| { |
| "best_metric": 0.4567190706729889, |
| "best_model_checkpoint": "/kaggle/working/results/checkpoint-1000", |
| "epoch": 0.048118564142046, |
| "eval_steps": 1000, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.024059282071023, |
| "grad_norm": 194828.078125, |
| "learning_rate": 2.4059282071023e-05, |
| "loss": 0.4234, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.048118564142046, |
| "grad_norm": 255341.578125, |
| "learning_rate": 4.8118564142046e-05, |
| "loss": 0.4196, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.048118564142046, |
| "eval_loss": 0.4567190706729889, |
| "eval_runtime": 243.8629, |
| "eval_samples_per_second": 107.236, |
| "eval_steps_per_second": 0.841, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 20782, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4240771055616000.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
