RLAIF-V_L0-q0_50
This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the RLAIF-V_L0-q0_50 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0366
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1363 | 0.3478 | 50 | 1.1215 |
| 1.0856 | 0.6957 | 100 | 1.0748 |
| 0.9426 | 1.0435 | 150 | 1.0553 |
| 0.9144 | 1.3913 | 200 | 1.0432 |
| 0.9069 | 1.7391 | 250 | 1.0292 |
| 0.8152 | 2.0870 | 300 | 1.0396 |
| 0.8141 | 2.4348 | 350 | 1.0376 |
| 0.8097 | 2.7826 | 400 | 1.0366 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.20.3
- Downloads last month
- 15
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for htlou/mm-interp-RLAIF-V_L0-q0_50
Base model
llava-hf/llava-v1.6-mistral-7b-hf