| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 477, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.7217, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6864463686943054, | |
| "eval_runtime": 1.553, | |
| "eval_samples_per_second": 45.719, | |
| "eval_steps_per_second": 5.795, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.7056, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6868877410888672, | |
| "eval_runtime": 1.5642, | |
| "eval_samples_per_second": 45.391, | |
| "eval_steps_per_second": 5.754, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.706, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6874909400939941, | |
| "eval_runtime": 1.5577, | |
| "eval_samples_per_second": 45.58, | |
| "eval_steps_per_second": 5.778, | |
| "step": 477 | |
| } | |
| ], | |
| "max_steps": 795, | |
| "num_train_epochs": 5, | |
| "total_flos": 1191798669219840.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |