|
--- |
|
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_new_step10_0_100 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# AA_preference_cocour_new_step10_0_100 |
|
|
|
This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the AA_preference_cocour_new_step10_0_100 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4957 |
|
- Rewards/chosen: -0.4320 |
|
- Rewards/rejected: -3.0552 |
|
- Rewards/accuracies: 0.7917 |
|
- Rewards/margins: 2.6232 |
|
- Logps/rejected: -248.9210 |
|
- Logps/chosen: -252.8571 |
|
- Logits/rejected: -2.2740 |
|
- Logits/chosen: -2.3049 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 0.577 | 0.3738 | 50 | 0.5782 | 0.7960 | -0.1800 | 0.7250 | 0.9759 | -220.1687 | -240.5771 | -2.1546 | -2.1689 | |
|
| 0.5388 | 0.7477 | 100 | 0.5391 | -0.4398 | -2.0133 | 0.7479 | 1.5735 | -238.5014 | -252.9343 | -2.1740 | -2.1991 | |
|
| 0.2653 | 1.1215 | 150 | 0.5247 | 0.2862 | -1.6846 | 0.7646 | 1.9708 | -235.2147 | -245.6745 | -2.3266 | -2.3485 | |
|
| 0.2571 | 1.4953 | 200 | 0.5108 | -0.5979 | -3.0808 | 0.7792 | 2.4828 | -249.1766 | -254.5160 | -2.4752 | -2.5016 | |
|
| 0.2803 | 1.8692 | 250 | 0.4817 | -0.2909 | -2.6866 | 0.7854 | 2.3957 | -245.2348 | -251.4460 | -2.3853 | -2.4107 | |
|
| 0.1739 | 2.2430 | 300 | 0.4912 | -0.3815 | -2.8477 | 0.7917 | 2.4662 | -246.8459 | -252.3520 | -2.3281 | -2.3560 | |
|
| 0.1631 | 2.6168 | 350 | 0.4965 | -0.4101 | -3.0083 | 0.7896 | 2.5982 | -248.4518 | -252.6378 | -2.2784 | -2.3092 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.20.3 |
|
|
