FIRM-Reward
Collection
The data and models of "Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation" • 6 items • Updated
edit_evaluation_sft_202602030104
This model is a fine-tuned version of Qwen/Qwen3-VL-8B-Instruct on the instruction_following_train_v3 and the consistency_train_v3 datasets. It achieves the following results on the evaluation set:
- Loss: 0.5041
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-05
- train_batch_size: 10
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 160
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.591 | 0.2182 | 500 | 0.5827 |
| 0.5605 | 0.4364 | 1000 | 0.5460 |
| 0.5252 | 0.6546 | 1500 | 0.5199 |
| 0.5075 | 0.8728 | 2000 | 0.5055 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.7.1+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 15