Hugging Face's logo

emrecan
/
bert-base-multilingual-cased-allnli_tr

Zero-Shot Classification
Transformers
PyTorch
Turkish
bert
text-classification
nli
Inference Endpoints
Model card Files Community
2
emrecan commited on
Commit
b115c8a
•
1 Parent(s): 29c4bf7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +146 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: bert-base-multilingual-cased_allnli_tr
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # bert-base-multilingual-cased_allnli_tr
16
+
17
+ This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6144
20
+ - Accuracy: 0.7662
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 32
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
+ | 0.8623 | 0.03 | 1000 | 0.9076 | 0.5917 |
52
+ | 0.7528 | 0.07 | 2000 | 0.8587 | 0.6119 |
53
+ | 0.7074 | 0.1 | 3000 | 0.7867 | 0.6647 |
54
+ | 0.6949 | 0.14 | 4000 | 0.7474 | 0.6772 |
55
+ | 0.6681 | 0.17 | 5000 | 0.7661 | 0.6814 |
56
+ | 0.6597 | 0.2 | 6000 | 0.7264 | 0.6943 |
57
+ | 0.6495 | 0.24 | 7000 | 0.7841 | 0.6781 |
58
+ | 0.6323 | 0.27 | 8000 | 0.7256 | 0.6952 |
59
+ | 0.6308 | 0.31 | 9000 | 0.7319 | 0.6958 |
60
+ | 0.6254 | 0.34 | 10000 | 0.7054 | 0.7004 |
61
+ | 0.6233 | 0.37 | 11000 | 0.7069 | 0.7085 |
62
+ | 0.6165 | 0.41 | 12000 | 0.6880 | 0.7181 |
63
+ | 0.6033 | 0.44 | 13000 | 0.6844 | 0.7197 |
64
+ | 0.6014 | 0.48 | 14000 | 0.6753 | 0.7129 |
65
+ | 0.5947 | 0.51 | 15000 | 0.7000 | 0.7039 |
66
+ | 0.5965 | 0.54 | 16000 | 0.6708 | 0.7263 |
67
+ | 0.5979 | 0.58 | 17000 | 0.6562 | 0.7285 |
68
+ | 0.5787 | 0.61 | 18000 | 0.6554 | 0.7297 |
69
+ | 0.58 | 0.65 | 19000 | 0.6544 | 0.7315 |
70
+ | 0.574 | 0.68 | 20000 | 0.6549 | 0.7339 |
71
+ | 0.5751 | 0.71 | 21000 | 0.6545 | 0.7289 |
72
+ | 0.5659 | 0.75 | 22000 | 0.6467 | 0.7371 |
73
+ | 0.5732 | 0.78 | 23000 | 0.6448 | 0.7362 |
74
+ | 0.5637 | 0.82 | 24000 | 0.6520 | 0.7355 |
75
+ | 0.5648 | 0.85 | 25000 | 0.6412 | 0.7345 |
76
+ | 0.5622 | 0.88 | 26000 | 0.6350 | 0.7358 |
77
+ | 0.5579 | 0.92 | 27000 | 0.6347 | 0.7393 |
78
+ | 0.5518 | 0.95 | 28000 | 0.6417 | 0.7392 |
79
+ | 0.5547 | 0.99 | 29000 | 0.6321 | 0.7437 |
80
+ | 0.524 | 1.02 | 30000 | 0.6430 | 0.7412 |
81
+ | 0.4982 | 1.05 | 31000 | 0.6253 | 0.7458 |
82
+ | 0.5002 | 1.09 | 32000 | 0.6316 | 0.7418 |
83
+ | 0.4993 | 1.12 | 33000 | 0.6197 | 0.7487 |
84
+ | 0.4963 | 1.15 | 34000 | 0.6307 | 0.7462 |
85
+ | 0.504 | 1.19 | 35000 | 0.6272 | 0.7480 |
86
+ | 0.4922 | 1.22 | 36000 | 0.6410 | 0.7433 |
87
+ | 0.5016 | 1.26 | 37000 | 0.6295 | 0.7461 |
88
+ | 0.4957 | 1.29 | 38000 | 0.6183 | 0.7506 |
89
+ | 0.4883 | 1.32 | 39000 | 0.6261 | 0.7502 |
