| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8807339449541285, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 1.4326, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8807339449541285, | |
| "eval_loss": 1.4250946044921875, | |
| "eval_runtime": 158.8147, | |
| "eval_samples_per_second": 5.491, | |
| "eval_steps_per_second": 5.491, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8807339449541285, | |
| "step": 6, | |
| "total_flos": 6.764886594315878e+16, | |
| "train_loss": 1.4339824716250102, | |
| "train_runtime": 610.6947, | |
| "train_samples_per_second": 1.428, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 6, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.764886594315878e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |