metadata
license: apache-2.0
base_model: HuggingFaceM4/idefics2-8b
tags:
- generated_from_trainer
model-index:
- name: 20240726-kibbe-prod-acr-only-396-redux
results: []
20240726-kibbe-prod-acr-only-396-redux
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: 0.0165
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0549 | 0.4452 | 500 | 0.0203 |
| 1.4694 | 0.8905 | 1000 | 0.0228 |
| 0.7129 | 1.3357 | 1500 | 0.0205 |
| 0.4846 | 1.7809 | 2000 | 0.0165 |
Framework versions
- Transformers 4.44.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1