| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.130232558139535, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18604651162790697, |
| "grad_norm": 1.0017040967941284, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 2.1225, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.37209302325581395, |
| "grad_norm": 0.5668206810951233, |
| "learning_rate": 0.00014545454545454546, |
| "loss": 0.9352, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5581395348837209, |
| "grad_norm": 0.3391001224517822, |
| "learning_rate": 0.00010909090909090909, |
| "loss": 0.837, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7441860465116279, |
| "grad_norm": 0.3862256109714508, |
| "learning_rate": 7.272727272727273e-05, |
| "loss": 0.7808, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9302325581395349, |
| "grad_norm": 0.3802544176578522, |
| "learning_rate": 3.6363636363636364e-05, |
| "loss": 0.7589, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.130232558139535, |
| "grad_norm": 0.3767041862010956, |
| "learning_rate": 0.0, |
| "loss": 0.7774, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1.3190234262208512e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
