flan-t5-base-nvidia
This model is a fine-tuned version of google/flan-t5-base trained on ajsbsd/datasets/nvidia-qa
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
It achieves the following results on the evaluation set:
- Loss: 1.7117
- Rouge1: 0.4290
- Rouge2: 0.2696
- Rougel: 0.3880
- Rougelsum: 0.3928
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 |
|---|---|---|---|---|---|---|---|
| 2.4618 | 1.0 | 711 | 1.9707 | 0.3886 | 0.2185 | 0.3472 | 0.3522 |
| 2.0575 | 2.0 | 1422 | 1.8104 | 0.4066 | 0.2407 | 0.3647 | 0.3701 |
| 1.5839 | 3.0 | 2133 | 1.7351 | 0.4185 | 0.2558 | 0.3770 | 0.3821 |
| 1.4314 | 4.0 | 2844 | 1.7079 | 0.4252 | 0.2655 | 0.3840 | 0.3892 |
| 1.2582 | 5.0 | 3555 | 1.7117 | 0.4290 | 0.2696 | 0.3880 | 0.3928 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0