metadata
license: apache-2.0
base_model: HuggingFaceM4/idefics2-8b
tags:
- generated_from_trainer
model-index:
- name: gm-lora-bfloat16-idefics2-8b-xrayvqa-finetuned-indiana-report
results: []
gm-lora-bfloat16-idefics2-8b-xrayvqa-finetuned-indiana-report
This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5424
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4228 | 0.1932 | 50 | 0.7378 |
| 0.6771 | 0.3864 | 100 | 0.6227 |
| 0.5602 | 0.5796 | 150 | 0.5832 |
| 0.5503 | 0.7728 | 200 | 0.5557 |
| 0.5054 | 0.9660 | 250 | 0.5424 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1