llama4-medical-finetuned
This model is a fine-tuned version of meta-llama/Llama-4-Scout-17B-16E-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.3331
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.4344 | 1.0 | 75 | 7.4153 |
| 7.3254 | 2.0 | 150 | 7.3079 |
| 7.3404 | 3.0 | 225 | 7.3313 |
| 7.316 | 4.0 | 300 | 7.3104 |
| 7.3159 | 5.0 | 375 | 7.3172 |
| 7.32 | 6.0 | 450 | 7.3138 |
| 7.3188 | 7.0 | 525 | 7.3098 |
| 7.3167 | 8.0 | 600 | 7.3209 |
| 7.3184 | 9.0 | 675 | 7.3284 |
| 7.3227 | 10.0 | 750 | 7.3331 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- 42
Model tree for Sathvik265/llama4-medical-finetuned
Base model
meta-llama/Llama-4-Scout-17B-16E