metadata
license: mit
tags:
- generated_from_trainer
base_model: ai4bharat/indic-bert
metrics:
- accuracy
- precision
- recall
model-index:
- name: IndicBERT_Finetuned_Final
results: []
IndicBERT_Finetuned_Final
This model is a fine-tuned version of 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