| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9999027710257655, | |
| "global_step": 10284, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.5574, | |
| "step": 2571 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.37848538160324097, | |
| "eval_runtime": 338.4836, | |
| "eval_samples_per_second": 6.677, | |
| "eval_steps_per_second": 6.677, | |
| "step": 2571 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.00194476857254e-06, | |
| "loss": 0.3059, | |
| "step": 5142 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.30628740787506104, | |
| "eval_runtime": 338.8936, | |
| "eval_samples_per_second": 6.669, | |
| "eval_steps_per_second": 6.669, | |
| "step": 5142 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.50194476857254e-06, | |
| "loss": 0.2494, | |
| "step": 7713 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.2887383997440338, | |
| "eval_runtime": 339.1381, | |
| "eval_samples_per_second": 6.664, | |
| "eval_steps_per_second": 6.664, | |
| "step": 7713 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.9447685725398677e-09, | |
| "loss": 0.2192, | |
| "step": 10284 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.2874472737312317, | |
| "eval_runtime": 339.3338, | |
| "eval_samples_per_second": 6.66, | |
| "eval_steps_per_second": 6.66, | |
| "step": 10284 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 10284, | |
| "total_flos": 6.108934613772534e+17, | |
| "train_loss": 0.3329931234673552, | |
| "train_runtime": 29997.8117, | |
| "train_samples_per_second": 2.743, | |
| "train_steps_per_second": 0.343 | |
| } | |
| ], | |
| "max_steps": 10284, | |
| "num_train_epochs": 4, | |
| "total_flos": 6.108934613772534e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |