| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.7520645260810852, |
| "learning_rate": 0.00013243778703071377, |
| "loss": 2.493, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.5891498327255249, |
| "learning_rate": 9.459841930765269e-05, |
| "loss": 2.23, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7333166599273682, |
| "learning_rate": 5.6759051584591616e-05, |
| "loss": 2.0981, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 90, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.789337010898944e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