90
+ | 0.4985 | 1.36 | 40000 | 0.6315 | 0.7496 |
91
+ | 0.4885 | 1.39 | 41000 | 0.6189 | 0.7529 |
92
+ | 0.4909 | 1.43 | 42000 | 0.6189 | 0.7473 |
93
+ | 0.4894 | 1.46 | 43000 | 0.6314 | 0.7433 |
94
+ | 0.4912 | 1.49 | 44000 | 0.6184 | 0.7446 |
95
+ | 0.4851 | 1.53 | 45000 | 0.6258 | 0.7461 |
96
+ | 0.4879 | 1.56 | 46000 | 0.6286 | 0.7480 |
97
+ | 0.4907 | 1.6 | 47000 | 0.6196 | 0.7512 |
98
+ | 0.4884 | 1.63 | 48000 | 0.6157 | 0.7526 |
99
+ | 0.4755 | 1.66 | 49000 | 0.6056 | 0.7591 |
100
+ | 0.4811 | 1.7 | 50000 | 0.5977 | 0.7582 |
101
+ | 0.4787 | 1.73 | 51000 | 0.5915 | 0.7621 |
102
+ | 0.4779 | 1.77 | 52000 | 0.6014 | 0.7583 |
103
+ | 0.4767 | 1.8 | 53000 | 0.6041 | 0.7623 |
104
+ | 0.4737 | 1.83 | 54000 | 0.6093 | 0.7563 |
105
+ | 0.4836 | 1.87 | 55000 | 0.6001 | 0.7568 |
106
+ | 0.4765 | 1.9 | 56000 | 0.6109 | 0.7601 |
107
+ | 0.4776 | 1.94 | 57000 | 0.6046 | 0.7599 |
108
+ | 0.4769 | 1.97 | 58000 | 0.5970 | 0.7568 |
109
+ | 0.4654 | 2.0 | 59000 | 0.6147 | 0.7614 |
110
+ | 0.4144 | 2.04 | 60000 | 0.6439 | 0.7566 |
111
+ | 0.4101 | 2.07 | 61000 | 0.6373 | 0.7527 |
112
+ | 0.4192 | 2.11 | 62000 | 0.6136 | 0.7575 |
113
+ | 0.4128 | 2.14 | 63000 | 0.6283 | 0.7560 |
114
+ | 0.4204 | 2.17 | 64000 | 0.6187 | 0.7625 |
115
+ | 0.4114 | 2.21 | 65000 | 0.6127 | 0.7621 |
116
+ | 0.4097 | 2.24 | 66000 | 0.6188 | 0.7626 |
117
+ | 0.4129 | 2.28 | 67000 | 0.6156 | 0.7639 |
118
+ | 0.4085 | 2.31 | 68000 | 0.6232 | 0.7616 |
119
+ | 0.4074 | 2.34 | 69000 | 0.6240 | 0.7605 |
120
+ | 0.409 | 2.38 | 70000 | 0.6153 | 0.7591 |
121
+ | 0.4046 | 2.41 | 71000 | 0.6375 | 0.7587 |
122
+ | 0.4117 | 2.45 | 72000 | 0.6145 | 0.7629 |
123
+ | 0.4002 | 2.48 | 73000 | 0.6279 | 0.7610 |
124
+ | 0.4042 | 2.51 | 74000 | 0.6176 | 0.7646 |
125
+ | 0.4055 | 2.55 | 75000 | 0.6277 | 0.7643 |
126
+ | 0.4021 | 2.58 | 76000 | 0.6196 | 0.7642 |
127
+ | 0.4081 | 2.62 | 77000 | 0.6127 | 0.7659 |
128
+ | 0.408 | 2.65 | 78000 | 0.6237 | 0.7638 |
129
+ | 0.3997 | 2.68 | 79000 | 0.6190 | 0.7636 |
130
+ | 0.4093 | 2.72 | 80000 | 0.6152 | 0.7648 |
131
+ | 0.4095 | 2.75 | 81000 | 0.6155 | 0.7627 |
132
+ | 0.4088 | 2.79 | 82000 | 0.6130 | 0.7641 |
133
+ | 0.4063 | 2.82 | 83000 | 0.6072 | 0.7646 |
134
+ | 0.3978 | 2.85 | 84000 | 0.6128 | 0.7662 |
135
+ | 0.4034 | 2.89 | 85000 | 0.6157 | 0.7627 |
136
+ | 0.4044 | 2.92 | 86000 | 0.6127 | 0.7661 |
137
+ | 0.403 | 2.96 | 87000 | 0.6126 | 0.7664 |
138
+ | 0.4033 | 2.99 | 88000 | 0.6144 | 0.7662 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.12.3
144
+ - Pytorch 1.10.0+cu102
145
+ - Datasets 1.15.1
146
+ - Tokenizers 0.10.3