metadata
library_name: transformers
base_model: ai4bharat/IndicBART
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: codemix-test
results: []
codemix-test
This model is a fine-tuned version of ai4bharat/IndicBART on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6472
- Bleu: 30.874
- Gen Len: 14.395
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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 7.0739 | 0.9965 | 500 | 3.9011 | 25.8809 | 21.0 |
| 2.6832 | 1.9945 | 1000 | 1.1507 | 31.3951 | 14.701 |
| 1.0226 | 2.9925 | 1500 | 0.6472 | 30.874 | 14.395 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1