| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 8552, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.6700000000000002e-05, | |
| "loss": 0.6345, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6611062288284302, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7702, | |
| "eval_samples_per_second": 45.805, | |
| "eval_steps_per_second": 5.753, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3400000000000002e-05, | |
| "loss": 0.6359, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6839953064918518, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7541, | |
| "eval_samples_per_second": 45.838, | |
| "eval_steps_per_second": 5.757, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1e-07, | |
| "loss": 0.6331, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6499619483947754, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.8768, | |
| "eval_samples_per_second": 45.592, | |
| "eval_steps_per_second": 5.726, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.966666666666667e-06, | |
| "loss": 0.6342, | |
| "step": 8552 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.6344217658042908, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7688, | |
| "eval_samples_per_second": 45.808, | |
| "eval_steps_per_second": 5.753, | |
| "step": 8552 | |
| } | |
| ], | |
| "max_steps": 10690, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.139857306141491e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |