| { | |
| "best_metric": 1.025160312652588, | |
| "best_model_checkpoint": "output/finetune/codellama-7b-hf/mbpp/2e-5-3epoch-mbpp-v1/checkpoint-6", | |
| "epoch": 3.0, | |
| "eval_steps": 1, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8214061260223389, | |
| "eval_runtime": 0.1571, | |
| "eval_samples_per_second": 273.715, | |
| "eval_steps_per_second": 12.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.293187141418457, | |
| "eval_runtime": 0.1412, | |
| "eval_samples_per_second": 304.583, | |
| "eval_steps_per_second": 14.167, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.1361353397369385, | |
| "eval_runtime": 0.1417, | |
| "eval_samples_per_second": 303.521, | |
| "eval_steps_per_second": 14.117, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0691229104995728, | |
| "eval_runtime": 0.1413, | |
| "eval_samples_per_second": 304.258, | |
| "eval_steps_per_second": 14.152, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 44.75, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 5.611, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.034167766571045, | |
| "eval_runtime": 0.1199, | |
| "eval_samples_per_second": 358.745, | |
| "eval_steps_per_second": 16.686, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.025160312652588, | |
| "eval_runtime": 0.1409, | |
| "eval_samples_per_second": 305.24, | |
| "eval_steps_per_second": 14.197, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 6, | |
| "total_flos": 2020360769765376.0, | |
| "train_loss": 5.318612337112427, | |
| "train_runtime": 420.7531, | |
| "train_samples_per_second": 0.856, | |
| "train_steps_per_second": 0.014 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2020360769765376.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |