flan-t5-small-nvidia
Imported from Kaggle (https://www.kaggle.com/datasets/gondimalladeepesh/nvidia-documentation-question-and-answer-pairs)
Q&A dataset for LLM finetuning about the NVIDIA about SDKs and blogs
This model is a fine-tuned version of google/flan-t5-small trained on ajsbsd/datasets/nvidia-qa
It achieves the following results on the evaluation set:
- Loss: 2.0857
- Rouge1: 0.3970
- Rouge2: 0.2295
- Rougel: 0.3537
- Rougelsum: 0.3593
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.8569 | 1.0 | 711 | 2.3454 | 0.3748 | 0.2036 | 0.3321 | 0.3375 |
| 2.5034 | 2.0 | 1422 | 2.2079 | 0.3841 | 0.2143 | 0.3417 | 0.3465 |
| 2.1886 | 3.0 | 2133 | 2.1342 | 0.3900 | 0.2227 | 0.3494 | 0.3543 |
| 2.0784 | 4.0 | 2844 | 2.0972 | 0.3951 | 0.2267 | 0.3522 | 0.3571 |
| 1.9843 | 5.0 | 3555 | 2.0857 | 0.3970 | 0.2295 | 0.3537 | 0.3593 |
Framework versions
- Transformers 4.35.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1