| { |
| "best_metric": 0.9388077259063721, |
| "best_model_checkpoint": "./fine_tuned_model/checkpoint-100", |
| "epoch": 0.18399264029438822, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0018399264029438822, |
| "grad_norm": 0.9244565963745117, |
| "learning_rate": 5e-06, |
| "loss": 2.0585, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09199632014719411, |
| "grad_norm": 1.1710466146469116, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 1.4162, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.18399264029438822, |
| "grad_norm": 1.0087119340896606, |
| "learning_rate": 0.0, |
| "loss": 0.9638, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.18399264029438822, |
| "eval_loss": 0.9388077259063721, |
| "eval_runtime": 52.1086, |
| "eval_samples_per_second": 2.322, |
| "eval_steps_per_second": 1.171, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3486225373593600.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
