| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4807692307692308, | |
| "eval_steps": 20, | |
| "global_step": 50, | |
| "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 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 208, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "total_flos": 4.026368678218957e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |