metadata
license: apache-2.0
base_model: HuggingFaceM4/idefics2-8b
tags:
- generated_from_trainer
model-index:
- name: gm-qlora-float16-idefics2-8b-midefics
results: []
gm-qlora-float16-idefics2-8b-midefics
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: 0.6749
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4646 | 0.2 | 38 | 0.7746 |
| 0.7849 | 0.4 | 76 | 0.7351 |
| 0.797 | 0.6 | 114 | 0.7129 |
| 0.7429 | 0.8 | 152 | 0.6936 |
| 0.7361 | 1.0 | 190 | 0.6865 |
| 0.587 | 1.2 | 228 | 0.6933 |
| 0.5768 | 1.4 | 266 | 0.6863 |
| 0.5911 | 1.6 | 304 | 0.6815 |
| 0.5815 | 1.8 | 342 | 0.6772 |
| 0.5496 | 2.0 | 380 | 0.6749 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1
- Datasets 2.19.1
- Tokenizers 0.19.1