| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5208580105288608, | |
| "las": 86.67697824023622, | |
| "step": 110, | |
| "uas": 90.34696101522128 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4618787513794126, | |
| "las": 88.56469926530039, | |
| "step": 220, | |
| "uas": 91.83745210391254 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.46524564599668655, | |
| "las": 89.09902625935952, | |
| "step": 330, | |
| "uas": 92.17492178437094 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.546365056488965, | |
| "las": 89.61929201673287, | |
| "step": 440, | |
| "uas": 92.61785073997258 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 1.684398889541626, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.4563, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 550, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 6024211271861760.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |