| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1491, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.1311028003692627, | |
| "eval_runtime": 4.522, | |
| "eval_samples_per_second": 48.872, | |
| "eval_steps_per_second": 12.384, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.0060362173038229, | |
| "grad_norm": 35.682647705078125, | |
| "learning_rate": 3.3501006036217306e-05, | |
| "loss": 2.1271, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.991774082183838, | |
| "eval_runtime": 4.5224, | |
| "eval_samples_per_second": 48.867, | |
| "eval_steps_per_second": 12.383, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 2.0120724346076457, | |
| "grad_norm": 17.350433349609375, | |
| "learning_rate": 1.6733735747820257e-05, | |
| "loss": 1.8126, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.9652814865112305, | |
| "eval_runtime": 4.5504, | |
| "eval_samples_per_second": 48.567, | |
| "eval_steps_per_second": 12.307, | |
| "step": 1491 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1491, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1557561802752000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |