Hugging Face's logo

gngpostalsrvc
/
BERiT_2000_enriched_optimized

Fill-Mask
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Model card Files
xet
 Metrics Community
1
gngpostalsrvc commited on
Commit
18fca67
·
1 Parent(s): eeca296

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +106 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: BERiT_2000_enriched_optimized
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
+ # BERiT_2000_enriched_optimized
14
+
15
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 6.5710
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: 6.732413659252984e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 10
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 6.4676 | 0.19 | 500 | 6.1516 |
49
+ | 6.0191 | 0.39 | 1000 | 5.8660 |
50
+ | 5.9008 | 0.58 | 1500 | 5.9956 |
51
+ | 5.7806 | 0.77 | 2000 | 5.7032 |
52
+ | 5.6932 | 0.97 | 2500 | 5.6910 |
53
+ | 6.4953 | 1.16 | 3000 | 6.6394 |
54
+ | 6.6419 | 1.36 | 3500 | 6.6176 |
55
+ | 6.6462 | 1.55 | 4000 | 6.5961 |
56
+ | 6.6402 | 1.74 | 4500 | 6.6224 |
57
+ | 6.6169 | 1.94 | 5000 | 6.6091 |
58
+ | 6.6396 | 2.13 | 5500 | 6.6443 |
59
+ | 6.6599 | 2.32 | 6000 | 6.6150 |
60
+ | 6.5956 | 2.52 | 6500 | 6.6173 |
61
+ | 6.6397 | 2.71 | 7000 | 6.6038 |
62
+ | 6.6261 | 2.9 | 7500 | 6.6214 |
63
+ | 6.6162 | 3.1 | 8000 | 6.6271 |
64
+ | 6.6102 | 3.29 | 8500 | 6.5843 |
65
+ | 6.6116 | 3.49 | 9000 | 6.6044 |
66
+ | 6.6146 | 3.68 | 9500 | 6.6092 |
67
+ | 6.5922 | 3.87 | 10000 | 6.6182 |
68
+ | 6.6246 | 4.07 | 10500 | 6.5832 |
69
+ | 6.6124 | 4.26 | 11000 | 6.6141 |
70
+ | 6.6002 | 4.45 | 11500 | 6.6385 |
71
+ | 6.6015 | 4.65 | 12000 | 6.5984 |
72
+ | 6.6024 | 4.84 | 12500 | 6.6236 |
73
+ | 6.6097 | 5.03 | 13000 | 6.6254 |
74
+ | 6.5937 | 5.23 | 13500 | 6.6154 |
75
+ | 6.5973 | 5.42 | 14000 | 6.5731 |
76
+ | 6.6141 | 5.62 | 14500 | 6.6308 |
77
+ | 6.5976 | 5.81 | 15000 | 6.5824 |
78
+ | 6.5982 | 6.0 | 15500 | 6.6024 |
79
+ | 6.6032 | 6.2 | 16000 | 6.5891 |
80
+ | 6.603 | 6.39 | 16500 | 6.5926 |
81
+ | 6.6089 | 6.58 | 17000 | 6.6090 |
82
+ | 6.6067 | 6.78 | 17500 | 6.6137 |
83
+ | 6.5718 | 6.97 | 18000 | 6.5817 |
84
+ | 6.6036 | 7.16 | 18500 | 6.6008 |
85
+ | 6.6001 | 7.36 | 19000 | 6.5571 |
86
+ | 6.6203 | 7.55 | 19500 | 6.5778 |
87
+ | 6.6055 | 7.75 | 20000 | 6.5805 |
88
+ | 6.6168 | 7.94 | 20500 | 6.6099 |
89
+ | 6.5874 | 8.13 | 21000 | 6.6125 |
90
+ | 6.5932 | 8.33 | 21500 | 6.5701 |
91
+ | 6.5984 | 8.52 | 22000 | 6.5719 |
92
+ | 6.5753 | 8.71 | 22500 | 6.6199 |
93
+ | 6.599 | 8.91 | 23000 | 6.5756 |
94
+ | 6.579 | 9.1 | 23500 | 6.5926 |
95
+ | 6.5805 | 9.3 | 24000 | 6.5623 |
96
+ | 6.5753 | 9.49 | 24500 | 6.5818 |
97
+ | 6.5645 | 9.68 | 25000 | 6.5726 |
98
+ | 6.6094 | 9.88 | 25500 | 6.5710 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.24.0
104
+ - Pytorch 1.12.1+cu113
105
+ - Datasets 2.6.1
106
+ - Tokenizers 0.13.2