bert_base_lda_50_v1
This model is a fine-tuned version of on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-50 dataset. It achieves the following results on the evaluation set:
- Loss: 8.4597
- Accuracy: 0.2087
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: 0.0001
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 9.5406 | 4.1982 | 10000 | 9.4149 | 0.1506 |
| 9.0789 | 8.3963 | 20000 | 9.0822 | 0.1531 |
| 8.9645 | 12.5945 | 30000 | 9.0110 | 0.1552 |
| 8.8927 | 16.7926 | 40000 | 8.9826 | 0.1533 |
| 8.5333 | 20.9908 | 50000 | 8.5200 | 0.2046 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
- Downloads last month
- 30
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for gokulsrinivasagan/bert_base_lda_50_v1
Dataset used to train gokulsrinivasagan/bert_base_lda_50_v1
Evaluation results
- Accuracy on gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-50self-reported0.209