| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9230769230769231, | |
| "eval_steps": 20, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.5e-06, | |
| "loss": 1.977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.3e-05, | |
| "loss": 2.1076, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9499999999999996e-05, | |
| "loss": 1.9238, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.6e-05, | |
| "loss": 2.2224, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.25e-05, | |
| "loss": 2.198, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.899999999999999e-05, | |
| "loss": 2.1477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.5499999999999995e-05, | |
| "loss": 2.0655, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.2e-05, | |
| "loss": 2.1448, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5.85e-05, | |
| "loss": 2.1936, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.5e-05, | |
| "loss": 2.201, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.499590914940094e-05, | |
| "loss": 2.169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.49836376274535e-05, | |
| "loss": 2.0327, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.496318852344776e-05, | |
| "loss": 2.2921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.493456698533623e-05, | |
| "loss": 2.0172, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.489778021843813e-05, | |
| "loss": 2.232, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 6.485283748362525e-05, | |
| "loss": 1.9163, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 6.479975009499076e-05, | |
| "loss": 2.0446, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 6.473853141700085e-05, | |
| "loss": 2.005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.466919686113032e-05, | |
| "loss": 2.1004, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.45917638819828e-05, | |
| "loss": 2.308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 2.1830556392669678, | |
| "eval_runtime": 2.6888, | |
| "eval_samples_per_second": 4.091, | |
| "eval_steps_per_second": 0.744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.450625197289675e-05, | |
| "loss": 2.119, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.441268266103796e-05, | |
| "loss": 2.1047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 6.43110795019803e-05, | |
| "loss": 2.0454, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 6.420146807377572e-05, | |
| "loss": 2.0439, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 6.408387597051511e-05, | |
| "loss": 2.0833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.395833279538157e-05, | |
| "loss": 1.9844, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6.382487015319812e-05, | |
| "loss": 2.1317, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.368352164247117e-05, | |
| "loss": 2.2273, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 6.35343228469324e-05, | |
| "loss": 2.1833, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.337731132658071e-05, | |
| "loss": 2.0888, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.321252660822672e-05, | |
| "loss": 2.0598, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.304001017554202e-05, | |
| "loss": 2.0894, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.285980545861596e-05, | |
| "loss": 2.0645, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.267195782302235e-05, | |
| "loss": 2.123, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.247651455839889e-05, | |
| "loss": 2.1683, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.227352486654226e-05, | |
| "loss": 2.2418, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.206303984902185e-05, | |
| "loss": 2.0361, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.184511249431519e-05, | |
| "loss": 1.9246, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.16197976644684e-05, | |
| "loss": 1.9607, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.138715208128501e-05, | |
| "loss": 2.1105, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 2.1629483699798584, | |
| "eval_runtime": 2.6976, | |
| "eval_samples_per_second": 4.078, | |
| "eval_steps_per_second": 0.741, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.114723431204641e-05, | |
| "loss": 2.1141, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.090010475476801e-05, | |
| "loss": 2.1362, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.0645825622994254e-05, | |
| "loss": 1.9861, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.038446093013675e-05, | |
| "loss": 2.0427, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.011607647335922e-05, | |
| "loss": 2.0936, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.9840739817013386e-05, | |
| "loss": 2.1971, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.955852027563006e-05, | |
| "loss": 2.033, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.9269488896469564e-05, | |
| "loss": 2.1994, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.897371844163591e-05, | |
| "loss": 2.0339, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.86712833697594e-05, | |
| "loss": 2.0523, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.8362259817252044e-05, | |
| "loss": 2.0054, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.8046725579140586e-05, | |
| "loss": 2.0617, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.772476008948209e-05, | |
| "loss": 2.0812, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.739644440136678e-05, | |
| "loss": 1.993, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.706186116651339e-05, | |
| "loss": 2.0843, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.6721094614462025e-05, | |
| "loss": 2.2769, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.637423053136982e-05, | |
| "loss": 2.0877, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.6021356238414775e-05, | |
| "loss": 1.995, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.5662560569813045e-05, | |
| "loss": 2.0595, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.5297933850455436e-05, | |
| "loss": 2.0496, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.146815299987793, | |
| "eval_runtime": 2.6998, | |
| "eval_samples_per_second": 4.074, | |
| "eval_steps_per_second": 0.741, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.492756787316864e-05, | |
| "loss": 2.0805, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.455155587560679e-05, | |
| "loss": 2.055, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.416999251677947e-05, | |
| "loss": 2.1191, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.3782973853221766e-05, | |
| "loss": 2.0373, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.339059731481252e-05, | |
| "loss": 1.9465, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 5.2992961680246975e-05, | |
| "loss": 2.0444, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.259016705216966e-05, | |
| "loss": 2.1411, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.218231483197416e-05, | |
| "loss": 2.0416, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.176950769427582e-05, | |
| "loss": 1.9937, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.135184956106394e-05, | |
| "loss": 2.0153, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.092944557554004e-05, | |
| "loss": 1.9772, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.0502402075648585e-05, | |
| "loss": 2.0616, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.007082656730692e-05, | |
| "loss": 2.0015, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.963482769734132e-05, | |
| "loss": 1.951, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.9194515226135705e-05, | |
| "loss": 2.0443, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.874999999999999e-05, | |
| "loss": 2.0238, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.830139392326523e-05, | |
| "loss": 1.9664, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.784880993011219e-05, | |
| "loss": 2.0828, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.739236195614084e-05, | |
| "loss": 2.0008, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.6932164909687655e-05, | |
| "loss": 2.0787, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 2.13932204246521, | |
| "eval_runtime": 2.7011, | |
| "eval_samples_per_second": 4.072, | |
| "eval_steps_per_second": 0.74, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.646833464289808e-05, | |
| "loss": 2.0961, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.600098792256131e-05, | |
| "loss": 1.986, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.5530242400714944e-05, | |
| "loss": 2.1558, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.505621658502667e-05, | |
| "loss": 1.9636, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.457902980896064e-05, | |
| "loss": 2.0659, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.409880220173583e-05, | |
| "loss": 2.0239, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.3615654658084234e-05, | |
| "loss": 2.0932, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.3129708807816206e-05, | |
| "loss": 1.8754, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.264108698520082e-05, | |
| "loss": 2.0868, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.2149912198168935e-05, | |
| "loss": 2.0433, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.1656308097346466e-05, | |
| "loss": 2.1271, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.116039894492613e-05, | |
| "loss": 2.1713, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.066230958338507e-05, | |
| "loss": 2.021, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.0162165404056384e-05, | |
| "loss": 2.021, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.9660092315562566e-05, | |
| "loss": 2.0075, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.91562167121187e-05, | |
| "loss": 2.0444, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.8650665441713327e-05, | |
| "loss": 1.9967, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.814356577417524e-05, | |
| "loss": 2.2019, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.763504536913387e-05, | |
| "loss": 1.936, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.712523224388177e-05, | |
| "loss": 1.9272, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.134587287902832, | |
| "eval_runtime": 2.7065, | |
| "eval_samples_per_second": 4.064, | |
| "eval_steps_per_second": 0.739, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.661425474114685e-05, | |
| "loss": 1.9903, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.610224149678286e-05, | |
| "loss": 2.1719, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.558932140738593e-05, | |
| "loss": 1.9709, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.507562359784562e-05, | |
| "loss": 2.098, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.456127738883834e-05, | |
| "loss": 2.21, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.404641226427163e-05, | |
| "loss": 2.0854, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.3531157838687204e-05, | |
| "loss": 2.0356, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.301564382463126e-05, | |
| "loss": 2.0967, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.25e-05, | |
| "loss": 1.9079, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.198435617536874e-05, | |
| "loss": 1.9948, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.1468842161312804e-05, | |
| "loss": 2.0195, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.095358773572837e-05, | |
| "loss": 2.0118, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.043872261116165e-05, | |
| "loss": 1.981, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.992437640215437e-05, | |
| "loss": 2.0501, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.9410678592614068e-05, | |
| "loss": 2.001, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.8897758503217142e-05, | |
| "loss": 2.0048, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.838574525885314e-05, | |
| "loss": 2.0039, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.7874767756118234e-05, | |
| "loss": 2.0204, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.7364954630866125e-05, | |
| "loss": 2.1493, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.6856434225824763e-05, | |
| "loss": 2.0527, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.132925271987915, | |
| "eval_runtime": 2.7003, | |
| "eval_samples_per_second": 4.074, | |
| "eval_steps_per_second": 0.741, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.6349334558286678e-05, | |
| "loss": 2.0877, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.5843783287881306e-05, | |
| "loss": 2.0201, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.5339907684437425e-05, | |
| "loss": 2.0471, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.4837834595943607e-05, | |
| "loss": 1.94, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.4337690416614925e-05, | |
| "loss": 1.9542, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.3839601055073866e-05, | |
| "loss": 2.0596, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.3343691902653532e-05, | |
| "loss": 1.9224, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.2850087801831076e-05, | |
| "loss": 2.0356, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.235891301479917e-05, | |
| "loss": 1.9185, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.1870291192183795e-05, | |
| "loss": 1.9719, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.1384345341915767e-05, | |
| "loss": 2.0634, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.0901197798264166e-05, | |
| "loss": 2.0109, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.0420970191039358e-05, | |
| "loss": 1.9339, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.9943783414973313e-05, | |
| "loss": 1.941, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.946975759928506e-05, | |
| "loss": 2.0228, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.899901207743869e-05, | |
