AA_preference_random_0_40
This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the AA_preference_random_0_40 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5902
- Rewards/chosen: 1.1361
- Rewards/rejected: -0.8413
- Rewards/accuracies: 0.7552
- Rewards/margins: 1.9774
- Logps/rejected: -247.4370
- Logps/chosen: -255.4082
- Logits/rejected: -2.3629
- Logits/chosen: -2.3927
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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5323 | 0.9346 | 50 | 0.5824 | 0.9205 | -0.3508 | 0.7396 | 1.2713 | -242.5313 | -257.5635 | -2.3512 | -2.3802 |
| 0.2441 | 1.8692 | 100 | 0.5841 | 1.0720 | -0.7661 | 0.7708 | 1.8380 | -246.6841 | -256.0490 | -2.3634 | -2.3957 |
| 0.1203 | 2.8037 | 150 | 0.5899 | 1.1373 | -0.8378 | 0.7760 | 1.9751 | -247.4010 | -255.3957 | -2.3639 | -2.3938 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.20.3
- Downloads last month
- 15
Inference API (serverless) does not yet support transformers models for this pipeline type.
Model tree for htlou/mm-interp-AA_preference_random_0_40
Base model
llava-hf/llava-v1.6-mistral-7b-hf