| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 804, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8756218905472638e-05, | |
| "loss": 0.6031, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7512437810945274e-05, | |
| "loss": 0.6069, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.626865671641791e-05, | |
| "loss": 0.6051, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5024875621890549e-05, | |
| "loss": 0.605, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3781094527363185e-05, | |
| "loss": 0.6197, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.2537313432835823e-05, | |
| "loss": 0.6119, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.129353233830846e-05, | |
| "loss": 0.5909, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0049751243781096e-05, | |
| "loss": 0.5973, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.805970149253732e-06, | |
| "loss": 0.6011, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.5621890547263685e-06, | |
| "loss": 0.5762, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.6180756092071533, | |
| "eval_matthews_correlation": 0.03718764224408827, | |
| "eval_runtime": 0.9687, | |
| "eval_samples_per_second": 1076.744, | |
| "eval_steps_per_second": 68.135, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.318407960199006e-06, | |
| "loss": 0.5628, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.074626865671642e-06, | |
| "loss": 0.5356, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.8308457711442784e-06, | |
| "loss": 0.546, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.5870646766169156e-06, | |
| "loss": 0.5495, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.3432835820895524e-06, | |
| "loss": 0.5208, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.950248756218906e-08, | |
| "loss": 0.5165, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 804, | |
| "total_flos": 389906945159640.0, | |
| "train_loss": 0.5781698523469232, | |
| "train_runtime": 80.7344, | |
| "train_samples_per_second": 317.746, | |
| "train_steps_per_second": 9.959 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 804, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 389906945159640.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |