| { |
| "best_global_step": 880, |
| "best_metric": 0.004267565440386534, |
| "best_model_checkpoint": "/content/drive/MyDrive/evo_CodeT5plus_fullFT/checkpoint-880", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1320, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.3628389537334442, |
| "learning_rate": 3e-05, |
| "loss": 0.4384054010564631, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.020545126870274544, |
| "eval_runtime": 15.8299, |
| "eval_samples_per_second": 13.898, |
| "eval_steps_per_second": 6.949, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.011017576791346073, |
| "learning_rate": 3e-05, |
| "loss": 0.05806919444691051, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.011296279728412628, |
| "eval_runtime": 15.6712, |
| "eval_samples_per_second": 14.038, |
| "eval_steps_per_second": 7.019, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7181199789047241, |
| "learning_rate": 3e-05, |
| "loss": 0.034655919941988855, |
| "step": 660 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.004910873249173164, |
| "eval_runtime": 15.6022, |
| "eval_samples_per_second": 14.101, |
| "eval_steps_per_second": 7.05, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.009874860756099224, |
| "learning_rate": 3e-05, |
| "loss": 0.01791459538719871, |
| "step": 880 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.004267565440386534, |
| "eval_runtime": 15.9107, |
| "eval_samples_per_second": 13.827, |
| "eval_steps_per_second": 6.914, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.03301338851451874, |
| "learning_rate": 3e-05, |
| "loss": 0.016247032989155162, |
| "step": 1100 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.007896807044744492, |
| "eval_runtime": 15.7075, |
| "eval_samples_per_second": 14.006, |
| "eval_steps_per_second": 7.003, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 5.63120174407959, |
| "learning_rate": 3e-05, |
| "loss": 0.01246725862676447, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.004386806860566139, |
| "eval_runtime": 15.5503, |
| "eval_samples_per_second": 14.148, |
| "eval_steps_per_second": 7.074, |
| "step": 1320 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6063405351321600.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
