| { | |
| "best_metric": 0.983181371856266, | |
| "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli_explanation-base-b16/checkpoint-2800", | |
| "epoch": 0.081547064305685, | |
| "global_step": 2800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.765482430596001e-07, | |
| "loss": 1.0726, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.7982117455801666, | |
| "eval_f1": 0.7974911320075254, | |
| "eval_loss": 0.8326770067214966, | |
| "eval_runtime": 12.8669, | |
| "eval_samples_per_second": 764.91, | |
| "eval_steps_per_second": 47.875, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5530964861192002e-06, | |
| "loss": 0.3233, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.9642349116033326, | |
| "eval_f1": 0.9642718853707861, | |
| "eval_loss": 0.14329373836517334, | |
| "eval_runtime": 12.933, | |
| "eval_samples_per_second": 760.998, | |
| "eval_steps_per_second": 47.63, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.3296447291788007e-06, | |
| "loss": 0.173, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.9762243446453973, | |
| "eval_f1": 0.9761597449883214, | |
| "eval_loss": 0.1054357960820198, | |
| "eval_runtime": 12.9969, | |
| "eval_samples_per_second": 757.258, | |
| "eval_steps_per_second": 47.396, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.1061929722384003e-06, | |
| "loss": 0.1452, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.9799837431416378, | |
| "eval_f1": 0.9799316333368723, | |
| "eval_loss": 0.09648650884628296, | |
| "eval_runtime": 13.0065, | |
| "eval_samples_per_second": 756.7, | |
| "eval_steps_per_second": 47.361, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.882741215298001e-06, | |
| "loss": 0.1449, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9813046128835603, | |
| "eval_f1": 0.9812341372941731, | |
| "eval_loss": 0.09331633150577545, | |
| "eval_runtime": 12.921, | |
| "eval_samples_per_second": 761.706, | |
| "eval_steps_per_second": 47.674, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.659289458357601e-06, | |
| "loss": 0.1303, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.9815078236130867, | |
| "eval_f1": 0.9814520761782233, | |
| "eval_loss": 0.10890379548072815, | |
| "eval_runtime": 12.8683, | |
| "eval_samples_per_second": 764.824, | |
| "eval_steps_per_second": 47.87, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.435837701417202e-06, | |
| "loss": 0.1372, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.9832351148140622, | |
| "eval_f1": 0.983181371856266, | |
| "eval_loss": 0.07784133404493332, | |
| "eval_runtime": 12.8322, | |
| "eval_samples_per_second": 766.977, | |
| "eval_steps_per_second": 48.004, | |
| "step": 2800 | |
| } | |
| ], | |
| "max_steps": 103008, | |
| "num_train_epochs": 3, | |
| "total_flos": 5492559907900896.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |