| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 63, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4984423676012461, |
| "grad_norm": 5.558856763336431, |
| "learning_rate": 1.4517876142803703e-05, |
| "loss": 2.0075, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9968847352024922, |
| "grad_norm": 3.939364153897192, |
| "learning_rate": 1.2304448840236316e-05, |
| "loss": 1.0126, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.4485981308411215, |
| "grad_norm": 3.370460015361011, |
| "learning_rate": 8.844605691080518e-06, |
| "loss": 0.7552, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.9470404984423677, |
| "grad_norm": 2.850119441352168, |
| "learning_rate": 5.03593213566874e-06, |
| "loss": 0.6562, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.398753894080997, |
| "grad_norm": 3.5602033469351277, |
| "learning_rate": 1.8665105184711027e-06, |
| "loss": 0.465, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.897196261682243, |
| "grad_norm": 2.5656408755103253, |
| "learning_rate": 1.5858236178481644e-07, |
| "loss": 0.4027, |
| "step": 60 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 63, |
| "total_flos": 2133208596480.0, |
| "train_loss": 0.856299222461761, |
| "train_runtime": 20701.3471, |
| "train_samples_per_second": 0.372, |
| "train_steps_per_second": 0.003 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 63, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2133208596480.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
