| { |
| "best_global_step": 3, |
| "best_metric": 0.7012545466423035, |
| "best_model_checkpoint": "distilbert_rand_20_v1_wnli/checkpoint-3", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.3092325925827026, |
| "learning_rate": 4.9e-05, |
| "loss": 0.7248, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5211267605633803, |
| "eval_loss": 0.7012545466423035, |
| "eval_runtime": 0.0407, |
| "eval_samples_per_second": 1745.783, |
| "eval_steps_per_second": 24.588, |
| "step": 3 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.4403125047683716, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6975, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.4084507042253521, |
| "eval_loss": 0.7416923642158508, |
| "eval_runtime": 0.0514, |
| "eval_samples_per_second": 1382.44, |
| "eval_steps_per_second": 19.471, |
| "step": 6 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7769876718521118, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6919, |
| "step": 9 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5352112676056338, |
| "eval_loss": 0.7232064008712769, |
| "eval_runtime": 0.0404, |
| "eval_samples_per_second": 1757.466, |
| "eval_steps_per_second": 24.753, |
| "step": 9 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.8125869035720825, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.6978, |
| "step": 12 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.39436619718309857, |
| "eval_loss": 0.738941490650177, |
| "eval_runtime": 0.0394, |
| "eval_samples_per_second": 1801.797, |
| "eval_steps_per_second": 25.377, |
| "step": 12 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.9107125401496887, |
| "learning_rate": 4.5e-05, |
| "loss": 0.6863, |
| "step": 15 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.29577464788732394, |
| "eval_loss": 0.7789391279220581, |
| "eval_runtime": 0.039, |
| "eval_samples_per_second": 1820.545, |
| "eval_steps_per_second": 25.641, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.7798742055892944, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.695, |
| "step": 18 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.15492957746478872, |
| "eval_loss": 0.7878522872924805, |
| "eval_runtime": 0.0392, |
| "eval_samples_per_second": 1809.098, |
| "eval_steps_per_second": 25.48, |
| "step": 18 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 18, |
| "total_flos": 252350394439680.0, |
| "train_loss": 0.698882540067037, |
| "train_runtime": 12.2409, |
| "train_samples_per_second": 2593.766, |
| "train_steps_per_second": 12.254 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 252350394439680.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
