Hugging Face's logo

gokuls
/
HBERTv1_emb_compress_48_L10_H512_A8

Fill-Mask
Transformers
PyTorch
hybridbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
gokuls commited on
Commit
e86e4a3
•
1 Parent(s): bc10297

Model save

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: HBERTv1_emb_compress_48_L10_H512_A8
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # HBERTv1_emb_compress_48_L10_H512_A8
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 5.7663
19
+ - Accuracy: 0.1739
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 56
40
+ - eval_batch_size: 56
41
+ - seed: 10
42
+ - distributed_type: multi-GPU
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 10000
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|
52
+ | 7.1035 | 0.1 | 10000 | 7.0837 | 0.0844 |
53
+ | 6.6799 | 0.19 | 20000 | 6.6737 | 0.1072 |
54
+ | 6.5327 | 0.29 | 30000 | 6.5279 | 0.1194 |
55
+ | 6.4362 | 0.38 | 40000 | 6.4358 | 0.1272 |
56
+ | 6.3648 | 0.48 | 50000 | 6.3700 | 0.1335 |
57
+ | 6.3181 | 0.57 | 60000 | 6.3158 | 0.1355 |
58
+ | 6.2776 | 0.67 | 70000 | 6.2769 | 0.1380 |
59
+ | 6.2469 | 0.76 | 80000 | 6.2438 | 0.1400 |
60
+ | 6.218 | 0.86 | 90000 | 6.2187 | 0.1422 |
61
+ | 6.2036 | 0.96 | 100000 | 6.1963 | 0.1434 |
62
+ | 6.1806 | 1.05 | 110000 | 6.1776 | 0.1451 |
63
+ | 6.1591 | 1.15 | 120000 | 6.1621 | 0.1456 |
64
+ | 6.1503 | 1.24 | 130000 | 6.1473 | 0.1468 |
65
+ | 6.1391 | 1.34 | 140000 | 6.1357 | 0.1466 |
66
+ | 6.126 | 1.43 | 150000 | 6.1230 | 0.1477 |
67
+ | 6.1145 | 1.53 | 160000 | 6.1133 | 0.1479 |
68
+ | 6.1067 | 1.62 | 170000 | 6.1040 | 0.1486 |
69
+ | 6.097 | 1.72 | 180000 | 6.0966 | 0.1488 |
70
+ | 6.0825 | 1.82 | 190000 | 6.0875 | 0.1492 |
71
+ | 6.0783 | 1.91 | 200000 | 6.0797 | 0.1494 |
72
+ | 6.0673 | 2.01 | 210000 | 6.0730 | 0.1499 |
73
+ | 6.066 | 2.1 | 220000 | 6.0623 | 0.1501 |
74
+ | 6.0534 | 2.2 | 230000 | 6.0510 | 0.1504 |
75
+ | 6.0004 | 2.29 | 240000 | 5.9972 | 0.1517 |
76
+ | 5.9609 | 2.39 | 250000 | 5.9492 | 0.1530 |
77
+ | 5.93 | 2.49 | 260000 | 5.9169 | 0.1551 |
78
+ | 5.9058 | 2.58 | 270000 | 5.8895 | 0.1571 |
79
+ | 5.8834 | 2.68 | 280000 | 5.8618 | 0.1597 |
80
+ | 5.8572 | 2.77 | 290000 | 5.8394 | 0.1623 |
81
+ | 5.8296 | 2.87 | 300000 | 5.8168 | 0.1661 |
82
+ | 5.8085 | 2.96 | 310000 | 5.7926 | 0.1703 |
83
+ | 5.7873 | 3.06 | 320000 | 5.7663 | 0.1739 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.33.2
89
+ - Pytorch 1.14.0a0+410ce96
90
+ - Datasets 2.14.5
91
+ - Tokenizers 0.13.3