| { | |
| "best_metric": 0.7347700085842469, | |
| "best_model_checkpoint": "robertuito-finetuned-class/run-2/checkpoint-1391", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2782, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1914, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7483922829581994, | |
| "eval_f1": 0.7347700085842469, | |
| "eval_loss": 2.130260705947876, | |
| "eval_recall": 0.7569745645507855, | |
| "eval_runtime": 2.6765, | |
| "eval_samples_per_second": 464.791, | |
| "eval_steps_per_second": 14.571, | |
| "step": 1391 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.132, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1005, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 5e-05, | |
| "loss": 0.124, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7009646302250804, | |
| "eval_f1": 0.6993935460471093, | |
| "eval_loss": 2.302142381668091, | |
| "eval_recall": 0.7212726944097146, | |
| "eval_runtime": 2.6927, | |
| "eval_samples_per_second": 461.986, | |
| "eval_steps_per_second": 14.483, | |
| "step": 2782 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2782, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 317966969208832.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.658861968938005e-05, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 4, | |
| "seed": 17 | |
| } | |
| } | |