| { | |
| "best_metric": 0.8, | |
| "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-1650", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1650, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.123150895957912e-06, | |
| "loss": 2.1151, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6326530612244898, | |
| "eval_loss": 1.7264677286148071, | |
| "eval_runtime": 1.125, | |
| "eval_samples_per_second": 217.778, | |
| "eval_steps_per_second": 14.222, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 5.540228474633931e-06, | |
| "loss": 1.5823, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 1.2948896884918213, | |
| "eval_runtime": 1.575, | |
| "eval_samples_per_second": 155.555, | |
| "eval_steps_per_second": 10.159, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 3.9573060533099506e-06, | |
| "loss": 1.2756, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.0647388696670532, | |
| "eval_runtime": 2.6287, | |
| "eval_samples_per_second": 93.202, | |
| "eval_steps_per_second": 6.087, | |
| "step": 1650 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2905718091150.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 8.706073317281892e-06, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 4, | |
| "seed": 1 | |
| } | |
| } | |