| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 1390, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0014388489208633094, |
| "grad_norm": 6.760711669921875, |
| "learning_rate": 1.9990407673860914e-05, |
| "loss": 1.7769, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.7194244604316546, |
| "grad_norm": 8.678190231323242, |
| "learning_rate": 1.5203836930455638e-05, |
| "loss": 0.7796, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7721952097965064, |
| "eval_loss": 0.6371583342552185, |
| "eval_runtime": 8.8787, |
| "eval_samples_per_second": 625.429, |
| "eval_steps_per_second": 19.597, |
| "step": 695 |
| }, |
| { |
| "epoch": 1.4388489208633093, |
| "grad_norm": 8.832938194274902, |
| "learning_rate": 1.0407673860911272e-05, |
| "loss": 0.5626, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7902034936070592, |
| "eval_loss": 0.6182695031166077, |
| "eval_runtime": 8.9224, |
| "eval_samples_per_second": 622.368, |
| "eval_steps_per_second": 19.502, |
| "step": 1390 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2085, |
| "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": 2921821645906944.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
