| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.999723718745683, | |
| "eval_steps": 10000, | |
| "global_step": 7238, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.338094023943002e-05, | |
| "loss": 1.5026, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 6.603029607687671e-05, | |
| "loss": 1.0126, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.391351098441528e-05, | |
| "loss": 0.8935, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1723804473876953, | |
| "eval_runtime": 3.4877, | |
| "eval_samples_per_second": 266.368, | |
| "eval_steps_per_second": 33.547, | |
| "step": 3619 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.669047011971501e-05, | |
| "loss": 0.7477, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.1761226035642205e-05, | |
| "loss": 0.5614, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.812260921465546e-05, | |
| "loss": 0.5577, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.529467786670231e-05, | |
| "loss": 0.55, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.163663625717163, | |
| "eval_runtime": 3.486, | |
| "eval_samples_per_second": 266.491, | |
| "eval_steps_per_second": 33.562, | |
| "step": 7238 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 7238, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 2.4227471261279846e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |