distilbert_lda_20_v1
This model is a fine-tuned version of on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-20 dataset. It achieves the following results on the evaluation set:
- Loss: 4.7631
- Accuracy: 0.5784
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 |
|---|---|---|---|---|
| 8.8106 | 4.1982 | 10000 | 8.6958 | 0.1517 |
| 5.9223 | 8.3963 | 20000 | 5.7065 | 0.4609 |
| 5.188 | 12.5945 | 30000 | 5.0790 | 0.5390 |
| 4.954 | 16.7926 | 40000 | 4.8613 | 0.5659 |
| 4.8413 | 20.9908 | 50000 | 4.7625 | 0.5789 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
- Downloads last month
- 3
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/distilbert_lda_20_v1
Dataset used to train gokulsrinivasagan/distilbert_lda_20_v1
Evaluation results
- Accuracy on gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-20self-reported0.578