| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 2758, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036258158085569254, | |
| "grad_norm": 3.518895387649536, | |
| "learning_rate": 0.0, | |
| "loss": 1.2042, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36258158085569253, | |
| "grad_norm": 4.220677852630615, | |
| "learning_rate": 9.053013140009063e-06, | |
| "loss": 1.1885, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36258158085569253, | |
| "eval_cosine_accuracy": 0.9711852073669434, | |
| "eval_loss": 0.3902958035469055, | |
| "eval_runtime": 34.6603, | |
| "eval_samples_per_second": 274.348, | |
| "eval_steps_per_second": 1.096, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7251631617113851, | |
| "grad_norm": 4.6132588386535645, | |
| "learning_rate": 1.811508835523335e-05, | |
| "loss": 0.8207, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7251631617113851, | |
| "eval_cosine_accuracy": 0.9699232578277588, | |
| "eval_loss": 0.37875595688819885, | |
| "eval_runtime": 33.7082, | |
| "eval_samples_per_second": 282.098, | |
| "eval_steps_per_second": 1.127, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 11032, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |