| { | |
| "best_metric": 0.8398890197433772, | |
| "best_model_checkpoint": "dtoya/llama3.1-8b_smangrul-hf-stack-v1/checkpoint-100", | |
| "epoch": 7.6923076923076925, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 0.4007813334465027, | |
| "learning_rate": 0.0, | |
| "loss": 0.6779, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "eval_accuracy": 0.8433724340175953, | |
| "eval_f1": 0.8398890197433772, | |
| "eval_loss": 1.0206197500228882, | |
| "eval_runtime": 19.5987, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 5.102, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "step": 100, | |
| "total_flos": 1.4318424572716646e+17, | |
| "train_loss": 0.6778616333007812, | |
| "train_runtime": 2288.3262, | |
| "train_samples_per_second": 1.398, | |
| "train_steps_per_second": 0.044 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 200, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4318424572716646e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |