| { | |
| "best_metric": 0.6663957373792107, | |
| "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/main_verb_lexical_content_the/checkpoint-1000", | |
| "epoch": 10.0, | |
| "global_step": 1150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.6620661616325378, | |
| "eval_f1": 0.6582776608401208, | |
| "eval_loss": 2.30867075920105, | |
| "eval_mcc": 0.324392989322274, | |
| "eval_runtime": 47.546, | |
| "eval_samples_per_second": 464.792, | |
| "eval_steps_per_second": 58.112, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_accuracy": 0.6655052304267883, | |
| "eval_f1": 0.6658227848101266, | |
| "eval_loss": 2.8982155323028564, | |
| "eval_mcc": 0.3310319252852772, | |
| "eval_runtime": 47.6227, | |
| "eval_samples_per_second": 464.043, | |
| "eval_steps_per_second": 58.019, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.826086956521739e-05, | |
| "loss": 0.0399, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_accuracy": 0.6654147505760193, | |
| "eval_f1": 0.6660041557502936, | |
| "eval_loss": 3.164363384246826, | |
| "eval_mcc": 0.3308414921193221, | |
| "eval_runtime": 47.0614, | |
| "eval_samples_per_second": 469.578, | |
| "eval_steps_per_second": 58.711, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.6656862497329712, | |
| "eval_f1": 0.6663656069364162, | |
| "eval_loss": 3.281757354736328, | |
| "eval_mcc": 0.3313815632182769, | |
| "eval_runtime": 46.96, | |
| "eval_samples_per_second": 470.592, | |
| "eval_steps_per_second": 58.837, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 0.0001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_accuracy": 0.6656862497329712, | |
| "eval_f1": 0.6663957373792107, | |
| "eval_loss": 3.3398125171661377, | |
| "eval_mcc": 0.33138060248198653, | |
| "eval_runtime": 47.4664, | |
| "eval_samples_per_second": 465.571, | |
| "eval_steps_per_second": 58.21, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1150, | |
| "total_flos": 6692589829785600.0, | |
| "train_loss": 0.017369135063465522, | |
| "train_runtime": 627.3796, | |
| "train_samples_per_second": 116.453, | |
| "train_steps_per_second": 1.833 | |
| } | |
| ], | |
| "max_steps": 1150, | |
| "num_train_epochs": 10, | |
| "total_flos": 6692589829785600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |