| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.45724737082761774, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.99484069051768e-06, | |
| "loss": 0.672, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.979374592503753e-06, | |
| "loss": 0.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.953637170129838e-06, | |
| "loss": 0.1594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.917687439985847e-06, | |
| "loss": 0.122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.87160783575339e-06, | |
| "loss": 0.0956, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.815504019183158e-06, | |
| "loss": 0.102, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.749504637809742e-06, | |
| "loss": 0.0888, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.673761029959426e-06, | |
| "loss": 0.097, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.588446877727417e-06, | |
| "loss": 0.0968, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.493757808720196e-06, | |
| "loss": 0.0808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 3.0685205274494365e-05, | |
| "eval_runtime": 30.877, | |
| "eval_samples_per_second": 141.659, | |
| "eval_steps_per_second": 23.61, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.389910947476252e-06, | |
| "loss": 0.0797, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.277144417593776e-06, | |
| "loss": 0.0933, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.155716795706948e-06, | |
| "loss": 0.084, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.02590651856289e-06, | |
| "loss": 0.0605, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.88801124455883e-06, | |
| "loss": 0.0746, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.742347171203542e-06, | |
| "loss": 0.1016, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.589248310068091e-06, | |
| "loss": 0.0919, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.429065720888471e-06, | |
| "loss": 0.1076, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.262166706576352e-06, | |
| "loss": 0.0586, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.088933970983793e-06, | |
| "loss": 0.0682, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 9.85040060186293e-06, | |
| "eval_runtime": 31.5055, | |
| "eval_samples_per_second": 138.833, | |
| "eval_steps_per_second": 23.139, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.909764741353188e-06, | |
| "loss": 0.069, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.7250698574647064e-06, | |
| "loss": 0.0483, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.5352728295698045e-06, | |
| "loss": 0.0639, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.340808867271031e-06, | |
| "loss": 0.0865, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.142123881574899e-06, | |
| "loss": 0.0861, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.939673462406165e-06, | |
| "loss": 0.0805, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.7339218339280815e-06, | |
| "loss": 0.0751, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.52534079006412e-06, | |
| "loss": 0.0687, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.314408612662028e-06, | |
| "loss": 0.092, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.101608974780918e-06, | |
| "loss": 0.0718, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.04687363395351e-06, | |
| "eval_runtime": 30.7873, | |
| "eval_samples_per_second": 142.071, | |
| "eval_steps_per_second": 23.679, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 656, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |