metadata
library_name: transformers
base_model: gokulsrinivasagan/bert_tiny_lda_5_v1_book
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_tiny_lda_5_v1_book_mnli
results: []
bert_tiny_lda_5_v1_book_mnli
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_5_v1_book on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8077
- Accuracy: 0.7532
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 |
|---|---|---|---|---|
| 0.7793 | 1.0 | 1534 | 0.6779 | 0.7105 |
| 0.6313 | 2.0 | 3068 | 0.6316 | 0.7361 |
| 0.5474 | 3.0 | 4602 | 0.6253 | 0.7505 |
| 0.4766 | 4.0 | 6136 | 0.6401 | 0.7538 |
| 0.414 | 5.0 | 7670 | 0.6470 | 0.7560 |
| 0.3555 | 6.0 | 9204 | 0.7034 | 0.7555 |
| 0.304 | 7.0 | 10738 | 0.7440 | 0.7554 |
| 0.2609 | 8.0 | 12272 | 0.8077 | 0.7532 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3