Hugging Face's logo

muhtasham
/
tiny-mlm-glue-qnli-custom-tokenizer

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
muhtasham commited on
Commit
16544cc
·
1 Parent(s): ac9cfab

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: tiny-mlm-glue-qnli-custom-tokenizer
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # tiny-mlm-glue-qnli-custom-tokenizer
14
+
15
+ This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 6.2339
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 3e-05
37
+ - train_batch_size: 32
38
+ - eval_batch_size: 32
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: constant
42
+ - num_epochs: 200
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 7.9951 | 0.4 | 500 | 7.3315 |
49
+ | 7.1282 | 0.8 | 1000 | 7.2457 |
50
+ | 7.0402 | 1.2 | 1500 | 7.2104 |
51
+ | 6.9634 | 1.6 | 2000 | 7.1415 |
52
+ | 6.9383 | 2.0 | 2500 | 7.0838 |
53
+ | 6.8365 | 2.4 | 3000 | 7.0031 |
54
+ | 6.7812 | 2.8 | 3500 | 6.9679 |
55
+ | 6.6959 | 3.2 | 4000 | 6.9121 |
56
+ | 6.6423 | 3.6 | 4500 | 6.8421 |
57
+ | 6.5766 | 4.0 | 5000 | 6.8474 |
58
+ | 6.5676 | 4.4 | 5500 | 6.8089 |
59
+ | 6.4728 | 4.8 | 6000 | 6.7246 |
60
+ | 6.5008 | 5.2 | 6500 | 6.7049 |
61
+ | 6.4367 | 5.6 | 7000 | 6.6539 |
62
+ | 6.4016 | 6.0 | 7500 | 6.6268 |
63
+ | 6.4063 | 6.4 | 8000 | 6.6038 |
64
+ | 6.3836 | 6.8 | 8500 | 6.5452 |
65
+ | 6.3576 | 7.2 | 9000 | 6.5932 |
66
+ | 6.2768 | 7.6 | 9500 | 6.5443 |
67
+ | 6.3002 | 8.0 | 10000 | 6.5018 |
68
+ | 6.304 | 8.4 | 10500 | 6.5263 |
69
+ | 6.2123 | 8.8 | 11000 | 6.4739 |
70
+ | 6.2015 | 9.2 | 11500 | 6.4407 |
71
+ | 6.1809 | 9.6 | 12000 | 6.4371 |
72
+ | 6.1624 | 10.0 | 12500 | 6.4379 |
73
+ | 6.1831 | 10.4 | 13000 | 6.3897 |
74
+ | 6.163 | 10.8 | 13500 | 6.4086 |
75
+ | 6.0881 | 11.2 | 14000 | 6.3902 |
76
+ | 6.0474 | 11.6 | 14500 | 6.3229 |
77
+ | 6.0454 | 12.0 | 15000 | 6.2995 |
78
+ | 6.0491 | 12.4 | 15500 | 6.3559 |
79
+ | 6.0045 | 12.8 | 16000 | 6.2820 |
80
+ | 6.043 | 13.2 | 16500 | 6.3260 |
81
+ | 5.9485 | 13.6 | 17000 | 6.2554 |
82
+ | 5.9513 | 14.0 | 17500 | 6.2668 |
83
+ | 5.9501 | 14.4 | 18000 | 6.2396 |
84
+ | 5.9882 | 14.8 | 18500 | 6.2655 |
85
+ | 5.9311 | 15.2 | 19000 | 6.1839 |
86
+ | 5.9662 | 15.6 | 19500 | 6.1942 |
87
+ | 5.9328 | 16.0 | 20000 | 6.2425 |
88
+ | 5.8984 | 16.4 | 20500 | 6.2339 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.26.0.dev0
94
+ - Pytorch 1.13.0+cu116
95
+ - Datasets 2.8.1.dev0
96
+ - Tokenizers 0.13.2