bert_uncased_L-4_H-512_A-8_sst2
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3331
- Accuracy: 0.8899
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 |
|---|---|---|---|---|
| 0.3288 | 1.0 | 264 | 0.3598 | 0.8601 |
| 0.1917 | 2.0 | 528 | 0.3433 | 0.8830 |
| 0.1386 | 3.0 | 792 | 0.3331 | 0.8899 |
| 0.108 | 4.0 | 1056 | 0.4032 | 0.8761 |
| 0.0871 | 5.0 | 1320 | 0.4482 | 0.8670 |
| 0.0734 | 6.0 | 1584 | 0.3767 | 0.8796 |
| 0.0592 | 7.0 | 1848 | 0.4376 | 0.8796 |
| 0.0509 | 8.0 | 2112 | 0.4948 | 0.8716 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 104
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/bert_uncased_L-4_H-512_A-8_sst2
Base model
google/bert_uncased_L-4_H-512_A-8