| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.8275862068965516, |
| "eval_steps": 100, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 5.382654666900635, |
| "learning_rate": 1.5714285714285715e-05, |
| "loss": 2.7034, |
| "mean_token_accuracy": 0.5253287822008132, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.3448275862068966, |
| "grad_norm": 5.657339096069336, |
| "learning_rate": 1.1428571428571429e-05, |
| "loss": 2.3733, |
| "mean_token_accuracy": 0.5574273027871784, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 8.469321250915527, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 2.0359, |
| "mean_token_accuracy": 0.5923066131378475, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.689655172413793, |
| "grad_norm": 6.4863386154174805, |
| "learning_rate": 1.904761904761905e-06, |
| "loss": 1.8282, |
| "mean_token_accuracy": 0.5966725200414658, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 42, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5131032009310208e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
