tinybert_train_book_v2_qnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_v2 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3852
- Accuracy: 0.8281
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
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5204 | 1.0 | 410 | 0.4145 | 0.8076 |
| 0.4116 | 2.0 | 820 | 0.3852 | 0.8281 |
| 0.3476 | 3.0 | 1230 | 0.3940 | 0.8217 |
| 0.2911 | 4.0 | 1640 | 0.4025 | 0.8327 |
| 0.2375 | 5.0 | 2050 | 0.4463 | 0.8250 |
| 0.1928 | 6.0 | 2460 | 0.4887 | 0.8301 |
| 0.1546 | 7.0 | 2870 | 0.5191 | 0.8283 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for gokulsrinivasagan/tinybert_train_book_v2_qnli
Base model
distilbert/distilbert-base-uncased
Finetuned
gokulsrinivasagan/tinybert_train_book_v2