| { | |
| "best_metric": 0.7648283038501561, | |
| "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-0\\checkpoint-242", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 605, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0003319904626826733, | |
| "loss": 0.3191, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7539021852237253, | |
| "eval_loss": 0.30957773327827454, | |
| "eval_runtime": 5.4184, | |
| "eval_samples_per_second": 354.72, | |
| "eval_steps_per_second": 2.953, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00024899284701200493, | |
| "loss": 0.2969, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7648283038501561, | |
| "eval_loss": 0.3051917552947998, | |
| "eval_runtime": 5.2967, | |
| "eval_samples_per_second": 362.87, | |
| "eval_steps_per_second": 3.021, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00016599523134133666, | |
| "loss": 0.2805, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.759105098855359, | |
| "eval_loss": 0.31477901339530945, | |
| "eval_runtime": 5.3306, | |
| "eval_samples_per_second": 360.562, | |
| "eval_steps_per_second": 3.002, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.299761567066833e-05, | |
| "loss": 0.2658, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7580645161290323, | |
| "eval_loss": 0.31553351879119873, | |
| "eval_runtime": 5.4316, | |
| "eval_samples_per_second": 353.855, | |
| "eval_steps_per_second": 2.946, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2575, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7565036420395421, | |
| "eval_loss": 0.3190446197986603, | |
| "eval_runtime": 5.3879, | |
| "eval_samples_per_second": 356.724, | |
| "eval_steps_per_second": 2.97, | |
| "step": 605 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 605, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 13731632367600.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.49498496921985724, | |
| "learning_rate": 0.0004149880783533416, | |
| "num_train_epochs": 5, | |
| "temperature": 14 | |
| } | |
| } | |