Hugging Face's logo

AndreaTacchella
/
TechTokenBert

Feature Extraction
Safetensors
English
bert
patents
ipc
embeddings
semantic-similarity
masked-language-modeling
patent-classification
Model card Files
xet
 Community
AndreaTacchella commited on
Commit
5121458
·
verified ·
1 Parent(s): 332bfca

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +24 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +37 -0
  7. tokenizer_config.json +58 -0
  8. trainer_state.json +190 -0
  9. training_args.bin +3 -0
  10. vocab (Copia).txt +0 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 47816
24
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f5f467292a4a7be7739b1eddc9adb874f06bef11faebb3f147df9dcc68d596
3
+ size 1411650472
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8435c89aad2d44f91574653e9adc3696cfb159119d11c00f80735e642527ca1c
3
+ size 2823542081
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c8d0e1aad9b37872018b8cf9d76adb5d162f3d56ed4be48ec2e47b026cff6d
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345d7ce6ac99d483d043368bc5fab4e7cac6b458917d252a9b472f17f6a526a1
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 551560,
3
+ "best_metric": 0.4202389121055603,
4
+ "best_model_checkpoint": "submission/results/model_TT_7dcodes_cls_tt_end_not_shuffled/checkpoint-551560",
5
+ "epoch": 2.0,
6
+ "eval_steps": 275780,
7
+ "global_step": 551564,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09999927478950765,
14
+ "grad_norm": 4.513119220733643,
15
+ "learning_rate": 4.7543207322561444e-05,
16
+ "loss": 0.7242,
17
+ "step": 27578
18
+ },
19
+ {
20
+ "epoch": 0.1999985495790153,
21
+ "grad_norm": 3.410264015197754,
22
+ "learning_rate": 4.50409571302063e-05,
23
+ "loss": 0.621,
24
+ "step": 55156
25
+ },
26
+ {
27
+ "epoch": 0.29999782436852296,
28
+ "grad_norm": 3.972125768661499,
29
+ "learning_rate": 4.253870693785114e-05,
30
+ "loss": 0.6056,
31
+ "step": 82734
32
+ },
33
+ {
34
+ "epoch": 0.3999970991580306,
35
+ "grad_norm": 3.088068962097168,
36
+ "learning_rate": 4.0036456745495986e-05,
37
+ "loss": 0.5958,
38
+ "step": 110312
39
+ },
40
+ {
41
+ "epoch": 0.49999637394753826,
42
+ "grad_norm": 2.8378355503082275,
43
+ "learning_rate": 3.753420655314083e-05,
44
+ "loss": 0.5842,
45
+ "step": 137890
46
+ },
47
+ {
48
+ "epoch": 0.5999956487370459,
49
+ "grad_norm": 2.7692346572875977,
50
+ "learning_rate": 3.503195636078569e-05,
51
+ "loss": 0.5735,
52
+ "step": 165468
53
+ },
54
+ {
55
+ "epoch": 0.6999949235265536,
56
+ "grad_norm": 4.5936598777771,
57
+ "learning_rate": 3.252970616843053e-05,
58
+ "loss": 0.5644,
59
+ "step": 193046
60
+ },
61
+ {
62
+ "epoch": 0.7999941983160612,
63
+ "grad_norm": 3.122809648513794,
64
+ "learning_rate": 3.0027455976075375e-05,
65
+ "loss": 0.5521,
66
+ "step": 220624
67
+ },
68
+ {
69
+ "epoch": 0.8999934731055689,
70
+ "grad_norm": 2.5449647903442383,
71
+ "learning_rate": 2.7525205783720222e-05,
72
+ "loss": 0.5396,
73
+ "step": 248202
74
+ },
75
+ {
76
+ "epoch": 0.9999927478950765,
77
+ "grad_norm": 2.232771635055542,
78
