| { |
| "best_global_step": 264, |
| "best_metric": 0.46261903643608093, |
| "best_model_checkpoint": "tiny_bert_km_50_v2_sst2/checkpoint-264", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1584, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 7.580273628234863, |
| "learning_rate": 4.9e-05, |
| "loss": 0.4553, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7993119266055045, |
| "eval_loss": 0.46261903643608093, |
| "eval_runtime": 0.2599, |
| "eval_samples_per_second": 3355.754, |
| "eval_steps_per_second": 15.393, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 5.606261730194092, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2508, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8004587155963303, |
| "eval_loss": 0.4972456395626068, |
| "eval_runtime": 0.2578, |
| "eval_samples_per_second": 3381.912, |
| "eval_steps_per_second": 15.513, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 5.3927998542785645, |
| "learning_rate": 4.7e-05, |
| "loss": 0.195, |
| "step": 792 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7935779816513762, |
| "eval_loss": 0.5118311643600464, |
| "eval_runtime": 0.2668, |
| "eval_samples_per_second": 3267.914, |
| "eval_steps_per_second": 14.99, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 6.790493011474609, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.162, |
| "step": 1056 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7947247706422018, |
| "eval_loss": 0.5829846262931824, |
| "eval_runtime": 0.2614, |
| "eval_samples_per_second": 3335.902, |
| "eval_steps_per_second": 15.302, |
| "step": 1056 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.9639827013015747, |
| "learning_rate": 4.5e-05, |
| "loss": 0.1344, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7912844036697247, |
| "eval_loss": 0.6257232427597046, |
| "eval_runtime": 0.2588, |
| "eval_samples_per_second": 3369.98, |
| "eval_steps_per_second": 15.459, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 10.239049911499023, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.114, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7809633027522935, |
| "eval_loss": 0.7445380687713623, |
| "eval_runtime": 0.276, |
| "eval_samples_per_second": 3159.177, |
| "eval_steps_per_second": 14.492, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1584, |
| "total_flos": 1.0596790573590528e+16, |
| "train_loss": 0.218592193391588, |
| "train_runtime": 217.1191, |
| "train_samples_per_second": 15509.691, |
| "train_steps_per_second": 60.796 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 13200, |
| "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": 1.0596790573590528e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
