| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.992, |
| "global_step": 186, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 4.973118279569893e-05, |
| "loss": 1.0487, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 4.9462365591397855e-05, |
| "loss": 0.4173, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 4.9193548387096775e-05, |
| "loss": 0.3554, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.89247311827957e-05, |
| "loss": 0.2972, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 4.865591397849463e-05, |
| "loss": 0.2958, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 4.8387096774193554e-05, |
| "loss": 0.2668, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 4.811827956989248e-05, |
| "loss": 0.2609, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 4.78494623655914e-05, |
| "loss": 0.2561, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 4.7580645161290326e-05, |
| "loss": 0.2567, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 4.731182795698925e-05, |
| "loss": 0.2422, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 4.704301075268818e-05, |
| "loss": 0.236, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 4.67741935483871e-05, |
| "loss": 0.2299, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 4.650537634408602e-05, |
| "loss": 0.2255, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 4.6236559139784944e-05, |
| "loss": 0.2212, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 4.596774193548387e-05, |
| "loss": 0.2031, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 4.56989247311828e-05, |
| "loss": 0.2157, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 4.543010752688172e-05, |
| "loss": 0.192, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 4.516129032258064e-05, |
| "loss": 0.2297, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 4.489247311827957e-05, |
| "loss": 0.2266, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 4.4623655913978496e-05, |
| "loss": 0.1764, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 0.2303156703710556, |
| "eval_runtime": 771.203, |
| "eval_samples_per_second": 460.457, |
| "eval_steps_per_second": 57.558, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 4.435483870967742e-05, |
| "loss": 0.2118, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 4.408602150537635e-05, |
| "loss": 0.2286, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 4.381720430107527e-05, |
| "loss": 0.1914, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 4.3548387096774194e-05, |
| "loss": 0.1766, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 4.327956989247312e-05, |
| "loss": 0.1839, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 4.301075268817205e-05, |
| "loss": 0.1815, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 4.2741935483870973e-05, |
| "loss": 0.1682, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 4.247311827956989e-05, |
| "loss": 0.1707, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 4.220430107526882e-05, |
| "loss": 0.1631, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 4.1935483870967746e-05, |
| "loss": 0.1576, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.1616, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 4.13978494623656e-05, |
| "loss": 0.157, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 4.112903225806452e-05, |
| "loss": 0.1506, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 4.0860215053763444e-05, |
| "loss": 0.1507, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 4.0591397849462364e-05, |
| "loss": 0.154, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 4.032258064516129e-05, |
| "loss": 0.1496, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.005376344086022e-05, |
| "loss": 0.1494, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 3.978494623655914e-05, |
| "loss": 0.1526, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 3.951612903225806e-05, |
| "loss": 0.1472, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3.924731182795699e-05, |
| "loss": 0.145, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 0.14696530997753143, |
| "eval_runtime": 771.7715, |
| "eval_samples_per_second": 460.118, |
| "eval_steps_per_second": 57.516, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.8978494623655915e-05, |
| "loss": 0.145, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 3.870967741935484e-05, |
| "loss": 0.1461, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 3.844086021505376e-05, |
| "loss": 0.1447, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 3.817204301075269e-05, |
| "loss": 0.1462, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 3.7903225806451614e-05, |
| "loss": 0.1391, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 3.763440860215054e-05, |
| "loss": 0.143, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3.736559139784947e-05, |
| "loss": 0.1388, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 3.7096774193548386e-05, |
| "loss": 0.1448, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 3.682795698924731e-05, |
| "loss": 0.141, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 3.655913978494624e-05, |
| "loss": 0.1412, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 3.6290322580645165e-05, |
| "loss": 0.14, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 3.602150537634409e-05, |
| "loss": 0.136, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 3.575268817204301e-05, |
| "loss": 0.1401, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 3.548387096774194e-05, |
| "loss": 0.137, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 3.5215053763440864e-05, |
| "loss": 0.1386, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3.494623655913979e-05, |
| "loss": 0.1348, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 3.467741935483872e-05, |
| "loss": 0.1352, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 3.4408602150537636e-05, |
| "loss": 0.1319, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 3.4139784946236556e-05, |
| "loss": 0.1329, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 3.387096774193548e-05, |
| "loss": 0.129, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 0.1321416050195694, |
| "eval_runtime": 771.9931, |
| "eval_samples_per_second": 459.986, |
| "eval_steps_per_second": 57.499, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 3.360215053763441e-05, |
| "loss": 0.1312, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.1328, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 3.306451612903226e-05, |
| "loss": 0.1941, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 3.279569892473118e-05, |
| "loss": 0.1338, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 3.252688172043011e-05, |
| "loss": 0.1349, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 3.2258064516129034e-05, |
| "loss": 0.1307, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 3.198924731182796e-05, |
| "loss": 0.129, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 3.172043010752688e-05, |
| "loss": 0.1308, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 3.1451612903225806e-05, |
| "loss": 0.1317, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 3.118279569892473e-05, |
| "loss": 0.1258, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 3.091397849462366e-05, |
| "loss": 0.1271, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 3.0645161290322585e-05, |
| "loss": 0.131, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 3.0376344086021508e-05, |
| "loss": 0.1274, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 3.010752688172043e-05, |
| "loss": 0.1269, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 2.9838709677419357e-05, |
| "loss": 0.1248, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 2.9569892473118284e-05, |
| "loss": 0.1286, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 2.9301075268817207e-05, |
| "loss": 0.1273, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 2.9032258064516133e-05, |
| "loss": 0.129, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 2.8763440860215056e-05, |
| "loss": 0.1291, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 2.8494623655913982e-05, |
| "loss": 0.1256, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.29, |
| "eval_loss": 0.126514732837677, |
| "eval_runtime": 772.8684, |
| "eval_samples_per_second": 459.465, |
| "eval_steps_per_second": 57.434, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 2.822580645161291e-05, |
| "loss": 0.1245, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 2.7956989247311828e-05, |
| "loss": 0.1269, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 2.768817204301075e-05, |
| "loss": 0.1297, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 2.7419354838709678e-05, |
| "loss": 0.1273, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 2.71505376344086e-05, |
| "loss": 0.1231, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 2.6881720430107527e-05, |
| "loss": 0.1227, |
| "step": 86 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 2.661290322580645e-05, |
| "loss": 0.1275, |
| "step": 87 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 2.6344086021505376e-05, |
| "loss": 0.1244, |
| "step": 88 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 2.6075268817204303e-05, |
| "loss": 0.1298, |
| "step": 89 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 2.5806451612903226e-05, |
| "loss": 0.1246, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 2.5537634408602152e-05, |
| "loss": 0.1312, |
| "step": 91 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 2.5268817204301075e-05, |
| "loss": 0.1228, |
| "step": 92 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 2.5e-05, |
| "loss": 0.1283, |
| "step": 93 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 2.4731182795698928e-05, |
| "loss": 0.1271, |
| "step": 94 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 2.446236559139785e-05, |
| "loss": 0.126, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 2.4193548387096777e-05, |
| "loss": 0.1232, |
| "step": 96 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 2.39247311827957e-05, |
| "loss": 0.1259, |
| "step": 97 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 2.3655913978494626e-05, |
| "loss": 0.1262, |
| "step": 98 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 2.338709677419355e-05, |
| "loss": 0.1253, |
| "step": 99 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 2.3118279569892472e-05, |
| "loss": 0.1304, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.61, |
| "eval_loss": 0.1252489686012268, |
| "eval_runtime": 772.5528, |
| "eval_samples_per_second": 459.653, |
| "eval_steps_per_second": 57.458, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 2.28494623655914e-05, |
| "loss": 0.1267, |
| "step": 101 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 2.258064516129032e-05, |
| "loss": 0.1254, |
| "step": 102 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 2.2311827956989248e-05, |
| "loss": 0.1265, |
| "step": 103 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 2.2043010752688174e-05, |
| "loss": 0.1267, |
| "step": 104 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 2.1774193548387097e-05, |
| "loss": 0.1301, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 2.1505376344086024e-05, |
| "loss": 0.1229, |
| "step": 106 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 2.1236559139784946e-05, |
| "loss": 0.1254, |
| "step": 107 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 2.0967741935483873e-05, |
| "loss": 0.125, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 2.06989247311828e-05, |
| "loss": 0.1217, |
| "step": 109 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 2.0430107526881722e-05, |
| "loss": 0.1295, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 2.0161290322580645e-05, |
| "loss": 0.1268, |
| "step": 111 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 1.989247311827957e-05, |
| "loss": 0.1277, |
| "step": 112 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 1.9623655913978494e-05, |
| "loss": 0.1265, |
| "step": 113 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 1.935483870967742e-05, |
| "loss": 0.1244, |
| "step": 114 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 1.9086021505376344e-05, |
| "loss": 0.1275, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 1.881720430107527e-05, |
| "loss": 0.1267, |
| "step": 116 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 1.8548387096774193e-05, |
| "loss": 0.1224, |
| "step": 117 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 1.827956989247312e-05, |
| "loss": 0.1268, |
| "step": 118 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 1.8010752688172046e-05, |
| "loss": 0.1238, |
| "step": 119 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 1.774193548387097e-05, |
| "loss": 0.1235, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.93, |
| "eval_loss": 0.12599562108516693, |
| "eval_runtime": 771.9019, |
| "eval_samples_per_second": 460.04, |
| "eval_steps_per_second": 57.506, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 1.7473118279569895e-05, |
| "loss": 0.1225, |
| "step": 121 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 1.7204301075268818e-05, |
| "loss": 0.1245, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 1.693548387096774e-05, |
| "loss": 0.1284, |
| "step": 123 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.1251, |
| "step": 124 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 1.639784946236559e-05, |
| "loss": 0.1843, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 1.6129032258064517e-05, |
| "loss": 0.1263, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 1.586021505376344e-05, |
| "loss": 0.1284, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 1.5591397849462366e-05, |
| "loss": 0.1277, |
| "step": 128 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 1.5322580645161292e-05, |
| "loss": 0.1223, |
| "step": 129 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 1.5053763440860215e-05, |
| "loss": 0.1241, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 1.4784946236559142e-05, |
| "loss": 0.1233, |
| "step": 131 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 1.4516129032258066e-05, |
| "loss": 0.1222, |
| "step": 132 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 1.4247311827956991e-05, |
| "loss": 0.1195, |
| "step": 133 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 1.3978494623655914e-05, |
| "loss": 0.1267, |
| "step": 134 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 1.3709677419354839e-05, |
| "loss": 0.124, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 1.3440860215053763e-05, |
| "loss": 0.125, |
| "step": 136 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 1.3172043010752688e-05, |
| "loss": 0.1242, |
| "step": 137 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 1.2903225806451613e-05, |
| "loss": 0.1231, |
| "step": 138 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 1.2634408602150537e-05, |
| "loss": 0.1208, |
| "step": 139 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 1.2365591397849464e-05, |
| "loss": 0.125, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.26, |
| "eval_loss": 0.12610550224781036, |
| "eval_runtime": 771.1365, |
| "eval_samples_per_second": 460.497, |
| "eval_steps_per_second": 57.563, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 1.2096774193548388e-05, |
| "loss": 0.1235, |
| "step": 141 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 1.1827956989247313e-05, |
| "loss": 0.1267, |
| "step": 142 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 1.1559139784946236e-05, |
| "loss": 0.1244, |
| "step": 143 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 1.129032258064516e-05, |
| "loss": 0.1215, |
| "step": 144 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 1.1021505376344087e-05, |
