| { |
| "best_global_step": 10, |
| "best_metric": 0.9213941097259521, |
| "best_model_checkpoint": "/kaggle/working/checkpoint-10", |
| "epoch": 0.02940095553105476, |
| "eval_steps": 10, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02940095553105476, |
| "grad_norm": 1150.6878662109375, |
| "learning_rate": 9.356725146198831e-07, |
| "loss": 131.7341, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02940095553105476, |
| "eval_model_preparation_time": 0.0078, |
| "eval_runtime": 355.0656, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "eval_validation_eval_cosine_accuracy": 0.9213941097259521, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1705, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
