Hugging Face's logo

pig4431
/
IMDB_ALBERT_5E

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Eval Results
Model card Files
xet
Community
1
pig4431 commited on
Commit
d72dc73
·
1 Parent(s): 4d4815f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +151 -0
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imdb
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: IMDB_ALBERT_5E
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: imdb
17
+ type: imdb
18
+ config: plain_text
19
+ split: train
20
+ args: plain_text
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9466666666666667
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
+ # IMDB_ALBERT_5E
31
+
32
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the imdb dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2220
35
+ - Accuracy: 0.9467
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: 16
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
+ | 0.5285 | 0.06 | 50 | 0.2692 | 0.9133 |
67
+ | 0.3515 | 0.13 | 100 | 0.2054 | 0.9267 |
68
+ | 0.2314 | 0.19 | 150 | 0.1669 | 0.94 |
69
+ | 0.2147 | 0.26 | 200 | 0.1660 | 0.92 |
70
+ | 0.2053 | 0.32 | 250 | 0.1546 | 0.94 |
71
+ | 0.2143 | 0.38 | 300 | 0.1636 | 0.9267 |
72
+ | 0.1943 | 0.45 | 350 | 0.2068 | 0.9467 |
73
+ | 0.2107 | 0.51 | 400 | 0.1655 | 0.9333 |
74
+ | 0.2059 | 0.58 | 450 | 0.1782 | 0.94 |
75
+ | 0.1839 | 0.64 | 500 | 0.1695 | 0.94 |
76
+ | 0.2014 | 0.7 | 550 | 0.1481 | 0.9333 |
77
+ | 0.2215 | 0.77 | 600 | 0.1588 | 0.9267 |
78
+ | 0.1837 | 0.83 | 650 | 0.1352 | 0.9333 |
79
+ | 0.1938 | 0.9 | 700 | 0.1389 | 0.94 |
80
+ | 0.221 | 0.96 | 750 | 0.1193 | 0.9467 |
81
+ | 0.1843 | 1.02 | 800 | 0.1294 | 0.9467 |
82
+ | 0.1293 | 1.09 | 850 | 0.1585 | 0.9467 |
83
+ | 0.1517 | 1.15 | 900 | 0.1353 | 0.9467 |
84
+ | 0.137 | 1.21 | 950 | 0.1391 | 0.9467 |
85
+ | 0.1858 | 1.28 | 1000 | 0.1547 | 0.9333 |
86
+ | 0.1478 | 1.34 | 1050 | 0.1019 | 0.9533 |
87
+ | 0.155 | 1.41 | 1100 | 0.1154 | 0.9667 |
88
+ | 0.1439 | 1.47 | 1150 | 0.1306 | 0.9467 |
89
+ | 0.1476 | 1.53 | 1200 | 0.2085 | 0.92 |
90
+ | 0.1702 | 1.6 | 1250 | 0.1190 | 0.9467 |
91
+ | 0.1517 | 1.66 | 1300 | 0.1303 | 0.9533 |
92
+ | 0.1551 | 1.73 | 1350 | 0.1200 | 0.9467 |
93
+ | 0.1554 | 1.79 | 1400 | 0.1297 | 0.9533 |
94
+ | 0.1543 | 1.85 | 1450 | 0.1222 | 0.96 |
95
+ | 0.1242 | 1.92 | 1500 | 0.1418 | 0.9467 |
96
+ | 0.1312 | 1.98 | 1550 | 0.1279 | 0.9467 |
97
+ | 0.1292 | 2.05 | 1600 | 0.1255 | 0.9533 |
98
+ | 0.0948 | 2.11 | 1650 | 0.1305 | 0.9667 |
99
+ | 0.088 | 2.17 | 1700 | 0.1912 | 0.9333 |
100
+ | 0.0949 | 2.24 | 1750 | 0.1594 | 0.9333 |
101
+ | 0.1094 | 2.3 | 1800 | 0.1958 | 0.9467 |
102
+ | 0.1179 | 2.37 | 1850 | 0.1427 | 0.94 |
103
+ | 0.1116 | 2.43 | 1900 | 0.1551 | 0.9333 |
104
+ | 0.0742 | 2.49 | 1950 | 0.1743 | 0.94 |
105
+ | 0.1016 | 2.56 | 2000 | 0.1603 | 0.9533 |
106
+ | 0.0835 | 2.62 | 2050 | 0.1866 | 0.9333 |
107
+ | 0.0882 | 2.69 | 2100 | 0.1191 | 0.9467 |
108
+ | 0.1032 | 2.75 | 2150 | 0.1420 | 0.96 |
109
+ | 0.0957 | 2.81 | 2200 | 0.1403 | 0.96 |
110
+ | 0.1234 | 2.88 | 2250 | 0.1232 | 0.96 |
111
+ | 0.0669 | 2.94 | 2300 | 0.1557 | 0.9467 |
112
+ | 0.0994 | 3.01 | 2350 | 0.1270 | 0.9533 |
113
+ | 0.0583 | 3.07 | 2400 | 0.1520 | 0.9533 |
114
+ | 0.0651 | 3.13 | 2450 | 0.1641 | 0.9467 |
115
+ | 0.0384 | 3.2 | 2500 | 0.2165 | 0.94 |
116
+ | 0.0839 | 3.26 | 2550 | 0.1755 | 0.9467 |
117
+ | 0.0546 | 3.32 | 2600 | 0.1782 | 0.9333 |
118
+ | 0.0703 | 3.39 | 2650 | 0.1945 | 0.94 |
119
+ | 0.0734 | 3.45 | 2700 | 0.2139 | 0.9467 |
120
+ | 0.0629 | 3.52 | 2750 | 0.1445 | 0.9467 |
121
+ | 0.0513 | 3.58 | 2800 | 0.1613 | 0.9667 |
122
+ | 0.0794 | 3.64 | 2850 | 0.1742 | 0.9333 |
123
+ | 0.0537 | 3.71 | 2900 | 0.1745 | 0.9467 |
124
+ | 0.0553 | 3.77 | 2950 | 0.1724 | 0.96 |
125
+ | 0.0483 | 3.84 | 3000 | 0.1638 | 0.9533 |
126
+ | 0.0647 | 3.9 | 3050 | 0.1986 | 0.9467 |
127
+ | 0.0443 | 3.96 | 3100 | 0.1926 | 0.9533 |
128
+ | 0.0418 | 4.03 | 3150 | 0.1879 | 0.94 |
129
+ | 0.0466 | 4.09 | 3200 | 0.2058 | 0.9333 |
130
+ | 0.0491 | 4.16 | 3250 | 0.2017 | 0.9467 |
131
+ | 0.0287 | 4.22 | 3300 | 0.2020 | 0.9533 |
132
+ | 0.0272 | 4.28 | 3350 | 0.1974 | 0.9533 |
133
+ | 0.0359 | 4.35 | 3400 | 0.2242 | 0.9333 |
134
+ | 0.0405 | 4.41 | 3450 | 0.2157 | 0.94 |
135
+ | 0.0309 | 4.48 | 3500 | 0.2142 | 0.9467 |
136
+ | 0.033 | 4.54 | 3550 | 0.2163 | 0.94 |
137
+ | 0.0408 | 4.6 | 3600 | 0.2368 | 0.94 |
138
+ | 0.0336 | 4.67 | 3650 | 0.2173 | 0.94 |
139
+ | 0.0356 | 4.73 | 3700 | 0.2230 | 0.94 |
140
+ | 0.0548 | 4.8 | 3750 | 0.2181 | 0.9533 |
141
+ | 0.042 | 4.86 | 3800 | 0.2240 | 0.9333 |
142
+ | 0.0292 | 4.92 | 3850 | 0.2259 | 0.9267 |
143
+ | 0.0196 | 4.99 | 3900 | 0.2220 | 0.9467 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - Transformers 4.24.0
149
+ - Pytorch 1.13.0
150
+ - Datasets 2.6.1
151
+ - Tokenizers 0.13.1