| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5806451612903225, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7741935483870968, | |
| "eval_loss": 1.1021013259887695, | |
| "eval_runtime": 3.7681, | |
| "eval_samples_per_second": 27.334, | |
| "eval_steps_per_second": 0.531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.6774193548387095, | |
| "eval_loss": 1.0564873218536377, | |
| "eval_runtime": 3.8252, | |
| "eval_samples_per_second": 26.927, | |
| "eval_steps_per_second": 0.523, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "eval_loss": 1.022459626197815, | |
| "eval_runtime": 2.2335, | |
| "eval_samples_per_second": 46.117, | |
| "eval_steps_per_second": 0.895, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "step": 9, | |
| "total_flos": 14865955553280.0, | |
| "train_loss": 1.2168584399753146, | |
| "train_runtime": 519.0855, | |
| "train_samples_per_second": 11.299, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9, | |
| "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": 14865955553280.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |