Hugging Face's logo

amrisaurus
/
pretrained-m-bert-100

Transformers
TensorFlow
bert
pretraining
generated_from_keras_callback
Model card Files
xet
 Community
amrisaurus commited on
Commit
730aa02
·
1 Parent(s): 433d7d1

Upload TFBertForPreTraining

Browse files
Files changed (3) hide show
  1. README.md +151 -0
  2. config.json +29 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_keras_callback
4
+ model-index:
5
+ - name: pretrained-m-bert-100
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
10
+ probably proofread and complete it, then remove this comment. -->
11
+
12
+ # pretrained-m-bert-100
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Train Loss: 5.7643
17
+ - Validation Loss: 15.3282
18
+ - Epoch: 99
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
+ - optimizer: {'name': 'Adam', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
38
+ - training_precision: float32
39
+
40
+ ### Training results
41
+
42
+ | Train Loss | Validation Loss | Epoch |
43
+ |:----------:|:---------------:|:-----:|
44
+ | 10.2677 | 10.9468 | 0 |
45
+ | 7.8146 | 10.9178 | 1 |
46
+ | 6.8830 | 11.4644 | 2 |
47
+ | 6.4854 | 11.6027 | 3 |
48
+ | 6.3696 | 11.5359 | 4 |
49
+ | 6.3373 | 12.1261 | 5 |
50
+ | 6.4347 | 11.7670 | 6 |
51
+ | 6.0652 | 12.2223 | 7 |
52
+ | 5.9448 | 12.1202 | 8 |
53
+ | 6.0746 | 12.0816 | 9 |
54
+ | 6.0138 | 12.4949 | 10 |
55
+ | 5.9344 | 12.8130 | 11 |
56
+ | 5.9458 | 12.4795 | 12 |
57
+ | 5.9723 | 12.8273 | 13 |
58
+ | 6.0556 | 12.3681 | 14 |
59
+ | 5.8662 | 12.5367 | 15 |
60
+ | 5.8969 | 12.8070 | 16 |
61
+ | 5.9584 | 13.0502 | 17 |
62
+ | 5.8317 | 12.9219 | 18 |
63
+ | 5.8259 | 13.0385 | 19 |
64
+ | 5.8747 | 13.0952 | 20 |
65
+ | 5.7600 | 13.2153 | 21 |
66
+ | 5.8675 | 13.2446 | 22 |
67
+ | 5.8878 | 13.1709 | 23 |
68
+ | 5.7433 | 13.0553 | 24 |
69
+ | 5.6823 | 13.2854 | 25 |
70
+ | 5.8674 | 13.5718 | 26 |
71
+ | 5.7787 | 14.0820 | 27 |
72
+ | 5.8037 | 13.5664 | 28 |
73
+ | 5.9530 | 13.0143 | 29 |
74
+ | 5.8236 | 13.0637 | 30 |
75
+ | 5.7696 | 13.5515 | 31 |
76
+ | 5.9817 | 13.4774 | 32 |
77
+ | 5.6877 | 13.6842 | 33 |
78
+ | 5.7816 | 13.5667 | 34 |
79
+ | 5.7775 | 13.3846 | 35 |
80
+ | 5.7104 | 13.6230 | 36 |
81
+ | 5.8429 | 13.5487 | 37 |
82
+ | 5.8082 | 13.6563 | 38 |
83
+ | 5.8588 | 13.6359 | 39 |
84
+ | 5.6482 | 13.8751 | 40 |
85
+ | 5.7874 | 13.6936 | 41 |
86
+ | 5.7451 | 14.1454 | 42 |
87
+ | 5.7165 | 13.8532 | 43 |
88
+ | 5.7180 | 14.0519 | 44 |
89
+ | 5.6640 | 14.0859 | 45 |
90
+ | 5.6735 | 14.0086 | 46 |
91
+ | 5.6666 | 14.1733 | 47 |
92
+ | 5.6681 | 13.9786 | 48 |
93
+ | 5.8221 | 14.0396 | 49 |
94
+ | 5.8544 | 14.0354 | 50 |
95
+ | 5.6817 | 14.4682 | 51 |
96
+ | 5.7215 | 14.2324 | 52 |
97
+ | 5.7315 | 13.9238 | 53 |
98
+ | 5.9291 | 14.2091 | 54 |
99
+ | 5.6790 | 13.6927 | 55 |
100
+ | 5.8746 | 14.1590 | 56 |
101
+ | 5.7267 | 14.4351 | 57 |
102
+ | 5.7268 | 14.0592 | 58 |
103
+ | 5.7535 | 14.2763 | 59 |
104
+ | 5.7884 | 13.8493 | 60 |
105
+ | 5.6596 | 14.0534 | 61 |
106
+ | 5.7041 | 14.4408 | 62 |
107
+ | 5.6752 | 14.4218 | 63 |
108
+ | 5.7102 | 14.3895 | 64 |
109
+ | 5.7761 | 14.3942 | 65 |
110
+ | 5.7248 | 14.5926 | 66 |
111
+ | 5.7945 | 14.2754 | 67 |
112
+ | 5.9298 | 14.3393 | 68 |
113
+ | 5.8765 | 14.5247 | 69 |
114
+ | 5.7173 | 14.3060 | 70 |
115
+ | 5.6568 | 14.1837 | 71 |
116
+ | 5.8706 | 14.0935 | 72 |
117
+ | 5.6913 | 14.0180 | 73 |
118
+ | 5.7403 | 14.9313 | 74 |
119
+ | 5.8633 | 14.1447 | 75 |
120
+ | 5.8216 | 14.5450 | 76 |
121
+ | 5.7655 | 14.4690 | 77 |
122
+ | 5.7860 | 14.4312 | 78 |
123
+ | 5.6992 | 14.1038 | 79 |
124
+ | 5.7390 | 14.5180 | 80 |
125
+ | 5.7588 | 14.2374 | 81 |
126
+ | 5.7709 | 14.4895 | 82 |
127
+ | 5.6294 | 14.9558 | 83 |
128
+ | 5.8151 | 14.5835 | 84 |
129
+ | 5.7965 | 14.8980 | 85 |
130
+ | 5.8296 | 14.5919 | 86 |
131
+ | 5.6494 | 15.2158 | 87 |
132
+ | 5.8014 | 14.9455 | 88 |
133
+ | 5.7313 | 14.4270 | 89 |
134
+ | 5.7492 | 14.2205 | 90 |
135
+ | 5.7618 | 15.2789 | 91 |
136
+ | 5.7249 | 15.0650 | 92 |
137
+ | 5.6761 | 14.8731 | 93 |
138
+ | 5.8601 | 14.6370 | 94 |
139
+ | 5.6296 | 14.8570 | 95 |
140
+ | 5.7572 | 14.7718 | 96 |
141
+ | 5.6341 | 14.9328 | 97 |
142
+ | 5.6881 | 14.9298 | 98 |
143
+ | 5.7643 | 15.3282 | 99 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - Transformers 4.27.0.dev0
149
+ - TensorFlow 2.9.2
150
+ - Datasets 2.9.0
151
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_fc_size": 768,
20
+ "pooler_num_attention_heads": 12,
21
+ "pooler_num_fc_layers": 3,
22
+ "pooler_size_per_head": 128,
23
+ "pooler_type": "first_token_transform",
24
+ "position_embedding_type": "absolute",
25
+ "transformers_version": "4.27.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 119547
29
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bccdcf48ba94c2c6a66431e991f8468ce18cc17b3190d894f24b2c229c8d462
3
+ size 1083389236