| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18895733343411059, | |
| "eval_steps": 1000, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07558293337364423, | |
| "grad_norm": 0.4784471392631531, | |
| "learning_rate": 1.5470699432892252e-05, | |
| "loss": 0.8895, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07558293337364423, | |
| "eval_loss": 0.8893495798110962, | |
| "eval_runtime": 30073.3919, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15116586674728846, | |
| "grad_norm": 0.38212183117866516, | |
| "learning_rate": 1.3958412098298676e-05, | |
| "loss": 0.8797, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15116586674728846, | |
| "eval_loss": 0.8847432136535645, | |
| "eval_runtime": 30074.8516, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 13230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.390804414660346e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |