sft-llava-1.5-7b-hf
This model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9015
- Bleu: 0.1590
- Rouge1: 0.4831
- Rouge2: 0.1929
- Rougel: 0.3755
- Bertscore Precision: 0.6733
- Bertscore Recall: 0.7670
- Bertscore F1: 0.7170
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel | Bertscore Precision | Bertscore Recall | Bertscore F1 |
---|---|---|---|---|---|---|---|---|---|---|
1.8936 | 2.4806 | 200 | 1.9120 | 0.1588 | 0.4829 | 0.1979 | 0.3788 | 0.6785 | 0.7674 | 0.7202 |
1.8101 | 4.9612 | 400 | 1.8884 | 0.1564 | 0.4794 | 0.1903 | 0.3721 | 0.6741 | 0.7674 | 0.7177 |
1.7378 | 7.4419 | 600 | 1.8965 | 0.1585 | 0.4833 | 0.1951 | 0.3754 | 0.6721 | 0.7659 | 0.7158 |
1.7213 | 9.9225 | 800 | 1.9015 | 0.1590 | 0.4831 | 0.1929 | 0.3755 | 0.6733 | 0.7670 | 0.7170 |
Framework versions
- PEFT 0.13.0
- Transformers 4.44.2
- Pytorch 2.2.0a0+81ea7a4
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 9
Model tree for rohitsaxena/sft-llava-1.5-7b-hf
Base model
llava-hf/llava-1.5-7b-hf