| { |
| "best_metric": 0.871670061638581, |
| "best_model_checkpoint": "./nlu_finetuned_models/mrpc/roberta-large_lr1e-05/checkpoint-1242", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 2070, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8065395095367848, |
| "eval_averaged_scores": 0.8346043775923768, |
| "eval_f1": 0.862669245647969, |
| "eval_loss": 0.4804929494857788, |
| "eval_runtime": 0.6868, |
| "eval_samples_per_second": 534.344, |
| "eval_steps_per_second": 33.487, |
| "step": 207 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8283378746594006, |
| "eval_averaged_scores": 0.8539394918230081, |
| "eval_f1": 0.8795411089866156, |
| "eval_loss": 0.37118858098983765, |
| "eval_runtime": 0.6817, |
| "eval_samples_per_second": 538.397, |
| "eval_steps_per_second": 33.742, |
| "step": 414 |
| }, |
| { |
| "epoch": 2.4154589371980677, |
| "grad_norm": 4.831421375274658, |
| "learning_rate": 8.071979434447301e-06, |
| "loss": 0.4647, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8419618528610354, |
| "eval_averaged_scores": 0.8641181813324785, |
| "eval_f1": 0.8862745098039215, |
| "eval_loss": 0.48132672905921936, |
| "eval_runtime": 0.6832, |
| "eval_samples_per_second": 537.177, |
| "eval_steps_per_second": 33.665, |
| "step": 621 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8119891008174387, |
| "eval_averaged_scores": 0.8351526612916762, |
| "eval_f1": 0.8583162217659138, |
| "eval_loss": 0.8502127528190613, |
| "eval_runtime": 0.6878, |
| "eval_samples_per_second": 533.624, |
| "eval_steps_per_second": 33.442, |
| "step": 828 |
| }, |
| { |
| "epoch": 4.830917874396135, |
| "grad_norm": 0.43216827511787415, |
| "learning_rate": 5.501285347043702e-06, |
| "loss": 0.195, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8147138964577657, |
| "eval_averaged_scores": 0.8340810861599173, |
| "eval_f1": 0.853448275862069, |
| "eval_loss": 0.8322831988334656, |
| "eval_runtime": 0.6811, |
| "eval_samples_per_second": 538.838, |
| "eval_steps_per_second": 33.769, |
| "step": 1035 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8501362397820164, |
| "eval_averaged_scores": 0.871670061638581, |
| "eval_f1": 0.8932038834951456, |
| "eval_loss": 0.8657367825508118, |
| "eval_runtime": 0.6818, |
| "eval_samples_per_second": 538.266, |
| "eval_steps_per_second": 33.733, |
| "step": 1242 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8474114441416893, |
| "eval_averaged_scores": 0.8688037612865309, |
| "eval_f1": 0.8901960784313726, |
| "eval_loss": 1.0117260217666626, |
| "eval_runtime": 0.6848, |
| "eval_samples_per_second": 535.935, |
| "eval_steps_per_second": 33.587, |
| "step": 1449 |
| }, |
| { |
| "epoch": 7.246376811594203, |
| "grad_norm": 68.54472351074219, |
| "learning_rate": 2.9305912596401033e-06, |
| "loss": 0.0681, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8501362397820164, |
| "eval_averaged_scores": 0.8703961517001533, |
| "eval_f1": 0.8906560636182902, |
| "eval_loss": 1.031515121459961, |
| "eval_runtime": 0.6825, |
| "eval_samples_per_second": 537.742, |
| "eval_steps_per_second": 33.7, |
| "step": 1656 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8474114441416893, |
| "eval_averaged_scores": 0.868369753691398, |
| "eval_f1": 0.8893280632411067, |
| "eval_loss": 1.0883642435073853, |
| "eval_runtime": 0.683, |
| "eval_samples_per_second": 537.339, |
| "eval_steps_per_second": 33.675, |
| "step": 1863 |
| }, |
| { |
| "epoch": 9.66183574879227, |
| "grad_norm": 0.01603771187365055, |
| "learning_rate": 3.598971722365039e-07, |
| "loss": 0.0242, |
| "step": 2000 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.8474114441416893, |
| "eval_averaged_scores": 0.8692310138996384, |
| "eval_f1": 0.8910505836575875, |
| "eval_loss": 1.1239808797836304, |
| "eval_runtime": 0.6749, |
| "eval_samples_per_second": 543.751, |
| "eval_steps_per_second": 34.077, |
| "step": 2070 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 2070, |
| "total_flos": 4586336388558792.0, |
| "train_loss": 0.18168080317009475, |
| "train_runtime": 314.5545, |
| "train_samples_per_second": 104.942, |
| "train_steps_per_second": 6.581 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2070, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4586336388558792.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
