Hugging Face's logo

gokuls
/
HBERTv1_emb_compress_48_L10_H256_A4

Fill-Mask
Transformers
PyTorch
hybridbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
gokuls commited on
Commit
8029521
•
1 Parent(s): a0332b1

Model save

Browse files
Files changed (1) hide show
  1. README.md +104 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: HBERTv1_emb_compress_48_L10_H256_A4
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_H256_A4
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: 6.0493
19
+ - Accuracy: 0.1509
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: 64
40
+ - eval_batch_size: 64
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
+ | 7.1164 | 0.11 | 10000 | 7.0967 | 0.0830 |
53
+ | 6.694 | 0.22 | 20000 | 6.6867 | 0.1065 |
54
+ | 6.545 | 0.33 | 30000 | 6.5445 | 0.1171 |
55
+ | 6.4556 | 0.44 | 40000 | 6.4527 | 0.1250 |
56
+ | 6.3891 | 0.55 | 50000 | 6.3831 | 0.1305 |
57
+ | 6.3404 | 0.66 | 60000 | 6.3334 | 0.1350 |
58
+ | 6.2962 | 0.76 | 70000 | 6.2940 | 0.1377 |
59
+ | 6.2669 | 0.87 | 80000 | 6.2629 | 0.1398 |
60
+ | 6.2352 | 0.98 | 90000 | 6.2361 | 0.1412 |
61
+ | 6.2179 | 1.09 | 100000 | 6.2150 | 0.1429 |
62
+ | 6.191 | 1.2 | 110000 | 6.1970 | 0.1443 |
63
+ | 6.1809 | 1.31 | 120000 | 6.1829 | 0.1441 |
64
+ | 6.1699 | 1.42 | 130000 | 6.1692 | 0.1455 |
65
+ | 6.1623 | 1.53 | 140000 | 6.1562 | 0.1453 |
66
+ | 6.1422 | 1.64 | 150000 | 6.1480 | 0.1468 |
67
+ | 6.1397 | 1.75 | 160000 | 6.1367 | 0.1468 |
68
+ | 6.1342 | 1.86 | 170000 | 6.1284 | 0.1475 |
69
+ | 6.1291 | 1.97 | 180000 | 6.1214 | 0.1478 |
70
+ | 6.1157 | 2.08 | 190000 | 6.1132 | 0.1483 |
71
+ | 6.1146 | 2.18 | 200000 | 6.1094 | 0.1484 |
72
+ | 6.1018 | 2.29 | 210000 | 6.1013 | 0.1488 |
73
+ | 6.1014 | 2.4 | 220000 | 6.0979 | 0.1488 |
74
+ | 6.0935 | 2.51 | 230000 | 6.0936 | 0.1489 |
75
+ | 6.0899 | 2.62 | 240000 | 6.0881 | 0.1491 |
76
+ | 6.0858 | 2.73 | 250000 | 6.0851 | 0.1498 |
77
+ | 6.0872 | 2.84 | 260000 | 6.0819 | 0.1497 |
78
+ | 6.0858 | 2.95 | 270000 | 6.0784 | 0.1500 |
79
+ | 6.0775 | 3.06 | 280000 | 6.0745 | 0.1501 |
80
+ | 6.0715 | 3.17 | 290000 | 6.0720 | 0.1502 |
81
+ | 6.0704 | 3.28 | 300000 | 6.0699 | 0.1502 |
82
+ | 6.0678 | 3.39 | 310000 | 6.0668 | 0.1503 |
83
+ | 6.0662 | 3.5 | 320000 | 6.0649 | 0.1503 |
84
+ | 6.0569 | 3.6 | 330000 | 6.0622 | 0.1505 |
85
+ | 6.0604 | 3.71 | 340000 | 6.0612 | 0.1506 |
86
+ | 6.0525 | 3.82 | 350000 | 6.0586 | 0.1507 |
87
+ | 6.0553 | 3.93 | 360000 | 6.0582 | 0.1506 |
88
+ | 6.053 | 4.04 | 370000 | 6.0544 | 0.1508 |
89
+ | 6.0594 | 4.15 | 380000 | 6.0553 | 0.1507 |
90
+ | 6.0488 | 4.26 | 390000 | 6.0527 | 0.1509 |
91
+ | 6.051 | 4.37 | 400000 | 6.0516 | 0.1509 |
92
+ | 6.0553 | 4.48 | 410000 | 6.0518 | 0.1509 |
93
+ | 6.0507 | 4.59 | 420000 | 6.0520 | 0.1509 |
94
+ | 6.0514 | 4.7 | 430000 | 6.0501 | 0.1509 |
95
+ | 6.0511 | 4.81 | 440000 | 6.0496 | 0.1511 |
96
+ | 6.0527 | 4.92 | 450000 | 6.0493 | 0.1509 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.33.2
102
+ - Pytorch 1.14.0a0+410ce96
103
+ - Datasets 2.14.5
104
+ - Tokenizers 0.13.3