Hugging Face's logo

rman-rahimi-29
/
bert-base-multilingual-uncased-finetuned-hp

Fill-Mask
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
rman-rahimi-29 commited on
Commit
46dae4a
•
1 Parent(s): c22bbb7

End of training

Browse files
Files changed (2) hide show
  1. README.md +102 -12
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.9471
19
 
20
  ## Model description
21
 
@@ -40,22 +40,112 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 10
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 2.6813 | 1.0 | 66 | 2.4897 |
50
- | 2.4377 | 2.0 | 132 | 2.2871 |
51
- | 2.2739 | 3.0 | 198 | 2.1468 |
52
- | 2.1432 | 4.0 | 264 | 2.1158 |
53
- | 2.058 | 5.0 | 330 | 2.0199 |
54
- | 2.0181 | 6.0 | 396 | 1.9629 |
55
- | 1.9669 | 7.0 | 462 | 2.0044 |
56
- | 1.9437 | 8.0 | 528 | 2.0210 |
57
- | 1.9289 | 9.0 | 594 | 1.8997 |
58
- | 1.9102 | 10.0 | 660 | 1.9474 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.4747
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 100
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.6826 | 1.0 | 66 | 2.4979 |
50
+ | 2.4316 | 2.0 | 132 | 2.2737 |
51
+ | 2.2563 | 3.0 | 198 | 2.1285 |
52
+ | 2.1158 | 4.0 | 264 | 2.0855 |
53
+ | 2.0196 | 5.0 | 330 | 1.9913 |
54
+ | 1.9651 | 6.0 | 396 | 1.9124 |
55
+ | 1.8956 | 7.0 | 462 | 1.9461 |
56
+ | 1.856 | 8.0 | 528 | 1.9519 |
57
+ | 1.8146 | 9.0 | 594 | 1.8063 |
58
+ | 1.7675 | 10.0 | 660 | 1.8229 |
59
+ | 1.7473 | 11.0 | 726 | 1.8271 |
60
+ | 1.7069 | 12.0 | 792 | 1.8147 |
61
+ | 1.678 | 13.0 | 858 | 1.8209 |
62
+ | 1.6291 | 14.0 | 924 | 1.7894 |
63
+ | 1.6251 | 15.0 | 990 | 1.7851 |
64
+ | 1.5939 | 16.0 | 1056 | 1.7237 |
65
+ | 1.5635 | 17.0 | 1122 | 1.7627 |
66
+ | 1.5088 | 18.0 | 1188 | 1.7392 |
67
+ | 1.5136 | 19.0 | 1254 | 1.6703 |
68
+ | 1.4782 | 20.0 | 1320 | 1.6922 |
69
+ | 1.4714 | 21.0 | 1386 | 1.6810 |
70
+ | 1.4451 | 22.0 | 1452 | 1.6318 |
71
+ | 1.4399 | 23.0 | 1518 | 1.6579 |
72
+ | 1.4262 | 24.0 | 1584 | 1.6303 |
73
+ | 1.3736 | 25.0 | 1650 | 1.6777 |
74
+ | 1.3896 | 26.0 | 1716 | 1.6887 |
75
+ | 1.3508 | 27.0 | 1782 | 1.6420 |
76
+ | 1.3939 | 28.0 | 1848 | 1.6026 |
77
+ | 1.3334 | 29.0 | 1914 | 1.6820 |
78
+ | 1.3169 | 30.0 | 1980 | 1.6018 |
79
+ | 1.2857 | 31.0 | 2046 | 1.6437 |
80
+ | 1.3152 | 32.0 | 2112 | 1.5975 |
81
+ | 1.2835 | 33.0 | 2178 | 1.6155 |
82
+ | 1.2388 | 34.0 | 2244 | 1.6033 |
83
+ | 1.2591 | 35.0 | 2310 | 1.6100 |
84
+ | 1.246 | 36.0 | 2376 | 1.5424 |
85
+ | 1.2196 | 37.0 | 2442 | 1.6082 |
86
+ | 1.2341 | 38.0 | 2508 | 1.4954 |
87
+ | 1.196 | 39.0 | 2574 | 1.5132 |
88
+ | 1.2025 | 40.0 | 2640 | 1.5710 |
89
+ | 1.1778 | 41.0 | 2706 | 1.5356 |
90
