Hugging Face's logo

gcyzsl
/
sup-VisualCSE-bert-base-uncased

Feature Extraction
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
1
gcyzsl commited on
Commit
2c58b5c
•
1 Parent(s): 4072764

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +105 -0
trainer_state.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8642076134243076,
3
+ "best_model_checkpoint": "result/my-sup-simcse-bert-base-uncased/SupCon-22-0.5-1e-7-0.05-0.00",
4
+ "epoch": 4.996296296296296,
5
+ "global_step": 1345,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.46,
12
+ "eval_avg_sts": 0.830579264692183,
13
+ "eval_sickr_spearman": 0.8086463403909065,
14
+ "eval_stsb_spearman": 0.8525121889934594,
15
+ "step": 125
16
+ },
17
+ {
18
+ "epoch": 0.93,
19
+ "eval_avg_sts": 0.8322678052622576,
20
+ "eval_sickr_spearman": 0.8059119778171362,
21
+ "eval_stsb_spearman": 0.858623632707379,
22
+ "step": 250
23
+ },
24
+ {
25
+ "epoch": 1.39,
26
+ "eval_avg_sts": 0.8321564310903964,
27
+ "eval_sickr_spearman": 0.8062460341276383,
28
+ "eval_stsb_spearman": 0.8580668280531545,
29
+ "step": 375
30
+ },
31
+ {
32
+ "epoch": 1.86,
33
+ "learning_rate": 3.148148148148148e-05,
34
+ "loss": 0.6799,
35
+ "step": 500
36
+ },
37
+ {
38
+ "epoch": 1.86,
39
+ "eval_avg_sts": 0.8379634197959601,
40
+ "eval_sickr_spearman": 0.8117192261676126,
41
+ "eval_stsb_spearman": 0.8642076134243076,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 2.32,
46
+ "eval_avg_sts": 0.8300517473847898,
47
+ "eval_sickr_spearman": 0.800890710410593,
48
+ "eval_stsb_spearman": 0.8592127843589866,
49
+ "step": 625
50
+ },
51
+ {
52
+ "epoch": 2.79,
53
+ "eval_avg_sts": 0.8331867449128545,
54
+ "eval_sickr_spearman": 0.8066284097261871,
55
+ "eval_stsb_spearman": 0.8597450800995219,
56
+ "step": 750
57
+ },
58
+ {
59
+ "epoch": 3.25,
60
+ "eval_avg_sts": 0.8318085085379562,
61
+ "eval_sickr_spearman": 0.8031442336278662,
62
+ "eval_stsb_spearman": 0.8604727834480461,
63
+ "step": 875
64
+ },
65
+ {
66
+ "epoch": 3.71,
67
+ "learning_rate": 1.2962962962962962e-05,
68
+ "loss": 0.4197,
69
+ "step": 1000
70
+ },
71
+ {
72
+ "epoch": 3.71,
73
+ "eval_avg_sts": 0.8353804358596084,
74
+ "eval_sickr_spearman": 0.8108888644859505,
75
+ "eval_stsb_spearman": 0.8598720072332664,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 4.18,
80
+ "eval_avg_sts": 0.8325858444728933,
81
+ "eval_sickr_spearman": 0.8039816078503385,
82
+ "eval_stsb_spearman": 0.8611900810954483,
83
+ "step": 1125
84
+ },
85
+ {
86
+ "epoch": 4.64,
87
+ "eval_avg_sts": 0.833323493417157,
88
+ "eval_sickr_spearman": 0.8065565551984356,
89
+ "eval_stsb_spearman": 0.8600904316358784,
90
+ "step": 1250
91
+ },
92
+ {
93
+ "epoch": 5.0,
94
+ "step": 1345,
95
+ "total_flos": 87911398260080640,
96
+ "train_runtime": 1044.4281,
97
+ "train_samples_per_second": 1.293
98
+ }
99
+ ],
100
+ "max_steps": 1350,
101
+ "num_train_epochs": 5,
102
+ "total_flos": 87911398260080640,
103
+ "trial_name": null,
104
+ "trial_params": null
105
+ }