| { |
| "best_metric": 2.4652068614959717, |
| "best_model_checkpoint": "outputs/42/baby-dev/2-20-03/checkpoint-50", |
| "epoch": 0.007046719751955465, |
| "eval_steps": 50, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00014093439503910928, |
| "eval_loss": 2.6642415523529053, |
| "eval_runtime": 32.5251, |
| "eval_samples_per_second": 183.704, |
| "eval_steps_per_second": 45.934, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007046719751955465, |
| "grad_norm": 10.878546714782715, |
| "learning_rate": 0.0002, |
| "loss": 10.002, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.007046719751955465, |
| "eval_loss": 2.4652068614959717, |
| "eval_runtime": 32.3693, |
| "eval_samples_per_second": 184.588, |
| "eval_steps_per_second": 46.155, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 332008985198592.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
