|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
base_model: ai4bharat/indic-bert |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: IndicBERT_Finetuned_Final |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# IndicBERT_Finetuned_Final |
|
|
|
This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6539 |
|
- Accuracy: 0.7227 |
|
- Precision: 0.7377 |
|
- Recall: 0.7227 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:| |
|
| 0.8979 | 1.0 | 190 | 0.9064 | 0.5493 | 0.3712 | 0.5493 | |
|
| 0.807 | 2.0 | 380 | 0.7564 | 0.65 | 0.6417 | 0.65 | |
|
| 0.6731 | 3.0 | 570 | 0.6962 | 0.6833 | 0.7411 | 0.6833 | |
|
| 0.6579 | 4.0 | 760 | 0.6723 | 0.6987 | 0.7213 | 0.6987 | |
|
| 0.5946 | 5.0 | 950 | 0.6539 | 0.7227 | 0.7377 | 0.7227 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
