Hugging Face's logo

anablasi
/
finqa_model

Question Answering
Transformers
PyTorch
roberta
Model card Files
xet
Community
1
anablasi commited on
Commit
6bfdbe0
路
1 Parent(s): c9228b9

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +132 -0
trainer_state.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.643835616438356,
5
+ "global_step": 9000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 1.9391171993911722e-05,
13
+ "loss": 1.0449,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 1.8782343987823442e-05,
19
+ "loss": 0.821,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 1.8173515981735163e-05,
25
+ "loss": 0.8326,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 1.756468797564688e-05,
31
+ "loss": 0.8143,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 1.69558599695586e-05,
37
+ "loss": 0.7836,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 1.634703196347032e-05,
43
+ "loss": 0.7796,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 1.573820395738204e-05,
49
+ "loss": 0.7676,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 1.5129375951293761e-05,
55
+ "loss": 0.7507,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.82,
60
+ "learning_rate": 1.4520547945205482e-05,
61
+ "loss": 0.7615,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.91,
66
+ "learning_rate": 1.39117199391172e-05,
67
+ "loss": 0.7582,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.0,
72
+ "eval_loss": 0.8703365921974182,
73
+ "eval_runtime": 270.4723,
74
+ "eval_samples_per_second": 39.08,
75
+ "eval_steps_per_second": 2.444,
76
+ "step": 5475
77
+ },
78
+ {
79
+ "epoch": 1.0,
80
+ "learning_rate": 1.330289193302892e-05,
81
+ "loss": 0.7364,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 1.1,
86
+ "learning_rate": 1.2694063926940641e-05,
87
+ "loss": 0.5517,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.19,
92
+ "learning_rate": 1.2085235920852361e-05,
93
+ "loss": 0.5915,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 1.28,
98
+ "learning_rate": 1.147640791476408e-05,
99
+ "loss": 0.5903,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 1.37,
104
+ "learning_rate": 1.08675799086758e-05,
105
+ "loss": 0.5782,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 1.46,
110
+ "learning_rate": 1.025875190258752e-05,
111
+ "loss": 0.5823,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 1.55,
116
+ "learning_rate": 9.64992389649924e-06,
117
+ "loss": 0.5812,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 1.64,
122
+ "learning_rate": 9.04109589041096e-06,
123
+ "loss": 0.5604,
124
+ "step": 9000
125
+ }
126
+ ],
127
+ "max_steps": 16425,
128
+ "num_train_epochs": 3,
129
+ "total_flos": 2.821985375492045e+16,
130
+ "trial_name": null,
131
+ "trial_params": null
132
+ }