+ | 1.1645 | 42.0 | 2772 | 1.5545 |
91
+ | 1.1729 | 43.0 | 2838 | 1.4637 |
92
+ | 1.1542 | 44.0 | 2904 | 1.5700 |
93
+ | 1.1505 | 45.0 | 2970 | 1.5840 |
94
+ | 1.1224 | 46.0 | 3036 | 1.5451 |
95
+ | 1.118 | 47.0 | 3102 | 1.6250 |
96
+ | 1.0997 | 48.0 | 3168 | 1.4816 |
97
+ | 1.109 | 49.0 | 3234 | 1.5641 |
98
+ | 1.1243 | 50.0 | 3300 | 1.5099 |
99
+ | 1.1159 | 51.0 | 3366 | 1.5584 |
100
+ | 1.0955 | 52.0 | 3432 | 1.5589 |
101
+ | 1.0557 | 53.0 | 3498 | 1.5601 |
102
+ | 1.0685 | 54.0 | 3564 | 1.5211 |
103
+ | 1.0674 | 55.0 | 3630 | 1.5651 |
104
+ | 1.0625 | 56.0 | 3696 | 1.5918 |
105
+ | 1.0403 | 57.0 | 3762 | 1.5817 |
106
+ | 1.0197 | 58.0 | 3828 | 1.4936 |
107
+ | 1.031 | 59.0 | 3894 | 1.5860 |
108
+ | 1.0364 | 60.0 | 3960 | 1.5774 |
109
+ | 1.0375 | 61.0 | 4026 | 1.5358 |
110
+ | 1.0127 | 62.0 | 4092 | 1.5451 |
111
+ | 0.9982 | 63.0 | 4158 | 1.5271 |
112
+ | 0.9949 | 64.0 | 4224 | 1.5242 |
113
+ | 0.9962 | 65.0 | 4290 | 1.5564 |
114
+ | 1.0084 | 66.0 | 4356 | 1.5668 |
115
+ | 1.0076 | 67.0 | 4422 | 1.5867 |
116
+ | 0.9892 | 68.0 | 4488 | 1.5238 |
117
+ | 0.9889 | 69.0 | 4554 | 1.5097 |
118
+ | 0.9932 | 70.0 | 4620 | 1.5491 |
119
+ | 0.9815 | 71.0 | 4686 | 1.4237 |
120
+ | 0.9777 | 72.0 | 4752 | 1.5569 |
121
+ | 0.9525 | 73.0 | 4818 | 1.5103 |
122
+ | 0.9607 | 74.0 | 4884 | 1.5665 |
123
+ | 0.9488 | 75.0 | 4950 | 1.5910 |
124
+ | 0.9492 | 76.0 | 5016 | 1.5779 |
125
+ | 0.9667 | 77.0 | 5082 | 1.5581 |
126
+ | 0.9495 | 78.0 | 5148 | 1.4898 |
127
+ | 0.9457 | 79.0 | 5214 | 1.5638 |
128
+ | 0.9511 | 80.0 | 5280 | 1.5825 |
129
+ | 0.9173 | 81.0 | 5346 | 1.5565 |
130
+ | 0.9209 | 82.0 | 5412 | 1.5550 |
131
+ | 0.9446 | 83.0 | 5478 | 1.5431 |
132
+ | 0.9479 | 84.0 | 5544 | 1.4988 |
133
+ | 0.8999 | 85.0 | 5610 | 1.5311 |
134
+ | 0.9096 | 86.0 | 5676 | 1.5187 |
135
+ | 0.9044 | 87.0 | 5742 | 1.4801 |
136
+ | 0.8849 | 88.0 | 5808 | 1.5176 |
137
+ | 0.9006 | 89.0 | 5874 | 1.5871 |
138
+ | 0.9038 | 90.0 | 5940 | 1.4757 |
139
+ | 0.9026 | 91.0 | 6006 | 1.5138 |
140
+ | 0.8935 | 92.0 | 6072 | 1.6166 |
141
+ | 0.8812 | 93.0 | 6138 | 1.5561 |
142
+ | 0.8725 | 94.0 | 6204 | 1.5315 |
143
+ | 0.8941 | 95.0 | 6270 | 1.5468 |
144
+ | 0.9013 | 96.0 | 6336 | 1.6091 |
145
+ | 0.9232 | 97.0 | 6402 | 1.5199 |
146
+ | 0.8891 | 98.0 | 6468 | 1.5210 |
147
+ | 0.8956 | 99.0 | 6534 | 1.4859 |
148
+ | 0.8876 | 100.0 | 6600 | 1.4610 |
149
 
150
 
151
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db22dfe40ee1dcbeed4b274786054df06b67a939de2074379da46465a303a3d9
3
  size 669924786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d558c23e35f4ecf11184a12bb2947afeea22b27b43ee4d6996878a22e0e52269
3
  size 669924786