metadata
library_name: transformers
license: mit
base_model: ai4bharat/indic-bert
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: indic-bert-hate-mr
results: []
indic-bert-hate-mr
This model is a fine-tuned version of ai4bharat/indic-bert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2408
- Accuracy: 0.9226
- Precision: 0.9270
- Recall: 0.9225
- F1: 0.9224
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: 16
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.6637 | 1.0 | 61 | 0.6441 | 0.6530 | 0.6780 | 0.6526 | 0.6400 |
0.678 | 2.0 | 122 | 0.6538 | 0.6386 | 0.6408 | 0.6387 | 0.6372 |
0.6422 | 3.0 | 183 | 0.6597 | 0.6410 | 0.6607 | 0.6405 | 0.6292 |
0.6281 | 4.0 | 244 | 0.6202 | 0.6578 | 0.6591 | 0.6579 | 0.6573 |
0.5374 | 5.0 | 305 | 0.6306 | 0.6723 | 0.6746 | 0.6721 | 0.6711 |
0.4418 | 6.0 | 366 | 0.7122 | 0.6795 | 0.6991 | 0.6799 | 0.6717 |
0.3981 | 7.0 | 427 | 0.7183 | 0.6602 | 0.6603 | 0.6602 | 0.6602 |
0.3054 | 8.0 | 488 | 0.8008 | 0.6867 | 0.6889 | 0.6869 | 0.6859 |
0.2445 | 9.0 | 549 | 0.9741 | 0.6578 | 0.6587 | 0.6577 | 0.6573 |
0.1882 | 10.0 | 610 | 0.9924 | 0.6723 | 0.6723 | 0.6723 | 0.6723 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0