Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
finetune-clip-flickr8
This model is a fine-tuned version of ybelkada/blip2-opt-2.7b-fp16-sharded on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7363
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_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: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8236 | 0.5650 | 1000 | 1.7750 |
| 1.7656 | 1.1299 | 2000 | 1.7508 |
| 1.7662 | 1.6949 | 3000 | 1.7363 |
Framework versions
- PEFT 0.15.2.dev0
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for duythanh1022/finetune-clip-flickr8
Base model
ybelkada/blip2-opt-2.7b-fp16-sharded