| { | |
| "best_metric": 0.8775137111517367, | |
| "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-41\\checkpoint-1437", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1437, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.422424637361342e-05, | |
| "loss": 0.481, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8638025594149908, | |
| "eval_loss": 0.4778817892074585, | |
| "eval_runtime": 10.8996, | |
| "eval_samples_per_second": 200.74, | |
| "eval_steps_per_second": 1.651, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.614949758240895e-05, | |
| "loss": 0.4596, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8743144424131627, | |
| "eval_loss": 0.4691072404384613, | |
| "eval_runtime": 10.9597, | |
| "eval_samples_per_second": 199.64, | |
| "eval_steps_per_second": 1.642, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.8074748791204473e-05, | |
| "loss": 0.4479, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8775137111517367, | |
| "eval_loss": 0.4681135416030884, | |
| "eval_runtime": 10.9428, | |
| "eval_samples_per_second": 199.949, | |
| "eval_steps_per_second": 1.645, | |
| "step": 1437 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1916, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 3716168818752.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 7.22989951648179e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 16, | |
| "seed": 30 | |
| } | |
| } | |