|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: HuggingFaceM4/idefics-9b |
|
model-index: |
|
- name: idefics-9b-YBT-Scores |
|
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-YBT-Scores |
|
|
|
This model is a fine-tuned version of [HuggingFaceM4/idefics-9b](https://huggingface.co/HuggingFaceM4/idefics-9b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.6189 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.1253 | 2.76 | 10 | 1.8248 | |
|
| 1.3929 | 5.52 | 20 | 1.6206 | |
|
| 1.1155 | 8.28 | 30 | 1.6422 | |
|
| 0.8392 | 11.03 | 40 | 1.6946 | |
|
| 0.5928 | 13.79 | 50 | 1.8916 | |
|
| 0.4053 | 16.55 | 60 | 2.0038 | |
|
| 0.2454 | 19.31 | 70 | 2.2366 | |
|
| 0.1412 | 22.07 | 80 | 2.3802 | |
|
| 0.0798 | 24.83 | 90 | 2.5553 | |
|
| 0.0667 | 27.59 | 100 | 2.6189 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.1.dev0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |