Hugging Face's logo

Jsevisal
/
balanced-augmented-roberta-gest-pred-seqeval-partialmatch

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
1
Jsevisal commited on
Commit
452c8e5
·
1 Parent(s): 9cd327f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: balanced-augmented-roberta-gest-pred-seqeval-partialmatch
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # balanced-augmented-roberta-gest-pred-seqeval-partialmatch
19
+
20
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.0890
23
+ - Precision: 0.8168
24
+ - Recall: 0.7954
25
+ - F1: 0.7899
26
+ - Accuracy: 0.7671
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 2e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 16
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 20
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | 3.3 | 1.0 | 32 | 2.8009 | 0.1141 | 0.0540 | 0.0277 | 0.1988 |
58
+ | 2.6869 | 2.0 | 64 | 2.2620 | 0.4024 | 0.2823 | 0.2481 | 0.4226 |
59
+ | 2.1156 | 3.0 | 96 | 1.8908 | 0.5454 | 0.4891 | 0.4747 | 0.5199 |
60
+ | 1.6102 | 4.0 | 128 | 1.5835 | 0.6868 | 0.5677 | 0.5695 | 0.5848 |
61
+ | 1.2618 | 5.0 | 160 | 1.4404 | 0.6727 | 0.6524 | 0.6344 | 0.6268 |
62
+ | 0.9889 | 6.0 | 192 | 1.2944 | 0.6989 | 0.6854 | 0.6678 | 0.6539 |
63
+ | 0.7903 | 7.0 | 224 | 1.2089 | 0.7593 | 0.7300 | 0.7268 | 0.6890 |
64
+ | 0.6012 | 8.0 | 256 | 1.1102 | 0.7518 | 0.7317 | 0.7253 | 0.7002 |
65
+ | 0.4669 | 9.0 | 288 | 1.1172 | 0.7721 | 0.7503 | 0.7444 | 0.7156 |
66
+ | 0.3804 | 10.0 | 320 | 1.0754 | 0.7632 | 0.7568 | 0.7470 | 0.7251 |
67
+ | 0.2976 | 11.0 | 352 | 1.0320 | 0.7794 | 0.7846 | 0.7703 | 0.7539 |
68
+ | 0.2444 | 12.0 | 384 | 1.0436 | 0.7900 | 0.7741 | 0.7734 | 0.7549 |
69
+ | 0.1991 | 13.0 | 416 | 1.0856 | 0.8092 | 0.7860 | 0.7805 | 0.7544 |
70
+ | 0.1706 | 14.0 | 448 | 1.0205 | 0.8078 | 0.7940 | 0.7858 | 0.7719 |
71
+ | 0.1406 | 15.0 | 480 | 1.0274 | 0.8149 | 0.7950 | 0.7914 | 0.7687 |
72
+ | 0.1209 | 16.0 | 512 | 1.0888 | 0.8094 | 0.7949 | 0.7864 | 0.7693 |
73
+ | 0.1145 | 17.0 | 544 | 1.1166 | 0.8103 | 0.7930 | 0.7848 | 0.7613 |
74
+ | 0.1022 | 18.0 | 576 | 1.0935 | 0.8068 | 0.7921 | 0.7842 | 0.7618 |
75
+ | 0.0963 | 19.0 | 608 | 1.0940 | 0.8139 | 0.7948 | 0.7878 | 0.7666 |
76
+ | 0.0953 | 20.0 | 640 | 1.0890 | 0.8168 | 0.7954 | 0.7899 | 0.7671 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.27.3
82
+ - Pytorch 1.13.1+cu116
83
+ - Datasets 2.10.1
84
+ - Tokenizers 0.13.2