Hugging Face's logo

gokuls
/
sa_bert_12_layer_modified_complete_training_48

Fill-Mask
Transformers
PyTorch
TensorBoard
hybridbert
Generated from Trainer
Model card Files
xet
 Metrics Community
gokuls commited on
Commit
994bdd9
·
1 Parent(s): 17649a6

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
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: sa_bert_12_layer_modified_complete_training_48
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
+ # sa_bert_12_layer_modified_complete_training_48
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.7897
19
+ - Accuracy: 0.5117
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: 32
40
+ - eval_batch_size: 32
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
+ | 6.5942 | 0.05 | 10000 | 6.5714 | 0.1229 |
53
+ | 6.1563 | 0.11 | 20000 | 6.3437 | 0.1392 |
54
+ | 6.1425 | 0.16 | 30000 | 6.2474 | 0.1444 |
55
+ | 6.2249 | 0.22 | 40000 | 6.1900 | 0.1468 |
56
+ | 6.1498 | 0.27 | 50000 | 6.1482 | 0.1487 |
57
+ | 6.0528 | 0.33 | 60000 | 6.1192 | 0.1492 |
58
+ | 6.0103 | 0.38 | 70000 | 6.0762 | 0.1504 |
59
+ | 5.8523 | 0.44 | 80000 | 5.8731 | 0.1615 |
60
+ | 5.91 | 0.49 | 90000 | 5.7442 | 0.1765 |
61
+ | 5.4931 | 0.55 | 100000 | 5.5985 | 0.1952 |
62
+ | 5.4145 | 0.6 | 110000 | 5.4716 | 0.2100 |
63
+ | 5.3729 | 0.66 | 120000 | 5.3366 | 0.2247 |
64
+ | 5.2655 | 0.71 | 130000 | 5.1946 | 0.2417 |
65
+ | 5.2975 | 0.76 | 140000 | 5.0287 | 0.2600 |
66
+ | 4.9997 | 0.82 | 150000 | 4.8593 | 0.2791 |
67
+ | 4.831 | 0.87 | 160000 | 4.6226 | 0.3041 |
68
+ | 4.9176 | 0.93 | 170000 | 4.4211 | 0.3257 |
69
+ | 4.5352 | 0.98 | 180000 | 4.2328 | 0.3429 |
70
+ | 4.1536 | 1.04 | 190000 | 4.0635 | 0.3598 |
71
+ | 4.0216 | 1.09 | 200000 | 3.9109 | 0.3755 |
72
+ | 4.0744 | 1.15 | 210000 | 3.7761 | 0.3897 |
73
+ | 3.7468 | 1.2 | 220000 | 3.6636 | 0.4038 |
74
+ | 3.5015 | 1.26 | 230000 | 3.5047 | 0.4236 |
75
+ | 3.5717 | 1.31 | 240000 | 3.4014 | 0.4370 |
76
+ | 3.1969 | 1.37 | 250000 | 3.3173 | 0.4479 |
77
+ | 3.5026 | 1.42 | 260000 | 3.2254 | 0.4588 |
78
+ | 3.287 | 1.47 | 270000 | 3.1845 | 0.4643 |
79
+ | 3.3462 | 1.53 | 280000 | 3.0979 | 0.4738 |
80
+ | 3.3996 | 1.58 | 290000 | 3.0808 | 0.4764 |
81
+ | 3.2324 | 1.64 | 300000 | 3.0163 | 0.4843 |
82
+ | 3.0972 | 1.69 | 310000 | 2.9738 | 0.4890 |
83
+ | 3.1621 | 1.75 | 320000 | 2.9450 | 0.4927 |
84
+ | 3.0282 | 1.8 | 330000 | 2.9135 | 0.4964 |
85
+ | 3.0674 | 1.86 | 340000 | 2.9059 | 0.4979 |
86
+ | 2.9437 | 1.91 | 350000 | 2.8810 | 0.5007 |
87
+ | 2.8208 | 1.97 | 360000 | 2.8316 | 0.5064 |
88
+ | 2.9005 | 2.02 | 370000 | 2.8061 | 0.5098 |
89
+ | 2.7574 | 2.08 | 380000 | 2.7897 | 0.5117 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.30.2
95
+ - Pytorch 1.14.0a0+410ce96
96
+ - Datasets 2.13.0
97
+ - Tokenizers 0.13.3