Hugging Face's logo

keefezowie
/
sa_mobileBERT

Text Classification
Transformers
LiteRT
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
keefezowie commited on
Commit
748392d
·
verified ·
1 Parent(s): aa00eb3

End of training

Browse files
Files changed (2) hide show
  1. README.md +114 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - emotion
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: sa_mobileBERT
10
+ results:
11
+ - task:
12
+ name: Text Classification
13
+ type: text-classification
14
+ dataset:
15
+ name: emotion
16
+ type: emotion
17
+ config: split
18
+ split: test
19
+ args: split
20
+ metrics:
21
+ - name: Accuracy
22
+ type: accuracy
23
+ value: 0.797
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # sa_mobileBERT
30
+
31
+ This model is a fine-tuned version of [](https://huggingface.co/) on the emotion dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.8327
34
+ - Accuracy: 0.797
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 2e-05
54
+ - train_batch_size: 64
55
+ - eval_batch_size: 64
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - lr_scheduler_warmup_ratio: 0.5
60
+ - lr_scheduler_warmup_steps: 500
61
+ - num_epochs: 40
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 250 | 1.5599 | 0.3475 |
68
+ | 1.627 | 2.0 | 500 | 1.5592 | 0.3475 |
69
+ | 1.627 | 3.0 | 750 | 1.5544 | 0.3475 |
70
+ | 1.4681 | 4.0 | 1000 | 1.2474 | 0.416 |
71
+ | 1.4681 | 5.0 | 1250 | 1.2073 | 0.4455 |
72
+ | 1.1155 | 6.0 | 1500 | 1.1868 | 0.461 |
73
+ | 1.1155 | 7.0 | 1750 | 1.1605 | 0.4725 |
74
+ | 1.0238 | 8.0 | 2000 | 1.1584 | 0.501 |
75
+ | 1.0238 | 9.0 | 2250 | 1.0098 | 0.628 |
76
+ | 0.8291 | 10.0 | 2500 | 0.9274 | 0.6835 |
77
+ | 0.8291 | 11.0 | 2750 | 0.8888 | 0.699 |
78
+ | 0.6307 | 12.0 | 3000 | 0.8986 | 0.7165 |
79
+ | 0.6307 | 13.0 | 3250 | 0.8386 | 0.7295 |
80
+ | 0.5668 | 14.0 | 3500 | 0.8552 | 0.7405 |
81
+ | 0.5668 | 15.0 | 3750 | 0.8898 | 0.742 |
82
+ | 0.5076 | 16.0 | 4000 | 0.8040 | 0.754 |
83
+ | 0.5076 | 17.0 | 4250 | 0.7774 | 0.7715 |
84
+ | 0.4339 | 18.0 | 4500 | 0.7777 | 0.79 |
85
+ | 0.4339 | 19.0 | 4750 | 0.7534 | 0.781 |
86
+ | 0.3963 | 20.0 | 5000 | 0.7293 | 0.7895 |
87
+ | 0.3963 | 21.0 | 5250 | 0.7837 | 0.7955 |
88
+ | 0.3704 | 22.0 | 5500 | 0.7520 | 0.8025 |
89
+ | 0.3704 | 23.0 | 5750 | 0.7604 | 0.7945 |
90
+ | 0.343 | 24.0 | 6000 | 0.7494 | 0.801 |
91
+ | 0.343 | 25.0 | 6250 | 0.7794 | 0.79 |
92
+ | 0.3175 | 26.0 | 6500 | 0.7747 | 0.8065 |
93
+ | 0.3175 | 27.0 | 6750 | 0.7595 | 0.7965 |
94
+ | 0.2975 | 28.0 | 7000 | 0.7423 | 0.8055 |
95
+ | 0.2975 | 29.0 | 7250 | 0.7685 | 0.8 |
96
+ | 0.2833 | 30.0 | 7500 | 0.7858 | 0.805 |
97
+ | 0.2833 | 31.0 | 7750 | 0.7899 | 0.7925 |
98
+ | 0.2743 | 32.0 | 8000 | 0.8048 | 0.7885 |
99
+ | 0.2743 | 33.0 | 8250 | 0.7856 | 0.8075 |
100
+ | 0.2581 | 34.0 | 8500 | 0.8239 | 0.801 |
101
+ | 0.2581 | 35.0 | 8750 | 0.8195 | 0.802 |
102
+ | 0.2502 | 36.0 | 9000 | 0.8283 | 0.8035 |
103
+ | 0.2502 | 37.0 | 9250 | 0.8263 | 0.7995 |
104
+ | 0.2438 | 38.0 | 9500 | 0.8356 | 0.797 |
105
+ | 0.2438 | 39.0 | 9750 | 0.8265 | 0.7995 |
106
+ | 0.238 | 40.0 | 10000 | 0.8327 | 0.797 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.35.0
112
+ - Pytorch 2.0.0
113
+ - Datasets 2.1.0
114
+ - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c759c08bdec5ef02abb0fc50fa14cfcef8a9ffaa3ecdfff9d90df85bcc124ef
3
  size 99529152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df16bbd01cfee1e1c26d263683c33a6249ffb14543b5851bdb09a41e4441ad7
3
  size 99529152