metadata
library_name: transformers
license: other
base_model: llava-hf/llava-v1.6-mistral-7b-hf
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: AA_preference_cocour_0_25
results: []
AA_preference_cocour_0_25
This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the AA_preference_cocour_0_25 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5255
- Rewards/chosen: 2.4023
- Rewards/rejected: -0.3121
- Rewards/accuracies: 0.8583
- Rewards/margins: 2.7144
- Logps/rejected: -213.8096
- Logps/chosen: -267.1278
- Logits/rejected: -2.3534
- Logits/chosen: -2.3587
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2339 | 1.4925 | 50 | 0.5196 | 2.3503 | -0.2564 | 0.8500 | 2.6068 | -213.2534 | -267.6478 | -2.2156 | -2.2193 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.20.3