Hugging Face's logo

vxbrandon
/
t5-base_sst2_dense

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
vxbrandon commited on
Commit
4c43137
•
1 Parent(s): f37abb0

End of training

Browse files
Files changed (1) hide show
  1. README.md +140 -0
README.md ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: t5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - glue
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: t5-base_sst2_dense
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: glue
18
+ type: glue
19
+ config: sst2
20
+ split: validation
21
+ args: sst2
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9243119266055045
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # t5-base_sst2_dense
32
+
33
+ This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.3118
36
+ - Accuracy: 0.9243
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 64
58
+ - seed: 42
59
+ - distributed_type: multi-GPU
60
+ - gradient_accumulation_steps: 2
61
+ - total_train_batch_size: 64
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 200
65
+ - num_epochs: 5
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 0.7121 | 0.01 | 10 | 0.6973 | 0.4989 |
72
+ | 0.6719 | 0.02 | 20 | 0.6858 | 0.5092 |
73
+ | 0.6727 | 0.03 | 30 | 0.6851 | 0.5092 |
74
+ | 0.6621 | 0.04 | 40 | 0.6685 | 0.5092 |
75
+ | 0.6359 | 0.05 | 50 | 0.6438 | 0.5975 |
76
+ | 0.6219 | 0.06 | 60 | 0.6044 | 0.8280 |
77
+ | 0.5648 | 0.07 | 70 | 0.5312 | 0.8452 |
78
+ | 0.4609 | 0.08 | 80 | 0.4129 | 0.8899 |
79
+ | 0.3486 | 0.09 | 90 | 0.3354 | 0.8842 |
80
+ | 0.291 | 0.1 | 100 | 0.2685 | 0.9106 |
81
+ | 0.28 | 0.1 | 110 | 0.2745 | 0.9014 |
82
+ | 0.2078 | 0.11 | 120 | 0.2994 | 0.9025 |
83
+ | 0.229 | 0.12 | 130 | 0.3541 | 0.8899 |
84
+ | 0.3003 | 0.13 | 140 | 0.2503 | 0.9106 |
85
+ | 0.1828 | 0.14 | 150 | 0.2430 | 0.9140 |
86
+ | 0.1957 | 0.15 | 160 | 0.2335 | 0.9140 |
87
+ | 0.2385 | 0.16 | 170 | 0.2552 | 0.9094 |
88
+ | 0.1792 | 0.17 | 180 | 0.2527 | 0.9174 |
89
+ | 0.2147 | 0.18 | 190 | 0.2657 | 0.9128 |
90
+ | 0.23 | 0.19 | 200 | 0.2290 | 0.9151 |
91
+ | 0.2376 | 0.2 | 210 | 0.2495 | 0.9209 |
92
+ | 0.2331 | 0.21 | 220 | 0.2370 | 0.9243 |
93
+ | 0.215 | 0.22 | 230 | 0.2258 | 0.9209 |
94
+ | 0.1833 | 0.23 | 240 | 0.2225 | 0.9209 |
95
+ | 0.2277 | 0.24 | 250 | 0.2202 | 0.9232 |
96
+ | 0.1969 | 0.25 | 260 | 0.2164 | 0.9209 |
97
+ | 0.2038 | 0.26 | 270 | 0.2147 | 0.9220 |
98
+ | 0.1421 | 0.27 | 280 | 0.2172 | 0.9186 |
99
+ | 0.1604 | 0.28 | 290 | 0.2408 | 0.9209 |
100
+ | 0.1864 | 0.29 | 300 | 0.2336 | 0.9220 |
101
+ | 0.1629 | 0.29 | 310 | 0.2293 | 0.9255 |
102
+ | 0.2334 | 0.3 | 320 | 0.2201 | 0.9243 |
103
+ | 0.1676 | 0.31 | 330 | 0.2108 | 0.9255 |
104
+ | 0.1672 | 0.32 | 340 | 0.2233 | 0.9209 |
105
+ | 0.1886 | 0.33 | 350 | 0.2229 | 0.9220 |
106
+ | 0.2081 | 0.34 | 360 | 0.2227 | 0.9209 |
107
+ | 0.2145 | 0.35 | 370 | 0.2185 | 0.9243 |
108
+ | 0.1322 | 0.36 | 380 | 0.2286 | 0.9209 |
109
+ | 0.2552 | 0.37 | 390 | 0.2193 | 0.9232 |
110
+ | 0.1542 | 0.38 | 400 | 0.2234 | 0.9232 |
111
+ | 0.2285 | 0.39 | 410 | 0.2190 | 0.9232 |
112
+ | 0.1633 | 0.4 | 420 | 0.2256 | 0.9255 |
113
+ | 0.1592 | 0.41 | 430 | 0.2386 | 0.9220 |
114
+ | 0.1525 | 0.42 | 440 | 0.2369 | 0.9255 |
115
+ | 0.2523 | 0.43 | 450 | 0.3649 | 0.9220 |
116
+ | 0.1938 | 0.44 | 460 | 0.2203 | 0.9255 |
117
+ | 0.1894 | 0.45 | 470 | 0.2067 | 0.9278 |
118
+ | 0.143 | 0.46 | 480 | 0.2143 | 0.9266 |
119
+ | 0.179 | 0.47 | 490 | 0.2090 | 0.9300 |
120
+ | 0.1589 | 0.48 | 500 | 0.2288 | 0.9255 |
121
+ | 0.1267 | 0.48 | 510 | 0.2129 | 0.9255 |
122
+ | 0.1822 | 0.49 | 520 | 0.2193 | 0.9255 |
123
+ | 0.172 | 0.5 | 530 | 0.3245 | 0.9220 |
124
+ | 0.1268 | 0.51 | 540 | 0.3119 | 0.9300 |
125
+ | 0.1243 | 0.52 | 550 | 0.3271 | 0.9255 |
126
+ | 0.141 | 0.53 | 560 | 0.3441 | 0.9220 |
127
+ | 0.1907 | 0.54 | 570 | 0.3205 | 0.9278 |
128
+ | 0.1688 | 0.55 | 580 | 0.3240 | 0.9243 |
129
+ | 0.1602 | 0.56 | 590 | 0.3146 | 0.9243 |
130
+ | 0.1292 | 0.57 | 600 | 0.3043 | 0.9289 |
131
+ | 0.1588 | 0.58 | 610 | 0.3345 | 0.9209 |
132
+ | 0.1381 | 0.59 | 620 | 0.3118 | 0.9243 |
133
+
134
+
135
+ ### Framework versions
136
+
137
+ - Transformers 4.33.3
138
+ - Pytorch 2.0.1+cu118
139
+ - Datasets 2.14.5
140
+ - Tokenizers 0.13.3