bert_tiny_lda_20_v1_mnli
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_20_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7126
- Accuracy: 0.6955
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 |
|---|---|---|---|---|
| 0.9696 | 1.0 | 1534 | 0.8635 | 0.6102 |
| 0.8307 | 2.0 | 3068 | 0.7849 | 0.6501 |
| 0.7523 | 3.0 | 4602 | 0.7467 | 0.6728 |
| 0.6962 | 4.0 | 6136 | 0.7247 | 0.6862 |
| 0.6472 | 5.0 | 7670 | 0.7248 | 0.6957 |
| 0.6032 | 6.0 | 9204 | 0.7455 | 0.6984 |
| 0.5606 | 7.0 | 10738 | 0.7510 | 0.6987 |
| 0.5204 | 8.0 | 12272 | 0.7849 | 0.6915 |
| 0.4808 | 9.0 | 13806 | 0.8428 | 0.6963 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for gokulsrinivasagan/bert_tiny_lda_20_v1_mnli
Base model
gokulsrinivasagan/bert_tiny_lda_20_v1