Hugging Face's logo

namin0202
/
pna-simcse-bert-base-uncased

Transformers
PyTorch
bert
Model card Files
xet
 Community
namin0202 commited on
Commit
48fe69f
·
verified ·
1 Parent(s): 2c9eff2

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +24 -0
  2. eval_results.txt +12 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +1 -0
  7. tokenizer_config.json +1 -0
  8. train_results.txt +3 -0
  9. trainer_state.json +233 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "result/my-sup-simcse-bert-base-lastterm",
3
+ "architectures": [
4
+ "BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
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
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.2.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
eval_results.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch = 3.0
2
+ eval_CR = 89.48
3
+ eval_MPQA = 89.68
4
+ eval_MR = 82.55
5
+ eval_MRPC = 76.67
6
+ eval_SST2 = 87.27
7
+ eval_SUBJ = 94.48
8
+ eval_TREC = 78.76
9
+ eval_avg_sts = 0.8170722172992666
10
+ eval_avg_transfer = 85.55571428571429
11
+ eval_sickr_spearman = 0.7818400385849915
12
+ eval_stsb_spearman = 0.8523043960135418
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df891a475e8137b73ce85bff69ebbc59b96f6bc0ef2ccf169ff9a9613e8605a8
3
+ size 875973285
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c5d3e54a49ce0c6c0a382525355ba9a6a5db0f9cb504bd1421ec54ed7a4eb3
3
+ size 438012465
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c4ae848e092d1dae85b8344f3b8f445b2c5373adfd9a7888568a422c676a4f
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 2076.5315
3
+ train_samples_per_second = 1.556
trainer_state.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8523043960135418,
3
+ "best_model_checkpoint": "result/my-sup-simcse-bert-base-lastterm",
4
+ "epoch": 3.0,
5
+ "global_step": 3231,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.12,
12
+ "eval_avg_sts": 0.8194254390928033,
13
+ "eval_sickr_spearman": 0.7990052495236399,
14
+ "eval_stsb_spearman": 0.8398456286619668,
15
+ "step": 125
16
+ },
17
+ {
18
+ "epoch": 0.23,
19
+ "eval_avg_sts": 0.8165670458735704,
20
+ "eval_sickr_spearman": 0.7869509320268182,
21
+ "eval_stsb_spearman": 0.8461831597203227,
22
+ "step": 250
23
+ },
24
+ {
25
+ "epoch": 0.35,
26
+ "eval_avg_sts": 0.8228159333151963,
27
+ "eval_sickr_spearman": 0.7957744855165066,
28
+ "eval_stsb_spearman": 0.8498573811138859,
29
+ "step": 375
30
+ },
31
+ {
32
+ "epoch": 0.46,
33
+ "learning_rate": 4.226245744351594e-05,
34
+ "loss": 1.0808,
35
+ "step": 500
36
+ },
37
+ {
38
+ "epoch": 0.46,
39
+ "eval_avg_sts": 0.8168153761131349,
40
+ "eval_sickr_spearman": 0.7877662119426287,
41
+ "eval_stsb_spearman": 0.8458645402836412,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 0.58,
46
+ "eval_avg_sts": 0.8156032349409434,
47
+ "eval_sickr_spearman": 0.7826891323962145,
48
+ "eval_stsb_spearman": 0.8485173374856724,
49
+ "step": 625
50
+ },
51
+ {
52
+ "epoch": 0.7,
53
+ "eval_avg_sts": 0.8169960567322327,
54
+ "eval_sickr_spearman": 0.7846676775577546,
55
+ "eval_stsb_spearman": 0.849324435906711,
56
+ "step": 750
57
+ },
58
+ {
59
+ "epoch": 0.81,
60
+ "eval_avg_sts": 0.8146560028725298,
61
+ "eval_sickr_spearman": 0.7835492733607682,
62
+ "eval_stsb_spearman": 0.8457627323842916,
63
+ "step": 875
64
+ },
65
+ {
66
+ "epoch": 0.93,
67
+ "learning_rate": 3.452491488703188e-05,
68
+ "loss": 0.8522,
69
+ "step": 1000
70
+ },
71
+ {
72
+ "epoch": 0.93,
73
+ "eval_avg_sts": 0.8163927093002852,
74
+ "eval_sickr_spearman": 0.7824352399940127,
75
+ "eval_stsb_spearman": 0.8503501786065577,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 1.04,
80
+ "eval_avg_sts": 0.8052909347246509,
81
+ "eval_sickr_spearman": 0.7662991914658787,
82
+ "eval_stsb_spearman": 0.8442826779834229,
83
+ "step": 1125
84
+ },
85
+ {
86
+ "epoch": 1.16,
87
+ "eval_avg_sts": 0.8106314735517854,
88
+ "eval_sickr_spearman": 0.77574806186519,
89
+ "eval_stsb_spearman": 0.8455148852383809,
90
+ "step": 1250
91
+ },
92
+ {
93
+ "epoch": 1.28,
94
+ "eval_avg_sts": 0.8113568861098444,
95
+ "eval_sickr_spearman": 0.7783763237358834,
96
+ "eval_stsb_spearman": 0.8443374484838054,
97
+ "step": 1375
98
+ },
99
+ {
100
+ "epoch": 1.39,
101
+ "learning_rate": 2.678737233054782e-05,
102
+ "loss": 0.6828,
103
+ "step": 1500
104
+ },
105
+ {
106
+ "epoch": 1.39,
107
+ "eval_avg_sts": 0.8208657443062924,
108
+ "eval_sickr_spearman": 0.7928466056350422,
109
+ "eval_stsb_spearman": 0.8488848829775427,
110
+ "step": 1500
111
+ },
112
+ {
113
+ "epoch": 1.51,
114
+ "eval_avg_sts": 0.8180871720303612,
115
+ "eval_sickr_spearman": 0.7858960729770345,
116
+ "eval_stsb_spearman": 0.8502782710836879,
117
+ "step": 1625
118
+ },
119
+ {
120
+ "epoch": 1.62,
121
+ "eval_avg_sts": 0.8170722172992666,
122
+ "eval_sickr_spearman": 0.7818400385849915,
123
+ "eval_stsb_spearman": 0.8523043960135418,
124
+ "step": 1750
125
+ },
126
+ {
127
+ "epoch": 1.74,
128
+ "eval_avg_sts": 0.81144903531131,
129
+ "eval_sickr_spearman": 0.7756615098203985,
130
+ "eval_stsb_spearman": 0.8472365608022215,
131
+ "step": 1875
132
+ },
133
+ {
134
+ "epoch": 1.86,
135
+ "learning_rate": 1.9049829774063757e-05,
136
+ "loss": 0.6522,
137
+ "step": 2000
138
+ },
139
+ {
140
+ "epoch": 1.86,
141
+ "eval_avg_sts": 0.8141474203440927,
142
+ "eval_sickr_spearman": 0.7794347370871737,
143
+ "eval_stsb_spearman": 0.8488601036010117,
144
+ "step": 2000
145
+ },
146
+ {
147
+ "epoch": 1.97,
148
+ "eval_avg_sts": 0.8158956922741192,
149
+ "eval_sickr_spearman": 0.7808102517701584,
150
+ "eval_stsb_spearman": 0.8509811327780799,
151
+ "step": 2125
152
+ },
153
+ {
154
+ "epoch": 2.09,
155
+ "eval_avg_sts": 0.814587631326179,
156
+ "eval_sickr_spearman": 0.7796313764164613,
157
+ "eval_stsb_spearman": 0.8495438862358966,
158
+ "step": 2250
159
+ },
160
+ {
161
+ "epoch": 2.21,
162
+ "eval_avg_sts": 0.8114095673015015,
163
+ "eval_sickr_spearman": 0.7735022716552481,
164
+ "eval_stsb_spearman": 0.8493168629477549,
165
+ "step": 2375
166
+ },
167
+ {
168
+ "epoch": 2.32,
169
+ "learning_rate": 1.1312287217579697e-05,
170
+ "loss": 0.5675,
171
+ "step": 2500
172
+ },
173
+ {
174
+ "epoch": 2.32,
175
+ "eval_avg_sts": 0.8121220784998155,
176
+ "eval_sickr_spearman": 0.7740748984465933,
177
+ "eval_stsb_spearman": 0.8501692585530379,
178
+ "step": 2500
179
+ },
180
+ {
181
+ "epoch": 2.44,
182
+ "eval_avg_sts": 0.8130334510314673,
183
+ "eval_sickr_spearman": 0.7768290018030546,
184
+ "eval_stsb_spearman": 0.84923790025988,
185
+ "step": 2625
186
+ },
187
+ {
188
+ "epoch": 2.55,
189
+ "eval_avg_sts": 0.8140933803428295,
190
+ "eval_sickr_spearman": 0.7770954303227319,
191
+ "eval_stsb_spearman": 0.8510913303629272,
192
+ "step": 2750
193
+ },
194
+ {
195
+ "epoch": 2.67,
196
+ "eval_avg_sts": 0.8149543004915998,
197
+ "eval_sickr_spearman": 0.7786629253181646,
198
+ "eval_stsb_spearman": 0.8512456756650348,
199
+ "step": 2875
200
+ },
201
+ {
202
+ "epoch": 2.79,
203
+ "learning_rate": 3.574744661095636e-06,
204
+ "loss": 0.5295,
205
+ "step": 3000
206
+ },
207
+ {
208
+ "epoch": 2.79,
209
+ "eval_avg_sts": 0.8162287995156676,
210
+ "eval_sickr_spearman": 0.7821816357784194,
211
+ "eval_stsb_spearman": 0.8502759632529158,
212
+ "step": 3000
213
+ },
214
+ {
215
+ "epoch": 2.9,
216
+ "eval_avg_sts": 0.8163857434466557,
217
+ "eval_sickr_spearman": 0.7826894686139245,
218
+ "eval_stsb_spearman": 0.850082018279387,
219
+ "step": 3125
220
+ },
221
+ {
222
+ "epoch": 3.0,
223
+ "step": 3231,
224
+ "train_runtime": 2076.5315,
225
+ "train_samples_per_second": 1.556
226
+ }
227
+ ],
228
+ "max_steps": 3231,
229
+ "num_train_epochs": 3,
230
+ "total_flos": 52139850005053440,
231
+ "trial_name": null,
232
+ "trial_params": null
233
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54624ed6cd245ae35c94b90dbf8c13889510b6d52ad29eb3631dc50eb346b47
3
+ size 2095
vocab.txt ADDED
The diff for this file is too large to render. See raw diff