| { | |
| "best_metric": 0.7933884297520661, | |
| "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-opfiuf68/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": 2.059823989868164, | |
| "learning_rate": 7.8013907877799e-05, | |
| "loss": 0.5447, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 4.656884670257568, | |
| "learning_rate": 7.123008980146864e-05, | |
| "loss": 0.3593, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.875, | |
| "eval_f1": 0.7933884297520661, | |
| "eval_loss": 0.30094608664512634, | |
| "eval_precision": 0.8067226890756303, | |
| "eval_recall": 0.7804878048780488, | |
| "eval_runtime": 1.5162, | |
| "eval_samples_per_second": 263.815, | |
| "eval_steps_per_second": 16.488, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 169558270279680.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 8.479772595412934e-05, | |
| "metric": "eval/loss", | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 64, | |
| "seed": 1 | |
| } | |
| } | |