Hugging Face's logo

isek-ai
/
isekai-bert-v1

Fill-Mask
Transformers
Safetensors
Japanese
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
p1atdev commited on
Commit
2985251
•
1 Parent(s): 0705e5e

Model save

Browse files
Files changed (3) hide show
  1. README.md +88 -0
  2. generation_config.json +5 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: cl-tohoku/bert-base-japanese-v3
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: kakuyomu-mlm-bert-2
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
+ # kakuyomu-mlm-bert-2
15
+
16
+ This model is a fine-tuned version of [cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.9164
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 2
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 2.9144 | 0.06 | 1000 | 2.6322 |
51
+ | 3.0793 | 0.13 | 2000 | 2.7752 |
52
+ | 3.0591 | 0.19 | 3000 | 2.8336 |
53
+ | 2.972 | 0.26 | 4000 | 2.9084 |
54
+ | 2.9967 | 0.32 | 5000 | 2.8845 |
55
+ | 2.9489 | 0.38 | 6000 | 2.7112 |
56
+ | 2.8639 | 0.45 | 7000 | 2.7209 |
57
+ | 2.8355 | 0.51 | 8000 | 2.6684 |
58
+ | 2.8162 | 0.58 | 9000 | 2.6209 |
59
+ | 2.7648 | 0.64 | 10000 | 2.5749 |
60
+ | 2.6663 | 0.7 | 11000 | 2.5231 |
61
+ | 2.6451 | 0.77 | 12000 | 2.4754 |
62
+ | 2.6041 | 0.83 | 13000 | 2.4279 |
63
+ | 2.5306 | 0.9 | 14000 | 2.3829 |
64
+ | 2.4765 | 0.96 | 15000 | 2.3137 |
65
+ | 2.3899 | 1.02 | 16000 | 2.3052 |
66
+ | 2.3681 | 1.09 | 17000 | 2.2123 |
67
+ | 2.2821 | 1.15 | 18000 | 2.1934 |
68
+ | 2.2288 | 1.22 | 19000 | 2.1399 |
69
+ | 2.1858 | 1.28 | 20000 | 2.0922 |
70
+ | 2.1964 | 1.34 | 21000 | 2.0689 |
71
+ | 2.1419 | 1.41 | 22000 | 2.0357 |
72
+ | 2.1011 | 1.47 | 23000 | 2.0327 |
73
+ | 2.039 | 1.54 | 24000 | 1.9853 |
74
+ | 2.0284 | 1.6 | 25000 | 1.9778 |
75
+ | 2.0253 | 1.66 | 26000 | 1.9869 |
76
+ | 2.0292 | 1.73 | 27000 | 1.9494 |
77
+ | 2.0016 | 1.79 | 28000 | 1.9158 |
78
+ | 2.0387 | 1.86 | 29000 | 1.9778 |
79
+ | 1.9679 | 1.92 | 30000 | 1.9171 |
80
+ | 2.0441 | 1.98 | 31000 | 1.9164 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.34.0
86
+ - Pytorch 2.0.0+cu118
87
+ - Datasets 2.14.5
88
+ - Tokenizers 0.14.0
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.34.0"
5
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:881b854fc2bd38f913c3b02ab32d27d5fa29ccca7fb1109e2bc0be65fa22f184
3
  size 222506736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf8d9d5f81bbad729c419981344776e5b5080a48633f76feae27cdcf4a42b59
3
  size 222506736