metadata
library_name: transformers
base_model: gokulsrinivasagan/distilbert_lda_20_v1_book
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert_lda_20_v1_book_mnli
results: []
distilbert_lda_20_v1_book_mnli
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_20_v1_book on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7587
- Accuracy: 0.7882
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 |
|---|---|---|---|---|
| 0.7024 | 1.0 | 1534 | 0.5843 | 0.7646 |
| 0.5147 | 2.0 | 3068 | 0.5409 | 0.7891 |
| 0.407 | 3.0 | 4602 | 0.5485 | 0.7910 |
| 0.3142 | 4.0 | 6136 | 0.6064 | 0.7893 |
| 0.2419 | 5.0 | 7670 | 0.6937 | 0.7876 |
| 0.1866 | 6.0 | 9204 | 0.7425 | 0.7875 |
| 0.1483 | 7.0 | 10738 | 0.7587 | 0.7882 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3