Downloads · 30 days
1
100% of all-time downloads
idefics2-8b-docvqa-finetuned
BikeshKun/idefics2-8b-docvqa-finetuned
idefics2-8b-docvqa-finetuned is a machine learning model from BikeshKun. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
1
Public
Repo size
93.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors93.4 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 2, 2024
- Updated
- Jul 2, 2024
- SHA
- af160f1c
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
idefics2-8b-docvqa-finetuned
This model is a fine-tuned version of HuggingFaceM4/idefics2-8b-chatty on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3258
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: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2645 | 0.992 | 62 | 0.3258 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- License
- apache-2.0
- Created
- Jul 2, 2024
- Updated
- Jul 2, 2024