| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005351027397260274, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010702054794520547, | |
| "grad_norm": 3.7062225341796875, | |
| "learning_rate": 1e-05, | |
| "loss": 19.3796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010702054794520547, | |
| "eval_loss": 1.1848125457763672, | |
| "eval_runtime": 812.6907, | |
| "eval_samples_per_second": 19.365, | |
| "eval_steps_per_second": 9.683, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021404109589041095, | |
| "grad_norm": 3.8322348594665527, | |
| "learning_rate": 2e-05, | |
| "loss": 18.6395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021404109589041095, | |
| "eval_loss": 1.1781624555587769, | |
| "eval_runtime": 1281.9826, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 6.138, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003210616438356164, | |
| "grad_norm": 4.463776111602783, | |
| "learning_rate": 3e-05, | |
| "loss": 19.9405, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004280821917808219, | |
| "grad_norm": 5.855804443359375, | |
| "learning_rate": 4e-05, | |
| "loss": 19.9278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004280821917808219, | |
| "eval_loss": 1.1730619668960571, | |
| "eval_runtime": 1499.2803, | |
| "eval_samples_per_second": 10.497, | |
| "eval_steps_per_second": 5.249, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005351027397260274, | |
| "grad_norm": 4.008087158203125, | |
| "learning_rate": 5e-05, | |
| "loss": 18.7957, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6514932543651840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |