| { | |
| "best_metric": 0.8218181818181818, | |
| "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/cola/checkpoint-200", | |
| "epoch": 10.0, | |
| "global_step": 1280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.7114818692207336, | |
| "eval_f1": 0.8218181818181818, | |
| "eval_loss": 0.5872910022735596, | |
| "eval_mcc": 0.18948085721928823, | |
| "eval_runtime": 2.1539, | |
| "eval_samples_per_second": 473.102, | |
| "eval_steps_per_second": 59.428, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.7173699736595154, | |
| "eval_f1": 0.8132295719844358, | |
| "eval_loss": 0.7240995168685913, | |
| "eval_mcc": 0.26281332883560804, | |
| "eval_runtime": 2.1671, | |
| "eval_samples_per_second": 470.217, | |
| "eval_steps_per_second": 59.066, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.0468750000000002e-05, | |
| "loss": 0.4445, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_accuracy": 0.707556426525116, | |
| "eval_f1": 0.807741935483871, | |
| "eval_loss": 0.9681539535522461, | |
| "eval_mcc": 0.23051552905227268, | |
| "eval_runtime": 2.1721, | |
| "eval_samples_per_second": 469.126, | |
| "eval_steps_per_second": 58.929, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy": 0.7242394685745239, | |
| "eval_f1": 0.8192926045016078, | |
| "eval_loss": 1.2346603870391846, | |
| "eval_mcc": 0.27596976231470044, | |
| "eval_runtime": 2.1584, | |
| "eval_samples_per_second": 472.114, | |
| "eval_steps_per_second": 59.304, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 0.1091, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_accuracy": 0.7163886427879333, | |
| "eval_f1": 0.8084824387011266, | |
| "eval_loss": 1.280194878578186, | |
| "eval_mcc": 0.2778508397362399, | |
| "eval_runtime": 2.1555, | |
| "eval_samples_per_second": 472.74, | |
| "eval_steps_per_second": 59.382, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_accuracy": 0.7212954163551331, | |
| "eval_f1": 0.8165374677002584, | |
| "eval_loss": 1.5132513046264648, | |
| "eval_mcc": 0.27088079409026794, | |
| "eval_runtime": 2.1614, | |
| "eval_samples_per_second": 471.454, | |
| "eval_steps_per_second": 59.221, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1280, | |
| "total_flos": 7478552336486400.0, | |
| "train_loss": 0.22346576005220414, | |
| "train_runtime": 448.112, | |
| "train_samples_per_second": 182.187, | |
| "train_steps_per_second": 2.856 | |
| } | |
| ], | |
| "max_steps": 1280, | |
| "num_train_epochs": 10, | |
| "total_flos": 7478552336486400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |