sft
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the odia_sft dataset. It achieves the following results on the evaluation set:
- Loss: 0.4275
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2064 | 4.4444 | 500 | 0.3316 |
| 0.0743 | 8.8889 | 1000 | 0.4199 |
Framework versions
- PEFT 0.11.1
- Transformers 4.43.2
- Pytorch 2.3.1+rocm6.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for sam2ai/llama3.1_odia_8b_lora_sft_v1.2
Base model
meta-llama/Llama-3.1-8B