| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "global_step": 1410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8e-05, | |
| "loss": 3.4965, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.779850721359253, | |
| "eval_runtime": 23.1518, | |
| "eval_samples_per_second": 8.639, | |
| "eval_steps_per_second": 1.08, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4526, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.738048791885376, | |
| "eval_runtime": 24.2844, | |
| "eval_samples_per_second": 8.236, | |
| "eval_steps_per_second": 1.029, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4012, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.6721441745758057, | |
| "eval_runtime": 23.2045, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 1.077, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2776, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.6650607585906982, | |
| "eval_runtime": 24.0682, | |
| "eval_samples_per_second": 8.31, | |
| "eval_steps_per_second": 1.039, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.2164, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.6554956436157227, | |
| "eval_runtime": 22.8547, | |
| "eval_samples_per_second": 8.751, | |
| "eval_steps_per_second": 1.094, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2701, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.648871421813965, | |
| "eval_runtime": 23.3072, | |
| "eval_samples_per_second": 8.581, | |
| "eval_steps_per_second": 1.073, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1847, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.699300765991211, | |
| "eval_runtime": 22.1301, | |
| "eval_samples_per_second": 9.037, | |
| "eval_steps_per_second": 1.13, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0959, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.636422634124756, | |
| "eval_runtime": 21.8919, | |
| "eval_samples_per_second": 9.136, | |
| "eval_steps_per_second": 1.142, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0506, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.6463677883148193, | |
| "eval_runtime": 22.9819, | |
| "eval_samples_per_second": 8.702, | |
| "eval_steps_per_second": 1.088, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.0497, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.63041615486145, | |
| "eval_runtime": 23.2242, | |
| "eval_samples_per_second": 8.612, | |
| "eval_steps_per_second": 1.076, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 3.0767, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.634387254714966, | |
| "eval_runtime": 23.8188, | |
| "eval_samples_per_second": 8.397, | |
| "eval_steps_per_second": 1.05, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0397, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.6142303943634033, | |
| "eval_runtime": 23.2502, | |
| "eval_samples_per_second": 8.602, | |
| "eval_steps_per_second": 1.075, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.982, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.678748369216919, | |
| "eval_runtime": 22.8778, | |
| "eval_samples_per_second": 8.742, | |
| "eval_steps_per_second": 1.093, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.883, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.6491620540618896, | |
| "eval_runtime": 22.7109, | |
| "eval_samples_per_second": 8.806, | |
| "eval_steps_per_second": 1.101, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8978, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 2.631659507751465, | |
| "eval_runtime": 23.5813, | |
| "eval_samples_per_second": 8.481, | |
| "eval_steps_per_second": 1.06, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 1410, | |
| "total_flos": 3.4352702816256e+17, | |
| "train_loss": 0.9919471253740026, | |
| "train_runtime": 710.2043, | |
| "train_samples_per_second": 15.841, | |
| "train_steps_per_second": 1.985 | |
| } | |
| ], | |
| "max_steps": 1410, | |
| "num_train_epochs": 15, | |
| "total_flos": 3.4352702816256e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |