kathe-kashmiri-indictrans2
This model is a fine-tuned version of ai4bharat/indictrans2-en-indic-dist-200M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1289
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: 16
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5273 | 1.0 | 2937 | 3.1289 |
| 4.1976 | 2.0 | 5874 | 3.4397 |
| 5.2173 | 3.0 | 8811 | 4.1950 |
| 6.5186 | 4.0 | 11748 | 5.8367 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.10.0+cu128
- Datasets 5.0.1
- Tokenizers 0.15.2
- Downloads last month
- 33
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for AFTAB-E-AALAM/kathe-kashmiri-indictrans2
Base model
ai4bharat/indictrans2-en-indic-dist-200M