| { |
| "best_global_step": 3, |
| "best_metric": 0.7200155854225159, |
| "best_model_checkpoint": "distilbert_km_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": 1.0904909372329712, |
| "learning_rate": 4.9e-05, |
| "loss": 0.7177, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.4647887323943662, |
| "eval_loss": 0.7200155854225159, |
| "eval_runtime": 0.0514, |
| "eval_samples_per_second": 1380.089, |
| "eval_steps_per_second": 19.438, |
| "step": 3 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.0988194942474365, |
| "learning_rate": 4.8e-05, |
| "loss": 0.7001, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.2676056338028169, |
| "eval_loss": 0.7573724985122681, |
| "eval_runtime": 0.0417, |
| "eval_samples_per_second": 1702.594, |
| "eval_steps_per_second": 23.98, |
| "step": 6 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.0403369665145874, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6907, |
| "step": 9 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.22535211267605634, |
| "eval_loss": 0.7639744281768799, |
| "eval_runtime": 0.0408, |
| "eval_samples_per_second": 1738.394, |
| "eval_steps_per_second": 24.484, |
| "step": 9 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.8606846332550049, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.691, |
| "step": 12 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.3380281690140845, |
| "eval_loss": 0.778499186038971, |
| "eval_runtime": 0.0478, |
| "eval_samples_per_second": 1484.043, |
| "eval_steps_per_second": 20.902, |
| "step": 12 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.482383370399475, |
| "learning_rate": 4.5e-05, |
| "loss": 0.685, |
| "step": 15 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.22535211267605634, |
| "eval_loss": 0.804027259349823, |
| "eval_runtime": 0.0455, |
| "eval_samples_per_second": 1560.234, |
| "eval_steps_per_second": 21.975, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.490465521812439, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.686, |
| "step": 18 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.18309859154929578, |
| "eval_loss": 0.825924277305603, |
| "eval_runtime": 0.0395, |
| "eval_samples_per_second": 1799.065, |
| "eval_steps_per_second": 25.339, |
| "step": 18 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 18, |
| "total_flos": 252350394439680.0, |
| "train_loss": 0.6951021220948961, |
| "train_runtime": 11.5746, |
| "train_samples_per_second": 2743.084, |
| "train_steps_per_second": 12.959 |
| } |
| ], |
| "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 |
| } |
|
|
