Hugging Face's logo

pig4431
/
SST2_ALBERT_5E

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Model card Files
xet
Community
1
pig4431 commited on
Commit
96e8009
·
1 Parent(s): f65e6cc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: SST2_ALBERT_5E
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # SST2_ALBERT_5E
16
+
17
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.5698
20
+ - Accuracy: 0.8933
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | 0.5574 | 0.12 | 50 | 0.4424 | 0.8 |
52
+ | 0.4078 | 0.23 | 100 | 0.3995 | 0.8533 |
53
+ | 0.3594 | 0.35 | 150 | 0.3805 | 0.8533 |
54
+ | 0.2952 | 0.46 | 200 | 0.3388 | 0.8933 |
55
+ | 0.3157 | 0.58 | 250 | 0.3629 | 0.8733 |
56
+ | 0.2623 | 0.69 | 300 | 0.5120 | 0.8667 |
57
+ | 0.261 | 0.81 | 350 | 0.2851 | 0.8867 |
58
+ | 0.3071 | 0.92 | 400 | 0.2754 | 0.8733 |
59
+ | 0.2905 | 1.04 | 450 | 0.3013 | 0.8867 |
60
+ | 0.2114 | 1.15 | 500 | 0.3205 | 0.9 |
61
+ | 0.2537 | 1.27 | 550 | 0.4157 | 0.8867 |
62
+ | 0.2106 | 1.39 | 600 | 0.5170 | 0.86 |
63
+ | 0.2227 | 1.5 | 650 | 0.3422 | 0.9 |
64
+ | 0.2304 | 1.62 | 700 | 0.5696 | 0.8533 |
65
+ | 0.2661 | 1.73 | 750 | 0.2975 | 0.9133 |
66
+ | 0.235 | 1.85 | 800 | 0.2692 | 0.92 |
67
+ | 0.2182 | 1.96 | 850 | 0.3247 | 0.9067 |
68
+ | 0.1762 | 2.08 | 900 | 0.3693 | 0.9133 |
69
+ | 0.2086 | 2.19 | 950 | 0.4465 | 0.8933 |
70
+ | 0.1444 | 2.31 | 1000 | 0.4225 | 0.9 |
71
+ | 0.2228 | 2.42 | 1050 | 0.3794 | 0.9067 |
72
+ | 0.1634 | 2.54 | 1100 | 0.4783 | 0.8933 |
73
+ | 0.1561 | 2.66 | 1150 | 0.3476 | 0.9267 |
74
+ | 0.1286 | 2.77 | 1200 | 0.5080 | 0.8933 |
75
+ | 0.1647 | 2.89 | 1250 | 0.4369 | 0.9067 |
76
+ | 0.1059 | 3.0 | 1300 | 0.4132 | 0.9133 |
77
+ | 0.1069 | 3.12 | 1350 | 0.6070 | 0.8733 |
78
+ | 0.108 | 3.23 | 1400 | 0.4909 | 0.9 |
79
+ | 0.0741 | 3.35 | 1450 | 0.5231 | 0.9 |
80
+ | 0.1204 | 3.46 | 1500 | 0.4517 | 0.9067 |
81
+ | 0.106 | 3.58 | 1550 | 0.4685 | 0.8933 |
82
+ | 0.1375 | 3.7 | 1600 | 0.4597 | 0.9067 |
83
+ | 0.0727 | 3.81 | 1650 | 0.4443 | 0.9 |
84
+ | 0.0669 | 3.93 | 1700 | 0.4324 | 0.9067 |
85
+ | 0.081 | 4.04 | 1750 | 0.4176 | 0.9133 |
86
+ | 0.0462 | 4.16 | 1800 | 0.4626 | 0.9133 |
87
+ | 0.0382 | 4.27 | 1850 | 0.4732 | 0.9067 |
88
+ | 0.0948 | 4.39 | 1900 | 0.5471 | 0.9 |
89
+ | 0.0667 | 4.5 | 1950 | 0.5581 | 0.8867 |
90
+ | 0.0878 | 4.62 | 2000 | 0.5429 | 0.8933 |
91
+ | 0.0651 | 4.73 | 2050 | 0.5852 | 0.8933 |
92
+ | 0.0492 | 4.85 | 2100 | 0.5793 | 0.8933 |
93
+ | 0.0496 | 4.97 | 2150 | 0.5698 | 0.8933 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.23.1
99
+ - Pytorch 1.13.0
100
+ - Datasets 2.6.1
101
+ - Tokenizers 0.13.1