akash_v1
This model is a fine-tuned version of sarvamai/sarvam-1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 10.6444
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.6339 | 1.0000 | 21071 | 10.6742 |
| 10.6283 | 2.0000 | 42142 | 10.6585 |
| 10.6017 | 3.0000 | 63213 | 10.6522 |
| 10.6133 | 4.0000 | 84284 | 10.6463 |
| 10.5949 | 5.0000 | 105355 | 10.6444 |
Framework versions
- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.6.0+cu118
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for dev-ashvi/akash_v1
Base model
sarvamai/sarvam-1