5.486803519061583, |
| "grad_norm": 0.6403030492297582, |
| "learning_rate": 1.9861767098136956e-05, |
| "loss": 0.0738, |
| "mean_token_accuracy": 0.9763150438666344, |
| "step": 938 |
| }, |
| { |
| "epoch": 5.492668621700879, |
| "grad_norm": 0.5364067645042216, |
| "learning_rate": 1.982772111172032e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9747820049524307, |
| "step": 939 |
| }, |
| { |
| "epoch": 5.4985337243401755, |
| "grad_norm": 0.6269041173082894, |
| "learning_rate": 1.9793683009798718e-05, |
| "loss": 0.0789, |
| "mean_token_accuracy": 0.9758682772517204, |
| "step": 940 |
| }, |
| { |
| "epoch": 5.504398826979472, |
| "grad_norm": 0.7056273697944462, |
| "learning_rate": 1.975965291591672e-05, |
| "loss": 0.0949, |
| "mean_token_accuracy": 0.9714619740843773, |
| "step": 941 |
| }, |
| { |
| "epoch": 5.510263929618768, |
| "grad_norm": 0.724661005419617, |
| "learning_rate": 1.9725630953589823e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.976491242647171, |
| "step": 942 |
| }, |
| { |
| "epoch": 5.516129032258064, |
| "grad_norm": 0.6126314687561928, |
| "learning_rate": 1.9691617246304007e-05, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.9713068008422852, |
| "step": 943 |
| }, |
| { |
| "epoch": 5.52199413489736, |
| "grad_norm": 0.6306172258207623, |
| "learning_rate": 1.9657611917515287e-05, |
| "loss": 0.0917, |
| "mean_token_accuracy": 0.9739942848682404, |
| "step": 944 |
| }, |
| { |
| "epoch": 5.527859237536656, |
| "grad_norm": 0.683564829563686, |
| "learning_rate": 1.962361509064928e-05, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.9768866300582886, |
| "step": 945 |
| }, |
| { |
| "epoch": 5.533724340175953, |
| "grad_norm": 0.6547403928859, |
| "learning_rate": 1.958962688910073e-05, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9767028167843819, |
| "step": 946 |
| }, |
| { |
| "epoch": 5.539589442815249, |
| "grad_norm": 0.5491533717582177, |
| "learning_rate": 1.9555647436233093e-05, |
| "loss": 0.0826, |
| "mean_token_accuracy": 0.9770181030035019, |
| "step": 947 |
| }, |
| { |
| "epoch": 5.545454545454545, |
| "grad_norm": 0.834495690001552, |
| "learning_rate": 1.9521676855378045e-05, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9766438603401184, |
| "step": 948 |
| }, |
| { |
| "epoch": 5.551319648093841, |
| "grad_norm": 0.5028599783842282, |
| "learning_rate": 1.9487715269835082e-05, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9753778874874115, |
| "step": 949 |
| }, |
| { |
| "epoch": 5.557184750733137, |
| "grad_norm": 0.584768110856237, |
| "learning_rate": 1.945376280287105e-05, |
| "loss": 0.0888, |
| "mean_token_accuracy": 0.9721104651689529, |
| "step": 950 |
| }, |
| { |
| "epoch": 5.563049853372434, |
| "grad_norm": 0.6577704782595352, |
| "learning_rate": 1.9419819577719684e-05, |
| "loss": 0.0862, |
| "mean_token_accuracy": 0.9739580526947975, |
| "step": 951 |
| }, |
| { |
| "epoch": 5.568914956011731, |
| "grad_norm": 0.7577193714244259, |
| "learning_rate": 1.9385885717581182e-05, |
| "loss": 0.1004, |
| "mean_token_accuracy": 0.9689623937010765, |
| "step": 952 |
| }, |
| { |
| "epoch": 5.574780058651027, |
| "grad_norm": 0.7853657951677275, |
| "learning_rate": 1.935196134562175e-05, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.9788500145077705, |
| "step": 953 |
| }, |
| { |
| "epoch": 5.580645161290323, |
| "grad_norm": 0.49572118058637943, |
| "learning_rate": 1.931804658497316e-05, |
| "loss": 0.0809, |
| "mean_token_accuracy": 0.9770422652363777, |
| "step": 954 |
| }, |
| { |
| "epoch": 5.586510263929619, |
| "grad_norm": 0.7179542536188659, |
| "learning_rate": 1.9284141558732296e-05, |
| "loss": 0.0878, |
| "mean_token_accuracy": 0.9743879362940788, |
| "step": 955 |
| }, |
| { |
| "epoch": 5.592375366568915, |
| "grad_norm": 0.7608646421982846, |
| "learning_rate": 1.925024638996071e-05, |
| "loss": 0.0853, |
| "mean_token_accuracy": 0.9749633818864822, |
| "step": 956 |
| }, |
| { |
| "epoch": 5.5982404692082115, |
| "grad_norm": 0.5043029695894444, |
| "learning_rate": 1.9216361201684174e-05, |
| "loss": 0.0818, |
| "mean_token_accuracy": 0.9793736785650253, |
| "step": 957 |
| }, |
| { |
| "epoch": 5.604105571847508, |
| "grad_norm": 0.7737524412575688, |
| "learning_rate": 1.918248611689224e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9757226184010506, |
| "step": 958 |
| }, |
| { |
| "epoch": 5.609970674486804, |
| "grad_norm": 0.7067522445553732, |
| "learning_rate": 1.9148621258537782e-05, |
| "loss": 0.0921, |
| "mean_token_accuracy": 0.9713330194354057, |
| "step": 959 |
| }, |
| { |
| "epoch": 5.6158357771261, |
| "grad_norm": 1.1027290922626314, |
| "learning_rate": 1.911476674953656e-05, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9776544645428658, |
| "step": 960 |
| }, |
| { |
| "epoch": 5.621700879765396, |
| "grad_norm": 0.6408775647360502, |
| "learning_rate": 1.9080922712766762e-05, |
| "loss": 0.0859, |
| "mean_token_accuracy": 0.9723746255040169, |
| "step": 961 |
| }, |
| { |
| "epoch": 5.627565982404692, |
| "grad_norm": 0.6998113063143537, |
| "learning_rate": 1.904708927106858e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.970834031701088, |
| "step": 962 |
| }, |
| { |
| "epoch": 5.633431085043989, |
| "grad_norm": 0.7806561332961518, |
| "learning_rate": 1.9013266547243742e-05, |
| "loss": 0.0757, |
| "mean_token_accuracy": 0.9781305715441704, |
| "step": 963 |
| }, |
| { |
| "epoch": 5.639296187683285, |
| "grad_norm": 0.4889372143222534, |
| "learning_rate": 1.8979454664055068e-05, |
| "loss": 0.0829, |
| "mean_token_accuracy": 0.9758122488856316, |
| "step": 964 |
| }, |
| { |
| "epoch": 5.645161290322581, |
| "grad_norm": 0.7863504294726643, |
| "learning_rate": 1.894565374422605e-05, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9774143546819687, |
| "step": 965 |
| }, |
| { |
| "epoch": 5.651026392961877, |
| "grad_norm": 0.5448893258732672, |
| "learning_rate": 1.891186391044037e-05, |
| "loss": 0.091, |
| "mean_token_accuracy": 0.971643827855587, |
| "step": 966 |
| }, |
| { |
| "epoch": 5.656891495601173, |
| "grad_norm": 0.6727468767040634, |
| "learning_rate": 1.887808528534148e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9740595147013664, |
| "step": 967 |
| }, |
| { |
| "epoch": 5.6627565982404695, |
| "grad_norm": 0.5251070795859373, |
| "learning_rate": 1.884431799153214e-05, |
| "loss": 0.078, |
| "mean_token_accuracy": 0.9773188605904579, |
| "step": 968 |
| }, |
| { |
| "epoch": 5.668621700879766, |
| "grad_norm": 0.69715074867768, |
| "learning_rate": 1.8810562151573993e-05, |
| "loss": 0.0953, |
| "mean_token_accuracy": 0.9737943336367607, |
| "step": 969 |
| }, |
| { |
| "epoch": 5.674486803519062, |
| "grad_norm": 0.8247784064007003, |
| "learning_rate": 1.8776817887987105e-05, |
| "loss": 0.0867, |
| "mean_token_accuracy": 0.974157802760601, |
| "step": 970 |
| }, |
| { |
| "epoch": 5.680351906158358, |
| "grad_norm": 0.6397418169092066, |
| "learning_rate": 1.8743085323249527e-05, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.9712603464722633, |
| "step": 971 |
| }, |
| { |
| "epoch": 5.686217008797654, |
| "grad_norm": 0.6415808131766715, |
| "learning_rate": 1.870936457979684e-05, |
| "loss": 0.0937, |
| "mean_token_accuracy": 0.976512186229229, |
| "step": 972 |
| }, |
| { |
| "epoch": 5.69208211143695, |
| "grad_norm": 0.6482792559594592, |
| "learning_rate": 1.8675655780021733e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9780119732022285, |
| "step": 973 |
| }, |
| { |
| "epoch": 5.697947214076247, |
| "grad_norm": 0.6985497602725447, |
| "learning_rate": 1.8641959046273525e-05, |
| "loss": 0.0945, |
| "mean_token_accuracy": 0.9735280200839043, |
| "step": 974 |
| }, |
| { |
| "epoch": 5.703812316715543, |
| "grad_norm": 0.649656727914582, |
| "learning_rate": 1.8608274500857756e-05, |
| "loss": 0.0863, |
| "mean_token_accuracy": 0.9729173704981804, |
| "step": 975 |
| }, |
| { |
| "epoch": 5.709677419354839, |
| "grad_norm": 0.6212445716603099, |
| "learning_rate": 1.8574602266035714e-05, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.977060005068779, |
| "step": 976 |
| }, |
| { |
| "epoch": 5.715542521994135, |
| "grad_norm": 0.6146079314603976, |
| "learning_rate": 1.854094246402402e-05, |
| "loss": 0.0924, |
| "mean_token_accuracy": 0.9719849154353142, |
| "step": 977 |
| }, |
| { |
| "epoch": 5.721407624633431, |
| "grad_norm": 0.6788062565147814, |
| "learning_rate": 1.8507295216994162e-05, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.979626290500164, |
| "step": 978 |
| }, |
| { |
| "epoch": 5.7272727272727275, |
| "grad_norm": 0.6423915968454387, |
| "learning_rate": 1.8473660647072053e-05, |
| "loss": 0.0871, |
| "mean_token_accuracy": 0.9703501686453819, |
| "step": 979 |
| }, |
| { |
| "epoch": 5.733137829912024, |
| "grad_norm": 0.558677799000313, |
| "learning_rate": 1.8440038876337597e-05, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9777565002441406, |
| "step": 980 |
| }, |
| { |
| "epoch": 5.73900293255132, |
| "grad_norm": 1.2785599487996107, |
| "learning_rate": 1.8406430026824252e-05, |
| "loss": 0.0879, |
| "mean_token_accuracy": 0.972544752061367, |
| "step": 981 |
| }, |
| { |
| "epoch": 5.744868035190616, |
| "grad_norm": 0.7056011251581465, |
| "learning_rate": 1.837283422051855e-05, |
| "loss": 0.0852, |
| "mean_token_accuracy": 0.9765041247010231, |
| "step": 982 |
| }, |
| { |
| "epoch": 5.750733137829912, |
| "grad_norm": 0.6694236578308186, |
| "learning_rate": 1.8339251579359713e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.9750206470489502, |
| "step": 983 |
| }, |
| { |
| "epoch": 5.756598240469208, |
| "grad_norm": 0.4853704060978793, |
| "learning_rate": 1.8305682225239167e-05, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9784371107816696, |
| "step": 984 |
| }, |
| { |
| "epoch": 5.762463343108505, |
| "grad_norm": 0.7741700176568748, |
| "learning_rate": 1.8272126280000102e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.972519189119339, |
| "step": 985 |
| }, |
| { |
| "epoch": 5.768328445747801, |
| "grad_norm": 0.7875155571594459, |
| "learning_rate": 1.823858386543705e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9750584587454796, |
| "step": 986 |
| }, |
| { |
| "epoch": 5.774193548387097, |
| "grad_norm": 1.1668685106669274, |
| "learning_rate": 1.8205055103295434e-05, |
| "loss": 0.088, |
| "mean_token_accuracy": 0.971601165831089, |
| "step": 987 |
| }, |
| { |
| "epoch": 5.780058651026393, |
| "grad_norm": 0.6957342162162067, |
| "learning_rate": 1.8171540115271108e-05, |
| "loss": 0.0884, |
| "mean_token_accuracy": 0.9688088670372963, |
| "step": 988 |
| }, |
| { |
| "epoch": 5.785923753665689, |
| "grad_norm": 0.5858122379925254, |
| "learning_rate": 1.813803902300995e-05, |
| "loss": 0.0828, |
| "mean_token_accuracy": 0.9737322106957436, |
| "step": 989 |
| }, |
| { |
| "epoch": 5.7917888563049855, |
| "grad_norm": 0.598739315562945, |
| "learning_rate": 1.8104551948107395e-05, |
| "loss": 0.0875, |
| "mean_token_accuracy": 0.9778008908033371, |
| "step": 990 |
| }, |
| { |
| "epoch": 5.797653958944282, |
| "grad_norm": 0.7749756964271326, |
| "learning_rate": 1.8071079012107997e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.9746625646948814, |
| "step": 991 |
| }, |
| { |
| "epoch": 5.803519061583578, |
| "grad_norm": 0.650221789959287, |
| "learning_rate": 1.8037620336504993e-05, |
| "loss": 0.0876, |
| "mean_token_accuracy": 0.9753068014979362, |
| "step": 992 |
| }, |
| { |
| "epoch": 5.809384164222874, |
| "grad_norm": 0.6479507750610883, |
| "learning_rate": 1.8004176042739877e-05, |
| "loss": 0.0845, |
| "mean_token_accuracy": 0.9764060229063034, |
| "step": 993 |
| }, |
| { |
| "epoch": 5.81524926686217, |
| "grad_norm": 0.7040519035215548, |
| "learning_rate": 1.797074625220191e-05, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.9756477698683739, |
| "step": 994 |
| }, |
| { |
| "epoch": 5.821114369501466, |
| "grad_norm": 0.5324611517794914, |
| "learning_rate": 1.7937331086227737e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9716223925352097, |
| "step": 995 |
| }, |
| { |
| "epoch": 5.826979472140763, |
| "grad_norm": 0.6583142672501221, |
| "learning_rate": 1.790393066610091e-05, |
| "loss": 0.0863, |
| "mean_token_accuracy": 0.9739385768771172, |
| "step": 996 |
| }, |
| { |
| "epoch": 5.832844574780059, |
| "grad_norm": 0.6840541212276599, |
| "learning_rate": 1.787054511305148e-05, |
| "loss": 0.0859, |
| "mean_token_accuracy": 0.9745663329958916, |
| "step": 997 |
| }, |
| { |
| "epoch": 5.838709677419355, |
| "grad_norm": 0.6422182464609407, |
| "learning_rate": 1.7837174548255504e-05, |
| "loss": 0.0855, |
| "mean_token_accuracy": 0.9756312891840935, |
| "step": 998 |
| }, |
| { |
| "epoch": 5.844574780058651, |
| "grad_norm": 0.551776661055142, |
| "learning_rate": 1.7803819092834668e-05, |
| "loss": 0.0737, |
| "mean_token_accuracy": 0.9777807220816612, |
| "step": 999 |
| }, |
| { |
| "epoch": 5.850439882697947, |
| "grad_norm": 0.734547203404358, |
| "learning_rate": 1.7770478867855797e-05, |
| "loss": 0.0866, |
| "mean_token_accuracy": 0.9762368500232697, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.8563049853372435, |
| "grad_norm": 0.7438149569779208, |
| "learning_rate": 1.7737153994330437e-05, |
| "loss": 0.1011, |
| "mean_token_accuracy": 0.9705447629094124, |
| "step": 1001 |
| }, |
| { |
| "epoch": 5.86217008797654, |
| "grad_norm": 0.5989262037995564, |
| "learning_rate": 1.7703844593214427e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9772868156433105, |
| "step": 1002 |
| }, |
| { |
| "epoch": 5.868035190615836, |
| "grad_norm": 0.5387325185762245, |
| "learning_rate": 1.7670550785407444e-05, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9779915139079094, |
| "step": 1003 |
| }, |
| { |
| "epoch": 5.873900293255132, |
| "grad_norm": 0.5529203720914665, |
| "learning_rate": 1.7637272691752548e-05, |
| "loss": 0.0824, |
| "mean_token_accuracy": 0.9724158346652985, |
| "step": 1004 |
| }, |
| { |
| "epoch": 5.879765395894428, |
| "grad_norm": 0.5081691050646204, |
| "learning_rate": 1.7604010433035793e-05, |
| "loss": 0.0893, |
| "mean_token_accuracy": 0.9720709770917892, |
| "step": 1005 |
| }, |
| { |
| "epoch": 5.885630498533724, |
| "grad_norm": 0.756502417771231, |
| "learning_rate": 1.7570764129985747e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9759951457381248, |
| "step": 1006 |
| }, |
| { |
| "epoch": 5.891495601173021, |
| "grad_norm": 0.5358224744677316, |
| "learning_rate": 1.7537533903273055e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9745610728859901, |
| "step": 1007 |
| }, |
| { |
| "epoch": 5.897360703812317, |
| "grad_norm": 0.7031782400736435, |
| "learning_rate": 1.7504319873510014e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.9742460176348686, |
| "step": 1008 |
| }, |
| { |
| "epoch": 5.903225806451613, |
| "grad_norm": 0.7417007125975534, |
| "learning_rate": 1.7471122161250153e-05, |
| "loss": 0.0873, |
| "mean_token_accuracy": 0.9722920358181, |
| "step": 1009 |
| }, |
| { |
| "epoch": 5.909090909090909, |
| "grad_norm": 0.766852011186241, |
| "learning_rate": 1.743794088698775e-05, |
| "loss": 0.0853, |
| "mean_token_accuracy": 0.9757792204618454, |
| "step": 1010 |
| }, |
| { |
| "epoch": 5.914956011730205, |
| "grad_norm": 0.6482473650913794, |
| "learning_rate": 1.7404776171157428e-05, |
| "loss": 0.0989, |
| "mean_token_accuracy": 0.9704331830143929, |
| "step": 1011 |
| }, |
| { |
| "epoch": 5.9208211143695015, |
| "grad_norm": 0.7240261222776643, |
| "learning_rate": 1.7371628134133716e-05, |
| "loss": 0.0968, |
| "mean_token_accuracy": 0.972036175429821, |
| "step": 1012 |
| }, |
| { |
| "epoch": 5.926686217008798, |
| "grad_norm": 0.628892680365792, |
| "learning_rate": 1.73384968962306e-05, |
| "loss": 0.0855, |
| "mean_token_accuracy": 0.9731899350881577, |
| "step": 1013 |
| }, |
| { |
| "epoch": 5.932551319648094, |
| "grad_norm": 0.7106790161768256, |
| "learning_rate": 1.7305382577701088e-05, |
| "loss": 0.0956, |
| "mean_token_accuracy": 0.9716820046305656, |
| "step": 1014 |
| }, |
| { |
| "epoch": 5.93841642228739, |
| "grad_norm": 0.6838469394111186, |
| "learning_rate": 1.7272285298736787e-05, |
| "loss": 0.0778, |
| "mean_token_accuracy": 0.9754338562488556, |
| "step": 1015 |
| }, |
| { |
| "epoch": 5.944281524926686, |
| "grad_norm": 0.6872214896209663, |
| "learning_rate": 1.7239205179467453e-05, |
| "loss": 0.1001, |
| "mean_token_accuracy": 0.972577653825283, |
| "step": 1016 |
| }, |
| { |
| "epoch": 5.9501466275659824, |
| "grad_norm": 0.6557151291069184, |
| "learning_rate": 1.720614233996056e-05, |
| "loss": 0.1091, |
| "mean_token_accuracy": 0.9667370170354843, |
| "step": 1017 |
| }, |
| { |
| "epoch": 5.956011730205279, |
| "grad_norm": 0.7872367392433527, |
| "learning_rate": 1.7173096900220852e-05, |
| "loss": 0.0852, |
| "mean_token_accuracy": 0.972346842288971, |
| "step": 1018 |
| }, |
| { |
| "epoch": 5.961876832844575, |
| "grad_norm": 0.5800535877487003, |
| "learning_rate": 1.7140068980189943e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9726891592144966, |
| "step": 1019 |
| }, |
| { |
| "epoch": 5.967741935483871, |
| "grad_norm": 0.7407124629984413, |
| "learning_rate": 1.710705869974583e-05, |
| "loss": 0.082, |
| "mean_token_accuracy": 0.9731708765029907, |
| "step": 1020 |
| }, |
| { |
| "epoch": 5.973607038123167, |
| "grad_norm": 0.48961326813702305, |
| "learning_rate": 1.7074066178702512e-05, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.977909691631794, |
| "step": 1021 |
| }, |
| { |
| "epoch": 5.979472140762463, |
| "grad_norm": 0.5617989892061567, |
| "learning_rate": 1.7041091536809506e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9753151684999466, |
| "step": 1022 |
| }, |
| { |
| "epoch": 5.9853372434017595, |
| "grad_norm": 0.6833500434939148, |
| "learning_rate": 1.7008134893751446e-05, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9776782914996147, |
| "step": 1023 |
| }, |
| { |
| "epoch": 5.991202346041056, |
| "grad_norm": 0.3999962713670006, |
| "learning_rate": 1.697519636914765e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.978028692305088, |
| "step": 1024 |
| }, |
| { |
| "epoch": 5.997067448680352, |
| "grad_norm": 0.6396083535043195, |
| "learning_rate": 1.6942276082551634e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.9712998270988464, |
| "step": 1025 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.1147420985091527, |
| "learning_rate": 1.6909374153450762e-05, |
| "loss": 0.1048, |
| "mean_token_accuracy": 0.9730786234140396, |
| "step": 1026 |
| }, |
| { |
| "epoch": 6.005865102639296, |
| "grad_norm": 0.5202288917529572, |
| "learning_rate": 1.6876490701265736e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9801736921072006, |
| "step": 1027 |
| }, |
| { |
| "epoch": 6.011730205278592, |
| "grad_norm": 0.5739041631655252, |
| "learning_rate": 1.684362584535022e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.976397916674614, |
| "step": 1028 |
| }, |
| { |
| "epoch": 6.0175953079178885, |
| "grad_norm": 0.5383910419538716, |
| "learning_rate": 1.6810779704990358e-05, |
| "loss": 0.0739, |
| "mean_token_accuracy": 0.9765185192227364, |
| "step": 1029 |
| }, |
| { |
| "epoch": 6.023460410557185, |
| "grad_norm": 0.5494319540629348, |
| "learning_rate": 1.677795239940438e-05, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9817954376339912, |
| "step": 1030 |
| }, |
| { |
| "epoch": 6.029325513196481, |
| "grad_norm": 0.5433321296105504, |
| "learning_rate": 1.674514404774214e-05, |
| "loss": 0.0752, |
| "mean_token_accuracy": 0.9775493144989014, |
| "step": 1031 |
| }, |
| { |
| "epoch": 6.035190615835777, |
| "grad_norm": 0.5151829348351332, |
| "learning_rate": 1.671235476908471e-05, |
| "loss": 0.0728, |
| "mean_token_accuracy": 0.9772488325834274, |
| "step": 1032 |
| }, |
| { |
| "epoch": 6.041055718475073, |
| "grad_norm": 0.4972524129628317, |
| "learning_rate": 1.6679584682443924e-05, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9799492433667183, |
| "step": 1033 |
| }, |
| { |
| "epoch": 6.0469208211143695, |
| "grad_norm": 0.46952005304609734, |
| "learning_rate": 1.6646833906761965e-05, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9775111898779869, |
| "step": 1034 |
| }, |
| { |
| "epoch": 6.052785923753666, |
| "grad_norm": 0.44315338871603027, |
| "learning_rate": 1.661410256091092e-05, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.9794765636324883, |
| "step": 1035 |
| }, |
| { |
| "epoch": 6.058651026392962, |
| "grad_norm": 0.5676214069603677, |
| "learning_rate": 1.658139076369236e-05, |
| "loss": 0.0793, |
| "mean_token_accuracy": 0.9757615253329277, |
| "step": 1036 |
| }, |
| { |
| "epoch": 6.064516129032258, |
| "grad_norm": 0.6429377797747571, |
| "learning_rate": 1.6548698633836893e-05, |
| "loss": 0.0793, |
| "mean_token_accuracy": 0.972226656973362, |
| "step": 1037 |
| }, |
| { |
| "epoch": 6.070381231671554, |
| "grad_norm": 0.5357438467822505, |
| "learning_rate": 1.6516026290003746e-05, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9822089746594429, |
| "step": 1038 |
| }, |
| { |
| "epoch": 6.07624633431085, |
| "grad_norm": 0.5993690137250399, |
| "learning_rate": 1.6483373850780328e-05, |
| "loss": 0.0717, |
| "mean_token_accuracy": 0.9774091765284538, |
| "step": 1039 |
| }, |
| { |
| "epoch": 6.0821114369501466, |
| "grad_norm": 0.4190984495167291, |
| "learning_rate": 1.645074143468181e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9807809740304947, |
| "step": 1040 |
| }, |
| { |
| "epoch": 6.087976539589443, |
| "grad_norm": 0.6597809731293542, |
| "learning_rate": 1.6418129160150692e-05, |
| "loss": 0.0731, |
| "mean_token_accuracy": 0.9749625474214554, |
| "step": 1041 |
| }, |
| { |
| "epoch": 6.093841642228739, |
| "grad_norm": 0.5336205207180447, |
| "learning_rate": 1.6385537145556346e-05, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9818411692976952, |
| "step": 1042 |
| }, |
| { |
| "epoch": 6.099706744868035, |
| "grad_norm": 0.47928728223975, |
| "learning_rate": 1.6352965509194634e-05, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9807577580213547, |
| "step": 1043 |
| }, |
| { |
| "epoch": 6.105571847507331, |
| "grad_norm": 0.48355345719317167, |
| "learning_rate": 1.6320414369287427e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9786029979586601, |
| "step": 1044 |
| }, |
| { |
| "epoch": 6.1114369501466275, |
| "grad_norm": 0.6144852297951959, |
| "learning_rate": 1.6287883843982223e-05, |
| "loss": 0.0733, |
| "mean_token_accuracy": 0.9777380973100662, |
| "step": 1045 |
| }, |
| { |
| "epoch": 6.117302052785924, |
| "grad_norm": 0.6340714518585042, |
| "learning_rate": 1.625537405135169e-05, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.9729229807853699, |
| "step": 1046 |
| }, |
| { |
| "epoch": 6.12316715542522, |
| "grad_norm": 0.5568337235876012, |
| "learning_rate": 1.622288510939325e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.9760441929101944, |
| "step": 1047 |
| }, |
| { |
| "epoch": 6.129032258064516, |
| "grad_norm": 0.5939116225097025, |
| "learning_rate": 1.619041713602864e-05, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.9749231860041618, |
| "step": 1048 |
| }, |
| { |
| "epoch": 6.134897360703812, |
| "grad_norm": 0.49431495980866813, |
| "learning_rate": 1.6157970249103484e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9751162528991699, |
| "step": 1049 |
| }, |
| { |
| "epoch": 6.140762463343108, |
| "grad_norm": 0.5876887177758083, |
| "learning_rate": 1.612554456638688e-05, |
| "loss": 0.078, |
| "mean_token_accuracy": 0.9751496464014053, |
| "step": 1050 |
| }, |
| { |
| "epoch": 6.146627565982405, |
| "grad_norm": 0.744948657520097, |
| "learning_rate": 1.6093140205570962e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.9704322144389153, |
| "step": 1051 |
| }, |
| { |
| "epoch": 6.152492668621701, |
| "grad_norm": 0.6326737035901645, |
| "learning_rate": 1.6060757284270474e-05, |
| "loss": 0.0882, |
| "mean_token_accuracy": 0.9718341752886772, |
| "step": 1052 |
| }, |
| { |
| "epoch": 6.158357771260997, |
| "grad_norm": 0.41910883057148673, |
| "learning_rate": 1.6028395920022336e-05, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9783205166459084, |
| "step": 1053 |
| }, |
| { |
| "epoch": 6.164222873900293, |
| "grad_norm": 0.48067835067712417, |
| "learning_rate": 1.5996056230285237e-05, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9760030433535576, |
| "step": 1054 |
| }, |
| { |
| "epoch": 6.170087976539589, |
| "grad_norm": 0.562185298887884, |
| "learning_rate": 1.596373833243918e-05, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9750814661383629, |
| "step": 1055 |
| }, |
| { |
| "epoch": 6.1759530791788855, |
| "grad_norm": 0.5522973486708462, |
| "learning_rate": 1.593144234378509e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9756905287504196, |
| "step": 1056 |
| }, |
| { |
| "epoch": 6.181818181818182, |
| "grad_norm": 0.4779934912831462, |
| "learning_rate": 1.5899168381544362e-05, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9793584048748016, |
| "step": 1057 |
| }, |
| { |
| "epoch": 6.187683284457478, |
| "grad_norm": 0.518336118011279, |
| "learning_rate": 1.5866916562858444e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9778865575790405, |
| "step": 1058 |
| }, |
| { |
| "epoch": 6.193548387096774, |
| "grad_norm": 0.4666524808220914, |
| "learning_rate": 1.5834687004788406e-05, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9767828062176704, |
| "step": 1059 |
| }, |
| { |
| "epoch": 6.19941348973607, |
| "grad_norm": 0.6436163754016054, |
| "learning_rate": 1.5802479824314537e-05, |
| "loss": 0.0808, |
| "mean_token_accuracy": 0.9713993892073631, |
| "step": 1060 |
| }, |
| { |
| "epoch": 6.205278592375366, |
| "grad_norm": 0.49132240296176427, |
| "learning_rate": 1.5770295138335896e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9808058738708496, |
| "step": 1061 |
| }, |
| { |
| "epoch": 6.211143695014663, |
| "grad_norm": 0.4753775907536774, |
| "learning_rate": 1.573813306366988e-05, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.981878250837326, |
| "step": 1062 |
| }, |
| { |
| "epoch": 6.217008797653959, |
| "grad_norm": 0.5673472220422602, |
| "learning_rate": 1.5705993717051838e-05, |
| "loss": 0.0833, |
| "mean_token_accuracy": 0.9748826399445534, |
| "step": 1063 |
| }, |
| { |
| "epoch": 6.222873900293255, |
| "grad_norm": 0.526645969703994, |
| "learning_rate": 1.567387721513462e-05, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9779791384935379, |
| "step": 1064 |
| }, |
| { |
| "epoch": 6.228739002932551, |
| "grad_norm": 0.5825082631105734, |
| "learning_rate": 1.5641783674488155e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9779115691781044, |
| "step": 1065 |
| }, |
| { |
| "epoch": 6.234604105571847, |
| "grad_norm": 0.5677888358987312, |
| "learning_rate": 1.5609713211599035e-05, |
| "loss": 0.0832, |
| "mean_token_accuracy": 0.9752690866589546, |
| "step": 1066 |
| }, |
| { |
| "epoch": 6.2404692082111435, |
| "grad_norm": 0.5709450414456684, |
| "learning_rate": 1.557766594287009e-05, |
| "loss": 0.0882, |
| "mean_token_accuracy": 0.9753549993038177, |
| "step": 1067 |
| }, |
| { |
| "epoch": 6.24633431085044, |
| "grad_norm": 0.7430276028327776, |
| "learning_rate": 1.554564198461996e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.9685186669230461, |
| "step": 1068 |
| }, |
| { |
| "epoch": 6.252199413489736, |
| "grad_norm": 0.6168855856289802, |
| "learning_rate": 1.5513641453082672e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9780802503228188, |
| "step": 1069 |
| }, |
| { |
| "epoch": 6.258064516129032, |
| "grad_norm": 0.6379867283389812, |
| "learning_rate": 1.5481664464407246e-05, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9805227667093277, |
| "step": 1070 |
| }, |
| { |
| "epoch": 6.263929618768328, |
| "grad_norm": 0.5302609136875379, |
| "learning_rate": 1.5449711134657224e-05, |
| "loss": 0.0815, |
| "mean_token_accuracy": 0.9738188460469246, |
| "step": 1071 |
| }, |
| { |
| "epoch": 6.269794721407624, |
| "grad_norm": 0.5668666714707467, |
| "learning_rate": 1.5417781579810296e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.975812129676342, |
| "step": 1072 |
| }, |
| { |
| "epoch": 6.275659824046921, |
| "grad_norm": 0.5530723747905679, |
| "learning_rate": 1.5385875915757846e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9774937778711319, |
| "step": 1073 |
| }, |
| { |
| "epoch": 6.281524926686217, |
| "grad_norm": 0.6109099842720831, |
| "learning_rate": 1.535399425830456e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9768806248903275, |
| "step": 1074 |
| }, |
| { |
| "epoch": 6.287390029325513, |
| "grad_norm": 0.5557413076689061, |
| "learning_rate": 1.5322136723167957e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9749912396073341, |
| "step": 1075 |
| }, |
| { |
| "epoch": 6.293255131964809, |
| "grad_norm": 0.5155497604370435, |
| "learning_rate": 1.5290303425978036e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9790643975138664, |
| "step": 1076 |
| }, |
| { |
| "epoch": 6.299120234604105, |
| "grad_norm": 0.5991722826094168, |
| "learning_rate": 1.525849448227681e-05, |
| "loss": 0.077, |
| "mean_token_accuracy": 0.9764990583062172, |
| "step": 1077 |
| }, |
| { |
| "epoch": 6.3049853372434015, |
| "grad_norm": 0.5400898196299592, |
| "learning_rate": 1.5226710007517894e-05, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.971705824136734, |
| "step": 1078 |
| }, |
| { |
| "epoch": 6.310850439882698, |
| "grad_norm": 0.46671688299599096, |
| "learning_rate": 1.5194950117066097e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9766178503632545, |
| "step": 1079 |
| }, |
| { |
| "epoch": 6.316715542521994, |
| "grad_norm": 0.5638659890737318, |
| "learning_rate": 1.5163214926196995e-05, |
| "loss": 0.0893, |
| "mean_token_accuracy": 0.9723503813147545, |
| "step": 1080 |
| }, |
| { |
| "epoch": 6.32258064516129, |
| "grad_norm": 0.6696695090363065, |
| "learning_rate": 1.5131504550096515e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9719719514250755, |
| "step": 1081 |
| }, |
| { |
| "epoch": 6.328445747800586, |
| "grad_norm": 0.5086536558966609, |
| "learning_rate": 1.5099819103860504e-05, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9775032550096512, |
| "step": 1082 |
| }, |
| { |
| "epoch": 6.334310850439882, |
| "grad_norm": 0.471688139385336, |
| "learning_rate": 1.5068158702494348e-05, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9810898527503014, |
| "step": 1083 |
| }, |
| { |
| "epoch": 6.340175953079179, |
| "grad_norm": 0.4175822937840527, |
| "learning_rate": 1.5036523460912511e-05, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9814708605408669, |
| "step": 1084 |
| }, |
| { |
| "epoch": 6.346041055718475, |
| "grad_norm": 0.4686690712794084, |
| "learning_rate": 1.5004913493938147e-05, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9775428622961044, |
| "step": 1085 |
| }, |
| { |
| "epoch": 6.351906158357771, |
| "grad_norm": 0.5230553954992002, |
| "learning_rate": 1.4973328916302667e-05, |
| "loss": 0.0804, |
| "mean_token_accuracy": 0.9741173461079597, |
| "step": 1086 |
| }, |
| { |
| "epoch": 6.357771260997067, |
| "grad_norm": 0.6417142179248468, |
| "learning_rate": 1.4941769842645335e-05, |
| "loss": 0.0744, |
| "mean_token_accuracy": 0.9732955172657967, |
| "step": 1087 |
| }, |
| { |
| "epoch": 6.363636363636363, |
| "grad_norm": 0.5595604356693998, |
| "learning_rate": 1.4910236387512837e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9762078300118446, |
| "step": 1088 |
| }, |
| { |
| "epoch": 6.3695014662756595, |
| "grad_norm": 0.5383764197029854, |
| "learning_rate": 1.487872866535888e-05, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.978789784014225, |
| "step": 1089 |
| }, |
| { |
| "epoch": 6.375366568914956, |
| "grad_norm": 0.5947779638063944, |
| "learning_rate": 1.4847246790543773e-05, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9754747003316879, |
| "step": 1090 |
| }, |
| { |
| "epoch": 6.381231671554252, |
| "grad_norm": 0.523837387093672, |
| "learning_rate": 1.4815790877334007e-05, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9779769256711006, |
| "step": 1091 |
| }, |
| { |
| "epoch": 6.387096774193548, |
| "grad_norm": 0.6428925856092318, |
| "learning_rate": 1.4784361039901844e-05, |
| "loss": 0.0816, |
| "mean_token_accuracy": 0.9758491739630699, |
| "step": 1092 |
| }, |
| { |
| "epoch": 6.392961876832844, |
| "grad_norm": 0.47087577274198766, |
| "learning_rate": 1.47529573923249e-05, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9800596609711647, |
| "step": 1093 |
| }, |
| { |
| "epoch": 6.39882697947214, |
| "grad_norm": 0.4926712898849946, |
| "learning_rate": 1.472158004858573e-05, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9772643595933914, |
| "step": 1094 |
| }, |
| { |
| "epoch": 6.404692082111437, |
| "grad_norm": 0.6392683738272947, |
| "learning_rate": 1.4690229122571419e-05, |
| "loss": 0.0868, |
| "mean_token_accuracy": 0.9720509201288223, |
| "step": 1095 |
| }, |
| { |
| "epoch": 6.410557184750733, |
| "grad_norm": 0.4332296080546844, |
| "learning_rate": 1.4658904728073169e-05, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9797382056713104, |
| "step": 1096 |
| }, |
| { |
| "epoch": 6.416422287390029, |
| "grad_norm": 0.6285097290934989, |
| "learning_rate": 1.4627606978785878e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.9753040000796318, |
| "step": 1097 |
| }, |
| { |
| "epoch": 6.422287390029325, |
| "grad_norm": 0.5639248567038654, |
| "learning_rate": 1.4596335988307736e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9763555377721786, |
| "step": 1098 |
| }, |
| { |
| "epoch": 6.428152492668621, |
| "grad_norm": 0.47561096888160737, |
| "learning_rate": 1.4565091870139814e-05, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9785003736615181, |
| "step": 1099 |
| }, |
| { |
| "epoch": 6.4340175953079175, |
| "grad_norm": 0.6245194955076678, |
| "learning_rate": 1.4533874737685638e-05, |
| "loss": 0.0954, |
| "mean_token_accuracy": 0.9722826331853867, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.439882697947214, |
| "grad_norm": 0.5706226716255113, |
| "learning_rate": 1.450268470425079e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9781828373670578, |
| "step": 1101 |
| }, |
| { |
| "epoch": 6.44574780058651, |
| "grad_norm": 0.48168970485274204, |
| "learning_rate": 1.4471521883042492e-05, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9778439179062843, |
| "step": 1102 |
| }, |
| { |
| "epoch": 6.451612903225806, |
| "grad_norm": 0.5020122286087533, |
| "learning_rate": 1.4440386387169207e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9767275303602219, |
| "step": 1103 |
| }, |
| { |
| "epoch": 6.457478005865102, |
| "grad_norm": 0.6034064679765079, |
| "learning_rate": 1.4409278329640218e-05, |
| "loss": 0.078, |
| "mean_token_accuracy": 0.9737183228135109, |
| "step": 1104 |
| }, |
| { |
| "epoch": 6.463343108504398, |
| "grad_norm": 0.5745820857166307, |
| "learning_rate": 1.4378197823365186e-05, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.976705364882946, |
| "step": 1105 |
| }, |
| { |
| "epoch": 6.469208211143695, |
| "grad_norm": 0.5625957570348558, |
| "learning_rate": 1.4347144981153807e-05, |
| "loss": 0.0868, |
| "mean_token_accuracy": 0.9726732224225998, |
| "step": 1106 |
| }, |
| { |
| "epoch": 6.475073313782991, |
| "grad_norm": 0.4930814898729793, |
| "learning_rate": 1.4316119915715363e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9789433181285858, |
| "step": 1107 |
| }, |
| { |
| "epoch": 6.480938416422287, |
| "grad_norm": 0.7989269250156616, |
| "learning_rate": 1.42851227396583e-05, |
| "loss": 0.0876, |
| "mean_token_accuracy": 0.973343163728714, |
| "step": 1108 |
| }, |
| { |
| "epoch": 6.486803519061583, |
| "grad_norm": 0.6763402109132646, |
| "learning_rate": 1.4254153565489861e-05, |
| "loss": 0.0854, |
| "mean_token_accuracy": 0.9718771129846573, |
| "step": 1109 |
| }, |
| { |
| "epoch": 6.492668621700879, |
| "grad_norm": 0.539486021642433, |
| "learning_rate": 1.4223212505615634e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9774969145655632, |
| "step": 1110 |
| }, |
| { |
| "epoch": 6.4985337243401755, |
| "grad_norm": 0.5251586229610573, |
| "learning_rate": 1.4192299672339167e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9784964397549629, |
| "step": 1111 |
| }, |
| { |
| "epoch": 6.504398826979472, |
| "grad_norm": 0.5309826113002859, |
| "learning_rate": 1.4161415177861568e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9744265750050545, |
| "step": 1112 |
| }, |
| { |
| "epoch": 6.510263929618768, |
| "grad_norm": 0.7047987370200421, |
| "learning_rate": 1.4130559134281074e-05, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.9792541116476059, |
| "step": 1113 |
| }, |
| { |
| "epoch": 6.516129032258064, |
| "grad_norm": 0.515674317504861, |
| "learning_rate": 1.4099731653592668e-05, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9781686887145042, |
| "step": 1114 |
| }, |
| { |
| "epoch": 6.52199413489736, |
| "grad_norm": 0.5947129051770558, |
| "learning_rate": 1.406893284768764e-05, |
| "loss": 0.0888, |
| "mean_token_accuracy": 0.9724589213728905, |
| "step": 1115 |
| }, |
| { |
| "epoch": 6.527859237536656, |
| "grad_norm": 0.500411834167771, |
| "learning_rate": 1.4038162828353223e-05, |
| "loss": 0.0808, |
| "mean_token_accuracy": 0.9722086489200592, |
| "step": 1116 |
| }, |
| { |
| "epoch": 6.533724340175953, |
| "grad_norm": 0.5342882535928477, |
| "learning_rate": 1.4007421707272167e-05, |
| "loss": 0.0792, |
| "mean_token_accuracy": 0.9754097685217857, |
| "step": 1117 |
| }, |
| { |
| "epoch": 6.539589442815249, |
| "grad_norm": 0.5937463096071416, |
| "learning_rate": 1.3976709596022313e-05, |
| "loss": 0.0787, |
| "mean_token_accuracy": 0.9737225919961929, |
| "step": 1118 |
| }, |
| { |
| "epoch": 6.545454545454545, |
| "grad_norm": 0.5066873416271005, |
| "learning_rate": 1.3946026606076232e-05, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9775821045041084, |
| "step": 1119 |
| }, |
| { |
| "epoch": 6.551319648093841, |
| "grad_norm": 0.45523037490484686, |
| "learning_rate": 1.3915372848800784e-05, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9771781116724014, |
| "step": 1120 |
| }, |
| { |
| "epoch": 6.557184750733137, |
| "grad_norm": 0.4600174852995777, |
| "learning_rate": 1.388474843545672e-05, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9782451391220093, |
| "step": 1121 |
| }, |
| { |
| "epoch": 6.563049853372434, |
| "grad_norm": 0.6097336256321833, |
| "learning_rate": 1.3854153477198305e-05, |
| "loss": 0.0989, |
| "mean_token_accuracy": 0.9664244577288628, |
| "step": 1122 |
| }, |
| { |
| "epoch": 6.568914956011731, |
| "grad_norm": 0.552123315680262, |
| "learning_rate": 1.3823588085072865e-05, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.9755944460630417, |
| "step": 1123 |
| }, |
| { |
| "epoch": 6.574780058651027, |
| "grad_norm": 0.5457720092668241, |
| "learning_rate": 1.3793052370020441e-05, |
| "loss": 0.0843, |
| "mean_token_accuracy": 0.9757449254393578, |
| "step": 1124 |
| }, |
| { |
| "epoch": 6.580645161290323, |
| "grad_norm": 0.43562839981910295, |
| "learning_rate": 1.3762546442873343e-05, |
| "loss": 0.0717, |
| "mean_token_accuracy": 0.9786180108785629, |
| "step": 1125 |
| }, |
| { |
| "epoch": 6.586510263929619, |
| "grad_norm": 0.6472330415954715, |
| "learning_rate": 1.3732070414355766e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9755496978759766, |
| "step": 1126 |
| }, |
| { |
| "epoch": 6.592375366568915, |
| "grad_norm": 0.4756335587174598, |
| "learning_rate": 1.370162439508339e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9780619740486145, |
| "step": 1127 |
| }, |
| { |
| "epoch": 6.5982404692082115, |
| "grad_norm": 0.5634011215648543, |
| "learning_rate": 1.367120849556296e-05, |
| "loss": 0.0752, |
| "mean_token_accuracy": 0.9766998812556267, |
| "step": 1128 |
| }, |
| { |
| "epoch": 6.604105571847508, |
| "grad_norm": 0.33348339382452186, |
| "learning_rate": 1.3640822826191907e-05, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9821174144744873, |
| "step": 1129 |
| }, |
| { |
| "epoch": 6.609970674486804, |
| "grad_norm": 0.5058118088375012, |
| "learning_rate": 1.361046749725794e-05, |
| "loss": 0.0729, |
| "mean_token_accuracy": 0.973750501871109, |
| "step": 1130 |
| }, |
| { |
| "epoch": 6.6158357771261, |
| "grad_norm": 0.3513140028655011, |
| "learning_rate": 1.3580142618938647e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9823877438902855, |
| "step": 1131 |
| }, |
| { |
| "epoch": 6.621700879765396, |
| "grad_norm": 0.6010898695910089, |
| "learning_rate": 1.354984830130109e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9730056077241898, |
| "step": 1132 |
| }, |
| { |
| "epoch": 6.627565982404692, |
| "grad_norm": 0.42939858042799467, |
| "learning_rate": 1.3519584654301401e-05, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.9771179631352425, |
| "step": 1133 |
| }, |
| { |
| "epoch": 6.633431085043989, |
| "grad_norm": 0.5852411490645988, |
| "learning_rate": 1.3489351787784398e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9754769504070282, |
| "step": 1134 |
| }, |
| { |
| "epoch": 6.639296187683285, |
| "grad_norm": 0.5712867655130404, |
| "learning_rate": 1.3459149811483178e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.974666953086853, |
| "step": 1135 |
| }, |
| { |
| "epoch": 6.645161290322581, |
| "grad_norm": 0.5264774383671567, |
| "learning_rate": 1.342897883501872e-05, |
| "loss": 0.0792, |
| "mean_token_accuracy": 0.9758988320827484, |
| "step": 1136 |
| }, |
| { |
| "epoch": 6.651026392961877, |
| "grad_norm": 0.5392883097179687, |
| "learning_rate": 1.3398838967899477e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9775514528155327, |
| "step": 1137 |
| }, |
| { |
| "epoch": 6.656891495601173, |
| "grad_norm": 0.5844035196310134, |
| "learning_rate": 1.3368730319520992e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.978425644338131, |
| "step": 1138 |
| }, |
| { |
| "epoch": 6.6627565982404695, |
| "grad_norm": 0.6218435188737981, |
| "learning_rate": 1.3338652999165511e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9742521271109581, |
| "step": 1139 |
| }, |
| { |
| "epoch": 6.668621700879766, |
| "grad_norm": 0.5031460449388016, |
| "learning_rate": 1.3308607116001549e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9794870689511299, |
| "step": 1140 |
| }, |
| { |
| "epoch": 6.674486803519062, |
| "grad_norm": 0.5079929252121882, |
| "learning_rate": 1.3278592779083534e-05, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.983228825032711, |
| "step": 1141 |
| }, |
| { |
| "epoch": 6.680351906158358, |
| "grad_norm": 0.5029542646309768, |
| "learning_rate": 1.324861009735138e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.978003516793251, |
| "step": 1142 |
| }, |
| { |
| "epoch": 6.686217008797654, |
| "grad_norm": 0.4683913564742217, |
| "learning_rate": 1.3218659179630112e-05, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9770939275622368, |
| "step": 1143 |
| }, |
| { |
| "epoch": 6.69208211143695, |
| "grad_norm": 0.4988823991555784, |
| "learning_rate": 1.3188740134629469e-05, |
| "loss": 0.0708, |
| "mean_token_accuracy": 0.9781245067715645, |
| "step": 1144 |
| }, |
| { |
| "epoch": 6.697947214076247, |
| "grad_norm": 0.45606696729566554, |
| "learning_rate": 1.3158853070943499e-05, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9791443273425102, |
| "step": 1145 |
| }, |
| { |
| "epoch": 6.703812316715543, |
| "grad_norm": 0.5221547094850065, |
| "learning_rate": 1.3128998097050174e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9777532517910004, |
| "step": 1146 |
| }, |
| { |
| "epoch": 6.709677419354839, |
| "grad_norm": 0.5490116094072529, |
| "learning_rate": 1.3099175321310993e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9768932908773422, |
| "step": 1147 |
| }, |
| { |
| "epoch": 6.715542521994135, |
| "grad_norm": 0.4176562136333769, |
| "learning_rate": 1.3069384851970584e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9779625982046127, |
| "step": 1148 |
| }, |
| { |
| "epoch": 6.721407624633431, |
| "grad_norm": 0.4980689337176214, |
| "learning_rate": 1.3039626797156321e-05, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.97952900826931, |
| "step": 1149 |
| }, |
| { |
| "epoch": 6.7272727272727275, |
| "grad_norm": 0.36731730926429257, |
| "learning_rate": 1.3009901264877924e-05, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9820658639073372, |
| "step": 1150 |
| }, |
| { |
| "epoch": 6.733137829912024, |
| "grad_norm": 0.3967447841170825, |
| "learning_rate": 1.298020836302707e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9772286713123322, |
| "step": 1151 |
| }, |
| { |
| "epoch": 6.73900293255132, |
| "grad_norm": 0.42726350650755013, |
| "learning_rate": 1.2950548199376999e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9814448952674866, |
| "step": 1152 |
| }, |
| { |
| "epoch": 6.744868035190616, |
| "grad_norm": 0.546805668816822, |
| "learning_rate": 1.292092088158213e-05, |
| "loss": 0.08, |
| "mean_token_accuracy": 0.9743905514478683, |
| "step": 1153 |
| }, |
| { |
| "epoch": 6.750733137829912, |
| "grad_norm": 0.4879375760409544, |
| "learning_rate": 1.2891326517177663e-05, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9839038699865341, |
| "step": 1154 |
| }, |
| { |
| "epoch": 6.756598240469208, |
| "grad_norm": 0.5831663350172862, |
| "learning_rate": 1.2861765213579177e-05, |
| "loss": 0.0824, |
| "mean_token_accuracy": 0.9725939705967903, |
| "step": 1155 |
| }, |
| { |
| "epoch": 6.762463343108505, |
| "grad_norm": 0.6866773053308828, |
| "learning_rate": 1.2832237078082272e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9758478626608849, |
| "step": 1156 |
| }, |
| { |
| "epoch": 6.768328445747801, |
| "grad_norm": 0.5665523571164475, |
| "learning_rate": 1.2802742217862156e-05, |
| "loss": 0.0782, |
| "mean_token_accuracy": 0.974516935646534, |
| "step": 1157 |
| }, |
| { |
| "epoch": 6.774193548387097, |
| "grad_norm": 0.6844894848581596, |
| "learning_rate": 1.2773280739973255e-05, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9749132618308067, |
| "step": 1158 |
| }, |
| { |
| "epoch": 6.780058651026393, |
| "grad_norm": 0.4389537006132902, |
| "learning_rate": 1.2743852751348833e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9811219125986099, |
| "step": 1159 |
| }, |
| { |
| "epoch": 6.785923753665689, |
| "grad_norm": 0.5507569863518943, |
| "learning_rate": 1.2714458358800612e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9827919527888298, |
| "step": 1160 |
| }, |
| { |
| "epoch": 6.7917888563049855, |
| "grad_norm": 0.7106774876218656, |
| "learning_rate": 1.2685097669018362e-05, |
| "loss": 0.09, |
| "mean_token_accuracy": 0.9727823808789253, |
| "step": 1161 |
| }, |
| { |
| "epoch": 6.797653958944282, |
| "grad_norm": 0.6314362358470937, |
| "learning_rate": 1.265577078856953e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9712254106998444, |
| "step": 1162 |
| }, |
| { |
| "epoch": 6.803519061583578, |
| "grad_norm": 0.5509327004441354, |
| "learning_rate": 1.2626477823898843e-05, |
| "loss": 0.0785, |
| "mean_token_accuracy": 0.9762394204735756, |
| "step": 1163 |
| }, |
| { |
| "epoch": 6.809384164222874, |
| "grad_norm": 0.543808641203145, |
| "learning_rate": 1.2597218881327944e-05, |
| "loss": 0.0763, |
| "mean_token_accuracy": 0.9751420989632607, |
| "step": 1164 |
| }, |
| { |
| "epoch": 6.81524926686217, |
| "grad_norm": 0.4711371688926112, |
| "learning_rate": 1.2567994067054961e-05, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9763290211558342, |
| "step": 1165 |
| }, |
| { |
| "epoch": 6.821114369501466, |
| "grad_norm": 0.4137756121566806, |
| "learning_rate": 1.2538803487154177e-05, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9790268614888191, |
| "step": 1166 |
| }, |
| { |
| "epoch": 6.826979472140763, |
| "grad_norm": 0.4621022306065054, |
| "learning_rate": 1.25096472475756e-05, |
| "loss": 0.0754, |
| "mean_token_accuracy": 0.9756415113806725, |
| "step": 1167 |
| }, |
| { |
| "epoch": 6.832844574780059, |
| "grad_norm": 0.609760780869737, |
| "learning_rate": 1.248052545414461e-05, |
| "loss": 0.0828, |
| "mean_token_accuracy": 0.9744556695222855, |
| "step": 1168 |
| }, |
| { |
| "epoch": 6.838709677419355, |
| "grad_norm": 0.594238030928876, |
| "learning_rate": 1.2451438212561556e-05, |
| "loss": 0.0835, |
| "mean_token_accuracy": 0.9688782170414925, |
| "step": 1169 |
| }, |
| { |
| "epoch": 6.844574780058651, |
| "grad_norm": 0.5363107528216697, |
| "learning_rate": 1.2422385628401377e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.975056879222393, |
| "step": 1170 |
| }, |
| { |
| "epoch": 6.850439882697947, |
| "grad_norm": 0.5043511960644672, |
| "learning_rate": 1.2393367807113217e-05, |
| "loss": 0.0727, |
| "mean_token_accuracy": 0.9775923490524292, |
| "step": 1171 |
| }, |
| { |
| "epoch": 6.8563049853372435, |
| "grad_norm": 0.39887527153514973, |
| "learning_rate": 1.236438485402005e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9786998331546783, |
| "step": 1172 |
| }, |
| { |
| "epoch": 6.86217008797654, |
| "grad_norm": 0.3888848351878772, |
| "learning_rate": 1.2335436874318293e-05, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.9791335985064507, |
| "step": 1173 |
| }, |
| { |
| "epoch": 6.868035190615836, |
| "grad_norm": 0.6715132177529508, |
| "learning_rate": 1.2306523973077416e-05, |
| "loss": 0.0887, |
| "mean_token_accuracy": 0.9724654704332352, |
| "step": 1174 |
| }, |
| { |
| "epoch": 6.873900293255132, |
| "grad_norm": 0.5119648654749844, |
| "learning_rate": 1.2277646255239572e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9759775921702385, |
| "step": 1175 |
| }, |
| { |
| "epoch": 6.879765395894428, |
| "grad_norm": 0.5514064582412531, |
| "learning_rate": 1.2248803825619224e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.975832425057888, |
| "step": 1176 |
| }, |
| { |
| "epoch": 6.885630498533724, |
| "grad_norm": 0.5353698021835701, |
| "learning_rate": 1.2219996788902734e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9779311493039131, |
| "step": 1177 |
| }, |
| { |
| "epoch": 6.891495601173021, |
| "grad_norm": 0.5915181123188481, |
| "learning_rate": 1.2191225249648016e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9749589264392853, |
| "step": 1178 |
| }, |
| { |
| "epoch": 6.897360703812317, |
| "grad_norm": 0.5164903900438643, |
| "learning_rate": 1.216248931228413e-05, |
| "loss": 0.0827, |
| "mean_token_accuracy": 0.9742263928055763, |
| "step": 1179 |
| }, |
| { |
| "epoch": 6.903225806451613, |
| "grad_norm": 0.44759904248078125, |
| "learning_rate": 1.2133789081110927e-05, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9794506952166557, |
| "step": 1180 |
| }, |
| { |
| "epoch": 6.909090909090909, |
| "grad_norm": 0.569379246167165, |
| "learning_rate": 1.2105124660298655e-05, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9769483134150505, |
| "step": 1181 |
| }, |
| { |
| "epoch": 6.914956011730205, |
| "grad_norm": 0.4885422172148321, |
| "learning_rate": 1.2076496153887587e-05, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9801295772194862, |
| "step": 1182 |
| }, |
| { |
| "epoch": 6.9208211143695015, |
| "grad_norm": 0.4453475631938246, |
| "learning_rate": 1.2047903665787633e-05, |
| "loss": 0.0685, |
| "mean_token_accuracy": 0.9790622964501381, |
| "step": 1183 |
| }, |
| { |
| "epoch": 6.926686217008798, |
| "grad_norm": 0.48406132453413675, |
| "learning_rate": 1.2019347299777981e-05, |
| "loss": 0.0637, |
| "mean_token_accuracy": 0.9804274588823318, |
| "step": 1184 |
| }, |
| { |
| "epoch": 6.932551319648094, |
| "grad_norm": 0.5372921912873875, |
| "learning_rate": 1.199082715950671e-05, |
| "loss": 0.0832, |
| "mean_token_accuracy": 0.9742497876286507, |
| "step": 1185 |
| }, |
| { |
| "epoch": 6.93841642228739, |
| "grad_norm": 0.474153710918661, |
| "learning_rate": 1.1962343348490407e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.979320339858532, |
| "step": 1186 |
| }, |
| { |
| "epoch": 6.944281524926686, |
| "grad_norm": 0.4893568094546928, |
| "learning_rate": 1.1933895970113798e-05, |
| "loss": 0.0775, |
| "mean_token_accuracy": 0.9794166311621666, |
| "step": 1187 |
| }, |
| { |
| "epoch": 6.9501466275659824, |
| "grad_norm": 0.49286831595383807, |
| "learning_rate": 1.1905485127629387e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9763789474964142, |
| "step": 1188 |
| }, |
| { |
| "epoch": 6.956011730205279, |
| "grad_norm": 0.5564449012573591, |
| "learning_rate": 1.1877110924157046e-05, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9768785759806633, |
| "step": 1189 |
| }, |
| { |
| "epoch": 6.961876832844575, |
| "grad_norm": 0.4806314265595714, |
| "learning_rate": 1.1848773462683684e-05, |
| "loss": 0.0783, |
| "mean_token_accuracy": 0.9757219702005386, |
| "step": 1190 |
| }, |
| { |
| "epoch": 6.967741935483871, |
| "grad_norm": 0.44614104084922607, |
| "learning_rate": 1.1820472846062842e-05, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9781024381518364, |
| "step": 1191 |
| }, |
| { |
| "epoch": 6.973607038123167, |
| "grad_norm": 0.4899717975189836, |
| "learning_rate": 1.1792209177014317e-05, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9795149564743042, |
| "step": 1192 |
| }, |
| { |
| "epoch": 6.979472140762463, |
| "grad_norm": 0.558509379737497, |
| "learning_rate": 1.1763982558123823e-05, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.977259911596775, |
| "step": 1193 |
| }, |
| { |
| "epoch": 6.9853372434017595, |
| "grad_norm": 0.5117843575515925, |
| "learning_rate": 1.1735793091842583e-05, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9768305420875549, |
| "step": 1194 |
| }, |
| { |
| "epoch": 6.991202346041056, |
| "grad_norm": 0.7538879848011749, |
| "learning_rate": 1.1707640880486975e-05, |
| "loss": 0.0957, |
| "mean_token_accuracy": 0.9704435393214226, |
| "step": 1195 |
| }, |
| { |
| "epoch": 6.997067448680352, |
| "grad_norm": 0.3002576605567238, |
| "learning_rate": 1.1679526026238155e-05, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9824624955654144, |
| "step": 1196 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.3002576605567238, |
| "learning_rate": 1.165144863114169e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9811327904462814, |
| "step": 1197 |
| }, |
| { |
| "epoch": 7.005865102639296, |
| "grad_norm": 0.6433063715747249, |
| "learning_rate": 1.1623408797107185e-05, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9747751802206039, |
| "step": 1198 |
| }, |
| { |
| "epoch": 7.011730205278592, |
| "grad_norm": 0.4650556964344494, |
| "learning_rate": 1.1595406625907914e-05, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9819451943039894, |
| "step": 1199 |
| }, |
| { |
| "epoch": 7.0175953079178885, |
| "grad_norm": 0.4519271364761177, |
| "learning_rate": 1.1567442219180446e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9809525832533836, |
| "step": 1200 |
| }, |
| { |
| "epoch": 7.023460410557185, |
| "grad_norm": 0.4074954888509191, |
| "learning_rate": 1.153951567842429e-05, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9832786470651627, |
| "step": 1201 |
| }, |
| { |
| "epoch": 7.029325513196481, |
| "grad_norm": 0.3356064558125727, |
| "learning_rate": 1.1511627105001501e-05, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9793870970606804, |
| "step": 1202 |
| }, |
| { |
| "epoch": 7.035190615835777, |
| "grad_norm": 0.543533892964494, |
| "learning_rate": 1.1483776600136344e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9736167937517166, |
| "step": 1203 |
| }, |
| { |
| "epoch": 7.041055718475073, |
| "grad_norm": 0.508836792144545, |
| "learning_rate": 1.1455964264914906e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9800908789038658, |
| "step": 1204 |
| }, |
| { |
| "epoch": 7.0469208211143695, |
| "grad_norm": 0.6127313068418908, |
| "learning_rate": 1.142819020028472e-05, |
| "loss": 0.0813, |
| "mean_token_accuracy": 0.9731275960803032, |
| "step": 1205 |
| }, |
| { |
| "epoch": 7.052785923753666, |
| "grad_norm": 0.5480092721545003, |
| "learning_rate": 1.140045450705443e-05, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.977430984377861, |
| "step": 1206 |
| }, |
| { |
| "epoch": 7.058651026392962, |
| "grad_norm": 0.5197554266463569, |
| "learning_rate": 1.13727572858934e-05, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9804290607571602, |
| "step": 1207 |
| }, |
| { |
| "epoch": 7.064516129032258, |
| "grad_norm": 0.41897297895717694, |
| "learning_rate": 1.1345098637331356e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9806567952036858, |
| "step": 1208 |
| }, |
| { |
| "epoch": 7.070381231671554, |
| "grad_norm": 0.5729005539563279, |
| "learning_rate": 1.1317478661758022e-05, |
| "loss": 0.0805, |
| "mean_token_accuracy": 0.973584771156311, |
| "step": 1209 |
| }, |
| { |
| "epoch": 7.07624633431085, |
| "grad_norm": 0.45278187335218867, |
| "learning_rate": 1.1289897459422756e-05, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9816871359944344, |
| "step": 1210 |
| }, |
| { |
| "epoch": 7.0821114369501466, |
| "grad_norm": 0.5535750142635363, |
| "learning_rate": 1.126235513043418e-05, |
| "loss": 0.0766, |
| "mean_token_accuracy": 0.9764493852853775, |
| "step": 1211 |
| }, |
| { |
| "epoch": 7.087976539589443, |
| "grad_norm": 0.5290761436847783, |
| "learning_rate": 1.1234851774759828e-05, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9827250093221664, |
| "step": 1212 |
| }, |
| { |
| "epoch": 7.093841642228739, |
| "grad_norm": 0.4338439220392749, |
| "learning_rate": 1.1207387492225772e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9795321822166443, |
| "step": 1213 |
| }, |
| { |
| "epoch": 7.099706744868035, |
| "grad_norm": 0.4229830435807885, |
| "learning_rate": 1.1179962382516268e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9799394384026527, |
| "step": 1214 |
| }, |
| { |
| "epoch": 7.105571847507331, |
| "grad_norm": 0.5596786809514015, |
| "learning_rate": 1.1152576545173388e-05, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9794164597988129, |
| "step": 1215 |
| }, |
| { |
| "epoch": 7.1114369501466275, |
| "grad_norm": 0.4190871184858409, |
| "learning_rate": 1.1125230079596654e-05, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9811462908983231, |
| "step": 1216 |
| }, |
| { |
| "epoch": 7.117302052785924, |
| "grad_norm": 0.4594859424747388, |
| "learning_rate": 1.10979230850427e-05, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9795415550470352, |
| "step": 1217 |
| }, |
| { |
| "epoch": 7.12316715542522, |
| "grad_norm": 0.47431112233441436, |
| "learning_rate": 1.1070655660624876e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9774219766259193, |
| "step": 1218 |
| }, |
| { |
| "epoch": 7.129032258064516, |
| "grad_norm": 0.5154540944862103, |
| "learning_rate": 1.1043427905312933e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9775685295462608, |
| "step": 1219 |
| }, |
| { |
| "epoch": 7.134897360703812, |
| "grad_norm": 0.39434647534644846, |
| "learning_rate": 1.1016239917932618e-05, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9800396636128426, |
| "step": 1220 |
| }, |
| { |
| "epoch": 7.140762463343108, |
| "grad_norm": 0.5032190860559029, |
| "learning_rate": 1.098909179716535e-05, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9765996113419533, |
| "step": 1221 |
| }, |
| { |
| "epoch": 7.146627565982405, |
| "grad_norm": 0.475595902088216, |
| "learning_rate": 1.096198364154784e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9804063886404037, |
| "step": 1222 |
| }, |
| { |
| "epoch": 7.152492668621701, |
| "grad_norm": 0.41368564350345344, |
| "learning_rate": 1.0934915549471747e-05, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9803172200918198, |
| "step": 1223 |
| }, |
| { |
| "epoch": 7.158357771260997, |
| "grad_norm": 0.5177453029351333, |
| "learning_rate": 1.0907887619183308e-05, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9804964661598206, |
| "step": 1224 |
| }, |
| { |
| "epoch": 7.164222873900293, |
| "grad_norm": 0.5051177169181578, |
| "learning_rate": 1.0880899948783002e-05, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9775585755705833, |
| "step": 1225 |
| }, |
| { |
| "epoch": 7.170087976539589, |
| "grad_norm": 0.5960031715664886, |
| "learning_rate": 1.0853952636225165e-05, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9809572696685791, |
| "step": 1226 |
| }, |
| { |
| "epoch": 7.1759530791788855, |
| "grad_norm": 0.5329760895034595, |
| "learning_rate": 1.0827045779317662e-05, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9801081269979477, |
| "step": 1227 |
| }, |
| { |
| "epoch": 7.181818181818182, |
| "grad_norm": 0.45414595161061955, |
| "learning_rate": 1.080017947572152e-05, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9822395518422127, |
| "step": 1228 |
| }, |
| { |
| "epoch": 7.187683284457478, |
| "grad_norm": 0.53901041860263, |
| "learning_rate": 1.0773353822950563e-05, |
| "loss": 0.0714, |
| "mean_token_accuracy": 0.9785963222384453, |
| "step": 1229 |
| }, |
| { |
| "epoch": 7.193548387096774, |
| "grad_norm": 0.4745632320224554, |
| "learning_rate": 1.074656891837108e-05, |
| "loss": 0.0555, |
| "mean_token_accuracy": 0.9822941496968269, |
| "step": 1230 |
| }, |
| { |
| "epoch": 7.19941348973607, |
| "grad_norm": 0.3665296243010212, |
| "learning_rate": 1.0719824859201457e-05, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.980594739317894, |
| "step": 1231 |
| }, |
| { |
| "epoch": 7.205278592375366, |
| "grad_norm": 0.6047864498585788, |
| "learning_rate": 1.0693121742511828e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9721439629793167, |
| "step": 1232 |
| }, |
| { |
| "epoch": 7.211143695014663, |
| "grad_norm": 0.5041682071363984, |
| "learning_rate": 1.0666459665223718e-05, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9779375120997429, |
| "step": 1233 |
| }, |
| { |
| "epoch": 7.217008797653959, |
| "grad_norm": 0.5019058566934924, |
| "learning_rate": 1.0639838724109708e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9792098253965378, |
| "step": 1234 |
| }, |
| { |
| "epoch": 7.222873900293255, |
| "grad_norm": 0.43810664457682996, |
| "learning_rate": 1.0613259015793056e-05, |
| "loss": 0.0528, |
| "mean_token_accuracy": 0.9823940470814705, |
| "step": 1235 |
| }, |
| { |
| "epoch": 7.228739002932551, |
| "grad_norm": 0.4417784699824646, |
| "learning_rate": 1.0586720636747368e-05, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9772520065307617, |
| "step": 1236 |
| }, |
| { |
| "epoch": 7.234604105571847, |
| "grad_norm": 0.4743340130011368, |
| "learning_rate": 1.0560223683296244e-05, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9788348078727722, |
| "step": 1237 |
| }, |
| { |
| "epoch": 7.2404692082111435, |
| "grad_norm": 0.4073966976376095, |
| "learning_rate": 1.0533768251612924e-05, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9761592745780945, |
| "step": 1238 |
| }, |
| { |
| "epoch": 7.24633431085044, |
| "grad_norm": 0.38289151835341184, |
| "learning_rate": 1.0507354437719938e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9810685515403748, |
| "step": 1239 |
| }, |
| { |
| "epoch": 7.252199413489736, |
| "grad_norm": 0.5293503986290922, |
| "learning_rate": 1.0480982337488768e-05, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9800685048103333, |
| "step": 1240 |
| }, |
| { |
| "epoch": 7.258064516129032, |
| "grad_norm": 0.4680528752727949, |
| "learning_rate": 1.0454652046639486e-05, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9787988215684891, |
| "step": 1241 |
| }, |
| { |
| "epoch": 7.263929618768328, |
| "grad_norm": 0.5371939764519806, |
| "learning_rate": 1.0428363660740407e-05, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9764540642499924, |
| "step": 1242 |
| }, |
| { |
| "epoch": 7.269794721407624, |
| "grad_norm": 0.4604907427704817, |
| "learning_rate": 1.0402117275207757e-05, |
| "loss": 0.0727, |
| "mean_token_accuracy": 0.9751237854361534, |
| "step": 1243 |
| }, |
| { |
| "epoch": 7.275659824046921, |
| "grad_norm": 0.543393907597377, |
| "learning_rate": 1.0375912985305319e-05, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9787429869174957, |
| "step": 1244 |
| }, |
| { |
| "epoch": 7.281524926686217, |
| "grad_norm": 0.44383993642036296, |
| "learning_rate": 1.0349750886144077e-05, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9764397814869881, |
| "step": 1245 |
| }, |
| { |
| "epoch": 7.287390029325513, |
| "grad_norm": 0.41378217779118326, |
| "learning_rate": 1.0323631072681888e-05, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9803901985287666, |
| "step": 1246 |
| }, |
| { |
| "epoch": 7.293255131964809, |
| "grad_norm": 0.355989396188892, |
| "learning_rate": 1.0297553639723123e-05, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.981739304959774, |
| "step": 1247 |
| }, |
| { |
| "epoch": 7.299120234604105, |
| "grad_norm": 0.43357089167776125, |
| "learning_rate": 1.027151868191834e-05, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9760547429323196, |
| "step": 1248 |
| }, |
| { |
| "epoch": 7.3049853372434015, |
| "grad_norm": 0.48332066026786996, |
| "learning_rate": 1.0245526293763908e-05, |
| "loss": 0.0786, |
| "mean_token_accuracy": 0.9736545458436012, |
| "step": 1249 |
| }, |
| { |
| "epoch": 7.310850439882698, |
| "grad_norm": 0.47753461671593495, |
| "learning_rate": 1.0219576569601707e-05, |
| "loss": 0.0794, |
| "mean_token_accuracy": 0.9766260907053947, |
| "step": 1250 |
| }, |
| { |
| "epoch": 7.316715542521994, |
| "grad_norm": 0.45521081483229914, |
| "learning_rate": 1.0193669603618757e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9787106961011887, |
| "step": 1251 |
| }, |
| { |
| "epoch": 7.32258064516129, |
| "grad_norm": 0.48836814239477233, |
| "learning_rate": 1.0167805489846873e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9792743027210236, |
| "step": 1252 |
| }, |
| { |
| "epoch": 7.328445747800586, |
| "grad_norm": 0.47006783479866115, |
| "learning_rate": 1.0141984322162353e-05, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9803495109081268, |
| "step": 1253 |
| }, |
| { |
| "epoch": 7.334310850439882, |
| "grad_norm": 0.4156017026046577, |
| "learning_rate": 1.0116206194285598e-05, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9772606119513512, |
| "step": 1254 |
| }, |
| { |
| "epoch": 7.340175953079179, |
| "grad_norm": 0.5125748013140727, |
| "learning_rate": 1.0090471199780812e-05, |
| "loss": 0.0729, |
| "mean_token_accuracy": 0.9776462465524673, |
| "step": 1255 |
| }, |
| { |
| "epoch": 7.346041055718475, |
| "grad_norm": 0.4569654216489075, |
| "learning_rate": 1.0064779432055616e-05, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.976767286658287, |
| "step": 1256 |
| }, |
| { |
| "epoch": 7.351906158357771, |
| "grad_norm": 0.45479785552447444, |
| "learning_rate": 1.0039130984360761e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.979149229824543, |
| "step": 1257 |
| }, |
| { |
| "epoch": 7.357771260997067, |
| "grad_norm": 0.40924296015239126, |
| "learning_rate": 1.0013525949789745e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9773788601160049, |
| "step": 1258 |
| }, |
| { |
| "epoch": 7.363636363636363, |
| "grad_norm": 0.41003497991772014, |
| "learning_rate": 9.987964421278512e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9816633462905884, |
| "step": 1259 |
| }, |
| { |
| "epoch": 7.3695014662756595, |
| "grad_norm": 0.4754148725808644, |
| "learning_rate": 9.962446491605084e-06, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9745640978217125, |
| "step": 1260 |
| }, |
| { |
| "epoch": 7.375366568914956, |
| "grad_norm": 0.5371881554820942, |
| "learning_rate": 9.936972253389235e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9805537834763527, |
| "step": 1261 |
| }, |
| { |
| "epoch": 7.381231671554252, |
| "grad_norm": 0.6119393072173988, |
| "learning_rate": 9.911541799092162e-06, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9751638323068619, |
| "step": 1262 |
| }, |
| { |
| "epoch": 7.387096774193548, |
| "grad_norm": 0.38304046490416693, |
| "learning_rate": 9.88615522101615e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9794823378324509, |
| "step": 1263 |
| }, |
| { |
| "epoch": 7.392961876832844, |
| "grad_norm": 0.407569526828338, |
| "learning_rate": 9.860812611304225e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9806607142090797, |
| "step": 1264 |
| }, |
| { |
| "epoch": 7.39882697947214, |
| "grad_norm": 0.43838874061417293, |
| "learning_rate": 9.835514061939822e-06, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9821709990501404, |
| "step": 1265 |
| }, |
| { |
| "epoch": 7.404692082111437, |
| "grad_norm": 0.39028973009973217, |
| "learning_rate": 9.810259664746454e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.979277141392231, |
| "step": 1266 |
| }, |
| { |
| "epoch": 7.410557184750733, |
| "grad_norm": 0.47142083942451735, |
| "learning_rate": 9.785049511387383e-06, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9790802374482155, |
| "step": 1267 |
| }, |
| { |
| "epoch": 7.416422287390029, |
| "grad_norm": 0.47820475224887893, |
| "learning_rate": 9.759883693365287e-06, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9772188812494278, |
| "step": 1268 |
| }, |
| { |
| "epoch": 7.422287390029325, |
| "grad_norm": 0.4438546581105144, |
| "learning_rate": 9.734762302021923e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9826917573809624, |
| "step": 1269 |
| }, |
| { |
| "epoch": 7.428152492668621, |
| "grad_norm": 0.36892193219065467, |
| "learning_rate": 9.709685428537794e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9822022542357445, |
| "step": 1270 |
| }, |
| { |
| "epoch": 7.4340175953079175, |
| "grad_norm": 0.5438930387436425, |
| "learning_rate": 9.684653163931823e-06, |
| "loss": 0.0807, |
| "mean_token_accuracy": 0.9757629334926605, |
| "step": 1271 |
| }, |
| { |
| "epoch": 7.439882697947214, |
| "grad_norm": 0.6492834212054615, |
| "learning_rate": 9.659665599061019e-06, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9740792885422707, |
| "step": 1272 |
| }, |
| { |
| "epoch": 7.44574780058651, |
| "grad_norm": 0.49786671471578997, |
| "learning_rate": 9.634722824620154e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9776691198348999, |
| "step": 1273 |
| }, |
| { |
| "epoch": 7.451612903225806, |
| "grad_norm": 0.45398970829477336, |
| "learning_rate": 9.609824931141423e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9789795354008675, |
| "step": 1274 |
| }, |
| { |
| "epoch": 7.457478005865102, |
| "grad_norm": 0.3880313111487553, |
| "learning_rate": 9.584972008994123e-06, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.980201467871666, |
| "step": 1275 |
| }, |
| { |
| "epoch": 7.463343108504398, |
| "grad_norm": 0.4387804564000816, |
| "learning_rate": 9.560164148384328e-06, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.9769189730286598, |
| "step": 1276 |
| }, |
| { |
| "epoch": 7.469208211143695, |
| "grad_norm": 0.6219576750479341, |
| "learning_rate": 9.53540143935455e-06, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9761852920055389, |
| "step": 1277 |
| }, |
| { |
| "epoch": 7.475073313782991, |
| "grad_norm": 0.5220170243856437, |
| "learning_rate": 9.510683971783425e-06, |
| "loss": 0.0892, |
| "mean_token_accuracy": 0.9741244614124298, |
| "step": 1278 |
| }, |
| { |
| "epoch": 7.480938416422287, |
| "grad_norm": 0.4293959414529352, |
| "learning_rate": 9.486011835385372e-06, |
| "loss": 0.0471, |
| "mean_token_accuracy": 0.9853230938315392, |
| "step": 1279 |
| }, |
| { |
| "epoch": 7.486803519061583, |
| "grad_norm": 0.4194976868757321, |
| "learning_rate": 9.461385119710282e-06, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9749538227915764, |
| "step": 1280 |
| }, |
| { |
| "epoch": 7.492668621700879, |
| "grad_norm": 0.41667970612082306, |
| "learning_rate": 9.436803914143189e-06, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9754650443792343, |
| "step": 1281 |
| }, |
| { |
| "epoch": 7.4985337243401755, |
| "grad_norm": 0.41015333720683506, |
| "learning_rate": 9.41226830790394e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9807113930583, |
| "step": 1282 |
| }, |
| { |
| "epoch": 7.504398826979472, |
| "grad_norm": 0.4689591041115801, |
| "learning_rate": 9.387778390046881e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9797599762678146, |
| "step": 1283 |
| }, |
| { |
| "epoch": 7.510263929618768, |
| "grad_norm": 0.3586841195731395, |
| "learning_rate": 9.363334249460519e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9795782417058945, |
| "step": 1284 |
| }, |
| { |
| "epoch": 7.516129032258064, |
| "grad_norm": 0.46454735014205756, |
| "learning_rate": 9.338935974867213e-06, |
| "loss": 0.0702, |
| "mean_token_accuracy": 0.977179504930973, |
| "step": 1285 |
| }, |
| { |
| "epoch": 7.52199413489736, |
| "grad_norm": 0.501859043750425, |
| "learning_rate": 9.314583654822844e-06, |
| "loss": 0.0707, |
| "mean_token_accuracy": 0.9769659638404846, |
| "step": 1286 |
| }, |
| { |
| "epoch": 7.527859237536656, |
| "grad_norm": 0.45384333056341686, |
| "learning_rate": 9.290277377716503e-06, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9742954969406128, |
| "step": 1287 |
| }, |
| { |
| "epoch": 7.533724340175953, |
| "grad_norm": 0.453406139729027, |
| "learning_rate": 9.266017231770155e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9797300845384598, |
| "step": 1288 |
| }, |
| { |
| "epoch": 7.539589442815249, |
| "grad_norm": 0.3578564197025334, |
| "learning_rate": 9.241803305038333e-06, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9783648028969765, |
| "step": 1289 |
| }, |
| { |
| "epoch": 7.545454545454545, |
| "grad_norm": 0.4350473692602661, |
| "learning_rate": 9.217635685407813e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9798745140433311, |
| "step": 1290 |
| }, |
| { |
| "epoch": 7.551319648093841, |
| "grad_norm": 0.3536173268233605, |
| "learning_rate": 9.19351446059729e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.983490340411663, |
| "step": 1291 |
| }, |
| { |
| "epoch": 7.557184750733137, |
| "grad_norm": 0.4679083834436488, |
| "learning_rate": 9.16943971815708e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9795430973172188, |
| "step": 1292 |
| }, |
| { |
| "epoch": 7.563049853372434, |
| "grad_norm": 0.4916207041114535, |
| "learning_rate": 9.145411545468756e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9794794097542763, |
| "step": 1293 |
| }, |
| { |
| "epoch": 7.568914956011731, |
| "grad_norm": 0.4242119544741855, |
| "learning_rate": 9.121430029744893e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9808191359043121, |
| "step": 1294 |
| }, |
| { |
| "epoch": 7.574780058651027, |
| "grad_norm": 0.5109235759797703, |
| "learning_rate": 9.097495258028703e-06, |
| "loss": 0.0704, |
| "mean_token_accuracy": 0.9759545400738716, |
| "step": 1295 |
| }, |
| { |
| "epoch": 7.580645161290323, |
| "grad_norm": 0.4640004900858478, |
| "learning_rate": 9.073607317193742e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9781745299696922, |
| "step": 1296 |
| }, |
| { |
| "epoch": 7.586510263929619, |
| "grad_norm": 0.4044944851920302, |
| "learning_rate": 9.049766293943589e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9784148558974266, |
| "step": 1297 |
| }, |
| { |
| "epoch": 7.592375366568915, |
| "grad_norm": 0.4823259605858935, |
| "learning_rate": 9.025972274811527e-06, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.97871433198452, |
| "step": 1298 |
| }, |
| { |
| "epoch": 7.5982404692082115, |
| "grad_norm": 0.4480002680288002, |
| "learning_rate": 9.002225346160238e-06, |
| "loss": 0.0637, |
| "mean_token_accuracy": 0.9780783578753471, |
| "step": 1299 |
| }, |
| { |
| "epoch": 7.604105571847508, |
| "grad_norm": 0.37868110690032336, |
| "learning_rate": 8.97852559418148e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9789452776312828, |
| "step": 1300 |
| }, |
| { |
| "epoch": 7.609970674486804, |
| "grad_norm": 0.4042692696917226, |
| "learning_rate": 8.954873104895787e-06, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9810117408633232, |
| "step": 1301 |
| }, |
| { |
| "epoch": 7.6158357771261, |
| "grad_norm": 0.44149411459840987, |
| "learning_rate": 8.931267964152132e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9778881147503853, |
| "step": 1302 |
| }, |
| { |
| "epoch": 7.621700879765396, |
| "grad_norm": 0.4177264074559071, |
| "learning_rate": 8.907710257627651e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9792383164167404, |
| "step": 1303 |
| }, |
| { |
| "epoch": 7.627565982404692, |
| "grad_norm": 0.415930949832212, |
| "learning_rate": 8.884200070827303e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9772908091545105, |
| "step": 1304 |
| }, |
| { |
| "epoch": 7.633431085043989, |
| "grad_norm": 0.4117164642861044, |
| "learning_rate": 8.86073748908357e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9795729070901871, |
| "step": 1305 |
| }, |
| { |
| "epoch": 7.639296187683285, |
| "grad_norm": 0.3694341756589927, |
| "learning_rate": 8.837322597556146e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9798577129840851, |
| "step": 1306 |
| }, |
| { |
| "epoch": 7.645161290322581, |
| "grad_norm": 0.4945771560752598, |
| "learning_rate": 8.813955481231633e-06, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.9765386283397675, |
| "step": 1307 |
| }, |
| { |
| "epoch": 7.651026392961877, |
| "grad_norm": 0.3859833883632323, |
| "learning_rate": 8.790636224923221e-06, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9768943637609482, |
| "step": 1308 |
| }, |
| { |
| "epoch": 7.656891495601173, |
| "grad_norm": 0.6038966303553363, |
| "learning_rate": 8.767364913270399e-06, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9774223938584328, |
| "step": 1309 |
| }, |
| { |
| "epoch": 7.6627565982404695, |
| "grad_norm": 0.4214725291176917, |
| "learning_rate": 8.744141630738624e-06, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.978145569562912, |
| "step": 1310 |
| }, |
| { |
| "epoch": 7.668621700879766, |
| "grad_norm": 0.4347493152025069, |
| "learning_rate": 8.720966461619038e-06, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9777267724275589, |
| "step": 1311 |
| }, |
| { |
| "epoch": 7.674486803519062, |
| "grad_norm": 0.4389100664263654, |
| "learning_rate": 8.69783949002814e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9805267155170441, |
| "step": 1312 |
| }, |
| { |
| "epoch": 7.680351906158358, |
| "grad_norm": 0.37417891099121087, |
| "learning_rate": 8.6747607999075e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.9824578687548637, |
| "step": 1313 |
| }, |
| { |
| "epoch": 7.686217008797654, |
| "grad_norm": 0.3872157231435952, |
| "learning_rate": 8.651730475023435e-06, |
| "loss": 0.0703, |
| "mean_token_accuracy": 0.9778390452265739, |
| "step": 1314 |
| }, |
| { |
| "epoch": 7.69208211143695, |
| "grad_norm": 0.5363255423638494, |
| "learning_rate": 8.628748598966739e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9759575873613358, |
| "step": 1315 |
| }, |
| { |
| "epoch": 7.697947214076247, |
| "grad_norm": 0.5743323555165211, |
| "learning_rate": 8.605815255152323e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9736444652080536, |
| "step": 1316 |
| }, |
| { |
| "epoch": 7.703812316715543, |
| "grad_norm": 0.5139795369015938, |
| "learning_rate": 8.582930526818973e-06, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9771385565400124, |
| "step": 1317 |
| }, |
| { |
| "epoch": 7.709677419354839, |
| "grad_norm": 0.4314235747530134, |
| "learning_rate": 8.560094497029008e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9789847880601883, |
| "step": 1318 |
| }, |
| { |
| "epoch": 7.715542521994135, |
| "grad_norm": 0.4453550791454817, |
| "learning_rate": 8.537307248667992e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9789009168744087, |
| "step": 1319 |
| }, |
| { |
| "epoch": 7.721407624633431, |
| "grad_norm": 0.39151849340341077, |
| "learning_rate": 8.514568864444432e-06, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.976598434150219, |
| "step": 1320 |
| }, |
| { |
| "epoch": 7.7272727272727275, |
| "grad_norm": 0.414862604020496, |
| "learning_rate": 8.491879426889483e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9806237667798996, |
| "step": 1321 |
| }, |
| { |
| "epoch": 7.733137829912024, |
| "grad_norm": 0.44999339741901423, |
| "learning_rate": 8.469239018356636e-06, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9762846529483795, |
| "step": 1322 |
| }, |
| { |
| "epoch": 7.73900293255132, |
| "grad_norm": 0.45252653701202344, |
| "learning_rate": 8.446647721021435e-06, |
| "loss": 0.0835, |
| "mean_token_accuracy": 0.9739138633012772, |
| "step": 1323 |
| }, |
| { |
| "epoch": 7.744868035190616, |
| "grad_norm": 0.5028896224891031, |
| "learning_rate": 8.424105616881161e-06, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9794121384620667, |
| "step": 1324 |
| }, |
| { |
| "epoch": 7.750733137829912, |
| "grad_norm": 0.47860397890481565, |
| "learning_rate": 8.40161278775455e-06, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9804290905594826, |
| "step": 1325 |
| }, |
| { |
| "epoch": 7.756598240469208, |
| "grad_norm": 0.5527107786202187, |
| "learning_rate": 8.379169315281485e-06, |
| "loss": 0.0776, |
| "mean_token_accuracy": 0.9751468449831009, |
| "step": 1326 |
| }, |
| { |
| "epoch": 7.762463343108505, |
| "grad_norm": 0.5582032307994943, |
| "learning_rate": 8.356775280922708e-06, |
| "loss": 0.0744, |
| "mean_token_accuracy": 0.9765750914812088, |
| "step": 1327 |
| }, |
| { |
| "epoch": 7.768328445747801, |
| "grad_norm": 0.3908594516424265, |
| "learning_rate": 8.334430765959522e-06, |
| "loss": 0.0717, |
| "mean_token_accuracy": 0.9744571521878242, |
| "step": 1328 |
| }, |
| { |
| "epoch": 7.774193548387097, |
| "grad_norm": 0.4215612562157994, |
| "learning_rate": 8.312135851493494e-06, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9762986898422241, |
| "step": 1329 |
| }, |
| { |
| "epoch": 7.780058651026393, |
| "grad_norm": 0.3985250756824816, |
| "learning_rate": 8.28989061844615e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9815426766872406, |
| "step": 1330 |
| }, |
| { |
| "epoch": 7.785923753665689, |
| "grad_norm": 0.4737274734055571, |
| "learning_rate": 8.267695147558705e-06, |
| "loss": 0.0798, |
| "mean_token_accuracy": 0.9746501669287682, |
| "step": 1331 |
| }, |
| { |
| "epoch": 7.7917888563049855, |
| "grad_norm": 0.5474729201560261, |
| "learning_rate": 8.245549519391758e-06, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9773770347237587, |
| "step": 1332 |
| }, |
| { |
| "epoch": 7.797653958944282, |
| "grad_norm": 0.4281595969799011, |
| "learning_rate": 8.22345381432499e-06, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9795331656932831, |
| "step": 1333 |
| }, |
| { |
| "epoch": 7.803519061583578, |
| "grad_norm": 0.3839556927790539, |
| "learning_rate": 8.201408112556893e-06, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9781799539923668, |
| "step": 1334 |
| }, |
| { |
| "epoch": 7.809384164222874, |
| "grad_norm": 0.50477297766562, |
| "learning_rate": 8.179412494104457e-06, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9756702482700348, |
| "step": 1335 |
| }, |
| { |
| "epoch": 7.81524926686217, |
| "grad_norm": 0.43758196800489896, |
| "learning_rate": 8.15746703880289e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.978801429271698, |
| "step": 1336 |
| }, |
| { |
| "epoch": 7.821114369501466, |
| "grad_norm": 0.3833872875436529, |
| "learning_rate": 8.135571826305339e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9793982282280922, |
| "step": 1337 |
| }, |
| { |
| "epoch": 7.826979472140763, |
| "grad_norm": 0.4203603565828973, |
| "learning_rate": 8.113726936082576e-06, |
| "loss": 0.0813, |
| "mean_token_accuracy": 0.9744042530655861, |
| "step": 1338 |
| }, |
| { |
| "epoch": 7.832844574780059, |
| "grad_norm": 0.6028233293566885, |
| "learning_rate": 8.091932447422737e-06, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9741432145237923, |
| "step": 1339 |
| }, |
| { |
| "epoch": 7.838709677419355, |
| "grad_norm": 0.41261972168356403, |
| "learning_rate": 8.070188439431005e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9784349501132965, |
| "step": 1340 |
| }, |
| { |
| "epoch": 7.844574780058651, |
| "grad_norm": 0.3952270775470951, |
| "learning_rate": 8.048494991029352e-06, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9790202602744102, |
| "step": 1341 |
| }, |
| { |
| "epoch": 7.850439882697947, |
| "grad_norm": 0.4811838432284508, |
| "learning_rate": 8.02685218095624e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9795545116066933, |
| "step": 1342 |
| }, |
| { |
| "epoch": 7.8563049853372435, |
| "grad_norm": 0.47515237201817584, |
| "learning_rate": 8.005260087766318e-06, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9771887883543968, |
| "step": 1343 |
| }, |
| { |
| "epoch": 7.86217008797654, |
| "grad_norm": 0.4539143892456011, |
| "learning_rate": 7.983718789830167e-06, |
| "loss": 0.0711, |
| "mean_token_accuracy": 0.9775839596986771, |
| "step": 1344 |
| }, |
| { |
| "epoch": 7.868035190615836, |
| "grad_norm": 0.45044656532473076, |
| "learning_rate": 7.962228365333999e-06, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.9797210469841957, |
| "step": 1345 |
| }, |
| { |
| "epoch": 7.873900293255132, |
| "grad_norm": 0.39707806692319203, |
| "learning_rate": 7.940788892279375e-06, |
| "loss": 0.0707, |
| "mean_token_accuracy": 0.9795804470777512, |
| "step": 1346 |
| }, |
| { |
| "epoch": 7.879765395894428, |
| "grad_norm": 0.4554192754757186, |
| "learning_rate": 7.919400448482928e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9769511744379997, |
| "step": 1347 |
| }, |
| { |
| "epoch": 7.885630498533724, |
| "grad_norm": 0.5364259319675938, |
| "learning_rate": 7.898063111576066e-06, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9751681387424469, |
| "step": 1348 |
| }, |
| { |
| "epoch": 7.891495601173021, |
| "grad_norm": 0.4464569996214825, |
| "learning_rate": 7.876776959004706e-06, |
| "loss": 0.0837, |
| "mean_token_accuracy": 0.9715655595064163, |
| "step": 1349 |
| }, |
| { |
| "epoch": 7.897360703812317, |
| "grad_norm": 0.44780600869493603, |
| "learning_rate": 7.855542068028981e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9795584827661514, |
| "step": 1350 |
| }, |
| { |
| "epoch": 7.903225806451613, |
| "grad_norm": 0.3485066511432153, |
| "learning_rate": 7.834358515722977e-06, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9794716238975525, |
| "step": 1351 |
| }, |
| { |
| "epoch": 7.909090909090909, |
| "grad_norm": 0.3447849555142869, |
| "learning_rate": 7.813226378974427e-06, |
| "loss": 0.0675, |
| "mean_token_accuracy": 0.977924183011055, |
| "step": 1352 |
| }, |
| { |
| "epoch": 7.914956011730205, |
| "grad_norm": 0.4688435626034042, |
| "learning_rate": 7.792145734484455e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.975438766181469, |
| "step": 1353 |
| }, |
| { |
| "epoch": 7.9208211143695015, |
| "grad_norm": 0.395352024579098, |
| "learning_rate": 7.771116658767286e-06, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9782473146915436, |
| "step": 1354 |
| }, |
| { |
| "epoch": 7.926686217008798, |
| "grad_norm": 0.4536644748137589, |
| "learning_rate": 7.750139228149978e-06, |
| "loss": 0.0741, |
| "mean_token_accuracy": 0.9761862754821777, |
| "step": 1355 |
| }, |
| { |
| "epoch": 7.932551319648094, |
| "grad_norm": 0.44439638707441587, |
| "learning_rate": 7.729213518772121e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9807272255420685, |
| "step": 1356 |
| }, |
| { |
| "epoch": 7.93841642228739, |
| "grad_norm": 0.36724032837204973, |
| "learning_rate": 7.708339606585591e-06, |
| "loss": 0.0693, |
| "mean_token_accuracy": 0.9746986031532288, |
| "step": 1357 |
| }, |
| { |
| "epoch": 7.944281524926686, |
| "grad_norm": 0.4764460524283809, |
| "learning_rate": 7.687517567354266e-06, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.976442739367485, |
| "step": 1358 |
| }, |
| { |
| "epoch": 7.9501466275659824, |
| "grad_norm": 0.45827023462979105, |
| "learning_rate": 7.66674747665373e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9784819781780243, |
| "step": 1359 |
| }, |
| { |
| "epoch": 7.956011730205279, |
| "grad_norm": 0.388246402879624, |
| "learning_rate": 7.646029409871029e-06, |
| "loss": 0.0728, |
| "mean_token_accuracy": 0.975219152867794, |
| "step": 1360 |
| }, |
| { |
| "epoch": 7.961876832844575, |
| "grad_norm": 0.35552101550272835, |
| "learning_rate": 7.625363442204379e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9826669692993164, |
| "step": 1361 |
| }, |
| { |
| "epoch": 7.967741935483871, |
| "grad_norm": 0.3797612701869844, |
| "learning_rate": 7.604749648662892e-06, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9792850464582443, |
| "step": 1362 |
| }, |
| { |
| "epoch": 7.973607038123167, |
| "grad_norm": 0.39566846200882205, |
| "learning_rate": 7.584188104066317e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9788248687982559, |
| "step": 1363 |
| }, |
| { |
| "epoch": 7.979472140762463, |
| "grad_norm": 0.5329907294697588, |
| "learning_rate": 7.563678883044754e-06, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.9761364907026291, |
| "step": 1364 |
| }, |
| { |
| "epoch": 7.9853372434017595, |
| "grad_norm": 0.5497543178648615, |
| "learning_rate": 7.5432220600383935e-06, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.973995603621006, |
| "step": 1365 |
| }, |
| { |
| "epoch": 7.991202346041056, |
| "grad_norm": 0.375109161415316, |
| "learning_rate": 7.522817709297241e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9805333688855171, |
| "step": 1366 |
| }, |
| { |
| "epoch": 7.997067448680352, |
| "grad_norm": 0.3931034615674967, |
| "learning_rate": 7.502465904880849e-06, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9779509454965591, |
| "step": 1367 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.7243852896511626, |
| "learning_rate": 7.482166720658046e-06, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9819488376379013, |
| "step": 1368 |
| }, |
| { |
| "epoch": 8.005865102639296, |
| "grad_norm": 0.3923119289851871, |
| "learning_rate": 7.461920230306674e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9765593409538269, |
| "step": 1369 |
| }, |
| { |
| "epoch": 8.011730205278592, |
| "grad_norm": 0.34742033683272505, |
| "learning_rate": 7.441726507313318e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9818401262164116, |
| "step": 1370 |
| }, |
| { |
| "epoch": 8.017595307917889, |
| "grad_norm": 0.39423410919506524, |
| "learning_rate": 7.421585624973033e-06, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.9781031236052513, |
| "step": 1371 |
| }, |
| { |
| "epoch": 8.023460410557185, |
| "grad_norm": 0.3493603544083918, |
| "learning_rate": 7.4014976563890915e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.980792760848999, |
| "step": 1372 |
| }, |
| { |
| "epoch": 8.029325513196481, |
| "grad_norm": 0.33145773920777494, |
| "learning_rate": 7.381462674472702e-06, |
| "loss": 0.0555, |
| "mean_token_accuracy": 0.9846704751253128, |
| "step": 1373 |
| }, |
| { |
| "epoch": 8.035190615835777, |
| "grad_norm": 0.3327332254267587, |
| "learning_rate": 7.36148075194276e-06, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9803121909499168, |
| "step": 1374 |
| }, |
| { |
| "epoch": 8.041055718475073, |
| "grad_norm": 0.35755724158142155, |
| "learning_rate": 7.341551961325574e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9821698665618896, |
| "step": 1375 |
| }, |
| { |
| "epoch": 8.04692082111437, |
| "grad_norm": 0.3459921058263699, |
| "learning_rate": 7.3216763749546025e-06, |
| "loss": 0.0528, |
| "mean_token_accuracy": 0.9846973270177841, |
| "step": 1376 |
| }, |
| { |
| "epoch": 8.052785923753666, |
| "grad_norm": 0.420527501236528, |
| "learning_rate": 7.301854064970202e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9815153554081917, |
| "step": 1377 |
| }, |
| { |
| "epoch": 8.058651026392962, |
| "grad_norm": 0.36370898558772446, |
| "learning_rate": 7.282085103319349e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9816609099507332, |
| "step": 1378 |
| }, |
| { |
| "epoch": 8.064516129032258, |
| "grad_norm": 0.5158426013736117, |
| "learning_rate": 7.2623695617553934e-06, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9795558750629425, |
| "step": 1379 |
| }, |
| { |
| "epoch": 8.070381231671554, |
| "grad_norm": 0.3759003395576899, |
| "learning_rate": 7.242707511837781e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9835638403892517, |
| "step": 1380 |
| }, |
| { |
| "epoch": 8.07624633431085, |
| "grad_norm": 0.3069917423790072, |
| "learning_rate": 7.223099024931817e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9842489287257195, |
| "step": 1381 |
| }, |
| { |
| "epoch": 8.082111436950147, |
| "grad_norm": 0.388069657624564, |
| "learning_rate": 7.203544172208387e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9819294437766075, |
| "step": 1382 |
| }, |
| { |
| "epoch": 8.087976539589443, |
| "grad_norm": 0.42963562388871895, |
| "learning_rate": 7.184043024643712e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9813325479626656, |
| "step": 1383 |
| }, |
| { |
| "epoch": 8.093841642228739, |
| "grad_norm": 0.5150673091985366, |
| "learning_rate": 7.16459565301908e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9807056784629822, |
| "step": 1384 |
| }, |
| { |
| "epoch": 8.099706744868035, |
| "grad_norm": 0.4915099085064982, |
| "learning_rate": 7.145202127920598e-06, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9762818515300751, |
| "step": 1385 |
| }, |
| { |
| "epoch": 8.105571847507331, |
| "grad_norm": 0.34525443548547485, |
| "learning_rate": 7.125862519738924e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.978920042514801, |
| "step": 1386 |
| }, |
| { |
| "epoch": 8.111436950146627, |
| "grad_norm": 0.40866276867871215, |
| "learning_rate": 7.106576898669031e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9809467121958733, |
| "step": 1387 |
| }, |
| { |
| "epoch": 8.117302052785924, |
| "grad_norm": 0.4275703636185301, |
| "learning_rate": 7.087345334709931e-06, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9750278368592262, |
| "step": 1388 |
| }, |
| { |
| "epoch": 8.12316715542522, |
| "grad_norm": 0.4453607889338328, |
| "learning_rate": 7.068167897664433e-06, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9771971851587296, |
| "step": 1389 |
| }, |
| { |
| "epoch": 8.129032258064516, |
| "grad_norm": 0.40445124023147544, |
| "learning_rate": 7.0490446571388925e-06, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9804186373949051, |
| "step": 1390 |
| }, |
| { |
| "epoch": 8.134897360703812, |
| "grad_norm": 0.3809170636214878, |
| "learning_rate": 7.0299756825429465e-06, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.979775458574295, |
| "step": 1391 |
| }, |
| { |
| "epoch": 8.140762463343108, |
| "grad_norm": 0.35758312690942345, |
| "learning_rate": 7.010961043089277e-06, |
| "loss": 0.0501, |
| "mean_token_accuracy": 0.984392948448658, |
| "step": 1392 |
| }, |
| { |
| "epoch": 8.146627565982405, |
| "grad_norm": 0.3705074517793997, |
| "learning_rate": 6.992000807793333e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9821308106184006, |
| "step": 1393 |
| }, |
| { |
| "epoch": 8.1524926686217, |
| "grad_norm": 0.40202702754880276, |
| "learning_rate": 6.973095045473124e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9799409285187721, |
| "step": 1394 |
| }, |
| { |
| "epoch": 8.158357771260997, |
| "grad_norm": 0.40834566224229935, |
| "learning_rate": 6.954243824748922e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9817368164658546, |
| "step": 1395 |
| }, |
| { |
| "epoch": 8.164222873900293, |
| "grad_norm": 0.3340248620481329, |
| "learning_rate": 6.93544721404305e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9808118641376495, |
| "step": 1396 |
| }, |
| { |
| "epoch": 8.17008797653959, |
| "grad_norm": 1.4026355726442485, |
| "learning_rate": 6.916705281579612e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9816148653626442, |
| "step": 1397 |
| }, |
| { |
| "epoch": 8.175953079178885, |
| "grad_norm": 0.4602551692432743, |
| "learning_rate": 6.898018095384252e-06, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9773136898875237, |
| "step": 1398 |
| }, |
| { |
| "epoch": 8.181818181818182, |
| "grad_norm": 0.4282779839360214, |
| "learning_rate": 6.879385723283913e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.980457104742527, |
| "step": 1399 |
| }, |
| { |
| "epoch": 8.187683284457478, |
| "grad_norm": 0.40072108525872063, |
| "learning_rate": 6.8608082329065775e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.98114163428545, |
| "step": 1400 |
| }, |
| { |
| "epoch": 8.193548387096774, |
| "grad_norm": 0.4949708344107772, |
| "learning_rate": 6.842285691681032e-06, |
| "loss": 0.0698, |
| "mean_token_accuracy": 0.9777880758047104, |
| "step": 1401 |
| }, |
| { |
| "epoch": 8.19941348973607, |
| "grad_norm": 0.41143780595437013, |
| "learning_rate": 6.8238181668366244e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9804578647017479, |
| "step": 1402 |
| }, |
| { |
| "epoch": 8.205278592375366, |
| "grad_norm": 0.446656112624407, |
| "learning_rate": 6.805405725403006e-06, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9786640405654907, |
| "step": 1403 |
| }, |
| { |
| "epoch": 8.211143695014663, |
| "grad_norm": 0.4317831312437193, |
| "learning_rate": 6.787048434209906e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.979246236383915, |
| "step": 1404 |
| }, |
| { |
| "epoch": 8.217008797653959, |
| "grad_norm": 0.44989525731094726, |
| "learning_rate": 6.768746359886882e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9802892208099365, |
| "step": 1405 |
| }, |
| { |
| "epoch": 8.222873900293255, |
| "grad_norm": 0.38725230143331046, |
| "learning_rate": 6.750499568863061e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9803582206368446, |
| "step": 1406 |
| }, |
| { |
| "epoch": 8.228739002932551, |
| "grad_norm": 0.45583599437841565, |
| "learning_rate": 6.732308127366931e-06, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9776536375284195, |
| "step": 1407 |
| }, |
| { |
| "epoch": 8.234604105571847, |
| "grad_norm": 0.48140191290947787, |
| "learning_rate": 6.714172101426077e-06, |
| "loss": 0.0685, |
| "mean_token_accuracy": 0.9765149429440498, |
| "step": 1408 |
| }, |
| { |
| "epoch": 8.240469208211143, |
| "grad_norm": 0.34413464461383864, |
| "learning_rate": 6.696091556866948e-06, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.9841427430510521, |
| "step": 1409 |
| }, |
| { |
| "epoch": 8.24633431085044, |
| "grad_norm": 0.41459274863437684, |
| "learning_rate": 6.678066559314622e-06, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9769286438822746, |
| "step": 1410 |
| }, |
| { |
| "epoch": 8.252199413489736, |
| "grad_norm": 0.463295539451374, |
| "learning_rate": 6.660097174192556e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9780315533280373, |
| "step": 1411 |
| }, |
| { |
| "epoch": 8.258064516129032, |
| "grad_norm": 0.37945484006643254, |
| "learning_rate": 6.642183466722363e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9778400585055351, |
| "step": 1412 |
| }, |
| { |
| "epoch": 8.263929618768328, |
| "grad_norm": 0.4058692987195602, |
| "learning_rate": 6.624325501923565e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9796192273497581, |
| "step": 1413 |
| }, |
| { |
| "epoch": 8.269794721407624, |
| "grad_norm": 0.5148308880148996, |
| "learning_rate": 6.606523344613362e-06, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.9737554267048836, |
| "step": 1414 |
| }, |
| { |
| "epoch": 8.27565982404692, |
| "grad_norm": 0.40329074589234587, |
| "learning_rate": 6.588777059406397e-06, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9812517613172531, |
| "step": 1415 |
| }, |
| { |
| "epoch": 8.281524926686217, |
| "grad_norm": 0.36054433665413455, |
| "learning_rate": 6.571086710714516e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9814741238951683, |
| "step": 1416 |
| }, |
| { |
| "epoch": 8.287390029325513, |
| "grad_norm": 0.425843553206683, |
| "learning_rate": 6.553452362746543e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9788385927677155, |
| "step": 1417 |
| }, |
| { |
| "epoch": 8.29325513196481, |
| "grad_norm": 0.4350712251738216, |
| "learning_rate": 6.5358740795080335e-06, |
| "loss": 0.0737, |
| "mean_token_accuracy": 0.9740309417247772, |
| "step": 1418 |
| }, |
| { |
| "epoch": 8.299120234604105, |
| "grad_norm": 0.4461854232913144, |
| "learning_rate": 6.518351924801061e-06, |
| "loss": 0.0687, |
| "mean_token_accuracy": 0.9785968512296677, |
| "step": 1419 |
| }, |
| { |
| "epoch": 8.304985337243401, |
| "grad_norm": 0.32524924858998455, |
| "learning_rate": 6.500885962223969e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9841800928115845, |
| "step": 1420 |
| }, |
| { |
| "epoch": 8.310850439882698, |
| "grad_norm": 0.4251399950470201, |
| "learning_rate": 6.483476255171146e-06, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.977549247443676, |
| "step": 1421 |
| }, |
| { |
| "epoch": 8.316715542521994, |
| "grad_norm": 0.36996569232809523, |
| "learning_rate": 6.4661228668328015e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9811054393649101, |
| "step": 1422 |
| }, |
| { |
| "epoch": 8.32258064516129, |
| "grad_norm": 0.45412035479532575, |
| "learning_rate": 6.448825860194722e-06, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9784989804029465, |
| "step": 1423 |
| }, |
| { |
| "epoch": 8.328445747800586, |
| "grad_norm": 0.3460756895624333, |
| "learning_rate": 6.431585298038057e-06, |
| "loss": 0.0468, |
| "mean_token_accuracy": 0.9839349910616875, |
| "step": 1424 |
| }, |
| { |
| "epoch": 8.334310850439882, |
| "grad_norm": 0.4192387101641489, |
| "learning_rate": 6.414401242939087e-06, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9777123183012009, |
| "step": 1425 |
| }, |
| { |
| "epoch": 8.340175953079179, |
| "grad_norm": 0.4254508423152308, |
| "learning_rate": 6.397273757268987e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9829535335302353, |
| "step": 1426 |
| }, |
| { |
| "epoch": 8.346041055718475, |
| "grad_norm": 0.44331662945401107, |
| "learning_rate": 6.380202903193616e-06, |
| "loss": 0.0733, |
| "mean_token_accuracy": 0.9791046679019928, |
| "step": 1427 |
| }, |
| { |
| "epoch": 8.351906158357771, |
| "grad_norm": 0.42973375916020207, |
| "learning_rate": 6.363188742673281e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9783178418874741, |
| "step": 1428 |
| }, |
| { |
| "epoch": 8.357771260997067, |
| "grad_norm": 0.44400134517648665, |
| "learning_rate": 6.346231337462513e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9802630767226219, |
| "step": 1429 |
| }, |
| { |
| "epoch": 8.363636363636363, |
| "grad_norm": 0.5332774215139838, |
| "learning_rate": 6.329330749109839e-06, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9744322821497917, |
| "step": 1430 |
| }, |
| { |
| "epoch": 8.36950146627566, |
| "grad_norm": 0.44670726539330724, |
| "learning_rate": 6.312487038957573e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9792210832238197, |
| "step": 1431 |
| }, |
| { |
| "epoch": 8.375366568914956, |
| "grad_norm": 0.3564342406919051, |
| "learning_rate": 6.295700268141579e-06, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9812228232622147, |
| "step": 1432 |
| }, |
| { |
| "epoch": 8.381231671554252, |
| "grad_norm": 0.34676297877859363, |
| "learning_rate": 6.2789704975910574e-06, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9819273874163628, |
| "step": 1433 |
| }, |
| { |
| "epoch": 8.387096774193548, |
| "grad_norm": 0.4412483888206217, |
| "learning_rate": 6.262297788028316e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9792822226881981, |
| "step": 1434 |
| }, |
| { |
| "epoch": 8.392961876832844, |
| "grad_norm": 0.4185238793799762, |
| "learning_rate": 6.245682199968556e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9784470945596695, |
| "step": 1435 |
| }, |
| { |
| "epoch": 8.39882697947214, |
| "grad_norm": 0.4118391479432624, |
| "learning_rate": 6.229123793719656e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.978393092751503, |
| "step": 1436 |
| }, |
| { |
| "epoch": 8.404692082111437, |
| "grad_norm": 0.3947979484149084, |
| "learning_rate": 6.21262262938194e-06, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9816270843148232, |
| "step": 1437 |
| }, |
| { |
| "epoch": 8.410557184750733, |
| "grad_norm": 0.3995440140541391, |
| "learning_rate": 6.196178766847969e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9799474999308586, |
| "step": 1438 |
| }, |
| { |
| "epoch": 8.416422287390029, |
| "grad_norm": 0.45065461106759747, |
| "learning_rate": 6.1797922658023264e-06, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9742324277758598, |
| "step": 1439 |
| }, |
| { |
| "epoch": 8.422287390029325, |
| "grad_norm": 0.4231965191553397, |
| "learning_rate": 6.16346318572139e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9804536998271942, |
| "step": 1440 |
| }, |
| { |
| "epoch": 8.428152492668621, |
| "grad_norm": 0.4374272740525697, |
| "learning_rate": 6.147191585873128e-06, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9777810722589493, |
| "step": 1441 |
| }, |
| { |
| "epoch": 8.434017595307918, |
| "grad_norm": 0.377152469018675, |
| "learning_rate": 6.130977525316878e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9798897877335548, |
| "step": 1442 |
| }, |
| { |
| "epoch": 8.439882697947214, |
| "grad_norm": 0.3637818282003128, |
| "learning_rate": 6.114821062903125e-06, |
| "loss": 0.0617, |
| "mean_token_accuracy": 0.9810713827610016, |
| "step": 1443 |
| }, |
| { |
| "epoch": 8.44574780058651, |
| "grad_norm": 0.3566863914606614, |
| "learning_rate": 6.098722257273303e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9771608412265778, |
| "step": 1444 |
| }, |
| { |
| "epoch": 8.451612903225806, |
| "grad_norm": 0.5411699563362643, |
| "learning_rate": 6.082681166859579e-06, |
| "loss": 0.0797, |
| "mean_token_accuracy": 0.9781805574893951, |
| "step": 1445 |
| }, |
| { |
| "epoch": 8.457478005865102, |
| "grad_norm": 0.3721832814334966, |
| "learning_rate": 6.066697849884629e-06, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9788375273346901, |
| "step": 1446 |
| }, |
| { |
| "epoch": 8.463343108504398, |
| "grad_norm": 0.3381336089514224, |
| "learning_rate": 6.0507723643614415e-06, |
| "loss": 0.0483, |
| "mean_token_accuracy": 0.9832936450839043, |
| "step": 1447 |
| }, |
| { |
| "epoch": 8.469208211143695, |
| "grad_norm": 0.4932957030708935, |
| "learning_rate": 6.034904768093095e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9772367179393768, |
| "step": 1448 |
| }, |
| { |
| "epoch": 8.47507331378299, |
| "grad_norm": 0.4159775829748118, |
| "learning_rate": 6.019095118672557e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9766595289111137, |
| "step": 1449 |
| }, |
| { |
| "epoch": 8.480938416422287, |
| "grad_norm": 0.458694278310154, |
| "learning_rate": 6.003343473482469e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9791706949472427, |
| "step": 1450 |
| }, |
| { |
| "epoch": 8.486803519061583, |
| "grad_norm": 0.45200635004622236, |
| "learning_rate": 5.98764988969494e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9770751595497131, |
| "step": 1451 |
| }, |
| { |
| "epoch": 8.49266862170088, |
| "grad_norm": 0.33939476846204236, |
| "learning_rate": 5.972014424271344e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9825559854507446, |
| "step": 1452 |
| }, |
| { |
| "epoch": 8.498533724340176, |
| "grad_norm": 0.40019157724081794, |
| "learning_rate": 5.956437133962103e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9802030697464943, |
| "step": 1453 |
| }, |
| { |
| "epoch": 8.504398826979472, |
| "grad_norm": 0.4903797639199131, |
| "learning_rate": 5.94091807530649e-06, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9779242128133774, |
| "step": 1454 |
| }, |
| { |
| "epoch": 8.510263929618768, |
| "grad_norm": 0.432188854067136, |
| "learning_rate": 5.925457304632421e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9784858375787735, |
| "step": 1455 |
| }, |
| { |
| "epoch": 8.516129032258064, |
| "grad_norm": 0.4354626927723909, |
| "learning_rate": 5.91005487805625e-06, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9774255007505417, |
| "step": 1456 |
| }, |
| { |
| "epoch": 8.52199413489736, |
| "grad_norm": 0.3889579760347756, |
| "learning_rate": 5.894710851482563e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9819393903017044, |
| "step": 1457 |
| }, |
| { |
| "epoch": 8.527859237536656, |
| "grad_norm": 0.4190443435761548, |
| "learning_rate": 5.879425280603981e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9783936589956284, |
| "step": 1458 |
| }, |
| { |
| "epoch": 8.533724340175953, |
| "grad_norm": 0.3716427805379074, |
| "learning_rate": 5.864198220900952e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9804115891456604, |
| "step": 1459 |
| }, |
| { |
| "epoch": 8.539589442815249, |
| "grad_norm": 0.4304695345860514, |
| "learning_rate": 5.849029727641552e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9779717996716499, |
| "step": 1460 |
| }, |
| { |
| "epoch": 8.545454545454545, |
| "grad_norm": 0.40629590116112413, |
| "learning_rate": 5.833919855881286e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9776366725564003, |
| "step": 1461 |
| }, |
| { |
| "epoch": 8.551319648093841, |
| "grad_norm": 0.3863860594277557, |
| "learning_rate": 5.818868660462886e-06, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9794067367911339, |
| "step": 1462 |
| }, |
| { |
| "epoch": 8.557184750733137, |
| "grad_norm": 0.3520313645458845, |
| "learning_rate": 5.803876196016114e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.982727088034153, |
| "step": 1463 |
| }, |
| { |
| "epoch": 8.563049853372434, |
| "grad_norm": 0.36907769611395586, |
| "learning_rate": 5.788942516957561e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9817357435822487, |
| "step": 1464 |
| }, |
| { |
| "epoch": 8.56891495601173, |
| "grad_norm": 0.5200410648312286, |
| "learning_rate": 5.774067677490448e-06, |
| "loss": 0.0703, |
| "mean_token_accuracy": 0.9768775627017021, |
| "step": 1465 |
| }, |
| { |
| "epoch": 8.574780058651026, |
| "grad_norm": 0.39888558956463543, |
| "learning_rate": 5.759251731604435e-06, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.9802219718694687, |
| "step": 1466 |
| }, |
| { |
| "epoch": 8.580645161290322, |
| "grad_norm": 0.44676621846863246, |
| "learning_rate": 5.744494733075424e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9792397990822792, |
| "step": 1467 |
| }, |
| { |
| "epoch": 8.586510263929618, |
| "grad_norm": 0.3931258333397362, |
| "learning_rate": 5.729796735465359e-06, |
| "loss": 0.0637, |
| "mean_token_accuracy": 0.9781016334891319, |
| "step": 1468 |
| }, |
| { |
| "epoch": 8.592375366568914, |
| "grad_norm": 0.4755690885762794, |
| "learning_rate": 5.7151577921220356e-06, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9788734018802643, |
| "step": 1469 |
| }, |
| { |
| "epoch": 8.59824046920821, |
| "grad_norm": 0.32224410997626207, |
| "learning_rate": 5.7005779561789046e-06, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9822601303458214, |
| "step": 1470 |
| }, |
| { |
| "epoch": 8.604105571847507, |
| "grad_norm": 0.38096415492092744, |
| "learning_rate": 5.686057280554882e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9811006933450699, |
| "step": 1471 |
| }, |
| { |
| "epoch": 8.609970674486803, |
| "grad_norm": 0.3798971384798509, |
| "learning_rate": 5.671595817954157e-06, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9809722378849983, |
| "step": 1472 |
| }, |
| { |
| "epoch": 8.6158357771261, |
| "grad_norm": 0.39712814437410365, |
| "learning_rate": 5.657193620865997e-06, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9817419350147247, |
| "step": 1473 |
| }, |
| { |
| "epoch": 8.621700879765395, |
| "grad_norm": 0.426717484698465, |
| "learning_rate": 5.642850741564562e-06, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9797801226377487, |
| "step": 1474 |
| }, |
| { |
| "epoch": 8.627565982404692, |
| "grad_norm": 0.39180647548645714, |
| "learning_rate": 5.62856723210871e-06, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9771608114242554, |
| "step": 1475 |
| }, |
| { |
| "epoch": 8.633431085043988, |
| "grad_norm": 0.4430059558951615, |
| "learning_rate": 5.614343144341814e-06, |
| "loss": 0.0674, |
| "mean_token_accuracy": 0.976546123623848, |
| "step": 1476 |
| }, |
| { |
| "epoch": 8.639296187683284, |
| "grad_norm": 0.3569576065869277, |
| "learning_rate": 5.600178529891564e-06, |
| "loss": 0.0555, |
| "mean_token_accuracy": 0.9811270162463188, |
| "step": 1477 |
| }, |
| { |
| "epoch": 8.64516129032258, |
| "grad_norm": 0.45417837250222987, |
| "learning_rate": 5.58607344016979e-06, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9747651368379593, |
| "step": 1478 |
| }, |
| { |
| "epoch": 8.651026392961876, |
| "grad_norm": 0.3698876433443863, |
| "learning_rate": 5.5720279263722795e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9789956957101822, |
| "step": 1479 |
| }, |
| { |
| "epoch": 8.656891495601172, |
| "grad_norm": 0.35791268214354616, |
| "learning_rate": 5.558042039478564e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9798028543591499, |
| "step": 1480 |
| }, |
| { |
| "epoch": 8.662756598240469, |
| "grad_norm": 0.45869214210455983, |
| "learning_rate": 5.544115830251769e-06, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9762693867087364, |
| "step": 1481 |
| }, |
| { |
| "epoch": 8.668621700879765, |
| "grad_norm": 0.39328389095358174, |
| "learning_rate": 5.530249349238407e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9799056574702263, |
| "step": 1482 |
| }, |
| { |
| "epoch": 8.674486803519061, |
| "grad_norm": 0.46693918116536703, |
| "learning_rate": 5.516442646768207e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9731965810060501, |
| "step": 1483 |
| }, |
| { |
| "epoch": 8.680351906158357, |
| "grad_norm": 0.40893126252597817, |
| "learning_rate": 5.502695772953922e-06, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9753478020429611, |
| "step": 1484 |
| }, |
| { |
| "epoch": 8.686217008797653, |
| "grad_norm": 0.4089615786595679, |
| "learning_rate": 5.489008777691151e-06, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.981198251247406, |
| "step": 1485 |
| }, |
| { |
| "epoch": 8.69208211143695, |
| "grad_norm": 0.44617842869601976, |
| "learning_rate": 5.475381710658161e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9780819341540337, |
| "step": 1486 |
| }, |
| { |
| "epoch": 8.697947214076246, |
| "grad_norm": 0.4292444383541708, |
| "learning_rate": 5.4618146213157e-06, |
| "loss": 0.0727, |
| "mean_token_accuracy": 0.974052220582962, |
| "step": 1487 |
| }, |
| { |
| "epoch": 8.703812316715542, |
| "grad_norm": 0.40014883458637857, |
| "learning_rate": 5.448307558906822e-06, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9791484698653221, |
| "step": 1488 |
| }, |
| { |
| "epoch": 8.709677419354838, |
| "grad_norm": 0.4054936264596516, |
| "learning_rate": 5.434860572456711e-06, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9779806360602379, |
| "step": 1489 |
| }, |
| { |
| "epoch": 8.715542521994134, |
| "grad_norm": 0.3718640448186527, |
| "learning_rate": 5.421473710772496e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9803246408700943, |
| "step": 1490 |
| }, |
| { |
| "epoch": 8.72140762463343, |
| "grad_norm": 0.39050493584924245, |
| "learning_rate": 5.408147022443077e-06, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9788827151060104, |
| "step": 1491 |
| }, |
| { |
| "epoch": 8.727272727272727, |
| "grad_norm": 0.41088568338867887, |
| "learning_rate": 5.39488055583895e-06, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.9798588156700134, |
| "step": 1492 |
| }, |
| { |
| "epoch": 8.733137829912023, |
| "grad_norm": 0.40538498630057557, |
| "learning_rate": 5.3816743591120365e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9792995974421501, |
| "step": 1493 |
| }, |
| { |
| "epoch": 8.739002932551319, |
| "grad_norm": 0.39709976977685296, |
| "learning_rate": 5.368528480195492e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9794448539614677, |
| "step": 1494 |
| }, |
| { |
| "epoch": 8.744868035190615, |
| "grad_norm": 0.29534621119213206, |
| "learning_rate": 5.355442966803544e-06, |
| "loss": 0.0499, |
| "mean_token_accuracy": 0.9821311086416245, |
| "step": 1495 |
| }, |
| { |
| "epoch": 8.750733137829911, |
| "grad_norm": 0.44576282146133084, |
| "learning_rate": 5.342417866431326e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9736595973372459, |
| "step": 1496 |
| }, |
| { |
| "epoch": 8.756598240469208, |
| "grad_norm": 0.4858368189644326, |
| "learning_rate": 5.329453226354692e-06, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9792052656412125, |
| "step": 1497 |
| }, |
| { |
| "epoch": 8.762463343108504, |
| "grad_norm": 0.39967097238505644, |
| "learning_rate": 5.31654909363005e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9812125638127327, |
| "step": 1498 |
| }, |
| { |
| "epoch": 8.7683284457478, |
| "grad_norm": 0.48415089273894846, |
| "learning_rate": 5.303705515094187e-06, |
| "loss": 0.0797, |
| "mean_token_accuracy": 0.9757314994931221, |
| "step": 1499 |
| }, |
| { |
| "epoch": 8.774193548387096, |
| "grad_norm": 0.48987771606948255, |
| "learning_rate": 5.290922537364109e-06, |
| "loss": 0.0778, |
| "mean_token_accuracy": 0.9723097234964371, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.780058651026392, |
| "grad_norm": 0.3870672590317324, |
| "learning_rate": 5.278200206836861e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.976532444357872, |
| "step": 1501 |
| }, |
| { |
| "epoch": 8.785923753665688, |
| "grad_norm": 0.3792488697620107, |
| "learning_rate": 5.265538569689365e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9791921749711037, |
| "step": 1502 |
| }, |
| { |
| "epoch": 8.791788856304985, |
| "grad_norm": 0.3755126980286468, |
| "learning_rate": 5.25293767187825e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9820508360862732, |
| "step": 1503 |
| }, |
| { |
| "epoch": 8.79765395894428, |
| "grad_norm": 0.45791046477915304, |
| "learning_rate": 5.240397559139685e-06, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.976809673011303, |
| "step": 1504 |
| }, |
| { |
| "epoch": 8.803519061583577, |
| "grad_norm": 0.339257377791184, |
| "learning_rate": 5.227918276989215e-06, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9784117043018341, |
| "step": 1505 |
| }, |
| { |
| "epoch": 8.809384164222873, |
| "grad_norm": 0.3563307355157344, |
| "learning_rate": 5.2154998707215976e-06, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9783895686268806, |
| "step": 1506 |
| }, |
| { |
| "epoch": 8.81524926686217, |
| "grad_norm": 0.391641788208127, |
| "learning_rate": 5.203142385410628e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9819121286273003, |
| "step": 1507 |
| }, |
| { |
| "epoch": 8.821114369501466, |
| "grad_norm": 0.3732982966201132, |
| "learning_rate": 5.190845865908987e-06, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9774733334779739, |
| "step": 1508 |
| }, |
| { |
| "epoch": 8.826979472140762, |
| "grad_norm": 0.4446554745627886, |
| "learning_rate": 5.178610356848075e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9783753901720047, |
| "step": 1509 |
| }, |
| { |
| "epoch": 8.832844574780058, |
| "grad_norm": 0.40749848731190025, |
| "learning_rate": 5.166435902637848e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9798924401402473, |
| "step": 1510 |
| }, |
| { |
| "epoch": 8.838709677419354, |
| "grad_norm": 0.3711771079046037, |
