|
--- |
|
license: other |
|
base_model: HuggingFaceM4/idefics-9b |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- diffusiondb |
|
model-index: |
|
- name: idefics-9b-ft-describe-diffusion-bf16 |
|
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. --> |
|
|
|
# idefics-9b-ft-describe-diffusion-bf16 |
|
|
|
This model is a fine-tuned version of [HuggingFaceM4/idefics-9b](https://huggingface.co/HuggingFaceM4/idefics-9b) on the diffusiondb dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4081 |
|
|
|
## 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: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.0874 | 0.07 | 50 | 2.1257 | |
|
| 2.0532 | 0.14 | 100 | 1.9973 | |
|
| 1.9417 | 0.21 | 150 | 1.9246 | |
|
| 1.8358 | 0.28 | 200 | 1.8735 | |
|
| 1.8499 | 0.36 | 250 | 1.8305 | |
|
| 1.7695 | 0.43 | 300 | 1.7770 | |
|
| 1.7505 | 0.5 | 350 | 1.7454 | |
|
| 1.713 | 0.57 | 400 | 1.7115 | |
|
| 1.7352 | 0.64 | 450 | 1.6791 | |
|
| 1.6689 | 0.71 | 500 | 1.6526 | |
|
| 1.6183 | 0.78 | 550 | 1.6257 | |
|
| 1.6118 | 0.85 | 600 | 1.6001 | |
|
| 1.6095 | 0.92 | 650 | 1.5800 | |
|
| 1.5598 | 1.0 | 700 | 1.5598 | |
|
| 1.4785 | 1.07 | 750 | 1.5403 | |
|
| 1.4999 | 1.14 | 800 | 1.5219 | |
|
| 1.4589 | 1.21 | 850 | 1.5063 | |
|
| 1.4559 | 1.28 | 900 | 1.4942 | |
|
| 1.4332 | 1.35 | 950 | 1.4792 | |
|
| 1.4859 | 1.42 | 1000 | 1.4658 | |
|
| 1.3888 | 1.49 | 1050 | 1.4537 | |
|
| 1.4032 | 1.56 | 1100 | 1.4445 | |
|
| 1.3702 | 1.64 | 1150 | 1.4352 | |
|
| 1.3625 | 1.71 | 1200 | 1.4276 | |
|
| 1.4067 | 1.78 | 1250 | 1.4199 | |
|
| 1.3829 | 1.85 | 1300 | 1.4149 | |
|
| 1.4251 | 1.92 | 1350 | 1.4103 | |
|
| 1.3619 | 1.99 | 1400 | 1.4081 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
