metadata
license: other
base_model: HuggingFaceM4/idefics-9b-instruct
tags:
- generated_from_trainer
model-index:
- name: idefics-9b-instruct-ft-instruct-compact
results: []
idefics-9b-instruct-ft-instruct-compact
This model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5312
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9471 | 0.18 | 25 | 3.9005 |
| 3.513 | 0.36 | 50 | 3.4236 |
| 2.8952 | 0.54 | 75 | 2.5822 |
| 1.9127 | 0.73 | 100 | 1.7289 |
| 1.2521 | 0.91 | 125 | 1.0073 |
| 0.7576 | 1.09 | 150 | 0.7103 |
| 0.6537 | 1.27 | 175 | 0.6171 |
| 0.5969 | 1.45 | 200 | 0.5845 |
| 0.5778 | 1.63 | 225 | 0.5681 |
| 0.5663 | 1.82 | 250 | 0.5559 |
| 0.558 | 2.0 | 275 | 0.5471 |
| 0.5595 | 2.18 | 300 | 0.5409 |
| 0.5417 | 2.36 | 325 | 0.5367 |
| 0.5422 | 2.54 | 350 | 0.5341 |
| 0.54 | 2.72 | 375 | 0.5321 |
| 0.5474 | 2.91 | 400 | 0.5312 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0