Hugging Face's logo

gokuls
/
mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_sst2

Text Classification
Transformers
PyTorch
TensorBoard
English
mobilebert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gokuls commited on
Commit
da74cb3
•
1 Parent(s): 9eeff92

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +97 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_sst2
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: glue
17
+ type: glue
18
+ config: sst2
19
+ split: validation
20
+ args: sst2
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9208715596330275
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
+ # mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_sst2
31
+
32
+ This model is a fine-tuned version of [gokuls/mobilebert_sa_pre-training-complete](https://huggingface.co/gokuls/mobilebert_sa_pre-training-complete) on the glue dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2677
35
+ - Accuracy: 0.9209
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: 5e-05
55
+ - train_batch_size: 128
56
+ - eval_batch_size: 128
57
+ - seed: 10
58
+ - distributed_type: multi-GPU
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 50
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | 0.4176 | 1.0 | 527 | 0.2978 | 0.9197 |
68
+ | 0.1807 | 2.0 | 1054 | 0.2951 | 0.9174 |
69
+ | 0.1163 | 3.0 | 1581 | 0.2749 | 0.9186 |
70
+ | 0.0862 | 4.0 | 2108 | 0.2988 | 0.9083 |
71
+ | 0.0695 | 5.0 | 2635 | 0.2760 | 0.9174 |
72
+ | 0.0598 | 6.0 | 3162 | 0.2695 | 0.9151 |
73
+ | 0.0525 | 7.0 | 3689 | 0.2723 | 0.9255 |
74
+ | 0.0464 | 8.0 | 4216 | 0.2430 | 0.9243 |
75
+ | 0.0422 | 9.0 | 4743 | 0.2814 | 0.9243 |
76
+ | 0.0395 | 10.0 | 5270 | 0.2464 | 0.9163 |
77
+ | 0.0357 | 11.0 | 5797 | 0.2390 | 0.9197 |
78
+ | 0.0341 | 12.0 | 6324 | 0.2713 | 0.9197 |
79
+ | 0.0328 | 13.0 | 6851 | 0.2685 | 0.9220 |
80
+ | 0.0315 | 14.0 | 7378 | 0.2585 | 0.9186 |
81
+ | 0.0296 | 15.0 | 7905 | 0.2367 | 0.9220 |
82
+ | 0.0283 | 16.0 | 8432 | 0.2560 | 0.9186 |
83
+ | 0.0277 | 17.0 | 8959 | 0.2635 | 0.9174 |
84
+ | 0.0269 | 18.0 | 9486 | 0.2364 | 0.9266 |
85
+ | 0.026 | 19.0 | 10013 | 0.2749 | 0.9209 |
86
+ | 0.0252 | 20.0 | 10540 | 0.2507 | 0.9174 |
87
+ | 0.0248 | 21.0 | 11067 | 0.2769 | 0.9163 |
88
+ | 0.0248 | 22.0 | 11594 | 0.2543 | 0.9220 |
89
+ | 0.024 | 23.0 | 12121 | 0.2677 | 0.9209 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.26.0
95
+ - Pytorch 1.14.0a0+410ce96
96
+ - Datasets 2.9.0
97
+ - Tokenizers 0.13.2