Hugging Face's logo

ajtamayoh
/
NeRUBioS_RoBERTa_base_bne_Training_Testing

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ajtamayoh commited on
Commit
1d05130
•
1 Parent(s): c36fe43

Fine-tuning completed

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: PlanTL-GOB-ES/roberta-base-bne
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: NeRUBioS_RoBERTa_base_bne_Training_Testing
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # NeRUBioS_RoBERTa_base_bne_Training_Testing
20
+
21
+ This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.3389
24
+ - Negref Precision: 0.5225
25
+ - Negref Recall: 0.5800
26
+ - Negref F1: 0.5498
27
+ - Neg Precision: 0.9521
28
+ - Neg Recall: 0.9642
29
+ - Neg F1: 0.9581
30
+ - Nsco Precision: 0.8732
31
+ - Nsco Recall: 0.9062
32
+ - Nsco F1: 0.8894
33
+ - Unc Precision: 0.8115
34
+ - Unc Recall: 0.8718
35
+ - Unc F1: 0.8405
36
+ - Usco Precision: 0.6862
37
+ - Usco Recall: 0.7532
38
+ - Usco F1: 0.7181
39
+ - Precision: 0.8150
40
+ - Recall: 0.8557
41
+ - F1: 0.8348
42
+ - Accuracy: 0.9505
43
+
44
+ ## Model description
45
+
46
+ More information needed
47
+
48
+ ## Intended uses & limitations
49
+
50
+ More information needed
51
+
52
+ ## Training and evaluation data
53
+
54
+ More information needed
55
+
56
+ ## Training procedure
57
+
58
+ ### Training hyperparameters
59
+
60
+ The following hyperparameters were used during training:
61
+ - learning_rate: 2e-05
62
+ - train_batch_size: 8
63
+ - eval_batch_size: 8
64
+ - seed: 42
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: linear
67
+ - num_epochs: 12
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Negref Precision | Negref Recall | Negref F1 | Neg Precision | Neg Recall | Neg F1 | Nsco Precision | Nsco Recall | Nsco F1 | Unc Precision | Unc Recall | Unc F1 | Usco Precision | Usco Recall | Usco F1 | Precision | Recall | F1 | Accuracy |
72
+ |:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------:|:-------------:|:----------:|:------:|:--------------:|:-----------:|:-------:|:-------------:|:----------:|:------:|:--------------:|:-----------:|:-------:|:---------:|:------:|:------:|:--------:|
73
+ | 0.1896 | 1.0 | 1729 | 0.1858 | 0.4255 | 0.4655 | 0.4446 | 0.9389 | 0.9501 | 0.9445 | 0.8327 | 0.8775 | 0.8545 | 0.7571 | 0.8231 | 0.7887 | 0.5996 | 0.6967 | 0.6445 | 0.7681 | 0.8136 | 0.7902 | 0.9407 |
74
+ | 0.1143 | 2.0 | 3458 | 0.1772 | 0.4907 | 0.5419 | 0.5150 | 0.9402 | 0.9600 | 0.9500 | 0.8400 | 0.8933 | 0.8658 | 0.7818 | 0.8359 | 0.8079 | 0.6035 | 0.7121 | 0.6533 | 0.7843 | 0.8369 | 0.8098 | 0.9441 |
75
+ | 0.0654 | 3.0 | 5187 | 0.1992 | 0.5314 | 0.4963 | 0.5133 | 0.9513 | 0.9600 | 0.9556 | 0.8648 | 0.8949 | 0.8796 | 0.7916 | 0.8667 | 0.8274 | 0.6033 | 0.7429 | 0.6659 | 0.8086 | 0.8357 | 0.8219 | 0.9459 |
76
+ | 0.0407 | 4.0 | 6916 | 0.2400 | 0.5270 | 0.5448 | 0.5357 | 0.9513 | 0.9607 | 0.9560 | 0.8554 | 0.8858 | 0.8703 | 0.8029 | 0.8462 | 0.8240 | 0.6635 | 0.7147 | 0.6881 | 0.8104 | 0.8364 | 0.8232 | 0.9456 |
77
+ | 0.0208 | 5.0 | 8645 | 0.2612 | 0.5132 | 0.5698 | 0.5400 | 0.9586 | 0.9600 | 0.9593 | 0.8726 | 0.8964 | 0.8843 | 0.8079 | 0.8410 | 0.8241 | 0.6571 | 0.7095 | 0.6823 | 0.8117 | 0.8426 | 0.8269 | 0.9472 |
78
+ | 0.0158 | 6.0 | 10374 | 0.2784 | 0.5019 | 0.5786 | 0.5375 | 0.9520 | 0.9614 | 0.9567 | 0.8669 | 0.9017 | 0.8839 | 0.8177 | 0.8282 | 0.8229 | 0.6490 | 0.7224 | 0.6837 | 0.8041 | 0.8462 | 0.8246 | 0.9485 |
79
+ | 0.0098 | 7.0 | 12103 | 0.3086 | 0.5159 | 0.5727 | 0.5428 | 0.9585 | 0.9572 | 0.9578 | 0.8743 | 0.8888 | 0.8815 | 0.8216 | 0.8385 | 0.8299 | 0.6855 | 0.7172 | 0.7010 | 0.8167 | 0.8402 | 0.8283 | 0.9489 |
80
+ | 0.0038 | 8.0 | 13832 | 0.3087 | 0.5189 | 0.5433 | 0.5308 | 0.9560 | 0.9614 | 0.9587 | 0.8810 | 0.8956 | 0.8882 | 0.8066 | 0.8769 | 0.8403 | 0.6808 | 0.7455 | 0.7117 | 0.8193 | 0.8452 | 0.8321 | 0.9482 |
81
+ | 0.0035 | 9.0 | 15561 | 0.3158 | 0.5147 | 0.5668 | 0.5395 | 0.9573 | 0.9614 | 0.9594 | 0.8820 | 0.8933 | 0.8876 | 0.8063 | 0.8538 | 0.8294 | 0.6573 | 0.7198 | 0.6871 | 0.8144 | 0.8438 | 0.8288 | 0.9501 |
82
+ | 0.0016 | 10.0 | 17290 | 0.3380 | 0.5171 | 0.5536 | 0.5348 | 0.9502 | 0.9656 | 0.9579 | 0.8635 | 0.9047 | 0.8836 | 0.8134 | 0.8718 | 0.8416 | 0.6690 | 0.7481 | 0.7063 | 0.8108 | 0.8509 | 0.8304 | 0.9491 |
83
+ | 0.0004 | 11.0 | 19019 | 0.3369 | 0.5164 | 0.5786 | 0.5457 | 0.9555 | 0.9649 | 0.9602 | 0.8759 | 0.9024 | 0.8890 | 0.8106 | 0.8667 | 0.8377 | 0.6822 | 0.7506 | 0.7148 | 0.8147 | 0.8538 | 0.8338 | 0.9502 |
84
+ | 0.0009 | 12.0 | 20748 | 0.3389 | 0.5225 | 0.5800 | 0.5498 | 0.9521 | 0.9642 | 0.9581 | 0.8732 | 0.9062 | 0.8894 | 0.8115 | 0.8718 | 0.8405 | 0.6862 | 0.7532 | 0.7181 | 0.8150 | 0.8557 | 0.8348 | 0.9505 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.38.2
90
+ - Pytorch 2.2.1+cu121
91
+ - Datasets 2.18.0
92
+ - Tokenizers 0.15.2