metadata
library_name: transformers
base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert_base_lda_20_v1_book_mrpc
results: []
bert_base_lda_20_v1_book_mrpc
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_20_v1_book on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9451
- Accuracy: 0.7892
- F1: 0.8604
- Combined Score: 0.8248
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6176 | 1.0 | 15 | 0.5701 | 0.7034 | 0.8180 | 0.7607 |
| 0.5574 | 2.0 | 30 | 0.5202 | 0.7377 | 0.8271 | 0.7824 |
| 0.4414 | 3.0 | 45 | 0.5004 | 0.7721 | 0.8312 | 0.8016 |
| 0.3089 | 4.0 | 60 | 0.6028 | 0.7598 | 0.8444 | 0.8021 |
| 0.1931 | 5.0 | 75 | 0.6150 | 0.8162 | 0.8727 | 0.8444 |
| 0.1366 | 6.0 | 90 | 0.7471 | 0.7794 | 0.8548 | 0.8171 |
| 0.0839 | 7.0 | 105 | 0.7483 | 0.7990 | 0.8656 | 0.8323 |
| 0.0409 | 8.0 | 120 | 0.9451 | 0.7892 | 0.8604 | 0.8248 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3