| { |
| "best_global_step": 150, |
| "best_metric": 0.9915354168771638, |
| "best_model_checkpoint": "/content/drive/MyDrive/model/Roberta_Squad/roberta_Squad/checkpoint-150", |
| "epoch": 0.11253868517302823, |
| "eval_steps": 150, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00018756447528838038, |
| "grad_norm": 36.069454193115234, |
| "learning_rate": 0.0, |
| "loss": 2.0268, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00937822376441902, |
| "grad_norm": 36.57353591918945, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 1.9985, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01875644752883804, |
| "grad_norm": 32.89529800415039, |
| "learning_rate": 3.03125e-07, |
| "loss": 1.7123, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.028134671293257058, |
| "grad_norm": 23.408254623413086, |
| "learning_rate": 4.5937500000000005e-07, |
| "loss": 1.0907, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.028134671293257058, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_min": 0.0, |
| "eval_f1_std": 0.4317863265269357, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.6054947972297668, |
| "eval_runtime": 36.4079, |
| "eval_samples_per_second": 116.705, |
| "eval_steps_per_second": 14.612, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.03751289505767608, |
| "grad_norm": 4.343844413757324, |
| "learning_rate": 6.15625e-07, |
| "loss": 0.3569, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.046891118822095096, |
| "grad_norm": 0.511622428894043, |
| "learning_rate": 7.718750000000001e-07, |
| "loss": 0.0798, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.056269342586514115, |
| "grad_norm": 0.18183819949626923, |
| "learning_rate": 9.281250000000001e-07, |
| "loss": 0.0387, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.056269342586514115, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_min": 0.0, |
| "eval_f1_std": 0.4317863265269357, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.04432486742734909, |
| "eval_runtime": 37.6466, |
| "eval_samples_per_second": 112.865, |
| "eval_steps_per_second": 14.131, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.06564756635093313, |
| "grad_norm": 0.1011849194765091, |
| "learning_rate": 1.084375e-06, |
| "loss": 0.0301, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.07502579011535215, |
| "grad_norm": 0.10675793141126633, |
| "learning_rate": 1.240625e-06, |
| "loss": 0.0826, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.08440401387977117, |
| "grad_norm": 0.07607711106538773, |
| "learning_rate": 1.396875e-06, |
| "loss": 0.0407, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.08440401387977117, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_min": 0.0, |
| "eval_f1_std": 0.4317863265269357, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.046333711594343185, |
| "eval_runtime": 38.4453, |
| "eval_samples_per_second": 110.521, |
| "eval_steps_per_second": 13.838, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.09378223764419019, |
| "grad_norm": 5.453103542327881, |
| "learning_rate": 1.553125e-06, |
| "loss": 0.0793, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.10316046140860921, |
| "grad_norm": 10.804566383361816, |
| "learning_rate": 1.709375e-06, |
| "loss": 0.1044, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.11253868517302823, |
| "grad_norm": 0.12722638249397278, |
| "learning_rate": 1.865625e-06, |
| "loss": 0.0787, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.11253868517302823, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_min": 0.0, |
| "eval_f1_std": 0.4317863265269357, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.04333716630935669, |
| "eval_runtime": 35.3066, |
| "eval_samples_per_second": 120.346, |
| "eval_steps_per_second": 15.068, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 31992, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 150, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 4, |
| "early_stopping_threshold": 0.0005 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2525934167654400.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
