Llama-3.2-11B-Vision-Instruct_lora_cot
This model is a fine-tuned version of [meta-llama/Llama-3.2-11B-Vision-Instruct(https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct) on the industrial_qa_cot dataset. It achieves the following results on the evaluation set:
- Loss: 0.4842
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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use adamw_torch 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: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5922 | 0.5996 | 500 | 0.5888 |
| 0.5281 | 1.1991 | 1000 | 0.5327 |
| 0.5061 | 1.7987 | 1500 | 0.5039 |
| 0.4397 | 2.3981 | 2000 | 0.4895 |
| 0.4517 | 2.9978 | 2500 | 0.4842 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Marine0506/AnomalyCoT_llama3.2_vision_sft_checkpoint
Base model
meta-llama/Llama-3.2-11B-Vision-Instruct