| { | |
| "best_metric": 0.5630330490405118, | |
| "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/control_raising_lexical_content_the/checkpoint-200", | |
| "epoch": 10.0, | |
| "global_step": 1070, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.6816968321800232, | |
| "eval_f1": 0.5630330490405118, | |
| "eval_loss": 2.454591989517212, | |
| "eval_mcc": 0.42501402837368374, | |
| "eval_runtime": 26.5947, | |
| "eval_samples_per_second": 774.704, | |
| "eval_steps_per_second": 96.861, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.6746104955673218, | |
| "eval_f1": 0.5315818893236445, | |
| "eval_loss": 2.9045093059539795, | |
| "eval_mcc": 0.4314830391212163, | |
| "eval_runtime": 26.5241, | |
| "eval_samples_per_second": 776.767, | |
| "eval_steps_per_second": 97.119, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.663551401869159e-05, | |
| "loss": 0.0402, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_accuracy": 0.6774741411209106, | |
| "eval_f1": 0.5421346379108386, | |
| "eval_loss": 2.9633610248565674, | |
| "eval_mcc": 0.4310984143652165, | |
| "eval_runtime": 26.4317, | |
| "eval_samples_per_second": 779.481, | |
| "eval_steps_per_second": 97.459, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_accuracy": 0.6771343946456909, | |
| "eval_f1": 0.541304647634809, | |
| "eval_loss": 3.033346176147461, | |
| "eval_mcc": 0.430658133290213, | |
| "eval_runtime": 26.6558, | |
| "eval_samples_per_second": 772.928, | |
| "eval_steps_per_second": 96.639, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 3.2710280373831774e-06, | |
| "loss": 0.0001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "eval_accuracy": 0.6705819368362427, | |
| "eval_f1": 0.5119021934555915, | |
| "eval_loss": 3.252445697784424, | |
| "eval_mcc": 0.43824410166582695, | |
| "eval_runtime": 26.5036, | |
| "eval_samples_per_second": 777.365, | |
| "eval_steps_per_second": 97.194, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1070, | |
| "total_flos": 1746700955320320.0, | |
| "train_loss": 0.018803110335318146, | |
| "train_runtime": 307.2203, | |
| "train_samples_per_second": 221.86, | |
| "train_steps_per_second": 3.483 | |
| } | |
| ], | |
| "max_steps": 1070, | |
| "num_train_epochs": 10, | |
| "total_flos": 1746700955320320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |