Hugging Face's logo

pig4431
/
TweetEval_DistilBERT_5E

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
pig4431 commited on
Commit
b440f5a
•
1 Parent(s): a4b6f4c

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: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - tweet_eval
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: TweetEval_DistilBERT_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: 0.9133333333333333
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_DistilBERT_5E
31
+
32
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tweet_eval dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.4043
35
+ - Accuracy: 0.9133
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: 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
+ | 0.5747 | 0.04 | 50 | 0.4843 | 0.7333 |
67
+ | 0.4336 | 0.08 | 100 | 0.2888 | 0.8667 |
68
+ | 0.3437 | 0.12 | 150 | 0.2895 | 0.8667 |
69
+ | 0.3375 | 0.16 | 200 | 0.2864 | 0.8733 |
70
+ | 0.3072 | 0.2 | 250 | 0.2577 | 0.8867 |
71
+ | 0.3019 | 0.24 | 300 | 0.2574 | 0.8933 |
72
+ | 0.2662 | 0.28 | 350 | 0.2621 | 0.8867 |
73
+ | 0.283 | 0.32 | 400 | 0.2340 | 0.92 |
74
+ | 0.2949 | 0.37 | 450 | 0.2482 | 0.8933 |
75
+ | 0.3066 | 0.41 | 500 | 0.2537 | 0.9 |
76
+ | 0.2457 | 0.45 | 550 | 0.2473 | 0.9 |
77
+ | 0.295 | 0.49 | 600 | 0.2177 | 0.9133 |
78
+ | 0.2862 | 0.53 | 650 | 0.2215 | 0.9133 |
79
+ | 0.2603 | 0.57 | 700 | 0.2272 | 0.9133 |
80
+ | 0.2976 | 0.61 | 750 | 0.2298 | 0.9067 |
81
+ | 0.2823 | 0.65 | 800 | 0.2451 | 0.8933 |
82
+ | 0.2583 | 0.69 | 850 | 0.2645 | 0.8933 |
83
+ | 0.2694 | 0.73 | 900 | 0.2352 | 0.9 |
84
+ | 0.2433 | 0.77 | 950 | 0.2322 | 0.9133 |
85
+ | 0.2598 | 0.81 | 1000 | 0.2300 | 0.9 |
86
+ | 0.2701 | 0.85 | 1050 | 0.2162 | 0.9 |
87
+ | 0.2227 | 0.89 | 1100 | 0.2135 | 0.8933 |
88
+ | 0.2045 | 0.93 | 1150 | 0.2233 | 0.9133 |
89
+ | 0.2821 | 0.97 | 1200 | 0.2194 | 0.9 |
90
+ | 0.2342 | 1.01 | 1250 | 0.2488 | 0.88 |
91
+ | 0.2028 | 1.06 | 1300 | 0.2451 | 0.8867 |
92
+ | 0.1509 | 1.1 | 1350 | 0.3174 | 0.88 |
93
+ | 0.1888 | 1.14 | 1400 | 0.2537 | 0.9133 |
94
+ | 0.1825 | 1.18 | 1450 | 0.2559 | 0.9067 |
95
+ | 0.1721 | 1.22 | 1500 | 0.2511 | 0.92 |
96
+ | 0.2137 | 1.26 | 1550 | 0.2963 | 0.9133 |
97
+ | 0.2153 | 1.3 | 1600 | 0.2210 | 0.92 |
98
+ | 0.1989 | 1.34 | 1650 | 0.2231 | 0.9133 |
99
+ | 0.2155 | 1.38 | 1700 | 0.1991 | 0.9133 |
100
+ | 0.1912 | 1.42 | 1750 | 0.2146 | 0.92 |
101
+ | 0.1623 | 1.46 | 1800 | 0.2721 | 0.9 |
102
+ | 0.2236 | 1.5 | 1850 | 0.2301 | 0.9267 |
103
+ | 0.1907 | 1.54 | 1900 | 0.1988 | 0.92 |
104
+ | 0.1286 | 1.58 | 1950 | 0.2326 | 0.9 |
105
+ | 0.2147 | 1.62 | 2000 | 0.2432 | 0.9267 |
106
+ | 0.2018 | 1.66 | 2050 | 0.2162 | 0.9067 |
107
+ | 0.2073 | 1.7 | 2100 | 0.2153 | 0.9133 |
108
+ | 0.1498 | 1.75 | 2150 | 0.2335 | 0.92 |
109
+ | 0.1812 | 1.79 | 2200 | 0.2275 | 0.9267 |
110
+ | 0.1482 | 1.83 | 2250 | 0.2734 | 0.9 |
111
+ | 0.2233 | 1.87 | 2300 | 0.2454 | 0.9 |
112
+ | 0.1673 | 1.91 | 2350 | 0.2394 | 0.92 |
113
+ | 0.1555 | 1.95 | 2400 | 0.2725 | 0.92 |
114
+ | 0.2082 | 1.99 | 2450 | 0.2684 | 0.9133 |
115
+ | 0.1545 | 2.03 | 2500 | 0.3049 | 0.9067 |
116
+ | 0.1384 | 2.07 | 2550 | 0.2960 | 0.9133 |
117
+ | 0.1201 | 2.11 | 2600 | 0.3259 | 0.9 |
118
+ | 0.1348 | 2.15 | 2650 | 0.3091 | 0.9133 |
119
+ | 0.1046 | 2.19 | 2700 | 0.2916 | 0.9267 |
120
+ | 0.1506 | 2.23 | 2750 | 0.2910 | 0.9133 |
121
+ | 0.1481 | 2.27 | 2800 | 0.2855 | 0.9067 |
122
+ | 0.1318 | 2.31 | 2850 | 0.3075 | 0.9 |
123
+ | 0.1204 | 2.35 | 2900 | 0.3169 | 0.8933 |
124
+ | 0.1669 | 2.39 | 2950 | 0.3050 | 0.9067 |
125
+ | 0.1725 | 2.44 | 3000 | 0.2970 | 0.9133 |
126
+ | 0.1305 | 2.48 | 3050 | 0.3065 | 0.9 |
127
+ | 0.1508 | 2.52 | 3100 | 0.3079 | 0.9133 |
128
+ | 0.184 | 2.56 | 3150 | 0.3482 | 0.9067 |
129
+ | 0.1263 | 2.6 | 3200 | 0.3310 | 0.9 |
130
+ | 0.1282 | 2.64 | 3250 | 0.3520 | 0.8933 |
131
+ | 0.1217 | 2.68 | 3300 | 0.3158 | 0.9067 |
132
+ | 0.1203 | 2.72 | 3350 | 0.3351 | 0.92 |
133
+ | 0.1068 | 2.76 | 3400 | 0.3239 | 0.92 |
134
+ | 0.1517 | 2.8 | 3450 | 0.3247 | 0.92 |
135
+ | 0.113 | 2.84 | 3500 | 0.3269 | 0.9133 |
136
+ | 0.1276 | 2.88 | 3550 | 0.3162 | 0.92 |
137
+ | 0.1548 | 2.92 | 3600 | 0.3196 | 0.9133 |
138
+ | 0.1305 | 2.96 | 3650 | 0.3163 | 0.92 |
139
+ | 0.149 | 3.0 | 3700 | 0.3013 | 0.92 |
140
+ | 0.0816 | 3.04 | 3750 | 0.3097 | 0.9267 |
141
+ | 0.0884 | 3.08 | 3800 | 0.3028 | 0.92 |
142
+ | 0.0727 | 3.12 | 3850 | 0.3487 | 0.9133 |
143
+ | 0.1018 | 3.17 | 3900 | 0.3447 | 0.92 |
144
+ | 0.1266 | 3.21 | 3950 | 0.3589 | 0.9133 |
145
+ | 0.1216 | 3.25 | 4000 | 0.3464 | 0.92 |
146
+ | 0.091 | 3.29 | 4050 | 0.3454 | 0.92 |
147
+ | 0.0829 | 3.33 | 4100 | 0.3450 | 0.92 |
148
+ | 0.1084 | 3.37 | 4150 | 0.3670 | 0.92 |
149
+ | 0.0754 | 3.41 | 4200 | 0.3661 | 0.92 |
150
+ | 0.094 | 3.45 | 4250 | 0.3588 | 0.9067 |
151
+ | 0.0641 | 3.49 | 4300 | 0.3936 | 0.92 |
152
+ | 0.1138 | 3.53 | 4350 | 0.3616 | 0.92 |
153
+ | 0.0744 | 3.57 | 4400 | 0.3562 | 0.92 |
154
+ | 0.0697 | 3.61 | 4450 | 0.3532 | 0.9267 |
155
+ | 0.1083 | 3.65 | 4500 | 0.3451 | 0.9267 |
156
+ | 0.0701 | 3.69 | 4550 | 0.3307 | 0.92 |
157
+ | 0.0849 | 3.73 | 4600 | 0.3797 | 0.92 |
158
+ | 0.09 | 3.77 | 4650 | 0.3746 | 0.9267 |
159
+ | 0.0799 | 3.81 | 4700 | 0.3799 | 0.92 |
160
+ | 0.0589 | 3.86 | 4750 | 0.3805 | 0.92 |
161
+ | 0.0578 | 3.9 | 4800 | 0.3910 | 0.9133 |
162
+ | 0.0816 | 3.94 | 4850 | 0.3856 | 0.9133 |
163
+ | 0.1366 | 3.98 | 4900 | 0.3707 | 0.92 |
164
+ | 0.0846 | 4.02 | 4950 | 0.3802 | 0.92 |
165
+ | 0.0401 | 4.06 | 5000 | 0.3842 | 0.92 |
166
+ | 0.0851 | 4.1 | 5050 | 0.3773 | 0.9267 |
167
+ | 0.0514 | 4.14 | 5100 | 0.3922 | 0.9133 |
168
+ | 0.0909 | 4.18 | 5150 | 0.3893 | 0.92 |
169
+ | 0.0764 | 4.22 | 5200 | 0.3818 | 0.9133 |
170
+ | 0.1208 | 4.26 | 5250 | 0.4096 | 0.92 |
171
+ | 0.0689 | 4.3 | 5300 | 0.3940 | 0.9133 |
172
+ | 0.0524 | 4.34 | 5350 | 0.4020 | 0.9133 |
173
+ | 0.0733 | 4.38 | 5400 | 0.4002 | 0.9133 |
174
+ | 0.0699 | 4.42 | 5450 | 0.4013 | 0.9133 |
175
+ | 0.0712 | 4.46 | 5500 | 0.4037 | 0.9067 |
176
+ | 0.0557 | 4.5 | 5550 | 0.4121 | 0.92 |
177
+ | 0.0679 | 4.55 | 5600 | 0.4067 | 0.9133 |
178
+ | 0.0651 | 4.59 | 5650 | 0.4194 | 0.9133 |
179
+ | 0.0607 | 4.63 | 5700 | 0.4007 | 0.9133 |
180
+ | 0.0676 | 4.67 | 5750 | 0.4013 | 0.9133 |
181
+ | 0.0303 | 4.71 | 5800 | 0.3984 | 0.9133 |
182
+ | 0.0674 | 4.75 | 5850 | 0.4037 | 0.9133 |
183
+ | 0.0842 | 4.79 | 5900 | 0.4072 | 0.9133 |
184
+ | 0.0516 | 4.83 | 5950 | 0.4096 | 0.9133 |
185
+ | 0.0556 | 4.87 | 6000 | 0.4111 | 0.92 |
186
+ | 0.0277 | 4.91 | 6050 | 0.4079 | 0.9133 |
187
+ | 0.0629 | 4.95 | 6100 | 0.4053 | 0.9133 |
188
+ | 0.0426 | 4.99 | 6150 | 0.4043 | 0.9133 |
189
+
190
+
191
+ ### Framework versions
192
+
193
+ - Transformers 4.24.0
194
+ - Pytorch 1.13.0
195
+ - Datasets 2.3.2
196
+ - Tokenizers 0.13.2