Hugging Face's logo

pig4431
/
TweetEval_XLNET_5E

Text Classification
Transformers
PyTorch
xlnet
Generated from Trainer
Eval Results
Model card Files
xet
Community
2
pig4431 commited on
Commit
4c08b2f
·
1 Parent(s): 0983c94

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +196 -0
README.md ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - tweet_eval
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: TweetEval_XLNET_5E
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: tweet_eval
17
+ type: tweet_eval
18
+ config: sentiment
19
+ split: train
20
+ args: sentiment
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9333333333333333
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
+ # TweetEval_XLNET_5E
31
+
32
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the tweet_eval dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.4591
35
+ - Accuracy: 0.9333
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: 3e-05
55
+ - train_batch_size: 16
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
+ | 0.5575 | 0.04 | 50 | 0.2675 | 0.9 |
67
+ | 0.4177 | 0.08 | 100 | 0.2193 | 0.9067 |
68
+ | 0.2911 | 0.12 | 150 | 0.2482 | 0.9 |
69
+ | 0.3503 | 0.16 | 200 | 0.2424 | 0.9 |
70
+ | 0.3412 | 0.2 | 250 | 0.1913 | 0.9267 |
71
+ | 0.2747 | 0.24 | 300 | 0.1783 | 0.92 |
72
+ | 0.2999 | 0.28 | 350 | 0.2495 | 0.9133 |
73
+ | 0.3141 | 0.32 | 400 | 0.2460 | 0.9 |
74
+ | 0.2935 | 0.37 | 450 | 0.2034 | 0.92 |
75
+ | 0.2619 | 0.41 | 500 | 0.2600 | 0.9067 |
76
+ | 0.2454 | 0.45 | 550 | 0.2178 | 0.92 |
77
+ | 0.2809 | 0.49 | 600 | 0.2254 | 0.9133 |
78
+ | 0.288 | 0.53 | 650 | 0.1849 | 0.92 |
79
+ | 0.2769 | 0.57 | 700 | 0.1896 | 0.9267 |
80
+ | 0.3079 | 0.61 | 750 | 0.2153 | 0.9133 |
81
+ | 0.2598 | 0.65 | 800 | 0.3279 | 0.9067 |
82
+ | 0.3149 | 0.69 | 850 | 0.1985 | 0.92 |
83
+ | 0.2872 | 0.73 | 900 | 0.1801 | 0.9333 |
84
+ | 0.2554 | 0.77 | 950 | 0.2023 | 0.9267 |
85
+ | 0.2645 | 0.81 | 1000 | 0.2208 | 0.9067 |
86
+ | 0.2509 | 0.85 | 1050 | 0.2012 | 0.9333 |
87
+ | 0.2404 | 0.89 | 1100 | 0.1995 | 0.9067 |
88
+ | 0.2361 | 0.93 | 1150 | 0.1808 | 0.9133 |
89
+ | 0.2298 | 0.97 | 1200 | 0.2226 | 0.9333 |
90
+ | 0.193 | 1.01 | 1250 | 0.2535 | 0.9267 |
91
+ | 0.1603 | 1.06 | 1300 | 0.2163 | 0.9467 |
92
+ | 0.1916 | 1.1 | 1350 | 0.2479 | 0.92 |
93
+ | 0.1963 | 1.14 | 1400 | 0.1964 | 0.94 |
94
+ | 0.1667 | 1.18 | 1450 | 0.3139 | 0.9133 |
95
+ | 0.1668 | 1.22 | 1500 | 0.2204 | 0.9267 |
96
+ | 0.1677 | 1.26 | 1550 | 0.2468 | 0.9333 |
97
+ | 0.1601 | 1.3 | 1600 | 0.2394 | 0.94 |
98
+ | 0.1714 | 1.34 | 1650 | 0.2326 | 0.94 |
99
+ | 0.197 | 1.38 | 1700 | 0.1861 | 0.94 |
100
+ | 0.1777 | 1.42 | 1750 | 0.2518 | 0.94 |
101
+ | 0.1925 | 1.46 | 1800 | 0.1806 | 0.94 |
102
+ | 0.2068 | 1.5 | 1850 | 0.1319 | 0.9467 |
103
+ | 0.1716 | 1.54 | 1900 | 0.1199 | 0.9667 |
104
+ | 0.1442 | 1.58 | 1950 | 0.1694 | 0.96 |
105
+ | 0.1929 | 1.62 | 2000 | 0.1990 | 0.9467 |
106
+ | 0.1654 | 1.66 | 2050 | 0.2972 | 0.9333 |
107
+ | 0.1759 | 1.7 | 2100 | 0.1584 | 0.9467 |
108
+ | 0.1788 | 1.75 | 2150 | 0.2266 | 0.94 |
109
+ | 0.1796 | 1.79 | 2200 | 0.2746 | 0.9333 |
110
+ | 0.172 | 1.83 | 2250 | 0.2313 | 0.9333 |
111
+ | 0.1637 | 1.87 | 2300 | 0.2918 | 0.9267 |
112
+ | 0.2359 | 1.91 | 2350 | 0.2121 | 0.9267 |
113
+ | 0.1778 | 1.95 | 2400 | 0.2022 | 0.9333 |
114
+ | 0.1581 | 1.99 | 2450 | 0.2936 | 0.9067 |
115
+ | 0.1312 | 2.03 | 2500 | 0.2531 | 0.9333 |
116
+ | 0.1178 | 2.07 | 2550 | 0.2525 | 0.9267 |
117
+ | 0.0924 | 2.11 | 2600 | 0.2715 | 0.9333 |
118
+ | 0.0774 | 2.15 | 2650 | 0.2123 | 0.9533 |
119
+ | 0.091 | 2.19 | 2700 | 0.2128 | 0.9467 |
120
+ | 0.0948 | 2.23 | 2750 | 0.2187 | 0.9533 |
121
+ | 0.1121 | 2.27 | 2800 | 0.2438 | 0.9467 |
122
+ | 0.1259 | 2.31 | 2850 | 0.2197 | 0.9467 |
123
+ | 0.0747 | 2.35 | 2900 | 0.2727 | 0.9333 |
124
+ | 0.114 | 2.39 | 2950 | 0.3197 | 0.9333 |
125
+ | 0.086 | 2.44 | 3000 | 0.3643 | 0.9333 |
126
+ | 0.1326 | 2.48 | 3050 | 0.2791 | 0.94 |
127
+ | 0.1017 | 2.52 | 3100 | 0.2661 | 0.9333 |
128
+ | 0.0719 | 2.56 | 3150 | 0.2797 | 0.94 |
129
+ | 0.1424 | 2.6 | 3200 | 0.1819 | 0.96 |
130
+ | 0.106 | 2.64 | 3250 | 0.2770 | 0.94 |
131
+ | 0.0996 | 2.68 | 3300 | 0.2213 | 0.94 |
132
+ | 0.0835 | 2.72 | 3350 | 0.2894 | 0.9333 |
133
+ | 0.0808 | 2.76 | 3400 | 0.3424 | 0.9333 |
134
+ | 0.1406 | 2.8 | 3450 | 0.2166 | 0.94 |
135
+ | 0.0345 | 2.84 | 3500 | 0.3146 | 0.9333 |
136
+ | 0.1247 | 2.88 | 3550 | 0.2824 | 0.9467 |
137
+ | 0.076 | 2.92 | 3600 | 0.2650 | 0.9467 |
138
+ | 0.134 | 2.96 | 3650 | 0.2758 | 0.9267 |
139
+ | 0.0521 | 3.0 | 3700 | 0.2693 | 0.9467 |
140
+ | 0.0366 | 3.04 | 3750 | 0.3428 | 0.9333 |
141
+ | 0.0682 | 3.08 | 3800 | 0.2779 | 0.9533 |
142
+ | 0.0624 | 3.12 | 3850 | 0.2563 | 0.9467 |
143
+ | 0.0402 | 3.17 | 3900 | 0.3086 | 0.94 |
144
+ | 0.052 | 3.21 | 3950 | 0.3324 | 0.94 |
145
+ | 0.0579 | 3.25 | 4000 | 0.3165 | 0.9467 |
146
+ | 0.0411 | 3.29 | 4050 | 0.3507 | 0.9467 |
147
+ | 0.0507 | 3.33 | 4100 | 0.3108 | 0.9533 |
148
+ | 0.0326 | 3.37 | 4150 | 0.3645 | 0.94 |
149
+ | 0.085 | 3.41 | 4200 | 0.3390 | 0.94 |
150
+ | 0.022 | 3.45 | 4250 | 0.3367 | 0.94 |
151
+ | 0.0689 | 3.49 | 4300 | 0.3433 | 0.94 |
152
+ | 0.0458 | 3.53 | 4350 | 0.3359 | 0.9533 |
153
+ | 0.0384 | 3.57 | 4400 | 0.3642 | 0.9467 |
154
+ | 0.0415 | 3.61 | 4450 | 0.3429 | 0.9467 |
155
+ | 0.0362 | 3.65 | 4500 | 0.3727 | 0.9467 |
156
+ | 0.0351 | 3.69 | 4550 | 0.3293 | 0.9467 |
157
+ | 0.06 | 3.73 | 4600 | 0.4717 | 0.92 |
158
+ | 0.0344 | 3.77 | 4650 | 0.3668 | 0.94 |
159
+ | 0.0518 | 3.81 | 4700 | 0.3461 | 0.94 |
160
+ | 0.046 | 3.86 | 4750 | 0.4020 | 0.9267 |
161
+ | 0.0735 | 3.9 | 4800 | 0.2660 | 0.9467 |
162
+ | 0.0453 | 3.94 | 4850 | 0.3364 | 0.9333 |
163
+ | 0.039 | 3.98 | 4900 | 0.4398 | 0.92 |
164
+ | 0.0497 | 4.02 | 4950 | 0.3476 | 0.94 |
165
+ | 0.0183 | 4.06 | 5000 | 0.3871 | 0.94 |
166
+ | 0.0558 | 4.1 | 5050 | 0.4066 | 0.9267 |
167
+ | 0.0358 | 4.14 | 5100 | 0.3926 | 0.92 |
168
+ | 0.0507 | 4.18 | 5150 | 0.3312 | 0.9467 |
169
+ | 0.0111 | 4.22 | 5200 | 0.3976 | 0.9267 |
170
+ | 0.0363 | 4.26 | 5250 | 0.4753 | 0.92 |
171
+ | 0.0283 | 4.3 | 5300 | 0.4234 | 0.9267 |
172
+ | 0.0097 | 4.34 | 5350 | 0.4547 | 0.9333 |
173
+ | 0.0018 | 4.38 | 5400 | 0.4687 | 0.9267 |
174
+ | 0.0344 | 4.42 | 5450 | 0.4274 | 0.9333 |
175
+ | 0.021 | 4.46 | 5500 | 0.4448 | 0.9333 |
176
+ | 0.0092 | 4.5 | 5550 | 0.4672 | 0.9333 |
177
+ | 0.0354 | 4.55 | 5600 | 0.4666 | 0.9333 |
178
+ | 0.029 | 4.59 | 5650 | 0.4614 | 0.9333 |
179
+ | 0.0182 | 4.63 | 5700 | 0.4840 | 0.9333 |
180
+ | 0.043 | 4.67 | 5750 | 0.4327 | 0.9333 |
181
+ | 0.0259 | 4.71 | 5800 | 0.4639 | 0.9333 |
182
+ | 0.0224 | 4.75 | 5850 | 0.4607 | 0.9333 |
183
+ | 0.0302 | 4.79 | 5900 | 0.4606 | 0.9333 |
184
+ | 0.0224 | 4.83 | 5950 | 0.4654 | 0.9333 |
185
+ | 0.0431 | 4.87 | 6000 | 0.4681 | 0.9333 |
186
+ | 0.0284 | 4.91 | 6050 | 0.4622 | 0.9333 |
187
+ | 0.0326 | 4.95 | 6100 | 0.4602 | 0.9333 |
188
+ | 0.018 | 4.99 | 6150 | 0.4591 | 0.9333 |
189
+
190
+
191
+ ### Framework versions
192
+
193
+ - Transformers 4.24.0
194
+ - Pytorch 1.13.0
195
+ - Datasets 2.7.1
196
+ - Tokenizers 0.13.2