metadata
library_name: transformers
license: mit
base_model: ai4bharat/indic-bert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: guj-eng-code-switch-indic-bert-data3
results: []
guj-eng-code-switch-indic-bert-data3
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: 0.1909
- Precision: 0.8836
- Recall: 0.9042
- F1: 0.8938
- Accuracy: 0.9578
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3428 | 1.0 | 247 | 0.3108 | 0.8107 | 0.8446 | 0.8273 | 0.9271 |
| 0.209 | 2.0 | 494 | 0.2041 | 0.8681 | 0.8953 | 0.8815 | 0.9502 |
| 0.1745 | 3.0 | 741 | 0.1909 | 0.8836 | 0.9042 | 0.8938 | 0.9578 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1