distilbert_lda_20
This model is a fine-tuned version of on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld dataset. It achieves the following results on the evaluation set:
- Loss: 4.2679
- Accuracy: 0.5769
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 |
|---|---|---|---|---|
| 8.3243 | 4.1982 | 10000 | 8.2446 | 0.1514 |
| 5.789 | 8.3963 | 20000 | 5.5968 | 0.4033 |
| 4.7261 | 12.5945 | 30000 | 4.6120 | 0.5311 |
| 4.4663 | 16.7926 | 40000 | 4.3618 | 0.5648 |
| 4.3476 | 20.9908 | 50000 | 4.2686 | 0.5743 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Dataset used to train gokulsrinivasagan/distilbert_lda_20
Evaluation results
- Accuracy on gokulsrinivasagan/processed_wikitext-103-raw-v1-ldself-reported0.577