| "loss": 2.0524, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.853166535710192e-05, | |
| "loss": 2.0208, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.806783509031234e-05, | |
| "loss": 1.951, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.760763804385916e-05, | |
| "loss": 2.031, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.7151190069887813e-05, | |
| "loss": 1.9507, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 2.131213903427124, | |
| "eval_runtime": 2.7, | |
| "eval_samples_per_second": 4.074, | |
| "eval_steps_per_second": 0.741, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.669860607673477e-05, | |
| "loss": 2.1314, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.6250000000000005e-05, | |
| "loss": 2.0099, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.5805484773864303e-05, | |
| "loss": 1.9891, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.536517230265867e-05, | |
| "loss": 2.0866, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.4929173432693088e-05, | |
| "loss": 2.0756, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.4497597924351416e-05, | |
| "loss": 2.02, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.4070554424459953e-05, | |
| "loss": 1.9735, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.3648150438936062e-05, | |
| "loss": 1.9393, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.3230492305724189e-05, | |
| "loss": 1.996, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.2817685168025838e-05, | |
| "loss": 2.0682, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.2409832947830327e-05, | |
| "loss": 1.9507, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.2007038319753028e-05, | |
| "loss": 2.047, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.160940268518747e-05, | |
| "loss": 1.9346, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.1217026146778237e-05, | |
| "loss": 2.0893, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0830007483220525e-05, | |
| "loss": 2.0265, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0448444124393207e-05, | |
| "loss": 1.9353, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.0072432126831366e-05, | |
| "loss": 1.9521, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.702066149544555e-06, | |
| "loss": 2.19, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.337439430186965e-06, | |
| "loss": 1.9153, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.978643761585217e-06, | |
| "loss": 2.1624, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 2.1307220458984375, | |
| "eval_runtime": 2.6925, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.743, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.62576946863017e-06, | |
| "loss": 2.1008, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.278905385537973e-06, | |
| "loss": 2.1097, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.938138833486609e-06, | |
| "loss": 1.9106, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.603555598633218e-06, | |
| "loss": 2.0616, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 7.275239910517899e-06, | |
| "loss": 2.0454, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.953274420859412e-06, | |
| "loss": 1.9152, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.637740182747952e-06, | |
| "loss": 1.9445, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 6.328716630240594e-06, | |
| "loss": 2.104, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 6.026281558364088e-06, | |
| "loss": 1.9787, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.730511103530437e-06, | |
| "loss": 2.0444, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.441479724369932e-06, | |
| "loss": 2.0611, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.159260182986607e-06, | |
| "loss": 2.2581, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.8839235266407855e-06, | |
| "loss": 2.0463, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.615539069863245e-06, | |
| "loss": 1.9841, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.3541743770057415e-06, | |
| "loss": 2.0033, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.0998952452319895e-06, | |
| "loss": 2.0378, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.852765687953586e-06, | |
| "loss": 1.9281, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.61284791871499e-06, | |
| "loss": 1.9945, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.3802023355315877e-06, | |
| "loss": 2.0826, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.154887505684815e-06, | |
| "loss": 2.022, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 2.1296370029449463, | |
| "eval_runtime": 2.696, | |
| "eval_samples_per_second": 4.08, | |
| "eval_steps_per_second": 0.742, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.9369601509781503e-06, | |
| "loss": 1.9314, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.7264751334577383e-06, | |
| "loss": 1.9625, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.5234854416011093e-06, | |
| "loss": 2.0141, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.3280421769776413e-06, | |
| "loss": 1.993, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.1401945413840336e-06, | |
| "loss": 2.0547, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.9599898244579795e-06, | |
| "loss": 2.0251, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.787473391773275e-06, | |
| "loss": 1.996, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.6226886734192767e-06, | |
| "loss": 2.0519, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.465677153067599e-06, | |
| "loss": 1.9686, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.316478357528839e-06, | |
| "loss": 2.0438, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.1751298468018836e-06, | |
| "loss": 2.1263, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.0416672046184219e-06, | |
| "loss": 2.0243, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 9.161240294848962e-07, | |
| "loss": 2.0935, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.98531926224271e-07, | |
| "loss": 1.9486, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.889204980196944e-07, | |
| "loss": 1.9792, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 5.873173389620319e-07, | |
| "loss": 2.0178, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.937480271032393e-07, | |
| "loss": 2.0261, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.0823611801718557e-07, | |
| "loss": 2.0456, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.308031388696877e-07, | |
| "loss": 2.0252, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.614685829991514e-07, | |
| "loss": 2.1779, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 2.1300740242004395, | |
| "eval_runtime": 2.6976, | |
| "eval_samples_per_second": 4.078, | |
| "eval_steps_per_second": 0.741, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 208, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "total_flos": 1.6306868494270464e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |