Hugging Face's logo

mschwab
/
va_bert_classification

Text Classification
Transformers
PyTorch
English
bert
sentence classification
vossian antonomasia
Inference Endpoints
Model card Files Community
mschwab commited on
Commit
e0bbdd1
•
1 Parent(s): 6f50e80

upload trainer state

Browse files
Files changed (1) hide show
  1. trainer_state.json +137 -0
trainer_state.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 9656,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.7410936205468105e-05,
13
+ "loss": 0.0291,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.21,
18
+ "learning_rate": 4.482187241093621e-05,
19
+ "loss": 0.0114,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.31,
24
+ "learning_rate": 4.2232808616404316e-05,
25
+ "loss": 0.0126,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.41,
30
+ "learning_rate": 3.964374482187241e-05,
31
+ "loss": 0.0514,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.52,
36
+ "learning_rate": 3.705468102734051e-05,
37
+ "loss": 0.0159,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.62,
42
+ "learning_rate": 3.4465617232808616e-05,
43
+ "loss": 0.0145,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.72,
48
+ "learning_rate": 3.187655343827672e-05,
49
+ "loss": 0.0107,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.83,
54
+ "learning_rate": 2.9287489643744827e-05,
55
+ "loss": 0.0085,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.93,
60
+ "learning_rate": 2.6698425849212926e-05,
61
+ "loss": 0.0067,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.04,
66
+ "learning_rate": 2.4109362054681028e-05,
67
+ "loss": 0.0068,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.14,
72
+ "learning_rate": 2.152029826014913e-05,
73
+ "loss": 0.0041,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.24,
78
+ "learning_rate": 1.8931234465617236e-05,
79
+ "loss": 0.0051,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.35,
84
+ "learning_rate": 1.6342170671085334e-05,
85
+ "loss": 0.0054,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.45,
90
+ "learning_rate": 1.375310687655344e-05,
91
+ "loss": 0.0038,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.55,
96
+ "learning_rate": 1.1164043082021542e-05,
97
+ "loss": 0.0068,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.66,
102
+ "learning_rate": 8.574979287489644e-06,
103
+ "loss": 0.0028,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.76,
108
+ "learning_rate": 5.9859154929577465e-06,
109
+ "loss": 0.0036,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.86,
114
+ "learning_rate": 3.396851698425849e-06,
115
+ "loss": 0.001,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.97,
120
+ "learning_rate": 8.07787903893952e-07,
121
+ "loss": 0.005,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 2.0,
126
+ "step": 9656,
127
+ "total_flos": 2.570302678695936e+16,
128
+ "train_runtime": 2777.1249,
129
+ "train_samples_per_second": 3.477
130
+ }
131
+ ],
132
+ "max_steps": 9656,
133
+ "num_train_epochs": 2,
134
+ "total_flos": 2.570302678695936e+16,
135
+ "trial_name": null,
136
+ "trial_params": null
137
+ }