| { |
| "best_metric": 0.9125154588177096, |
| "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-56855", |
| "epoch": 5.0, |
| "global_step": 56855, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 1.777760406488177e-05, |
| "loss": 0.3331, |
| "step": 11371 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8918872124659906, |
| "eval_combined_score": 0.8741442698553219, |
| "eval_f1": 0.8564013272446532, |
| "eval_loss": 0.25236421823501587, |
| "eval_runtime": 183.9392, |
| "eval_samples_per_second": 219.801, |
| "eval_steps_per_second": 27.476, |
| "step": 11371 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 1.3333203048661326e-05, |
| "loss": 0.2043, |
| "step": 22742 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.904699480583725, |
| "eval_combined_score": 0.8889967855745091, |
| "eval_f1": 0.8732940905652932, |
| "eval_loss": 0.23582789301872253, |
| "eval_runtime": 184.4786, |
| "eval_samples_per_second": 219.158, |
| "eval_steps_per_second": 27.396, |
| "step": 22742 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 8.888802032440885e-06, |
| "loss": 0.1327, |
| "step": 34113 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9093742270591145, |
| "eval_combined_score": 0.894668767310189, |
| "eval_f1": 0.8799633075612633, |
| "eval_loss": 0.25910505652427673, |
| "eval_runtime": 184.7125, |
| "eval_samples_per_second": 218.881, |
| "eval_steps_per_second": 27.361, |
| "step": 34113 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.4444010162204425e-06, |
| "loss": 0.0893, |
| "step": 45484 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9120702448676725, |
| "eval_combined_score": 0.8976971395660034, |
| "eval_f1": 0.8833240342643344, |
| "eval_loss": 0.3531641662120819, |
| "eval_runtime": 184.8553, |
| "eval_samples_per_second": 218.712, |
| "eval_steps_per_second": 27.34, |
| "step": 45484 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.0, |
| "loss": 0.0633, |
| "step": 56855 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9125154588177096, |
| "eval_combined_score": 0.8974312649841467, |
| "eval_f1": 0.8823470711505838, |
| "eval_loss": 0.40157535672187805, |
| "eval_runtime": 184.919, |
| "eval_samples_per_second": 218.636, |
| "eval_steps_per_second": 27.331, |
| "step": 56855 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 56855, |
| "total_flos": 1.196648813106432e+17, |
| "train_loss": 0.16454659021579016, |
| "train_runtime": 22957.988, |
| "train_samples_per_second": 79.242, |
| "train_steps_per_second": 2.476 |
| } |
| ], |
| "max_steps": 56855, |
| "num_train_epochs": 5, |
| "total_flos": 1.196648813106432e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