| "loss": 0.1261, |
| "step": 145 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 1.0752688172043012e-05, |
| "loss": 0.1226, |
| "step": 146 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 1.0483870967741936e-05, |
| "loss": 0.1277, |
| "step": 147 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 1.0215053763440861e-05, |
| "loss": 0.1262, |
| "step": 148 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 9.946236559139786e-06, |
| "loss": 0.1248, |
| "step": 149 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 9.67741935483871e-06, |
| "loss": 0.1293, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 9.408602150537635e-06, |
| "loss": 0.1266, |
| "step": 151 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 9.13978494623656e-06, |
| "loss": 0.1276, |
| "step": 152 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 8.870967741935484e-06, |
| "loss": 0.1246, |
| "step": 153 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 8.602150537634409e-06, |
| "loss": 0.1263, |
| "step": 154 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.1251, |
| "step": 155 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 8.064516129032258e-06, |
| "loss": 0.1263, |
| "step": 156 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 7.795698924731183e-06, |
| "loss": 0.1285, |
| "step": 157 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 7.526881720430108e-06, |
| "loss": 0.1238, |
| "step": 158 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 7.258064516129033e-06, |
| "loss": 0.1261, |
| "step": 159 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 6.989247311827957e-06, |
| "loss": 0.1263, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.58, |
| "eval_loss": 0.12619347870349884, |
| "eval_runtime": 771.1616, |
| "eval_samples_per_second": 460.482, |
| "eval_steps_per_second": 57.561, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 6.720430107526882e-06, |
| "loss": 0.1228, |
| "step": 161 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 6.451612903225806e-06, |
| "loss": 0.1245, |
| "step": 162 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 6.182795698924732e-06, |
| "loss": 0.1229, |
| "step": 163 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 5.9139784946236566e-06, |
| "loss": 0.1216, |
| "step": 164 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 5.64516129032258e-06, |
| "loss": 0.1268, |
| "step": 165 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 5.376344086021506e-06, |
| "loss": 0.1237, |
| "step": 166 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 5.1075268817204305e-06, |
| "loss": 0.1251, |
| "step": 167 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 4.838709677419355e-06, |
| "loss": 0.1241, |
| "step": 168 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 4.56989247311828e-06, |
| "loss": 0.1247, |
| "step": 169 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 4.3010752688172045e-06, |
| "loss": 0.1241, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 4.032258064516129e-06, |
| "loss": 0.1242, |
| "step": 171 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 3.763440860215054e-06, |
| "loss": 0.1265, |
| "step": 172 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 3.4946236559139785e-06, |
| "loss": 0.1209, |
| "step": 173 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 3.225806451612903e-06, |
| "loss": 0.1234, |
| "step": 174 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 2.9569892473118283e-06, |
| "loss": 0.1231, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 2.688172043010753e-06, |
| "loss": 0.1274, |
| "step": 176 |
| }, |
| { |
| "epoch": 2.85, |
| "learning_rate": 2.4193548387096776e-06, |
| "loss": 0.1247, |
| "step": 177 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 2.1505376344086023e-06, |
| "loss": 0.1251, |
| "step": 178 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 1.881720430107527e-06, |
| "loss": 0.1229, |
| "step": 179 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 1.6129032258064516e-06, |
| "loss": 0.1244, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.9, |
| "eval_loss": 0.1256006360054016, |
| "eval_runtime": 771.5064, |
| "eval_samples_per_second": 460.276, |
| "eval_steps_per_second": 57.535, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 1.3440860215053765e-06, |
| "loss": 0.1266, |
| "step": 181 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 1.0752688172043011e-06, |
| "loss": 0.1213, |
| "step": 182 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 8.064516129032258e-07, |
| "loss": 0.1245, |
| "step": 183 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 5.376344086021506e-07, |
| "loss": 0.1244, |
| "step": 184 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 2.688172043010753e-07, |
| "loss": 0.1278, |
| "step": 185 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 0.0, |
| "loss": 0.1247, |
| "step": 186 |
| }, |
| { |
| "epoch": 2.99, |
| "step": 186, |
| "total_flos": 3.806816568043341e+17, |
| "train_loss": 0.1504179045798317, |
| "train_runtime": 22764.4166, |
| "train_samples_per_second": 65.892, |
| "train_steps_per_second": 0.008 |
| } |
| ], |
| "max_steps": 186, |
| "num_train_epochs": 3, |
| "total_flos": 3.806816568043341e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
