| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.225806451612903, |
| "eval_steps": 10, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.2903225806451613, |
| "grad_norm": 43.65163803100586, |
| "learning_rate": 6.800000000000001e-06, |
| "loss": 3.4682, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.2903225806451613, |
| "eval_loss": 1.9507067203521729, |
| "eval_runtime": 13.6194, |
| "eval_samples_per_second": 1.468, |
| "eval_steps_per_second": 0.734, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "grad_norm": 37.454410552978516, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 1.4213, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "eval_loss": 1.0588676929473877, |
| "eval_runtime": 13.7025, |
| "eval_samples_per_second": 1.46, |
| "eval_steps_per_second": 0.73, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2048335432805376.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
