Downloads · 30 days
10
4% of all-time downloads
t5-dialogue-classification
veronica-girolimetti/t5-dialogue-classification
t5-dialogue-classification is a machine learning model from veronica-girolimetti. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
242
Public
Parameters
77M
616 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors308 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Jan 7, 2024
- Updated
- Jan 7, 2024
- SHA
- 054ef830
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. -->
t5-dialogue-classification
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
-
Loss: 0.2827
-
Classification Report: precision recall f1-score support
ALLERGY 1.00 0.92 0.96 12ASSESSMENT 0.14 0.09 0.11 11 CC 0.35 0.55 0.43 11 DIAGNOSIS 0.00 0.00 0.00 1 DISPOSITION 1.00 1.00 1.00 1 EDCOURSE 0.00 0.00 0.00 4 EXAM 0.40 0.40 0.40 5 FAM/SOCHX 0.88 0.96 0.91 45 GENHX 0.77 0.83 0.80 53 GYNHX 0.00 0.00 0.00 1 IMAGING 0.00 0.00 0.00 1 IMMUNIZATIONS 0.00 0.00 0.00 1 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.83 1.00 0.91 10 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.58 0.79 0.67 14 PASTSURGICAL 1.00 0.86 0.92 7 PLAN 0.00 0.00 0.00 1 PROCEDURES 0.00 0.00 0.00 1 ROS 0.85 0.65 0.73 17
accuracy 0.73 200 macro avg 0.39 0.40 0.39 200 weighted avg 0.69 0.73 0.71 200
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 | Classification Report |
|---|---|---|---|---|
| No log | 1.0 | 163 | 0.3372 | precision recall f1-score support |
ALLERGY 1.00 0.92 0.96 12
ASSESSMENT 0.00 0.00 0.00 11 CC 0.20 0.09 0.13 11 DIAGNOSIS 0.00 0.00 0.00 1 DISPOSITION 0.00 0.00 0.00 1 EDCOURSE 0.00 0.00 0.00 4 EXAM 0.50 0.20 0.29 5 FAM/SOCHX 0.90 0.96 0.92 45 GENHX 0.63 0.77 0.69 53 GYNHX 0.00 0.00 0.00 1 IMAGING 0.00 0.00 0.00 1 IMMUNIZATIONS 0.00 0.00 0.00 1 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.83 1.00 0.91 10 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.31 0.64 0.42 14 PASTSURGICAL 0.78 1.00 0.88 7 PLAN 0.00 0.00 0.00 1 PROCEDURES 0.00 0.00 0.00 1 ROS 0.75 0.35 0.48 17
accuracy 0.65 200
macro avg 0.29 0.30 0.28 200
weighted avg 0.61 0.65 0.61 200 | | No log | 2.0 | 326 | 0.2335 | precision recall f1-score support
ALLERGY 1.00 0.92 0.96 12
ASSESSMENT 0.00 0.00 0.00 11 CC 0.26 0.55 0.35 11 DIAGNOSIS 0.00 0.00 0.00 1 DISPOSITION 0.00 0.00 0.00 1 EDCOURSE 0.00 0.00 0.00 4 EXAM 0.67 0.40 0.50 5 FAM/SOCHX 0.88 0.96 0.91 45 GENHX 0.79 0.87 0.83 53 GYNHX 0.00 0.00 0.00 1 IMAGING 0.00 0.00 0.00 1 IMMUNIZATIONS 0.00 0.00 0.00 1 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.83 1.00 0.91 10 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.46 0.79 0.58 14 PASTSURGICAL 1.00 0.86 0.92 7 PLAN 0.00 0.00 0.00 1 PROCEDURES 0.00 0.00 0.00 1 ROS 0.83 0.59 0.69 17
accuracy 0.73 200
macro avg 0.34 0.35 0.33 200
weighted avg 0.68 0.72 0.69 200 | | No log | 3.0 | 489 | 0.2770 | precision recall f1-score support
ALLERGY 1.00 0.92 0.96 12
ASSESSMENT 0.00 0.00 0.00 11 CC 0.26 0.45 0.33 11 DIAGNOSIS 0.00 0.00 0.00 1 DISPOSITION 0.00 0.00 0.00 1 EDCOURSE 0.00 0.00 0.00 4 EXAM 0.50 0.40 0.44 5 FAM/SOCHX 0.88 0.96 0.91 45 GENHX 0.75 0.85 0.80 53 GYNHX 0.00 0.00 0.00 1 IMAGING 0.00 0.00 0.00 1 IMMUNIZATIONS 0.00 0.00 0.00 1 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.83 1.00 0.91 10 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.43 0.64 0.51 14 PASTSURGICAL 0.78 1.00 0.88 7 PLAN 0.00 0.00 0.00 1 PROCEDURES 0.00 0.00 0.00 1 ROS 0.79 0.65 0.71 17
accuracy 0.71 200
macro avg 0.31 0.34 0.32 200
weighted avg 0.65 0.71 0.68 200 | | 0.3713 | 4.0 | 652 | 0.2746 | precision recall f1-score support
ALLERGY 1.00 0.92 0.96 12
ASSESSMENT 0.11 0.09 0.10 11 CC 0.35 0.55 0.43 11 DIAGNOSIS 0.00 0.00 0.00 1 DISPOSITION 1.00 1.00 1.00 1 EDCOURSE 0.00 0.00 0.00 4 EXAM 0.25 0.20 0.22 5 FAM/SOCHX 0.88 0.93 0.90 45 GENHX 0.86 0.83 0.85 53 GYNHX 0.00 0.00 0.00 1 IMAGING 0.00 0.00 0.00 1 IMMUNIZATIONS 0.00 0.00 0.00 1 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.83 1.00 0.91 10 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.52 0.79 0.63 14 PASTSURGICAL 1.00 1.00 1.00 7 PLAN 0.00 0.00 0.00 1 PROCEDURES 0.00 0.00 0.00 1 ROS 0.86 0.71 0.77 17
accuracy 0.73 200
macro avg 0.38 0.40 0.39 200
weighted avg 0.71 0.73 0.71 200 | | 0.3713 | 5.0 | 815 | 0.2827 | precision recall f1-score support
ALLERGY 1.00 0.92 0.96 12
ASSESSMENT 0.14 0.09 0.11 11 CC 0.35 0.55 0.43 11 DIAGNOSIS 0.00 0.00 0.00 1 DISPOSITION 1.00 1.00 1.00 1 EDCOURSE 0.00 0.00 0.00 4 EXAM 0.40 0.40 0.40 5 FAM/SOCHX 0.88 0.96 0.91 45 GENHX 0.77 0.83 0.80 53 GYNHX 0.00 0.00 0.00 1 IMAGING 0.00 0.00 0.00 1 IMMUNIZATIONS 0.00 0.00 0.00 1 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.83 1.00 0.91 10 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.58 0.79 0.67 14 PASTSURGICAL 1.00 0.86 0.92 7 PLAN 0.00 0.00 0.00 1 PROCEDURES 0.00 0.00 0.00 1 ROS 0.85 0.65 0.73 17
accuracy 0.73 200
macro avg 0.39 0.40 0.39 200
weighted avg 0.69 0.73 0.71 200 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Jan 7, 2024
- Updated
- Jan 7, 2024