| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 36.8421052631579, |
| "eval_steps": 500, |
| "global_step": 4200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 4.385964912280702, |
| "grad_norm": 9.875, |
| "learning_rate": 2.5e-05, |
| "loss": 2.8556, |
| "step": 500 |
| }, |
| { |
| "epoch": 8.771929824561404, |
| "grad_norm": 10.625, |
| "learning_rate": 5e-05, |
| "loss": 1.9744, |
| "step": 1000 |
| }, |
| { |
| "epoch": 13.157894736842104, |
| "grad_norm": 21.625, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 1.7097, |
| "step": 1500 |
| }, |
| { |
| "epoch": 17.54385964912281, |
| "grad_norm": 16.375, |
| "learning_rate": 0.0001, |
| "loss": 1.4299, |
| "step": 2000 |
| }, |
| { |
| "epoch": 21.92982456140351, |
| "grad_norm": 13.625, |
| "learning_rate": 9.087924065757919e-05, |
| "loss": 1.1377, |
| "step": 2500 |
| }, |
| { |
| "epoch": 26.31578947368421, |
| "grad_norm": 8.25, |
| "learning_rate": 6.6844492669611e-05, |
| "loss": 0.7634, |
| "step": 3000 |
| }, |
| { |
| "epoch": 30.70175438596491, |
| "grad_norm": 6.5, |
| "learning_rate": 3.666436212625509e-05, |
| "loss": 0.451, |
| "step": 3500 |
| }, |
| { |
| "epoch": 35.08771929824562, |
| "grad_norm": 5.84375, |
| "learning_rate": 1.134947733186315e-05, |
| "loss": 0.2987, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4560, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 40, |
| "save_steps": 150, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.435577786302464e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
