|
--- |
|
license: apache-2.0 |
|
base_model: HuggingFaceM4/idefics2-8b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gm-qlora-float16-idefics2-8b-midefics |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# gm-qlora-float16-idefics2-8b-midefics |
|
|
|
This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6739 |
|
|
|
## 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: 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: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.5316 | 0.2 | 38 | 0.7854 | |
|
| 0.7931 | 0.4 | 76 | 0.7384 | |
|
| 0.8019 | 0.6 | 114 | 0.7167 | |
|
| 0.7487 | 0.8 | 152 | 0.6992 | |
|
| 0.7416 | 1.0 | 190 | 0.6887 | |
|
| 0.5919 | 1.2 | 228 | 0.6977 | |
|
| 0.5819 | 1.4 | 266 | 0.6903 | |
|
| 0.5948 | 1.6 | 304 | 0.6849 | |
|
| 0.5858 | 1.8 | 342 | 0.6780 | |
|
| 0.5539 | 2.0 | 380 | 0.6739 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0.dev0 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|