| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07964601769911504, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008849557522123894, | |
| "eval_loss": 7.850747108459473, | |
| "eval_runtime": 11.9245, | |
| "eval_samples_per_second": 7.967, | |
| "eval_steps_per_second": 2.013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02654867256637168, | |
| "grad_norm": 23.30268096923828, | |
| "learning_rate": 3e-05, | |
| "loss": 32.3052, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05309734513274336, | |
| "grad_norm": 24.82865333557129, | |
| "learning_rate": 6e-05, | |
| "loss": 26.7374, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07964601769911504, | |
| "grad_norm": 16.411090850830078, | |
| "learning_rate": 9e-05, | |
| "loss": 15.0507, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07964601769911504, | |
| "eval_loss": 1.889989972114563, | |
| "eval_runtime": 12.1586, | |
| "eval_samples_per_second": 7.813, | |
| "eval_steps_per_second": 1.974, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.255823024062464e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |