Hugging Face's logo

Jsevisal
/
balanced-augmented-ft-distilbert-gest-pred-seqeval-partialmatch-2

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
 Metrics Community
2
Jsevisal commited on
Commit
feec673
·
1 Parent(s): 8a01360

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: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: balanced-augmented-distilbert-gest-pred-seqeval-partialmatch-2
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-distilbert-gest-pred-seqeval-partialmatch-2
19
+
20
+ This model is a fine-tuned version of [elastic/distilbert-base-cased-finetuned-conll03-english](https://huggingface.co/elastic/distilbert-base-cased-finetuned-conll03-english) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4169
23
+ - Precision: 0.9354
24
+ - Recall: 0.9332
25
+ - F1: 0.9318
26
+ - Accuracy: 0.9045
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
+ | 3.0695 | 1.0 | 52 | 2.5141 | 0.2818 | 0.1807 | 0.1859 | 0.3513 |
58
+ | 2.0917 | 2.0 | 104 | 1.7339 | 0.5812 | 0.4292 | 0.4154 | 0.5762 |
59
+ | 1.5351 | 3.0 | 156 | 1.3550 | 0.6292 | 0.5467 | 0.5425 | 0.6605 |
60
+ | 1.1628 | 4.0 | 208 | 1.0871 | 0.7170 | 0.6335 | 0.6293 | 0.7178 |
61
+ | 0.9034 | 5.0 | 260 | 0.9700 | 0.7687 | 0.7115 | 0.7025 | 0.7526 |
62
+ | 0.6951 | 6.0 | 312 | 0.7716 | 0.8085 | 0.7743 | 0.7727 | 0.8074 |
63
+ | 0.5451 | 7.0 | 364 | 0.6747 | 0.8210 | 0.8130 | 0.8095 | 0.8192 |
64
+ | 0.4201 | 8.0 | 416 | 0.5731 | 0.8928 | 0.8667 | 0.8719 | 0.8569 |
65
+ | 0.3372 | 9.0 | 468 | 0.5272 | 0.8996 | 0.8765 | 0.8790 | 0.8658 |
66
+ | 0.2615 | 10.0 | 520 | 0.4916 | 0.9093 | 0.8895 | 0.8939 | 0.8716 |
67
+ | 0.2105 | 11.0 | 572 | 0.4471 | 0.9202 | 0.9087 | 0.9108 | 0.8917 |
68
+ | 0.1757 | 12.0 | 624 | 0.4235 | 0.9259 | 0.9147 | 0.9173 | 0.8961 |
69
+ | 0.1472 | 13.0 | 676 | 0.4269 | 0.9308 | 0.9195 | 0.9220 | 0.9000 |
70
+ | 0.1208 | 14.0 | 728 | 0.4233 | 0.9301 | 0.9212 | 0.9229 | 0.9000 |
71
+ | 0.1067 | 15.0 | 780 | 0.4126 | 0.9342 | 0.9273 | 0.9284 | 0.9025 |
72
+ | 0.0886 | 16.0 | 832 | 0.4132 | 0.9346 | 0.9297 | 0.9297 | 0.9045 |
73
+ | 0.0823 | 17.0 | 884 | 0.4301 | 0.9330 | 0.9277 | 0.9273 | 0.9025 |
74
+ | 0.0748 | 18.0 | 936 | 0.4147 | 0.9347 | 0.9325 | 0.9312 | 0.9054 |
75
+ | 0.0731 | 19.0 | 988 | 0.4178 | 0.9357 | 0.9335 | 0.9321 | 0.9049 |
76
+ | 0.0664 | 20.0 | 1040 | 0.4169 | 0.9354 | 0.9332 | 0.9318 | 0.9045 |
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