| "learning_rate": 5.154322547466658e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9817164465785027, |
| "step": 1511 |
| }, |
| { |
| "epoch": 8.84457478005865, |
| "grad_norm": 0.4084163982169611, |
| "learning_rate": 5.142270335301095e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9804741069674492, |
| "step": 1512 |
| }, |
| { |
| "epoch": 8.850439882697946, |
| "grad_norm": 0.36704184008992147, |
| "learning_rate": 5.130279309885817e-06, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9785638004541397, |
| "step": 1513 |
| }, |
| { |
| "epoch": 8.856304985337243, |
| "grad_norm": 0.48744936724567456, |
| "learning_rate": 5.118349514743404e-06, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9747727289795876, |
| "step": 1514 |
| }, |
| { |
| "epoch": 8.862170087976539, |
| "grad_norm": 0.5326424417819942, |
| "learning_rate": 5.1064809931741975e-06, |
| "loss": 0.0786, |
| "mean_token_accuracy": 0.974541112780571, |
| "step": 1515 |
| }, |
| { |
| "epoch": 8.868035190615835, |
| "grad_norm": 0.43515177370388725, |
| "learning_rate": 5.094673788256137e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9825545847415924, |
| "step": 1516 |
| }, |
| { |
| "epoch": 8.873900293255131, |
| "grad_norm": 0.49677928721350817, |
| "learning_rate": 5.082927942844603e-06, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9781579226255417, |
| "step": 1517 |
| }, |
| { |
| "epoch": 8.879765395894427, |
| "grad_norm": 0.4087812579703352, |
| "learning_rate": 5.0712434995722734e-06, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.97551279515028, |
| "step": 1518 |
| }, |
| { |
| "epoch": 8.885630498533724, |
| "grad_norm": 0.4484581230306622, |
| "learning_rate": 5.059620500848964e-06, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9802887737751007, |
| "step": 1519 |
| }, |
| { |
| "epoch": 8.89149560117302, |
| "grad_norm": 0.4349996172658484, |
| "learning_rate": 5.048058988861455e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9786894470453262, |
| "step": 1520 |
| }, |
| { |
| "epoch": 8.897360703812316, |
| "grad_norm": 0.3788164408254738, |
| "learning_rate": 5.0365590055733715e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.980890542268753, |
| "step": 1521 |
| }, |
| { |
| "epoch": 8.903225806451612, |
| "grad_norm": 0.47821896076846393, |
| "learning_rate": 5.025120592725009e-06, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9776649847626686, |
| "step": 1522 |
| }, |
| { |
| "epoch": 8.909090909090908, |
| "grad_norm": 0.4392969635422559, |
| "learning_rate": 5.013743791833187e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.9793538227677345, |
| "step": 1523 |
| }, |
| { |
| "epoch": 8.914956011730204, |
| "grad_norm": 0.43229020194353457, |
| "learning_rate": 5.002428644191094e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9785308763384819, |
| "step": 1524 |
| }, |
| { |
| "epoch": 8.9208211143695, |
| "grad_norm": 0.5650155135114429, |
| "learning_rate": 4.991175190868148e-06, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9788858294487, |
| "step": 1525 |
| }, |
| { |
| "epoch": 8.926686217008797, |
| "grad_norm": 0.3791246428901692, |
| "learning_rate": 4.9799834727098415e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9807322397828102, |
| "step": 1526 |
| }, |
| { |
| "epoch": 8.932551319648093, |
| "grad_norm": 0.4199681370793567, |
| "learning_rate": 4.968853530337587e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.979116789996624, |
| "step": 1527 |
| }, |
| { |
| "epoch": 8.93841642228739, |
| "grad_norm": 0.33066038490437366, |
| "learning_rate": 4.957785404148585e-06, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9786024838685989, |
| "step": 1528 |
| }, |
| { |
| "epoch": 8.944281524926687, |
| "grad_norm": 0.4365370500260649, |
| "learning_rate": 4.946779134315662e-06, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9773358777165413, |
| "step": 1529 |
| }, |
| { |
| "epoch": 8.950146627565982, |
| "grad_norm": 0.3908055069300888, |
| "learning_rate": 4.935834760787133e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9808821976184845, |
| "step": 1530 |
| }, |
| { |
| "epoch": 8.95601173020528, |
| "grad_norm": 0.42105218806769806, |
| "learning_rate": 4.924952323286651e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9778595939278603, |
| "step": 1531 |
| }, |
| { |
| "epoch": 8.961876832844574, |
| "grad_norm": 0.42944765888744796, |
| "learning_rate": 4.91413186131307e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9791755601763725, |
| "step": 1532 |
| }, |
| { |
| "epoch": 8.967741935483872, |
| "grad_norm": 0.38789725100449346, |
| "learning_rate": 4.9033734141402964e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9773519560694695, |
| "step": 1533 |
| }, |
| { |
| "epoch": 8.973607038123166, |
| "grad_norm": 0.39321990127885054, |
| "learning_rate": 4.892677020817151e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9775725901126862, |
| "step": 1534 |
| }, |
| { |
| "epoch": 8.979472140762464, |
| "grad_norm": 0.42869069521785264, |
| "learning_rate": 4.8820427201672195e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9767110124230385, |
| "step": 1535 |
| }, |
| { |
| "epoch": 8.985337243401759, |
| "grad_norm": 0.4786492298609853, |
| "learning_rate": 4.871470550788717e-06, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9734204337000847, |
| "step": 1536 |
| }, |
| { |
| "epoch": 8.991202346041057, |
| "grad_norm": 0.4053785268805127, |
| "learning_rate": 4.860960551054352e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9776445254683495, |
| "step": 1537 |
| }, |
| { |
| "epoch": 8.997067448680351, |
| "grad_norm": 0.35094233757463134, |
| "learning_rate": 4.850512759111177e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9781850948929787, |
| "step": 1538 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.35094233757463134, |
| "learning_rate": 4.840127212880457e-06, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.9817498177289963, |
| "step": 1539 |
| }, |
| { |
| "epoch": 9.005865102639296, |
| "grad_norm": 0.5237297972324702, |
| "learning_rate": 4.82980395005753e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9797078743577003, |
| "step": 1540 |
| }, |
| { |
| "epoch": 9.011730205278592, |
| "grad_norm": 0.44512166679517556, |
| "learning_rate": 4.8195430081116715e-06, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.9778907150030136, |
| "step": 1541 |
| }, |
| { |
| "epoch": 9.017595307917889, |
| "grad_norm": 0.3971540226360805, |
| "learning_rate": 4.809344424285959e-06, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9832166880369186, |
| "step": 1542 |
| }, |
| { |
| "epoch": 9.023460410557185, |
| "grad_norm": 0.4344511380877736, |
| "learning_rate": 4.799208235597129e-06, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.975956417620182, |
| "step": 1543 |
| }, |
| { |
| "epoch": 9.029325513196481, |
| "grad_norm": 0.4443832424460116, |
| "learning_rate": 4.7891344788354535e-06, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9792809188365936, |
| "step": 1544 |
| }, |
| { |
| "epoch": 9.035190615835777, |
| "grad_norm": 0.4256572665128867, |
| "learning_rate": 4.779123190564601e-06, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9784202426671982, |
| "step": 1545 |
| }, |
| { |
| "epoch": 9.041055718475073, |
| "grad_norm": 0.4221529309761034, |
| "learning_rate": 4.769174407121508e-06, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9809971302747726, |
| "step": 1546 |
| }, |
| { |
| "epoch": 9.04692082111437, |
| "grad_norm": 0.3734102169463082, |
| "learning_rate": 4.7592881646162336e-06, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9773375019431114, |
| "step": 1547 |
| }, |
| { |
| "epoch": 9.052785923753666, |
| "grad_norm": 0.447186570979957, |
| "learning_rate": 4.749464498931852e-06, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9823371693491936, |
| "step": 1548 |
| }, |
| { |
| "epoch": 9.058651026392962, |
| "grad_norm": 0.3671698486649876, |
| "learning_rate": 4.739703445724296e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.982838973402977, |
| "step": 1549 |
| }, |
| { |
| "epoch": 9.064516129032258, |
| "grad_norm": 0.37297501174682546, |
| "learning_rate": 4.730005040422253e-06, |
| "loss": 0.0553, |
| "mean_token_accuracy": 0.9813901260495186, |
| "step": 1550 |
| }, |
| { |
| "epoch": 9.070381231671554, |
| "grad_norm": 0.38009096211845106, |
| "learning_rate": 4.720369318227014e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9810118600726128, |
| "step": 1551 |
| }, |
| { |
| "epoch": 9.07624633431085, |
| "grad_norm": 0.3900939913077741, |
| "learning_rate": 4.710796314112358e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.980675220489502, |
| "step": 1552 |
| }, |
| { |
| "epoch": 9.082111436950147, |
| "grad_norm": 0.4026706110167321, |
| "learning_rate": 4.701286062824425e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9805927649140358, |
| "step": 1553 |
| }, |
| { |
| "epoch": 9.087976539589443, |
| "grad_norm": 0.45380931104767136, |
| "learning_rate": 4.691838598881587e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9795587509870529, |
| "step": 1554 |
| }, |
| { |
| "epoch": 9.093841642228739, |
| "grad_norm": 0.3600842002137639, |
| "learning_rate": 4.68245395657432e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9825239703059196, |
| "step": 1555 |
| }, |
| { |
| "epoch": 9.099706744868035, |
| "grad_norm": 0.36982100027726045, |
| "learning_rate": 4.673132169965089e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.981265015900135, |
| "step": 1556 |
| }, |
| { |
| "epoch": 9.105571847507331, |
| "grad_norm": 0.3408794742470351, |
| "learning_rate": 4.663873272888212e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9842574149370193, |
| "step": 1557 |
| }, |
| { |
| "epoch": 9.111436950146627, |
| "grad_norm": 0.35088642747738386, |
| "learning_rate": 4.654677298949746e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9791886806488037, |
| "step": 1558 |
| }, |
| { |
| "epoch": 9.117302052785924, |
| "grad_norm": 0.36467197514575506, |
| "learning_rate": 4.645544281527362e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9801543280482292, |
| "step": 1559 |
| }, |
| { |
| "epoch": 9.12316715542522, |
| "grad_norm": 0.34756702727558925, |
| "learning_rate": 4.636474253770226e-06, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9805246517062187, |
| "step": 1560 |
| }, |
| { |
| "epoch": 9.129032258064516, |
| "grad_norm": 0.37383863828715663, |
| "learning_rate": 4.627467248598876e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9800150692462921, |
| "step": 1561 |
| }, |
| { |
| "epoch": 9.134897360703812, |
| "grad_norm": 0.389051327036322, |
| "learning_rate": 4.618523298705101e-06, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.9797752350568771, |
| "step": 1562 |
| }, |
| { |
| "epoch": 9.140762463343108, |
| "grad_norm": 0.4206126663755432, |
| "learning_rate": 4.609642436551828e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9813887402415276, |
| "step": 1563 |
| }, |
| { |
| "epoch": 9.146627565982405, |
| "grad_norm": 0.35220076392965055, |
| "learning_rate": 4.600824694373e-06, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.9830791279673576, |
| "step": 1564 |
| }, |
| { |
| "epoch": 9.1524926686217, |
| "grad_norm": 0.3906579664451844, |
| "learning_rate": 4.592070104173461e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9816785305738449, |
| "step": 1565 |
| }, |
| { |
| "epoch": 9.158357771260997, |
| "grad_norm": 0.3955333597592588, |
| "learning_rate": 4.583378697728835e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9795950427651405, |
| "step": 1566 |
| }, |
| { |
| "epoch": 9.164222873900293, |
| "grad_norm": 0.38507961041809957, |
| "learning_rate": 4.574750506585419e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9788780435919762, |
| "step": 1567 |
| }, |
| { |
| "epoch": 9.17008797653959, |
| "grad_norm": 0.4103182153300624, |
| "learning_rate": 4.566185562060062e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9781305864453316, |
| "step": 1568 |
| }, |
| { |
| "epoch": 9.175953079178885, |
| "grad_norm": 0.3887724325841942, |
| "learning_rate": 4.557683895240052e-06, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9806842058897018, |
| "step": 1569 |
| }, |
| { |
| "epoch": 9.181818181818182, |
| "grad_norm": 0.4716208696133187, |
| "learning_rate": 4.549245536983009e-06, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9804612249135971, |
| "step": 1570 |
| }, |
| { |
| "epoch": 9.187683284457478, |
| "grad_norm": 0.5070036957239129, |
| "learning_rate": 4.540870517916765e-06, |
| "loss": 0.0613, |
| "mean_token_accuracy": 0.9818564429879189, |
| "step": 1571 |
| }, |
| { |
| "epoch": 9.193548387096774, |
| "grad_norm": 0.4470372868463617, |
| "learning_rate": 4.532558868439249e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9813555926084518, |
| "step": 1572 |
| }, |
| { |
| "epoch": 9.19941348973607, |
| "grad_norm": 0.38207644337118024, |
| "learning_rate": 4.524310618718403e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9805998206138611, |
| "step": 1573 |
| }, |
| { |
| "epoch": 9.205278592375366, |
| "grad_norm": 0.39814646651964014, |
| "learning_rate": 4.516125798692037e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9801303371787071, |
| "step": 1574 |
| }, |
| { |
| "epoch": 9.211143695014663, |
| "grad_norm": 0.43225612025999705, |
| "learning_rate": 4.508004438067742e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9784739464521408, |
| "step": 1575 |
| }, |
| { |
| "epoch": 9.217008797653959, |
| "grad_norm": 0.39246909818546494, |
| "learning_rate": 4.4999465663227785e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9829608574509621, |
| "step": 1576 |
| }, |
| { |
| "epoch": 9.222873900293255, |
| "grad_norm": 0.3600372585620087, |
| "learning_rate": 4.491952212703964e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9804084450006485, |
| "step": 1577 |
| }, |
| { |
| "epoch": 9.228739002932551, |
| "grad_norm": 0.39264492417648206, |
| "learning_rate": 4.484021406227576e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9805421456694603, |
| "step": 1578 |
| }, |
| { |
| "epoch": 9.234604105571847, |
| "grad_norm": 0.42510250192373583, |
| "learning_rate": 4.476154175679239e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9789351969957352, |
| "step": 1579 |
| }, |
| { |
| "epoch": 9.240469208211143, |
| "grad_norm": 0.3938384763118357, |
| "learning_rate": 4.468350549613822e-06, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.9829250946640968, |
| "step": 1580 |
| }, |
| { |
| "epoch": 9.24633431085044, |
| "grad_norm": 0.4246125900175589, |
| "learning_rate": 4.460610556355333e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9760880768299103, |
| "step": 1581 |
| }, |
| { |
| "epoch": 9.252199413489736, |
| "grad_norm": 0.36802833825061815, |
| "learning_rate": 4.452934223996824e-06, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9816494733095169, |
| "step": 1582 |
| }, |
| { |
| "epoch": 9.258064516129032, |
| "grad_norm": 0.37411173603250736, |
| "learning_rate": 4.445321580400281e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.978959359228611, |
| "step": 1583 |
| }, |
| { |
| "epoch": 9.263929618768328, |
| "grad_norm": 0.3890694859810841, |
| "learning_rate": 4.437772653196527e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9814217388629913, |
| "step": 1584 |
| }, |
| { |
| "epoch": 9.269794721407624, |
| "grad_norm": 0.44573942459915583, |
| "learning_rate": 4.430287469785118e-06, |
| "loss": 0.0739, |
| "mean_token_accuracy": 0.9738015979528427, |
| "step": 1585 |
| }, |
| { |
| "epoch": 9.27565982404692, |
| "grad_norm": 0.48678328598976534, |
| "learning_rate": 4.422866057334246e-06, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9811902418732643, |
| "step": 1586 |
| }, |
| { |
| "epoch": 9.281524926686217, |
| "grad_norm": 0.41976267189188704, |
| "learning_rate": 4.415508442780642e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9764698594808578, |
| "step": 1587 |
| }, |
| { |
| "epoch": 9.287390029325513, |
| "grad_norm": 0.4342338051618334, |
| "learning_rate": 4.408214652829473e-06, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9801175519824028, |
| "step": 1588 |
| }, |
| { |
| "epoch": 9.29325513196481, |
| "grad_norm": 0.3584174292660337, |
| "learning_rate": 4.400984713954253e-06, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9840468168258667, |
| "step": 1589 |
| }, |
| { |
| "epoch": 9.299120234604105, |
| "grad_norm": 0.36705643787783054, |
| "learning_rate": 4.39381865239674e-06, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9782479926943779, |
| "step": 1590 |
| }, |
| { |
| "epoch": 9.304985337243401, |
| "grad_norm": 0.43484590696065256, |
| "learning_rate": 4.386716494166842e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9777791127562523, |
| "step": 1591 |
| }, |
| { |
| "epoch": 9.310850439882698, |
| "grad_norm": 0.45480469469795737, |
| "learning_rate": 4.379678265042529e-06, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9770721420645714, |
| "step": 1592 |
| }, |
| { |
| "epoch": 9.316715542521994, |
| "grad_norm": 0.43015696322178737, |
| "learning_rate": 4.372703990569725e-06, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.980101153254509, |
| "step": 1593 |
| }, |
| { |
| "epoch": 9.32258064516129, |
| "grad_norm": 0.42007509787839914, |
| "learning_rate": 4.365793696062231e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9778276085853577, |
| "step": 1594 |
| }, |
| { |
| "epoch": 9.328445747800586, |
| "grad_norm": 0.4149482516608359, |
| "learning_rate": 4.358947406601626e-06, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.9816755205392838, |
| "step": 1595 |
| }, |
| { |
| "epoch": 9.334310850439882, |
| "grad_norm": 0.34040334345484463, |
| "learning_rate": 4.352165147037177e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9789953827857971, |
| "step": 1596 |
| }, |
| { |
| "epoch": 9.340175953079179, |
| "grad_norm": 0.4023555043611021, |
| "learning_rate": 4.345446941985741e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.980284109711647, |
| "step": 1597 |
| }, |
| { |
| "epoch": 9.346041055718475, |
| "grad_norm": 0.36962446757993983, |
| "learning_rate": 4.338792815831698e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9776437729597092, |
| "step": 1598 |
| }, |
| { |
| "epoch": 9.351906158357771, |
| "grad_norm": 0.4596662981829499, |
| "learning_rate": 4.332202792726832e-06, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9775255918502808, |
| "step": 1599 |
| }, |
| { |
| "epoch": 9.357771260997067, |
| "grad_norm": 0.42975827996705523, |
| "learning_rate": 4.3256768965902684e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9770565405488014, |
| "step": 1600 |
| }, |
| { |
| "epoch": 9.363636363636363, |
| "grad_norm": 0.4470080718132124, |
| "learning_rate": 4.319215151108373e-06, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9741783291101456, |
| "step": 1601 |
| }, |
| { |
| "epoch": 9.36950146627566, |
| "grad_norm": 0.41580223631412677, |
| "learning_rate": 4.312817579734673e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9820943027734756, |
| "step": 1602 |
| }, |
| { |
| "epoch": 9.375366568914956, |
| "grad_norm": 0.43117316682024365, |
| "learning_rate": 4.306484205689768e-06, |
| "loss": 0.0675, |
| "mean_token_accuracy": 0.9774612933397293, |
| "step": 1603 |
| }, |
| { |
| "epoch": 9.381231671554252, |
| "grad_norm": 0.42448166413412824, |
| "learning_rate": 4.300215051961248e-06, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9788782298564911, |
| "step": 1604 |
| }, |
| { |
| "epoch": 9.387096774193548, |
| "grad_norm": 0.41207232977220787, |
| "learning_rate": 4.2940101413036115e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9822210595011711, |
| "step": 1605 |
| }, |
| { |
| "epoch": 9.392961876832844, |
| "grad_norm": 0.3969085611246392, |
| "learning_rate": 4.287869496238174e-06, |
| "loss": 0.0687, |
| "mean_token_accuracy": 0.9773961007595062, |
| "step": 1606 |
| }, |
| { |
| "epoch": 9.39882697947214, |
| "grad_norm": 0.38674351125589457, |
| "learning_rate": 4.281793139053001e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.978922612965107, |
| "step": 1607 |
| }, |
| { |
| "epoch": 9.404692082111437, |
| "grad_norm": 0.44522870176548146, |
| "learning_rate": 4.275781091802811e-06, |
| "loss": 0.0804, |
| "mean_token_accuracy": 0.9744135141372681, |
| "step": 1608 |
| }, |
| { |
| "epoch": 9.410557184750733, |
| "grad_norm": 0.5050856462926645, |
| "learning_rate": 4.26983337630891e-06, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.979136548936367, |
| "step": 1609 |
| }, |
| { |
| "epoch": 9.416422287390029, |
| "grad_norm": 0.46147350712406626, |
| "learning_rate": 4.263950014159103e-06, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9783479198813438, |
| "step": 1610 |
| }, |
| { |
| "epoch": 9.422287390029325, |
| "grad_norm": 0.35759283649520646, |
| "learning_rate": 4.258131026707618e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9823313504457474, |
| "step": 1611 |
| }, |
| { |
| "epoch": 9.428152492668621, |
| "grad_norm": 0.4068410294223593, |
| "learning_rate": 4.2523764350750305e-06, |
| "loss": 0.0674, |
| "mean_token_accuracy": 0.9794067889451981, |
| "step": 1612 |
| }, |
| { |
| "epoch": 9.434017595307918, |
| "grad_norm": 0.4185738461055289, |
| "learning_rate": 4.246686260148179e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9806213080883026, |
| "step": 1613 |
| }, |
| { |
| "epoch": 9.439882697947214, |
| "grad_norm": 0.48641041661236, |
| "learning_rate": 4.241060522580108e-06, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9752521067857742, |
| "step": 1614 |
| }, |
| { |
| "epoch": 9.44574780058651, |
| "grad_norm": 0.4453163153136548, |
| "learning_rate": 4.2354992427899674e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9813522100448608, |
| "step": 1615 |
| }, |
| { |
| "epoch": 9.451612903225806, |
| "grad_norm": 0.40238271305787837, |
| "learning_rate": 4.23000244096296e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.978582575917244, |
| "step": 1616 |
| }, |
| { |
| "epoch": 9.457478005865102, |
| "grad_norm": 0.3997496093412971, |
| "learning_rate": 4.224570137050254e-06, |
| "loss": 0.049, |
| "mean_token_accuracy": 0.9842732697725296, |
| "step": 1617 |
| }, |
| { |
| "epoch": 9.463343108504398, |
| "grad_norm": 0.3539750438856785, |
| "learning_rate": 4.219202350768919e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9794608727097511, |
| "step": 1618 |
| }, |
| { |
| "epoch": 9.469208211143695, |
| "grad_norm": 0.38463794727155115, |
| "learning_rate": 4.213899101601853e-06, |
| "loss": 0.0617, |
| "mean_token_accuracy": 0.9791621938347816, |
| "step": 1619 |
| }, |
| { |
| "epoch": 9.47507331378299, |
| "grad_norm": 0.376559715948642, |
| "learning_rate": 4.208660408797708e-06, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9801753237843513, |
| "step": 1620 |
| }, |
| { |
| "epoch": 9.480938416422287, |
| "grad_norm": 0.39527726743081754, |
| "learning_rate": 4.203486291370821e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.980688601732254, |
| "step": 1621 |
| }, |
| { |
| "epoch": 9.486803519061583, |
| "grad_norm": 0.4421038272813132, |
| "learning_rate": 4.198376768101149e-06, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.978269450366497, |
| "step": 1622 |
| }, |
| { |
| "epoch": 9.49266862170088, |
| "grad_norm": 0.45644675105726096, |
| "learning_rate": 4.193331857534198e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9808766692876816, |
| "step": 1623 |
| }, |
| { |
| "epoch": 9.498533724340176, |
| "grad_norm": 0.3628850686906786, |
| "learning_rate": 4.188351577980961e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.9819683060050011, |
| "step": 1624 |
| }, |
| { |
| "epoch": 9.504398826979472, |
| "grad_norm": 0.4057038844877085, |
| "learning_rate": 4.183435947517836e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9803583696484566, |
| "step": 1625 |
| }, |
| { |
| "epoch": 9.510263929618768, |
| "grad_norm": 0.3679923800134878, |
| "learning_rate": 4.178584983986575e-06, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.9833980947732925, |
| "step": 1626 |
| }, |
| { |
| "epoch": 9.516129032258064, |
| "grad_norm": 0.35069345182619793, |
| "learning_rate": 4.173798704994221e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9815231710672379, |
| "step": 1627 |
| }, |
| { |
| "epoch": 9.52199413489736, |
| "grad_norm": 0.3952790895573117, |
| "learning_rate": 4.169077127913031e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9765211567282677, |
| "step": 1628 |
| }, |
| { |
| "epoch": 9.527859237536656, |
| "grad_norm": 0.4108655452567332, |
| "learning_rate": 4.164420269880422e-06, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9768633097410202, |
| "step": 1629 |
| }, |
| { |
| "epoch": 9.533724340175953, |
| "grad_norm": 0.39953251365980913, |
| "learning_rate": 4.159828147798914e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9824348241090775, |
| "step": 1630 |
| }, |
| { |
| "epoch": 9.539589442815249, |
| "grad_norm": 0.3722601174054308, |
| "learning_rate": 4.155300778336047e-06, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9787588939070702, |
| "step": 1631 |
| }, |
| { |
| "epoch": 9.545454545454545, |
| "grad_norm": 0.4843120313142688, |
| "learning_rate": 4.150838177924349e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9840193539857864, |
| "step": 1632 |
| }, |
| { |
| "epoch": 9.551319648093841, |
| "grad_norm": 0.3390691465939108, |
| "learning_rate": 4.146440362761256e-06, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9807577356696129, |
| "step": 1633 |
| }, |
| { |
| "epoch": 9.557184750733137, |
| "grad_norm": 0.39197990083896755, |
| "learning_rate": 4.142107348809058e-06, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9762087687849998, |
| "step": 1634 |
| }, |
| { |
| "epoch": 9.563049853372434, |
| "grad_norm": 0.42470639878785044, |
| "learning_rate": 4.1378391517948505e-06, |
| "loss": 0.0552, |
| "mean_token_accuracy": 0.9833284765481949, |
| "step": 1635 |
| }, |
| { |
| "epoch": 9.56891495601173, |
| "grad_norm": 0.4205496957044024, |
| "learning_rate": 4.1336357872104614e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9796880483627319, |
| "step": 1636 |
| }, |
| { |
| "epoch": 9.574780058651026, |
| "grad_norm": 0.37017733597857505, |
| "learning_rate": 4.12949727031241e-06, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9796748831868172, |
| "step": 1637 |
| }, |
| { |
| "epoch": 9.580645161290322, |
| "grad_norm": 0.4084323347975372, |
| "learning_rate": 4.125423616121837e-06, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.9810463264584541, |
| "step": 1638 |
| }, |
| { |
| "epoch": 9.586510263929618, |
| "grad_norm": 0.34366109037322107, |
| "learning_rate": 4.121414839424464e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9815482944250107, |
| "step": 1639 |
| }, |
| { |
| "epoch": 9.592375366568914, |
| "grad_norm": 0.4338152320928124, |
| "learning_rate": 4.117470954770529e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9788042083382607, |
| "step": 1640 |
| }, |
| { |
| "epoch": 9.59824046920821, |
| "grad_norm": 0.31292211012562876, |
| "learning_rate": 4.1135919764747454e-06, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9811399206519127, |
| "step": 1641 |
| }, |
| { |
| "epoch": 9.604105571847507, |
| "grad_norm": 0.3803411380006481, |
| "learning_rate": 4.109777918616235e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9828116968274117, |
| "step": 1642 |
| }, |
| { |
| "epoch": 9.609970674486803, |
| "grad_norm": 0.3997887550659777, |
| "learning_rate": 4.106028795038487e-06, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9773474633693695, |
| "step": 1643 |
| }, |
| { |
| "epoch": 9.6158357771261, |
| "grad_norm": 0.45750394844022496, |
| "learning_rate": 4.102344619349307e-06, |
| "loss": 0.0754, |
| "mean_token_accuracy": 0.9736003801226616, |
| "step": 1644 |
| }, |
| { |
| "epoch": 9.621700879765395, |
| "grad_norm": 0.4527628966223273, |
| "learning_rate": 4.098725404920763e-06, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9779922664165497, |
| "step": 1645 |
| }, |
| { |
| "epoch": 9.627565982404692, |
| "grad_norm": 0.4896423936917076, |
| "learning_rate": 4.095171164889143e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9796406477689743, |
| "step": 1646 |
| }, |
| { |
| "epoch": 9.633431085043988, |
| "grad_norm": 0.36707664122576916, |
| "learning_rate": 4.091681912154903e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9778028726577759, |
| "step": 1647 |
| }, |
| { |
| "epoch": 9.639296187683284, |
| "grad_norm": 0.483706919881383, |
| "learning_rate": 4.088257659382619e-06, |
| "loss": 0.0805, |
| "mean_token_accuracy": 0.9733972549438477, |
| "step": 1648 |
| }, |
| { |
| "epoch": 9.64516129032258, |
| "grad_norm": 0.49231494455117975, |
| "learning_rate": 4.0848984190009495e-06, |
| "loss": 0.0679, |
| "mean_token_accuracy": 0.9761296063661575, |
| "step": 1649 |
| }, |
| { |
| "epoch": 9.651026392961876, |
| "grad_norm": 0.3301630427949935, |
| "learning_rate": 4.081604203202577e-06, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9833341687917709, |
| "step": 1650 |
| }, |
| { |
| "epoch": 9.656891495601172, |
| "grad_norm": 0.3566237115058431, |
| "learning_rate": 4.078375023944175e-06, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9809886366128922, |
| "step": 1651 |
| }, |
| { |
| "epoch": 9.662756598240469, |
| "grad_norm": 0.42277619963529384, |
| "learning_rate": 4.0752108929463625e-06, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9733963310718536, |
| "step": 1652 |
| }, |
| { |
| "epoch": 9.668621700879765, |
| "grad_norm": 0.46959145501834476, |
| "learning_rate": 4.072111821693655e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9796183854341507, |
| "step": 1653 |
| }, |
| { |
| "epoch": 9.674486803519061, |
| "grad_norm": 0.40768391294874307, |
| "learning_rate": 4.069077821434429e-06, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9786179140210152, |
| "step": 1654 |
| }, |
| { |
| "epoch": 9.680351906158357, |
| "grad_norm": 0.4324953028254213, |
| "learning_rate": 4.06610890318088e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9801836982369423, |
| "step": 1655 |
| }, |
| { |
| "epoch": 9.686217008797653, |
| "grad_norm": 0.3104747760584785, |
| "learning_rate": 4.063205077708986e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.980313815176487, |
| "step": 1656 |
| }, |
| { |
| "epoch": 9.69208211143695, |
| "grad_norm": 0.45565777906402427, |
| "learning_rate": 4.060366355558456e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9771944209933281, |
| "step": 1657 |
| }, |
| { |
| "epoch": 9.697947214076246, |
| "grad_norm": 0.40108477777956064, |
| "learning_rate": 4.057592747032707e-06, |
| "loss": 0.0757, |
| "mean_token_accuracy": 0.9765976965427399, |
| "step": 1658 |
| }, |
| { |
| "epoch": 9.703812316715542, |
| "grad_norm": 0.4160024663073042, |
| "learning_rate": 4.054884262198816e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9806254580616951, |
| "step": 1659 |
| }, |
| { |
| "epoch": 9.709677419354838, |
| "grad_norm": 0.32521915471745955, |
| "learning_rate": 4.052240910887493e-06, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9815412387251854, |
| "step": 1660 |
| }, |
| { |
| "epoch": 9.715542521994134, |
| "grad_norm": 0.36235203791702825, |
| "learning_rate": 4.049662702693031e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.979137234389782, |
| "step": 1661 |
| }, |
| { |
| "epoch": 9.72140762463343, |
| "grad_norm": 0.4092475894856, |
| "learning_rate": 4.047149646973288e-06, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9769327864050865, |
| "step": 1662 |
| }, |
| { |
| "epoch": 9.727272727272727, |
| "grad_norm": 0.38561476103820486, |
| "learning_rate": 4.044701752849639e-06, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9809937924146652, |
| "step": 1663 |
| }, |
| { |
| "epoch": 9.733137829912023, |
| "grad_norm": 0.35666343819836077, |
| "learning_rate": 4.042319029206954e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9806043654680252, |
| "step": 1664 |
| }, |
| { |
| "epoch": 9.739002932551319, |
| "grad_norm": 0.3515754455773045, |
| "learning_rate": 4.040001484693553e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9808334335684776, |
| "step": 1665 |
| }, |
| { |
| "epoch": 9.744868035190615, |
| "grad_norm": 0.42662693644488175, |
| "learning_rate": 4.037749127721191e-06, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.980788104236126, |
| "step": 1666 |
| }, |
| { |
| "epoch": 9.750733137829911, |
| "grad_norm": 0.3414509899736225, |
| "learning_rate": 4.03556196646501e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9821551591157913, |
| "step": 1667 |
| }, |
| { |
| "epoch": 9.756598240469208, |
| "grad_norm": 0.38406704462610125, |
| "learning_rate": 4.033440008863528e-06, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9784510284662247, |
| "step": 1668 |
| }, |
| { |
| "epoch": 9.762463343108504, |
| "grad_norm": 0.39541896479899535, |
| "learning_rate": 4.031383262618588e-06, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9789265245199203, |
| "step": 1669 |
| }, |
| { |
| "epoch": 9.7683284457478, |
| "grad_norm": 0.44476429549220314, |
| "learning_rate": 4.0293917351953505e-06, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9808274731040001, |
| "step": 1670 |
| }, |
| { |
| "epoch": 9.774193548387096, |
| "grad_norm": 0.3761626945474277, |
| "learning_rate": 4.027465433822255e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9801682159304619, |
| "step": 1671 |
| }, |
| { |
| "epoch": 9.780058651026392, |
| "grad_norm": 0.3849732857892804, |
| "learning_rate": 4.025604365490999e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9807082116603851, |
| "step": 1672 |
| }, |
| { |
| "epoch": 9.785923753665688, |
| "grad_norm": 0.3654616184162646, |
| "learning_rate": 4.0238085369565085e-06, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9807479158043861, |
| "step": 1673 |
| }, |
| { |
| "epoch": 9.791788856304985, |
| "grad_norm": 0.36013060483944914, |
| "learning_rate": 4.022077954736916e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9814224913716316, |
| "step": 1674 |
| }, |
| { |
| "epoch": 9.79765395894428, |
| "grad_norm": 0.4312325517010621, |
| "learning_rate": 4.020412625113535e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9808504059910774, |
| "step": 1675 |
| }, |
| { |
| "epoch": 9.803519061583577, |
| "grad_norm": 0.4150291627126331, |
| "learning_rate": 4.018812554130839e-06, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9782455414533615, |
| "step": 1676 |
| }, |
| { |
| "epoch": 9.809384164222873, |
| "grad_norm": 0.4560487035026618, |
| "learning_rate": 4.01727774759644e-06, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9782388657331467, |
| "step": 1677 |
| }, |
| { |
| "epoch": 9.81524926686217, |
| "grad_norm": 0.4118036587851704, |
| "learning_rate": 4.0158082110810695e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9800616651773453, |
| "step": 1678 |
| }, |
| { |
| "epoch": 9.821114369501466, |
| "grad_norm": 0.3973369869246667, |
| "learning_rate": 4.014403949918545e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9799008816480637, |
| "step": 1679 |
| }, |
| { |
| "epoch": 9.826979472140762, |
| "grad_norm": 0.41088958891964444, |
| "learning_rate": 4.0130649692057715e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9786461591720581, |
| "step": 1680 |
| }, |
| { |
| "epoch": 9.832844574780058, |
| "grad_norm": 0.4143453814451513, |
| "learning_rate": 4.01179127380271e-06, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9771526828408241, |
| "step": 1681 |
| }, |
| { |
| "epoch": 9.838709677419354, |
| "grad_norm": 0.380721992706745, |
| "learning_rate": 4.010582868332353e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9828857779502869, |
| "step": 1682 |
| }, |
| { |
| "epoch": 9.84457478005865, |
| "grad_norm": 0.39817461806336085, |
| "learning_rate": 4.009439757180732e-06, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9773422405123711, |
| "step": 1683 |
| }, |
| { |
| "epoch": 9.850439882697946, |
| "grad_norm": 0.4300740276902467, |
| "learning_rate": 4.008361944496875e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9794062152504921, |
| "step": 1684 |
| }, |
| { |
| "epoch": 9.856304985337243, |
| "grad_norm": 0.44892781542634275, |
| "learning_rate": 4.00734943419281e-06, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9764518886804581, |
| "step": 1685 |
| }, |
| { |
| "epoch": 9.862170087976539, |
| "grad_norm": 0.44639082159205296, |
| "learning_rate": 4.006402229943534e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9779683649539948, |
| "step": 1686 |
| }, |
| { |
| "epoch": 9.868035190615835, |
| "grad_norm": 0.3674527728427102, |
| "learning_rate": 4.005520335187023e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9792613238096237, |
| "step": 1687 |
| }, |
| { |
| "epoch": 9.873900293255131, |
| "grad_norm": 0.4474897338230872, |
| "learning_rate": 4.004703753124195e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9801800698041916, |
| "step": 1688 |
| }, |
| { |
| "epoch": 9.879765395894427, |
| "grad_norm": 0.36367963546103926, |
| "learning_rate": 4.003952486718913e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9815207943320274, |
| "step": 1689 |
| }, |
| { |
| "epoch": 9.885630498533724, |
| "grad_norm": 0.35053871103024664, |
| "learning_rate": 4.003266538697973e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9800309017300606, |
| "step": 1690 |
| }, |
| { |
| "epoch": 9.89149560117302, |
| "grad_norm": 0.3548403767867107, |
| "learning_rate": 4.002645911551086e-06, |
| "loss": 0.055, |
| "mean_token_accuracy": 0.9804805964231491, |
| "step": 1691 |
| }, |
| { |
| "epoch": 9.897360703812316, |
| "grad_norm": 0.355690224320949, |
| "learning_rate": 4.002090607530882e-06, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9794489368796349, |
| "step": 1692 |
| }, |
| { |
| "epoch": 9.903225806451612, |
| "grad_norm": 0.41235923928942947, |
| "learning_rate": 4.001600628652887e-06, |
| "loss": 0.0745, |
| "mean_token_accuracy": 0.974931038916111, |
| "step": 1693 |
| }, |
| { |
| "epoch": 9.909090909090908, |
| "grad_norm": 0.41724843581429083, |
| "learning_rate": 4.001175976695527e-06, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9750220105051994, |
| "step": 1694 |
| }, |
| { |
| "epoch": 9.914956011730204, |
| "grad_norm": 0.4054950367550597, |
| "learning_rate": 4.000816653200117e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9841560870409012, |
| "step": 1695 |
| }, |
| { |
| "epoch": 9.9208211143695, |
| "grad_norm": 0.3962265652117708, |
| "learning_rate": 4.000522659470857e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9802296236157417, |
| "step": 1696 |
| }, |
| { |
| "epoch": 9.926686217008797, |
| "grad_norm": 0.48407966179185175, |
| "learning_rate": 4.000293996574826e-06, |
| "loss": 0.0788, |
| "mean_token_accuracy": 0.9757120013237, |
| "step": 1697 |
| }, |
| { |
| "epoch": 9.932551319648093, |
| "grad_norm": 0.445480333364879, |
| "learning_rate": 4.000130665341977e-06, |
| "loss": 0.0739, |
| "mean_token_accuracy": 0.976716510951519, |
| "step": 1698 |
| }, |
| { |
| "epoch": 9.93841642228739, |
| "grad_norm": 0.3844841575441866, |
| "learning_rate": 4.000032666365136e-06, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9814257994294167, |
| "step": 1699 |
| }, |
| { |
| "epoch": 9.944281524926687, |
| "grad_norm": 0.36797610892426286, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9790479391813278, |
| "step": 1700 |
| }, |
| { |
| "epoch": 9.944281524926687, |
| "step": 1700, |
| "total_flos": 16679922416640.0, |
| "train_loss": 0.20836789276889142, |
| "train_runtime": 36621.1179, |
| "train_samples_per_second": 1.49, |
| "train_steps_per_second": 0.046 |
| } |
| ], |
| "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": 16679922416640.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
