<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert_sa_GLUE_Experiment_data_aug_qqp
This model is a fine-tuned version of distilbert-base-uncased on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.6240
- Accuracy: 0.8026
- F1: 0.7392
- Combined Score: 0.7709
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
---|---|---|---|---|---|---|
0.2706 | 1.0 | 29671 | 0.6240 | 0.8026 | 0.7392 | 0.7709 |
0.0776 | 2.0 | 59342 | 0.8567 | 0.8033 | 0.7426 | 0.7729 |
0.0413 | 3.0 | 89013 | 0.9095 | 0.8077 | 0.7440 | 0.7759 |
0.0283 | 4.0 | 118684 | 1.0795 | 0.8087 | 0.7408 | 0.7747 |
0.0218 | 5.0 | 148355 | 1.2082 | 0.8097 | 0.7443 | 0.7770 |
0.0183 | 6.0 | 178026 | 1.2471 | 0.8032 | 0.7372 | 0.7702 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2