+ "learning_rate": 2.5022955591365072e-05,
79
+ "loss": 0.53,
80
+ "step": 275780
81
+ },
82
+ {
83
+ "epoch": 0.9999927478950765,
84
+ "eval_loss": 0.4933322072029114,
85
+ "eval_runtime": 6025.5826,
86
+ "eval_samples_per_second": 61.025,
87
+ "eval_steps_per_second": 5.085,
88
+ "step": 275780
89
+ },
90
+ {
91
+ "epoch": 1.0999920226845843,
92
+ "grad_norm": 1.9279263019561768,
93
+ "learning_rate": 2.2520705399009916e-05,
94
+ "loss": 0.5164,
95
+ "step": 303358
96
+ },
97
+ {
98
+ "epoch": 1.1999912974740918,
99
+ "grad_norm": 2.2434041500091553,
100
+ "learning_rate": 2.0018455206654763e-05,
101
+ "loss": 0.5062,
102
+ "step": 330936
103
+ },
104
+ {
105
+ "epoch": 1.2999905722635994,
106
+ "grad_norm": 4.116876602172852,
107
+ "learning_rate": 1.751620501429961e-05,
108
+ "loss": 0.4966,
109
+ "step": 358514
110
+ },
111
+ {
112
+ "epoch": 1.3999898470531071,
113
+ "grad_norm": 2.3324735164642334,
114
+ "learning_rate": 1.5013954821944456e-05,
115
+ "loss": 0.4867,
116
+ "step": 386092
117
+ },
118
+ {
119
+ "epoch": 1.499989121842615,
120
+ "grad_norm": 2.4795002937316895,
121
+ "learning_rate": 1.2511704629589305e-05,
122
+ "loss": 0.4773,
123
+ "step": 413670
124
+ },
125
+ {
126
+ "epoch": 1.5999883966321224,
127
+ "grad_norm": 2.851177453994751,
128
+ "learning_rate": 1.0009454437234152e-05,
129
+ "loss": 0.4695,
130
+ "step": 441248
131
+ },
132
+ {
133
+ "epoch": 1.69998767142163,
134
+ "grad_norm": 2.3028323650360107,
135
+ "learning_rate": 7.507204244878999e-06,
136
+ "loss": 0.4601,
137
+ "step": 468826
138
+ },
139
+ {
140
+ "epoch": 1.7999869462111378,
141
+ "grad_norm": 2.5855956077575684,
142
+ "learning_rate": 5.004954052523845e-06,
143
+ "loss": 0.4512,
144
+ "step": 496404
145
+ },
146
+ {
147
+ "epoch": 1.8999862210006455,
148
+ "grad_norm": 3.5067687034606934,
149
+ "learning_rate": 2.502703860168692e-06,
150
+ "loss": 0.4444,
151
+ "step": 523982
152
+ },
153
+ {
154
+ "epoch": 1.999985495790153,
155
+ "grad_norm": 3.1099815368652344,
156
+ "learning_rate": 4.536678135388993e-10,
157
+ "loss": 0.4395,
158
+ "step": 551560
159
+ },
160
+ {
161
+ "epoch": 1.999985495790153,
162
+ "eval_loss": 0.4202389121055603,
163
+ "eval_runtime": 6034.8002,
164
+ "eval_samples_per_second": 60.931,
165
+ "eval_steps_per_second": 5.078,
166
+ "step": 551560
167
+ }
168
+ ],
169
+ "logging_steps": 27578,
170
+ "max_steps": 551564,
171
+ "num_input_tokens_seen": 0,
172
+ "num_train_epochs": 2,
173
+ "save_steps": 27578,
174
+ "stateful_callbacks": {
175
+ "TrainerControl": {
176
+ "args": {
177
+ "should_epoch_stop": false,
178
+ "should_evaluate": false,
179
+ "should_log": false,
180
+ "should_save": true,
181
+ "should_training_stop": true
182
+ },
183
+ "attributes": {}
184
+ }
185
+ },
186
+ "total_flos": 6.1691929035264e+18,
187
+ "train_batch_size": 12,
188
+ "trial_name": null,
189
+ "trial_params": null
190
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8189dae00a3c1eedba3e40263699e4120a6debfcf8ada5b14f363ceb229c288
3
+ size 5841
vocab (Copia).txt ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff