Hugging Face's logo

gcyzsl
/
unsup-VisualCSE-bert-base-uncased

Transformers
PyTorch
bert
Model card Files
xet
 Community
gcyzsl commited on
Commit
0744c0e
·
1 Parent(s): 3afcb6f

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +159 -0
trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8364591679967303,
3
+ "best_model_checkpoint": "result/my-unsup-simcse-bert-base-uncased/SupCon-48-0.05-1e-6-0.07-0.0",
4
+ "epoch": 0.13599129655702036,
5
+ "global_step": 2125,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "eval_avg_sts": 0.5970383001895778,
13
+ "eval_sickr_spearman": 0.6019806627713715,
14
+ "eval_stsb_spearman": 0.5920959376077841,
15
+ "step": 125
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "eval_avg_sts": 0.611701821974194,
20
+ "eval_sickr_spearman": 0.6004132638381416,
21
+ "eval_stsb_spearman": 0.6229903801102463,
22
+ "step": 250
23
+ },
24
+ {
25
+ "epoch": 0.02,
26
+ "eval_avg_sts": 0.6755999453554371,
27
+ "eval_sickr_spearman": 0.663436697216944,
28
+ "eval_stsb_spearman": 0.6877631934939302,
29
+ "step": 375
30
+ },
31
+ {
32
+ "epoch": 0.03,
33
+ "learning_rate": 2.9040061436068092e-05,
34
+ "loss": 0.0096,
35
+ "step": 500
36
+ },
37
+ {
38
+ "epoch": 0.03,
39
+ "eval_avg_sts": 0.7051607278341783,
40
+ "eval_sickr_spearman": 0.6914595787911848,
41
+ "eval_stsb_spearman": 0.7188618768771717,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 0.04,
46
+ "eval_avg_sts": 0.7185324383897518,
47
+ "eval_sickr_spearman": 0.7105461298495607,
48
+ "eval_stsb_spearman": 0.7265187469299428,
49
+ "step": 625
50
+ },
51
+ {
52
+ "epoch": 0.05,
53
+ "eval_avg_sts": 0.7407726508059268,
54
+ "eval_sickr_spearman": 0.7263214648058943,
55
+ "eval_stsb_spearman": 0.7552238368059593,
56
+ "step": 750
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "eval_avg_sts": 0.7519081237039615,
61
+ "eval_sickr_spearman": 0.7255188651008634,
62
+ "eval_stsb_spearman": 0.7782973823070597,
63
+ "step": 875
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 2.8080122872136184e-05,
68
+ "loss": 0.0003,
69
+ "step": 1000
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "eval_avg_sts": 0.7500467602180523,
74
+ "eval_sickr_spearman": 0.7223982364093279,
75
+ "eval_stsb_spearman": 0.7776952840267766,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 0.07,
80
+ "eval_avg_sts": 0.7467502119755708,
81
+ "eval_sickr_spearman": 0.728734211124435,
82
+ "eval_stsb_spearman": 0.7647662128267065,
83
+ "step": 1125
84
+ },
85
+ {
86
+ "epoch": 0.08,
87
+ "eval_avg_sts": 0.7596796374404999,
88
+ "eval_sickr_spearman": 0.7285124515290953,
89
+ "eval_stsb_spearman": 0.7908468233519046,
90
+ "step": 1250
91
+ },
92
+ {
93
+ "epoch": 0.09,
94
+ "eval_avg_sts": 0.7624163252799534,
95
+ "eval_sickr_spearman": 0.7287400709188105,
96
+ "eval_stsb_spearman": 0.7960925796410961,
97
+ "step": 1375
98
+ },
99
+ {
100
+ "epoch": 0.1,
101
+ "learning_rate": 2.7120184308204276e-05,
102
+ "loss": 0.0002,
103
+ "step": 1500
104
+ },
105
+ {
106
+ "epoch": 0.1,
107
+ "eval_avg_sts": 0.7646980100640273,
108
+ "eval_sickr_spearman": 0.7311422984261363,
109
+ "eval_stsb_spearman": 0.7982537217019183,
110
+ "step": 1500
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "eval_avg_sts": 0.77192901208638,
115
+ "eval_sickr_spearman": 0.7326283807046314,
116
+ "eval_stsb_spearman": 0.8112296434681285,
117
+ "step": 1625
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "eval_avg_sts": 0.7801417411637921,
122
+ "eval_sickr_spearman": 0.7344049550846243,
123
+ "eval_stsb_spearman": 0.8258785272429598,
124
+ "step": 1750
125
+ },
126
+ {
127
+ "epoch": 0.12,
128
+ "eval_avg_sts": 0.7833167465924272,
129
+ "eval_sickr_spearman": 0.7375878320836238,
130
+ "eval_stsb_spearman": 0.8290456611012307,
131
+ "step": 1875
132
+ },
133
+ {
134
+ "epoch": 0.13,
135
+ "learning_rate": 2.6160245744272367e-05,
136
+ "loss": 0.0002,
137
+ "step": 2000
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "eval_avg_sts": 0.7741958728035641,
142
+ "eval_sickr_spearman": 0.7297883016765958,
143
+ "eval_stsb_spearman": 0.8186034439305322,
144
+ "step": 2000
145
+ },
146
+ {
147
+ "epoch": 0.14,
148
+ "eval_avg_sts": 0.7860888148061913,
149
+ "eval_sickr_spearman": 0.7357184616156525,
150
+ "eval_stsb_spearman": 0.8364591679967303,
151
+ "step": 2125
152
+ }
153
+ ],
154
+ "max_steps": 15626,
155
+ "num_train_epochs": 1,
156
+ "total_flos": 0,
157
+ "trial_name": null,
158
+ "trial_params": null
159
+ }