| { | |
| "best_metric": 0.7507804370447451, | |
| "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-2\\checkpoint-363", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 363, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00011029236363001645, | |
| "loss": 0.286, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7200832466181062, | |
| "eval_loss": 0.27681800723075867, | |
| "eval_runtime": 5.4424, | |
| "eval_samples_per_second": 353.152, | |
| "eval_steps_per_second": 2.94, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.191030302501371e-05, | |
| "loss": 0.2718, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7476586888657648, | |
| "eval_loss": 0.27226677536964417, | |
| "eval_runtime": 5.4231, | |
| "eval_samples_per_second": 354.413, | |
| "eval_steps_per_second": 2.95, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.352824242001096e-05, | |
| "loss": 0.2651, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7507804370447451, | |
| "eval_loss": 0.27160072326660156, | |
| "eval_runtime": 5.419, | |
| "eval_samples_per_second": 354.676, | |
| "eval_steps_per_second": 2.953, | |
| "step": 363 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 847, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "total_flos": 8247964642380.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.4285130419277947, | |
| "learning_rate": 0.0001286744242350192, | |
| "num_train_epochs": 7, | |
| "temperature": 15 | |
| } | |
| } | |