| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.9504950495049505, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6674917491749177e-05, | |
| "loss": 1.9722, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.093264102935791, | |
| "eval_runtime": 1.5252, | |
| "eval_samples_per_second": 1433.916, | |
| "eval_steps_per_second": 45.24, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3349834983498351e-05, | |
| "loss": 1.9372, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9881993532180786, | |
| "eval_runtime": 1.5777, | |
| "eval_samples_per_second": 1386.229, | |
| "eval_steps_per_second": 43.736, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.0024752475247525e-05, | |
| "loss": 1.9278, | |
| "step": 1209 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.013523578643799, | |
| "eval_runtime": 1.6453, | |
| "eval_samples_per_second": 1329.222, | |
| "eval_steps_per_second": 41.937, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 6.6996699669967e-06, | |
| "loss": 1.9295, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.9506467580795288, | |
| "eval_runtime": 1.7203, | |
| "eval_samples_per_second": 1271.257, | |
| "eval_steps_per_second": 40.108, | |
| "step": 1616 | |
| } | |
| ], | |
| "max_steps": 2424, | |
| "num_train_epochs": 6, | |
| "total_flos": 2119255202506752.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |