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: 3.5032
- Bleu: 17.4363
- Gen Len: 20.978
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: 1e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 5.8666 | 1.0 | 1004 | 4.9742 | 13.3823 | 21.0 |
| 4.8088 | 2.0 | 2008 | 4.0212 | 15.3375 | 21.0 |
| 4.2735 | 3.0 | 3012 | 3.6499 | 16.3145 | 21.0 |
| 4.0836 | 4.0 | 4016 | 3.5329 | 17.3835 | 20.996 |
| 4.0152 | 5.0 | 5020 | 3.5032 | 17.4363 | 20.978 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1