Downloads · 30 days
1
4% of all-time downloads
BMU_Finetuned_BIO-T5_MedQuad
Radhikaaaa/BMU_Finetuned_BIO-T5_MedQuad
BMU_Finetuned_BIO-T5_MedQuad is a machine learning model from Radhikaaaa. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Parameters
252M
1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- t5
- Access
- Public
- Created
- Apr 8, 2025
- Updated
- Apr 8, 2025
- SHA
- d51193cb
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
BMU_Finetuned_BIO-T5_MedQuad
This model is a fine-tuned version of QizhiPei/biot5-plus-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7809
- Rouge1: 33.17
- Rouge2: 21.92
- Rougel: 29.98
- Rougelsum: 30.13
- Meteor: 26.03
- Bertscore Precision: 83.93
- Bertscore Recall: 83.04
- Bertscore F1: 83.42
- Gen Len: 253.87
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Meteor | Bertscore Precision | Bertscore Recall | Bertscore F1 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.9374 | 1.0 | 411 | 1.9522 | 30.44 | 20.11 | 27.91 | 28.03 | 24.37 | 82.41 | 82.4 | 82.34 | 284.71 |
| 1.8427 | 2.0 | 822 | 1.8545 | 31.88 | 21.02 | 29.02 | 29.16 | 24.87 | 83.37 | 82.69 | 82.96 | 258.57 |
| 1.7604 | 3.0 | 1233 | 1.8089 | 32.57 | 21.39 | 29.52 | 29.64 | 25.49 | 83.6 | 82.86 | 83.17 | 258.54 |
| 1.6879 | 4.0 | 1644 | 1.7866 | 33.04 | 21.95 | 30.0 | 30.11 | 26.03 | 83.83 | 82.99 | 83.35 | 257.24 |
| 1.697 | 4.9896 | 2050 | 1.7809 | 33.17 | 21.92 | 29.98 | 30.13 | 26.03 | 83.93 | 83.04 | 83.42 | 253.87 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Library
- transformers
- Type
- t5
- License
- mit
- Created
- Apr 8, 2025
- Updated
- Apr 8, 2025