metadata
library_name: transformers
base_model: ai4bharat/IndicBART
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: codemix-hi_enhi_4.8
results: []
codemix-hi_enhi_4.8
This model is a fine-tuned version of ai4bharat/IndicBART on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.2552
- Bleu: 13.9653
- Gen Len: 20.928
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 4.4983 | 1.0 | 2787 | 3.8967 | 13.2892 | 20.959 |
| 3.9008 | 2.0 | 5574 | 3.5217 | 12.6416 | 20.963 |
| 3.7108 | 3.0 | 8361 | 3.3617 | 13.5284 | 20.973 |
| 3.6022 | 4.0 | 11148 | 3.2797 | 13.9418 | 20.933 |
| 3.5622 | 5.0 | 13935 | 3.2552 | 13.9653 | 20.928 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2