llama3.2_1binst_full_sft
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the radiology_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.3101
- Num Input Tokens Seen: 1408680
Model description
Full SFT finetuned with same dataset with v1 version.
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 1.0699 | 0.8475 | 150 | 1.3370 | 398976 |
| 0.7075 | 1.6949 | 300 | 1.1712 | 799168 |
| 0.2458 | 2.5424 | 450 | 1.3173 | 1193632 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for jj97/Radiology_v2_llama3.2_1B_Instruct_Full_SFT
Base model
meta-llama/Llama-3.2-1B-Instruct