| { | |
| "best_metric": 0.8555758683729433, | |
| "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-4\\checkpoint-479", | |
| "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": 2.3576485733382427e-06, | |
| "loss": 0.6038, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8555758683729433, | |
| "eval_loss": 0.5434475541114807, | |
| "eval_runtime": 10.704, | |
| "eval_samples_per_second": 204.409, | |
| "eval_steps_per_second": 1.682, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.5717657155588285e-06, | |
| "loss": 0.5237, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8555758683729433, | |
| "eval_loss": 0.5071110129356384, | |
| "eval_runtime": 10.7179, | |
| "eval_samples_per_second": 204.144, | |
| "eval_steps_per_second": 1.679, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.858828577794142e-07, | |
| "loss": 0.5001, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8555758683729433, | |
| "eval_loss": 0.49807029962539673, | |
| "eval_runtime": 10.7711, | |
| "eval_samples_per_second": 203.135, | |
| "eval_steps_per_second": 1.671, | |
| "step": 1437 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1916, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 3733082796768.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.143531431117657e-06, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 16, | |
| "seed": 14 | |
| } | |
| } | |