Hugging Face's logo

NDugar
/
v2xl-again-mnli

Zero-Shot Classification
Transformers
PyTorch
English
deberta-v2
text-classification
deberta-v1
deberta-mnli
Inference Endpoints
Model card Files Community
NDugar commited on
Commit
b82bf83
•
1 Parent(s): 7b889c6

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +142 -0
trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9068051101949407,
3
+ "best_model_checkpoint": "./resultsv3l32/output/checkpoint-294528",
4
+ "epoch": 4.0,
5
+ "global_step": 392704,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.25,
12
+ "learning_rate": 4.681694100391135e-06,
13
+ "loss": 0.5874,
14
+ "step": 25000
15
+ },
16
+ {
17
+ "epoch": 0.51,
18
+ "learning_rate": 4.363388200782269e-06,
19
+ "loss": 0.5086,
20
+ "step": 50000
21
+ },
22
+ {
23
+ "epoch": 0.76,
24
+ "learning_rate": 4.045082301173403e-06,
25
+ "loss": 0.48,
26
+ "step": 75000
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_accuracy": 0.9011044943248333,
31
+ "eval_loss": 0.47157734632492065,
32
+ "eval_runtime": 213.0954,
33
+ "eval_samples_per_second": 92.198,
34
+ "eval_steps_per_second": 23.051,
35
+ "step": 98176
36
+ },
37
+ {
38
+ "epoch": 1.02,
39
+ "learning_rate": 3.7267764015645376e-06,
40
+ "loss": 0.4559,
41
+ "step": 100000
42
+ },
43
+ {
44
+ "epoch": 1.27,
45
+ "learning_rate": 3.408470501955672e-06,
46
+ "loss": 0.3309,
47
+ "step": 125000
48
+ },
49
+ {
50
+ "epoch": 1.53,
51
+ "learning_rate": 3.0901646023468064e-06,
52
+ "loss": 0.3398,
53
+ "step": 150000
54
+ },
55
+ {
56
+ "epoch": 1.78,
57
+ "learning_rate": 2.77185870273794e-06,
58
+ "loss": 0.3382,
59
+ "step": 175000
60
+ },
61
+ {
62
+ "epoch": 2.0,
63
+ "eval_accuracy": 0.9044128874637349,
64
+ "eval_loss": 0.5638315081596375,
65
+ "eval_runtime": 212.5015,
66
+ "eval_samples_per_second": 92.456,
67
+ "eval_steps_per_second": 23.115,
68
+ "step": 196352
69
+ },
70
+ {
71
+ "epoch": 2.04,
72
+ "learning_rate": 2.4535528031290744e-06,
73
+ "loss": 0.3082,
74
+ "step": 200000
75
+ },
76
+ {
77
+ "epoch": 2.29,
78
+ "learning_rate": 2.135246903520209e-06,
79
+ "loss": 0.1952,
80
+ "step": 225000
81
+ },
82
+ {
83
+ "epoch": 2.55,
84
+ "learning_rate": 1.816941003911343e-06,
85
+ "loss": 0.2029,
86
+ "step": 250000
87
+ },
88
+ {
89
+ "epoch": 2.8,
90
+ "learning_rate": 1.4986351043024774e-06,
91
+ "loss": 0.2027,
92
+ "step": 275000
93
+ },
94
+ {
95
+ "epoch": 3.0,
96
+ "eval_accuracy": 0.9068051101949407,
97
+ "eval_loss": 0.6681745052337646,
98
+ "eval_runtime": 212.8042,
99
+ "eval_samples_per_second": 92.324,
100
+ "eval_steps_per_second": 23.082,
101
+ "step": 294528
102
+ },
103
+ {
104
+ "epoch": 3.06,
105
+ "learning_rate": 1.1803292046936116e-06,
106
+ "loss": 0.1771,
107
+ "step": 300000
108
+ },
109
+ {
110
+ "epoch": 3.31,
111
+ "learning_rate": 8.620233050847459e-07,
112
+ "loss": 0.1124,
113
+ "step": 325000
114
+ },
115
+ {
116
+ "epoch": 3.57,
117
+ "learning_rate": 5.437174054758801e-07,
118
+ "loss": 0.1095,
119
+ "step": 350000
120
+ },
121
+ {
122
+ "epoch": 3.82,
123
+ "learning_rate": 2.2541150586701436e-07,
124
+ "loss": 0.1038,
125
+ "step": 375000
126
+ },
127
+ {
128
+ "epoch": 4.0,
129
+ "eval_accuracy": 0.9064997200590421,
130
+ "eval_loss": 0.7638580799102783,
131
+ "eval_runtime": 211.2725,
132
+ "eval_samples_per_second": 92.994,
133
+ "eval_steps_per_second": 23.25,
134
+ "step": 392704
135
+ }
136
+ ],
137
+ "max_steps": 392704,
138
+ "num_train_epochs": 4,
139
+ "total_flos": 3.755067886948521e+17,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }