Hugging Face's logo

soravoid
/
bert-twitch-emotes

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
soravoid commited on
Commit
c3f017c
•
1 Parent(s): 94eb217

End of training

Browse files
Files changed (3) hide show
  1. README.md +108 -11
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -4,18 +4,18 @@ base_model: bert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
- - name: bert-twitch
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
- # bert-twitch
15
 
16
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 4.8105
19
 
20
  ## Model description
21
 
@@ -40,20 +40,117 @@ 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: 3.0
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 1.5329 | 1.0 | 165 | 5.1209 |
50
- | 1.7499 | 2.0 | 330 | 4.7902 |
51
- | 2.7708 | 3.0 | 495 | 4.9339 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
55
 
56
- - Transformers 4.36.0.dev0
57
- - Pytorch 2.1.1+cpu
58
  - Datasets 2.15.0
59
  - Tokenizers 0.15.0
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: bert-twitch-emotes
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
+ # bert-twitch-emotes
15
 
16
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.9711
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
+ | 5.5495 | 1.0 | 165 | 4.6986 |
50
+ | 4.6634 | 2.0 | 330 | 3.8592 |
51
+ | 4.3587 | 3.0 | 495 | nan |
52
+ | 4.0264 | 4.0 | 660 | 3.6984 |
53
+ | 3.5892 | 5.0 | 825 | nan |
54
+ | 3.7685 | 6.0 | 990 | 3.8205 |
55
+ | 3.3314 | 7.0 | 1155 | 3.7551 |
56
+ | 3.3483 | 8.0 | 1320 | 3.4611 |
57
+ | 3.1391 | 9.0 | 1485 | 3.4480 |
58
+ | 2.9446 | 10.0 | 1650 | 3.4619 |
59
+ | 2.918 | 11.0 | 1815 | 3.5393 |
60
+ | 2.7561 | 12.0 | 1980 | 3.4080 |
61
+ | 2.9775 | 13.0 | 2145 | 3.5564 |
62
+ | 2.6634 | 14.0 | 2310 | nan |
63
+ | 2.6358 | 15.0 | 2475 | nan |
64
+ | 2.5163 | 16.0 | 2640 | nan |
65
+ | 2.6054 | 17.0 | 2805 | nan |
66
+ | 2.3735 | 18.0 | 2970 | nan |
67
+ | 2.5114 | 19.0 | 3135 | 3.1434 |
68
+ | 2.3668 | 20.0 | 3300 | nan |
69
+ | 2.3008 | 21.0 | 3465 | 3.4670 |
70
+ | 2.1246 | 22.0 | 3630 | 3.2320 |
71
+ | 2.1345 | 23.0 | 3795 | nan |
72
+ | 2.1379 | 24.0 | 3960 | 3.4308 |
73
+ | 2.3027 | 25.0 | 4125 | nan |
74
+ | 2.2912 | 26.0 | 4290 | 3.8554 |
75
+ | 2.0533 | 27.0 | 4455 | nan |
76
+ | 2.0029 | 28.0 | 4620 | 3.6411 |
77
+ | 2.0801 | 29.0 | 4785 | 3.3145 |
78
+ | 1.9242 | 30.0 | 4950 | 3.8866 |
79
+ | 1.8617 | 31.0 | 5115 | nan |
80
+ | 1.7359 | 32.0 | 5280 | 3.6191 |
81
+ | 1.7567 | 33.0 | 5445 | 3.4290 |
82
+ | 1.5816 | 34.0 | 5610 | nan |
83
+ | 1.6193 | 35.0 | 5775 | 3.6239 |
84
+ | 1.7555 | 36.0 | 5940 | 3.8294 |
85
+ | 1.5949 | 37.0 | 6105 | nan |
86
+ | 1.5287 | 38.0 | 6270 | nan |
87
+ | 1.7165 | 39.0 | 6435 | 3.9250 |
88
+ | 1.4955 | 40.0 | 6600 | nan |
89
+ | 1.5768 | 41.0 | 6765 | 3.5979 |
90
+ | 1.4145 | 42.0 | 6930 | 4.3696 |
91
+ | 1.3059 | 43.0 | 7095 | 3.8834 |
92
+ | 1.4716 | 44.0 | 7260 | 3.8716 |
93
+ | 1.4055 | 45.0 | 7425 | 3.5523 |
94
+ | 1.231 | 46.0 | 7590 | 3.5275 |
95
+ | 1.2732 | 47.0 | 7755 | 3.5954 |
96
+ | 1.4179 | 48.0 | 7920 | 3.9041 |
97
+ | 1.3136 | 49.0 | 8085 | 3.7871 |
98
+ | 1.4072 | 50.0 | 8250 | 3.7365 |
99
+ | 1.2083 | 51.0 | 8415 | 3.9303 |
100
+ | 1.2625 | 52.0 | 8580 | 3.6428 |
101
+ | 1.1998 | 53.0 | 8745 | 3.7615 |
102
+ | 1.224 | 54.0 | 8910 | nan |
103
+ | 1.0882 | 55.0 | 9075 | 3.9539 |
104
+ | 1.1847 | 56.0 | 9240 | 4.2988 |
105
+ | 1.1108 | 57.0 | 9405 | nan |
106
+ | 1.1376 | 58.0 | 9570 | nan |
107
+ | 1.073 | 59.0 | 9735 | nan |
108
+ | 0.9939 | 60.0 | 9900 | 4.3302 |
109
+ | 1.0409 | 61.0 | 10065 | 3.9883 |
110
+ | 1.1136 | 62.0 | 10230 | 3.9496 |
111
+ | 1.0054 | 63.0 | 10395 | nan |
112
+ | 0.8614 | 64.0 | 10560 | 3.8033 |
113
+ | 0.9833 | 65.0 | 10725 | nan |
114
+ | 1.0471 | 66.0 | 10890 | 3.7918 |
115
+ | 0.9947 | 67.0 | 11055 | nan |
116
+ | 1.0328 | 68.0 | 11220 | 3.8372 |
117
+ | 1.0071 | 69.0 | 11385 | nan |
118
+ | 0.9151 | 70.0 | 11550 | nan |
119
+ | 1.114 | 71.0 | 11715 | 4.0105 |
120
+ | 0.8184 | 72.0 | 11880 | nan |
121
+ | 1.1402 | 73.0 | 12045 | 4.1616 |
122
+ | 1.0118 | 74.0 | 12210 | 4.1463 |
123
+ | 1.0308 | 75.0 | 12375 | 4.1884 |
124
+ | 0.8101 | 76.0 | 12540 | nan |
125
+ | 0.9185 | 77.0 | 12705 | 3.8719 |
126
+ | 0.9617 | 78.0 | 12870 | 3.5809 |
127
+ | 0.7833 | 79.0 | 13035 | 3.6456 |
128
+ | 0.8115 | 80.0 | 13200 | 4.0877 |
129
+ | 0.9021 | 81.0 | 13365 | 4.5326 |
130
+ | 0.7471 | 82.0 | 13530 | 3.6400 |
131
+ | 0.862 | 83.0 | 13695 | 4.4030 |
132
+ | 0.9765 | 84.0 | 13860 | nan |
133
+ | 0.8329 | 85.0 | 14025 | 4.2526 |
134
+ | 0.7722 | 86.0 | 14190 | nan |
135
+ | 0.7735 | 87.0 | 14355 | nan |
136
+ | 0.736 | 88.0 | 14520 | nan |
137
+ | 0.9181 | 89.0 | 14685 | nan |
138
+ | 0.7734 | 90.0 | 14850 | 4.2560 |
139
+ | 0.7839 | 91.0 | 15015 | nan |
140
+ | 0.7987 | 92.0 | 15180 | 4.1558 |
141
+ | 0.8994 | 93.0 | 15345 | 4.0585 |
142
+ | 0.8252 | 94.0 | 15510 | 3.5777 |
143
+ | 0.6863 | 95.0 | 15675 | 4.1786 |
144
+ | 0.8669 | 96.0 | 15840 | 3.8966 |
145
+ | 0.792 | 97.0 | 16005 | 3.9439 |
146
+ | 0.681 | 98.0 | 16170 | 3.5610 |
147
+ | 0.8098 | 99.0 | 16335 | nan |
148
+ | 0.7167 | 100.0 | 16500 | nan |
149
 
150
 
151
  ### Framework versions
152
 
153
+ - Transformers 4.35.2
154
+ - Pytorch 2.1.1+cu121
155
  - Datasets 2.15.0
156
  - Tokenizers 0.15.0
generation_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
  "_from_model_config": true,
3
  "pad_token_id": 0,
4
- "transformers_version": "4.36.0.dev0"
5
  }
 
1
  {
2
  "_from_model_config": true,
3
  "pad_token_id": 0,
4
+ "transformers_version": "4.35.2"
5
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe6d33a7bb442c4f07780a006ace96716d5278255e14dc8d0cbeadd3ffd31913
3
  size 437268824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b92e9f930a093628b2764d7715425e2d81bcf1efec996c4f5d8041d7d115503
3
  size 437268824