| { | |
| "best_metric": 0.7364016736401674, | |
| "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-0nyui8bu/checkpoint-25", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.2732082605361938, | |
| "learning_rate": 5.6232629293362164e-05, | |
| "loss": 0.5343, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.3999197483062744, | |
| "learning_rate": 1.8744209764454056e-05, | |
| "loss": 0.4344, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8425, | |
| "eval_f1": 0.7364016736401674, | |
| "eval_loss": 0.3744986355304718, | |
| "eval_precision": 0.7586206896551724, | |
| "eval_recall": 0.7154471544715447, | |
| "eval_runtime": 1.5686, | |
| "eval_samples_per_second": 255.002, | |
| "eval_steps_per_second": 15.938, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 169558270279680.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 9.372104882227028e-05, | |
| "metric": "eval/loss", | |
| "num_train_epochs": 1, | |
| "per_device_train_batch_size": 64, | |
| "seed": 37 | |
| } | |
| } | |