| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 8, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.125, |
| "grad_norm": 14.48385238647461, |
| "learning_rate": 0.00019914448613738106, |
| "loss": 3.3605, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 6.853867530822754, |
| "learning_rate": 0.00019659258262890683, |
| "loss": 1.993, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 5.492555141448975, |
| "learning_rate": 0.0001923879532511287, |
| "loss": 2.0817, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 5.457701206207275, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 2.0102, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 5.994251251220703, |
| "learning_rate": 0.00017933533402912354, |
| "loss": 1.9157, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 5.06940221786499, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 1.6613, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.875, |
| "grad_norm": 5.290867805480957, |
| "learning_rate": 0.00016087614290087208, |
| "loss": 1.6786, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.920886993408203, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 1.1838, |
| "step": 8 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 24, |
| "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": 329592329994240.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
