metadata
library_name: peft
base_model: sarvamai/sarvam-1
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Dr25_Abu_Mala_llama321
results: []
Dr25_Abu_Mala_llama321
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: nan
- Accuracy: 0.5351
- F1: 0.3731
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-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0 | 0.9829 | 43 | nan | 0.5351 | 0.3731 |
| 0.0 | 1.9829 | 86 | nan | 0.5351 | 0.3731 |
| 0.0 | 2.9829 | 129 | nan | 0.5351 | 0.3731 |
| 0.0 | 3.9829 | 172 | nan | 0.5351 | 0.3731 |
| 0.0 | 4.9829 | 215 | nan | 0.5351 | 0.3731 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0