Hugging Face's logo

pig4431
/
amazonPolarity_ALBERT_5E

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
pig4431 commited on
Commit
099a705
•
1 Parent(s): 403aebf

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +166 -0
README.md ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - amazon_polarity
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: amazonPolarity_ALBERT_5E
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: amazon_polarity
17
+ type: amazon_polarity
18
+ config: amazon_polarity
19
+ split: train
20
+ args: amazon_polarity
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9533333333333334
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # amazonPolarity_ALBERT_5E
31
+
32
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the amazon_polarity dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2404
35
+ - Accuracy: 0.9533
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 5
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 0.43 | 0.05 | 50 | 0.4090 | 0.8467 |
67
+ | 0.2597 | 0.11 | 100 | 0.3132 | 0.8933 |
68
+ | 0.2517 | 0.16 | 150 | 0.2642 | 0.9 |
69
+ | 0.2218 | 0.21 | 200 | 0.1973 | 0.9333 |
70
+ | 0.21 | 0.27 | 250 | 0.2880 | 0.88 |
71
+ | 0.2076 | 0.32 | 300 | 0.2646 | 0.8933 |
72
+ | 0.2219 | 0.37 | 350 | 0.2053 | 0.94 |
73
+ | 0.2086 | 0.43 | 400 | 0.2122 | 0.92 |
74
+ | 0.1725 | 0.48 | 450 | 0.2145 | 0.92 |
75
+ | 0.2074 | 0.53 | 500 | 0.2174 | 0.9267 |
76
+ | 0.1966 | 0.59 | 550 | 0.2013 | 0.9467 |
77
+ | 0.1777 | 0.64 | 600 | 0.2352 | 0.9133 |
78
+ | 0.1695 | 0.69 | 650 | 0.2965 | 0.9133 |
79
+ | 0.177 | 0.75 | 700 | 0.2204 | 0.94 |
80
+ | 0.187 | 0.8 | 750 | 0.2328 | 0.9133 |
81
+ | 0.1721 | 0.85 | 800 | 0.1713 | 0.9267 |
82
+ | 0.1747 | 0.91 | 850 | 0.2365 | 0.9 |
83
+ | 0.1627 | 0.96 | 900 | 0.2202 | 0.9267 |
84
+ | 0.1421 | 1.01 | 950 | 0.2681 | 0.9133 |
85
+ | 0.1516 | 1.07 | 1000 | 0.2116 | 0.9333 |
86
+ | 0.1196 | 1.12 | 1050 | 0.1885 | 0.94 |
87
+ | 0.1444 | 1.17 | 1100 | 0.2121 | 0.9267 |
88
+ | 0.1198 | 1.23 | 1150 | 0.2335 | 0.9333 |
89
+ | 0.1474 | 1.28 | 1200 | 0.2348 | 0.9067 |
90
+ | 0.125 | 1.33 | 1250 | 0.2401 | 0.9267 |
91
+ | 0.117 | 1.39 | 1300 | 0.2041 | 0.9467 |
92
+ | 0.114 | 1.44 | 1350 | 0.1985 | 0.9467 |
93
+ | 0.1293 | 1.49 | 1400 | 0.1891 | 0.9533 |
94
+ | 0.1231 | 1.55 | 1450 | 0.2168 | 0.9467 |
95
+ | 0.1306 | 1.6 | 1500 | 0.2097 | 0.94 |
96
+ | 0.1449 | 1.65 | 1550 | 0.1790 | 0.9333 |
97
+ | 0.132 | 1.71 | 1600 | 0.1838 | 0.9333 |
98
+ | 0.124 | 1.76 | 1650 | 0.1890 | 0.94 |
99
+ | 0.1419 | 1.81 | 1700 | 0.1575 | 0.9533 |
100
+ | 0.139 | 1.87 | 1750 | 0.1794 | 0.94 |
101
+ | 0.1171 | 1.92 | 1800 | 0.1981 | 0.9533 |
102
+ | 0.1343 | 1.97 | 1850 | 0.1539 | 0.96 |
103
+ | 0.0924 | 2.03 | 1900 | 0.1875 | 0.9533 |
104
