tinybert_train_book_v2_mnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_v2 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.5840
- Accuracy: 0.7631
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 |
|---|---|---|---|---|
| 0.7774 | 1.0 | 1534 | 0.6661 | 0.7188 |
| 0.6247 | 2.0 | 3068 | 0.6113 | 0.7501 |
| 0.5397 | 3.0 | 4602 | 0.6048 | 0.7577 |
| 0.4702 | 4.0 | 6136 | 0.6143 | 0.7658 |
| 0.409 | 5.0 | 7670 | 0.6276 | 0.7655 |
| 0.3531 | 6.0 | 9204 | 0.6843 | 0.7641 |
| 0.3063 | 7.0 | 10738 | 0.7110 | 0.7648 |
| 0.2619 | 8.0 | 12272 | 0.7525 | 0.7624 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 2
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_mnli
Base model
distilbert/distilbert-base-uncased
Finetuned
gokulsrinivasagan/tinybert_train_book_v2