250212_Abroad_LLaVANeXTVideo_7B
This model is a fine-tuned version of llava-hf/LLaVA-NeXT-Video-7B-hf on the qwen2_vl_dora dataset. It achieves the following results on the evaluation set:
- Loss: 0.1177
- Num Input Tokens Seen: 6558464
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 1.6583 | 1.0354 | 30 | 0.2256 | 1400256 |
| 0.6975 | 2.0708 | 60 | 0.1229 | 2800512 |
| 0.72 | 3.1062 | 90 | 0.1204 | 4200768 |
| 0.1667 | 4.1416 | 120 | 0.1198 | 5601024 |
Framework versions
- PEFT 0.12.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Jeckmu/LLaVA-NeXT-Video-7B-lora-SurveillanceVideo-250212
Base model
llava-hf/LLaVA-NeXT-Video-7B-hf