| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.864417568427753, | |
| "global_step": 4500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.469552302143009e-05, | |
| "loss": 3.9931, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9391046042860174e-05, | |
| "loss": 3.5268, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.408656906429026e-05, | |
| "loss": 3.2464, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.909851312637329, | |
| "eval_runtime": 0.2776, | |
| "eval_samples_per_second": 205.333, | |
| "eval_steps_per_second": 104.468, | |
| "step": 1571 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8782092085720346e-05, | |
| "loss": 2.4823, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3477615107150435e-05, | |
| "loss": 2.3432, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.817313812858052e-05, | |
| "loss": 2.2658, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.7735772132873535, | |
| "eval_runtime": 0.3496, | |
| "eval_samples_per_second": 163.04, | |
| "eval_steps_per_second": 82.95, | |
| "step": 3142 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.286866115001061e-05, | |
| "loss": 1.8291, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.564184171440697e-06, | |
| "loss": 1.6394, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.259707192870783e-06, | |
| "loss": 1.611, | |
| "step": 4500 | |
| } | |
| ], | |
| "max_steps": 4713, | |
| "num_train_epochs": 3, | |
| "total_flos": 133475318784000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |