| { | |
| "best_metric": 1.0150294303894043, | |
| "best_model_checkpoint": "output/finetune/llama-3.1-8b/mbpp/1e-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": 2.062755823135376, | |
| "eval_runtime": 0.127, | |
| "eval_samples_per_second": 338.532, | |
| "eval_steps_per_second": 15.746, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3784940242767334, | |
| "eval_runtime": 0.1304, | |
| "eval_samples_per_second": 329.723, | |
| "eval_steps_per_second": 15.336, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.210484504699707, | |
| "eval_runtime": 0.1313, | |
| "eval_samples_per_second": 327.416, | |
| "eval_steps_per_second": 15.229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.063664436340332, | |
| "eval_runtime": 0.1312, | |
| "eval_samples_per_second": 327.796, | |
| "eval_steps_per_second": 15.246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 56.75, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 6.0573, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.0268363952636719, | |
| "eval_runtime": 0.1093, | |
| "eval_samples_per_second": 393.58, | |
| "eval_steps_per_second": 18.306, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0150294303894043, | |
| "eval_runtime": 0.1322, | |
| "eval_samples_per_second": 325.146, | |
| "eval_steps_per_second": 15.123, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 6, | |
| "total_flos": 1872868942020608.0, | |
| "train_loss": 5.656974633534749, | |
| "train_runtime": 519.8713, | |
| "train_samples_per_second": 0.692, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "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": 1872868942020608.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |