| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.67022696929239, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6675567423230975, |
| "grad_norm": 26.4691104888916, |
| "learning_rate": 3.887405429461504e-05, |
| "loss": 3.0221, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.436640501022339, |
| "eval_runtime": 397.2989, |
| "eval_samples_per_second": 0.423, |
| "eval_steps_per_second": 0.053, |
| "step": 749 |
| }, |
| { |
| "epoch": 1.335113484646195, |
| "grad_norm": 52.74542999267578, |
| "learning_rate": 2.774810858923009e-05, |
| "loss": 2.3297, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.2850723266601562, |
| "eval_runtime": 382.014, |
| "eval_samples_per_second": 0.44, |
| "eval_steps_per_second": 0.055, |
| "step": 1498 |
| }, |
| { |
| "epoch": 2.0026702269692924, |
| "grad_norm": 24.449501037597656, |
| "learning_rate": 1.6622162883845125e-05, |
| "loss": 1.9653, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.67022696929239, |
| "grad_norm": 30.147035598754883, |
| "learning_rate": 5.4962171784601695e-06, |
| "loss": 1.6578, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2247, |
| "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": 2090336256000000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
