| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9615384615384616, | |
| "eval_steps": 20, | |
| "global_step": 100, | |
| "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 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 208, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "total_flos": 8.151676451238707e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |