| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6632124352331606, | |
| "eval_steps": 500, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9981033287370443e-05, | |
| "loss": 1.6989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9529420004271568e-05, | |
| "loss": 1.6739, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.816196912356222e-05, | |
| "loss": 1.5982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.6026346363792565e-05, | |
| "loss": 1.5122, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.3323547994796597e-05, | |
| "loss": 1.4548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0307950585561705e-05, | |
| "loss": 1.4138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.263370099279173e-06, | |
| "loss": 1.3893, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.3753963708877563, | |
| "eval_runtime": 450.7868, | |
| "eval_samples_per_second": 51.785, | |
| "eval_steps_per_second": 0.81, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "step": 34, | |
| "total_flos": 5.186340030460723e+16, | |
| "train_loss": 1.4978124744751875, | |
| "train_runtime": 20714.0195, | |
| "train_samples_per_second": 10.136, | |
| "train_steps_per_second": 0.002 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 51, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 5.186340030460723e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |