Hugging Face's logo

tmnam20
/
bert-base-multilingual-cased-cola-10

Text Classification
Transformers
Safetensors
English
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
tmnam20 commited on
Commit
035e085
•
1 Parent(s): 84c73f8

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +133 -0
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19,
13
+ "learning_rate": 1.8756218905472638e-05,
14
+ "loss": 0.6031,
15
+ "step": 50
16
+ },
17
+ {
18
+ "epoch": 0.37,
19
+ "learning_rate": 1.7512437810945274e-05,
20
+ "loss": 0.6069,
21
+ "step": 100
22
+ },
23
+ {
24
+ "epoch": 0.56,
25
+ "learning_rate": 1.626865671641791e-05,
26
+ "loss": 0.6051,
27
+ "step": 150
28
+ },
29
+ {
30
+ "epoch": 0.75,
31
+ "learning_rate": 1.5024875621890549e-05,
32
+ "loss": 0.605,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 0.93,
37
+ "learning_rate": 1.3781094527363185e-05,
38
+ "loss": 0.6197,
39
+ "step": 250
40
+ },
41
+ {
42
+ "epoch": 1.12,
43
+ "learning_rate": 1.2537313432835823e-05,
44
+ "loss": 0.6119,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 1.31,
49
+ "learning_rate": 1.129353233830846e-05,
50
+ "loss": 0.5909,
51
+ "step": 350
52
+ },
53
+ {
54
+ "epoch": 1.49,
55
+ "learning_rate": 1.0049751243781096e-05,
56
+ "loss": 0.5973,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 1.68,
61
+ "learning_rate": 8.805970149253732e-06,
62
+ "loss": 0.6011,
63
+ "step": 450
64
+ },
65
+ {
66
+ "epoch": 1.87,
67
+ "learning_rate": 7.5621890547263685e-06,
68
+ "loss": 0.5762,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 1.87,
73
+ "eval_loss": 0.6180756092071533,
74
+ "eval_matthews_correlation": 0.03718764224408827,
75
+ "eval_runtime": 0.9687,
76
+ "eval_samples_per_second": 1076.744,
77
+ "eval_steps_per_second": 68.135,
78
+ "step": 500
79
+ },
80
+ {
81
+ "epoch": 2.05,
82
+ "learning_rate": 6.318407960199006e-06,
83
+ "loss": 0.5628,
84
+ "step": 550
85
+ },
86
+ {
87
+ "epoch": 2.24,
88
+ "learning_rate": 5.074626865671642e-06,
89
+ "loss": 0.5356,
90
+ "step": 600
91
+ },
92
+ {
93
+ "epoch": 2.43,
94
+ "learning_rate": 3.8308457711442784e-06,
95
+ "loss": 0.546,
96
+ "step": 650
97
+ },
98
+ {
99
+ "epoch": 2.61,
100
+ "learning_rate": 2.5870646766169156e-06,
101
+ "loss": 0.5495,
102
+ "step": 700
103
+ },
104
+ {
105
+ "epoch": 2.8,
106
+ "learning_rate": 1.3432835820895524e-06,
107
+ "loss": 0.5208,
108
+ "step": 750
109
+ },
110
+ {
111
+ "epoch": 2.99,
112
+ "learning_rate": 9.950248756218906e-08,
113
+ "loss": 0.5165,
114
+ "step": 800
115
+ },
116
+ {
117
+ "epoch": 3.0,
118
+ "step": 804,
119
+ "total_flos": 389906945159640.0,
120
+ "train_loss": 0.5781698523469232,
121
+ "train_runtime": 80.7344,
122
+ "train_samples_per_second": 317.746,
123
+ "train_steps_per_second": 9.959
124
+ }
125
+ ],
126
+ "logging_steps": 50,
127
+ "max_steps": 804,
128
+ "num_train_epochs": 3,
129
+ "save_steps": 500,
130
+ "total_flos": 389906945159640.0,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }