Instructions to use SU-FMI-AI/multiclinner-enigma-es-procedure-RigoBERTa-Clinical with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SU-FMI-AI/multiclinner-enigma-es-procedure-RigoBERTa-Clinical with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="SU-FMI-AI/multiclinner-enigma-es-procedure-RigoBERTa-Clinical")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("SU-FMI-AI/multiclinner-enigma-es-procedure-RigoBERTa-Clinical") model = AutoModelForTokenClassification.from_pretrained("SU-FMI-AI/multiclinner-enigma-es-procedure-RigoBERTa-Clinical", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- .gitattributes +1 -0
- README.md +27 -0
- tokenizer.json +3 -0
- tokenizer_config.json +18 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -4,6 +4,11 @@ license: other
|
|
| 4 |
base_model: IIC/RigoBERTa-Clinical
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: RigoBERTa-Clinical_es_procedure
|
| 9 |
results: []
|
|
@@ -16,6 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# RigoBERTa-Clinical_es_procedure
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [IIC/RigoBERTa-Clinical](https://huggingface.co/IIC/RigoBERTa-Clinical) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -42,6 +53,22 @@ The following hyperparameters were used during training:
|
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 10
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
### Framework versions
|
| 46 |
|
| 47 |
- Transformers 5.4.0
|
|
|
|
| 4 |
base_model: IIC/RigoBERTa-Clinical
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- f1
|
| 11 |
+
- accuracy
|
| 12 |
model-index:
|
| 13 |
- name: RigoBERTa-Clinical_es_procedure
|
| 14 |
results: []
|
|
|
|
| 21 |
# RigoBERTa-Clinical_es_procedure
|
| 22 |
|
| 23 |
This model is a fine-tuned version of [IIC/RigoBERTa-Clinical](https://huggingface.co/IIC/RigoBERTa-Clinical) on an unknown dataset.
|
| 24 |
+
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 0.0013
|
| 26 |
+
- Precision: 0.9965
|
| 27 |
+
- Recall: 0.9982
|
| 28 |
+
- F1: 0.9973
|
| 29 |
+
- Accuracy: 0.9997
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
|
|
|
| 53 |
- lr_scheduler_type: linear
|
| 54 |
- num_epochs: 10
|
| 55 |
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 60 |
+
| 0.1097 | 1.0 | 739 | 0.0422 | 0.8979 | 0.8993 | 0.8986 | 0.9833 |
|
| 61 |
+
| 0.0658 | 2.0 | 1478 | 0.0285 | 0.9237 | 0.9368 | 0.9302 | 0.9891 |
|
| 62 |
+
| 0.0382 | 3.0 | 2217 | 0.0198 | 0.9278 | 0.9653 | 0.9462 | 0.9925 |
|
| 63 |
+
| 0.0313 | 4.0 | 2956 | 0.0123 | 0.9652 | 0.9734 | 0.9693 | 0.9955 |
|
| 64 |
+
| 0.0182 | 5.0 | 3695 | 0.0078 | 0.9786 | 0.9813 | 0.9799 | 0.9973 |
|
| 65 |
+
| 0.0148 | 6.0 | 4434 | 0.0048 | 0.9850 | 0.9914 | 0.9882 | 0.9984 |
|
| 66 |
+
| 0.0083 | 7.0 | 5173 | 0.0037 | 0.9907 | 0.9918 | 0.9913 | 0.9988 |
|
| 67 |
+
| 0.0069 | 8.0 | 5912 | 0.0020 | 0.9944 | 0.9964 | 0.9954 | 0.9994 |
|
| 68 |
+
| 0.0040 | 9.0 | 6651 | 0.0016 | 0.9961 | 0.9964 | 0.9962 | 0.9995 |
|
| 69 |
+
| 0.0031 | 10.0 | 7390 | 0.0013 | 0.9965 | 0.9982 | 0.9973 | 0.9997 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- Transformers 5.4.0
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
| 3 |
+
size 17082832
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"do_lower_case": false,
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"is_local": false,
|
| 10 |
+
"keep_accents": true,
|
| 11 |
+
"mask_token": "<mask>",
|
| 12 |
+
"model_max_len": 512,
|
| 13 |
+
"model_max_length": 512,
|
| 14 |
+
"pad_token": "<pad>",
|
| 15 |
+
"sep_token": "</s>",
|
| 16 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 17 |
+
"unk_token": "<unk>"
|
| 18 |
+
}
|