+ | 0.0662 | 2.08 | 1950 | 0.2658 | 0.9467 |
105
+ | 0.1024 | 2.13 | 2000 | 0.1869 | 0.9467 |
106
+ | 0.1051 | 2.19 | 2050 | 0.1967 | 0.94 |
107
+ | 0.1047 | 2.24 | 2100 | 0.1625 | 0.9533 |
108
+ | 0.0972 | 2.29 | 2150 | 0.1754 | 0.9533 |
109
+ | 0.0885 | 2.35 | 2200 | 0.1831 | 0.94 |
110
+ | 0.0999 | 2.4 | 2250 | 0.1830 | 0.9533 |
111
+ | 0.0628 | 2.45 | 2300 | 0.1663 | 0.96 |
112
+ | 0.0957 | 2.51 | 2350 | 0.1708 | 0.9467 |
113
+ | 0.0864 | 2.56 | 2400 | 0.1977 | 0.9467 |
114
+ | 0.0752 | 2.61 | 2450 | 0.2427 | 0.9467 |
115
+ | 0.0913 | 2.67 | 2500 | 0.2325 | 0.94 |
116
+ | 0.139 | 2.72 | 2550 | 0.1470 | 0.96 |
117
+ | 0.0839 | 2.77 | 2600 | 0.2193 | 0.94 |
118
+ | 0.1045 | 2.83 | 2650 | 0.1672 | 0.9533 |
119
+ | 0.0775 | 2.88 | 2700 | 0.1782 | 0.96 |
120
+ | 0.0909 | 2.93 | 2750 | 0.2241 | 0.94 |
121
+ | 0.1182 | 2.99 | 2800 | 0.1942 | 0.9533 |
122
+ | 0.0721 | 3.04 | 2850 | 0.1774 | 0.9533 |
123
+ | 0.0562 | 3.09 | 2900 | 0.1877 | 0.9467 |
124
+ | 0.0613 | 3.14 | 2950 | 0.1576 | 0.96 |
125
+ | 0.0433 | 3.2 | 3000 | 0.2294 | 0.9467 |
126
+ | 0.0743 | 3.25 | 3050 | 0.2050 | 0.9533 |
127
+ | 0.0568 | 3.3 | 3100 | 0.1770 | 0.9667 |
128
+ | 0.0785 | 3.36 | 3150 | 0.1732 | 0.96 |
129
+ | 0.0434 | 3.41 | 3200 | 0.2130 | 0.9533 |
130
+ | 0.0534 | 3.46 | 3250 | 0.1902 | 0.9667 |
131
+ | 0.0748 | 3.52 | 3300 | 0.2082 | 0.9333 |
132
+ | 0.0691 | 3.57 | 3350 | 0.1820 | 0.96 |
133
+ | 0.0493 | 3.62 | 3400 | 0.1933 | 0.9533 |
134
+ | 0.0388 | 3.68 | 3450 | 0.2319 | 0.94 |
135
+ | 0.0649 | 3.73 | 3500 | 0.2071 | 0.94 |
136
+ | 0.0369 | 3.78 | 3550 | 0.2092 | 0.9533 |
137
+ | 0.0381 | 3.84 | 3600 | 0.2171 | 0.9533 |
138
+ | 0.0461 | 3.89 | 3650 | 0.2430 | 0.9467 |
139
+ | 0.0682 | 3.94 | 3700 | 0.2372 | 0.9467 |
140
+ | 0.0438 | 4.0 | 3750 | 0.2335 | 0.9467 |
141
+ | 0.0293 | 4.05 | 3800 | 0.2337 | 0.9533 |
142
+ | 0.0313 | 4.1 | 3850 | 0.2349 | 0.9467 |
143
+ | 0.0467 | 4.16 | 3900 | 0.2806 | 0.94 |
144
+ | 0.0243 | 4.21 | 3950 | 0.2493 | 0.94 |
145
+ | 0.0409 | 4.26 | 4000 | 0.2460 | 0.9533 |
146
+ | 0.041 | 4.32 | 4050 | 0.2550 | 0.9533 |
147
+ | 0.0319 | 4.37 | 4100 | 0.2438 | 0.9533 |
148
+ | 0.0457 | 4.42 | 4150 | 0.2469 | 0.9533 |
149
+ | 0.0343 | 4.48 | 4200 | 0.2298 | 0.9533 |
150
+ | 0.0464 | 4.53 | 4250 | 0.2555 | 0.9467 |
151
+ | 0.0289 | 4.58 | 4300 | 0.2486 | 0.9533 |
152
+ | 0.0416 | 4.64 | 4350 | 0.2539 | 0.9533 |
153
+ | 0.0422 | 4.69 | 4400 | 0.2534 | 0.9533 |
154
+ | 0.037 | 4.74 | 4450 | 0.2492 | 0.9467 |
155
+ | 0.0387 | 4.8 | 4500 | 0.2406 | 0.9533 |
156
+ | 0.0472 | 4.85 | 4550 | 0.2411 | 0.9533 |
157
+ | 0.0404 | 4.9 | 4600 | 0.2419 | 0.9533 |
158
+ | 0.0267 | 4.96 | 4650 | 0.2404 | 0.9533 |
159
+
160
+
161
+ ### Framework versions
162
+
163
+ - Transformers 4.24.0
164
+ - Pytorch 1.13.0
165
+ - Datasets 2.6.1
166
+ - Tokenizers 0.13.1