| { | |
| "best_metric": 0.49799539554804517, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1605, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.85192391864203e-05, | |
| "loss": 0.5264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.46143588423728943, | |
| "eval_matthews_correlation": 0.49799539554804517, | |
| "eval_runtime": 1.0072, | |
| "eval_samples_per_second": 1035.567, | |
| "eval_steps_per_second": 65.53, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.4261942821725978e-05, | |
| "loss": 0.3406, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5079557299613953, | |
| "eval_matthews_correlation": 0.48003141444537994, | |
| "eval_runtime": 0.8361, | |
| "eval_samples_per_second": 1247.424, | |
| "eval_steps_per_second": 78.936, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.0004646457031656e-05, | |
| "loss": 0.2246, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6419426202774048, | |
| "eval_matthews_correlation": 0.49626557567073315, | |
| "eval_runtime": 0.7375, | |
| "eval_samples_per_second": 1414.219, | |
| "eval_steps_per_second": 89.49, | |
| "step": 1605 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2675, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 128728040623236.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.277653555111462e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 16, | |
| "seed": 38 | |
| } | |
| } | |