| { | |
| "best_metric": 0.6578601002693176, | |
| "best_model_checkpoint": "hBERTv2_new_no_pretrain_qqp/checkpoint-14215", | |
| "epoch": 10.0, | |
| "global_step": 28430, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0004900105522335561, | |
| "loss": 0.6669, | |
| "step": 2843 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6595353484153748, | |
| "eval_runtime": 67.7356, | |
| "eval_samples_per_second": 596.88, | |
| "eval_steps_per_second": 4.665, | |
| "step": 2843 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0004800105522335561, | |
| "loss": 0.6591, | |
| "step": 5686 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6586501598358154, | |
| "eval_runtime": 67.7263, | |
| "eval_samples_per_second": 596.962, | |
| "eval_steps_per_second": 4.666, | |
| "step": 5686 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0004700105522335561, | |
| "loss": 0.6589, | |
| "step": 8529 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6581756472587585, | |
| "eval_runtime": 67.7959, | |
| "eval_samples_per_second": 596.348, | |
| "eval_steps_per_second": 4.661, | |
| "step": 8529 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0004600140696447415, | |
| "loss": 0.6587, | |
| "step": 11372 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6579899787902832, | |
| "eval_runtime": 67.7187, | |
| "eval_samples_per_second": 597.028, | |
| "eval_steps_per_second": 4.666, | |
| "step": 11372 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0004500175870559268, | |
| "loss": 0.6586, | |
| "step": 14215 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6578601002693176, | |
| "eval_runtime": 67.6584, | |
| "eval_samples_per_second": 597.561, | |
| "eval_steps_per_second": 4.671, | |
| "step": 14215 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0004400211044671122, | |
| "loss": 0.6586, | |
| "step": 17058 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6580154895782471, | |
| "eval_runtime": 67.6879, | |
| "eval_samples_per_second": 597.3, | |
| "eval_steps_per_second": 4.668, | |
| "step": 17058 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00043002110446711226, | |
| "loss": 0.6586, | |
| "step": 19901 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6579923629760742, | |
| "eval_runtime": 67.6844, | |
| "eval_samples_per_second": 597.331, | |
| "eval_steps_per_second": 4.669, | |
| "step": 19901 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00042002813928948297, | |
| "loss": 0.6586, | |
| "step": 22744 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6579098701477051, | |
| "eval_runtime": 67.6644, | |
| "eval_samples_per_second": 597.508, | |
| "eval_steps_per_second": 4.67, | |
| "step": 22744 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.00041003165670066834, | |
| "loss": 0.6586, | |
| "step": 25587 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6579644680023193, | |
| "eval_runtime": 67.7204, | |
| "eval_samples_per_second": 597.014, | |
| "eval_steps_per_second": 4.666, | |
| "step": 25587 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0004000351741118537, | |
| "loss": 0.6586, | |
| "step": 28430 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6579644680023193, | |
| "eval_runtime": 67.7641, | |
| "eval_samples_per_second": 596.629, | |
| "eval_steps_per_second": 4.663, | |
| "step": 28430 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 28430, | |
| "total_flos": 5.3244920021909504e+17, | |
| "train_loss": 0.6595250953891686, | |
| "train_runtime": 18380.3319, | |
| "train_samples_per_second": 989.77, | |
| "train_steps_per_second": 7.734 | |
| } | |
| ], | |
| "max_steps": 142150, | |
| "num_train_epochs": 50, | |
| "total_flos": 5.3244920021909504e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |