Hugging Face's logo

Chessmen
/
fine_tune_bert-base-cased

Question Answering
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Chessmen commited on
Commit
765eb97
•
1 Parent(s): 3ac1a78

Training complete

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: bert-base-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: fine_tune_bert-base-cased
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # fine_tune_bert-base-cased
21
+
22
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0842
25
+ - Precision: 0.9376
26
+ - Recall: 0.9541
27
+ - F1: 0.9458
28
+ - Accuracy: 0.9866
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 64
49
+ - eval_batch_size: 64
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 20
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.2667 | 1.0 | 220 | 0.0739 | 0.8619 | 0.9118 | 0.8862 | 0.9776 |
60
+ | 0.0602 | 2.0 | 440 | 0.0641 | 0.9109 | 0.9357 | 0.9231 | 0.9830 |
61
+ | 0.0361 | 3.0 | 660 | 0.0594 | 0.9187 | 0.9401 | 0.9293 | 0.9845 |
62
+ | 0.0234 | 4.0 | 880 | 0.0564 | 0.9233 | 0.9461 | 0.9346 | 0.9854 |
63
+ | 0.0164 | 5.0 | 1100 | 0.0585 | 0.9211 | 0.9465 | 0.9336 | 0.9856 |
64
+ | 0.0123 | 6.0 | 1320 | 0.0656 | 0.9212 | 0.9483 | 0.9346 | 0.9850 |
65
+ | 0.0084 | 7.0 | 1540 | 0.0639 | 0.9290 | 0.9514 | 0.9401 | 0.9864 |
66
+ | 0.0072 | 8.0 | 1760 | 0.0735 | 0.9325 | 0.9482 | 0.9403 | 0.9862 |
67
+ | 0.0051 | 9.0 | 1980 | 0.0745 | 0.9319 | 0.9488 | 0.9403 | 0.9856 |
68
+ | 0.0042 | 10.0 | 2200 | 0.0783 | 0.9308 | 0.9490 | 0.9398 | 0.9858 |
69
+ | 0.0034 | 11.0 | 2420 | 0.0782 | 0.9337 | 0.9509 | 0.9422 | 0.9862 |
70
+ | 0.0026 | 12.0 | 2640 | 0.0822 | 0.9328 | 0.9505 | 0.9416 | 0.9858 |
71
+ | 0.0019 | 13.0 | 2860 | 0.0785 | 0.9335 | 0.9525 | 0.9429 | 0.9862 |
72
+ | 0.0018 | 14.0 | 3080 | 0.0819 | 0.9382 | 0.9525 | 0.9453 | 0.9865 |
73
+ | 0.0015 | 15.0 | 3300 | 0.0846 | 0.9349 | 0.9524 | 0.9436 | 0.9863 |
74
+ | 0.0013 | 16.0 | 3520 | 0.0880 | 0.9353 | 0.9519 | 0.9435 | 0.9860 |
75
+ | 0.0012 | 17.0 | 3740 | 0.0846 | 0.9362 | 0.9527 | 0.9444 | 0.9864 |
76
+ | 0.001 | 18.0 | 3960 | 0.0868 | 0.9374 | 0.9532 | 0.9453 | 0.9864 |
77
+ | 0.0009 | 19.0 | 4180 | 0.0842 | 0.9381 | 0.9536 | 0.9458 | 0.9868 |
78
+ | 0.0009 | 20.0 | 4400 | 0.0842 | 0.9376 | 0.9541 | 0.9458 | 0.9866 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.44.2
84
+ - Pytorch 2.2.0+cu121
85
+ - Datasets 2.21.0
86
+ - Tokenizers 0.19.1