Hugging Face's logo

anablasi
/
model_10k_qa

Question Answering
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
1
anablasi commited on
Commit
6f03798
•
1 Parent(s): 18189c3

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +150 -0
trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9178082191780823,
5
+ "global_step": 10500,
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": 1.9086757990867582e-05,
13
+ "loss": 1.0336,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 1.8173515981735163e-05,
19
+ "loss": 0.8372,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 1.726027397260274e-05,
25
+ "loss": 0.8389,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 1.634703196347032e-05,
31
+ "loss": 0.813,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 1.54337899543379e-05,
37
+ "loss": 0.7993,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 1.4520547945205482e-05,
43
+ "loss": 0.783,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 1.360730593607306e-05,
49
+ "loss": 0.7708,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 1.2694063926940641e-05,
55
+ "loss": 0.7512,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.82,
60
+ "learning_rate": 1.178082191780822e-05,
61
+ "loss": 0.7617,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.91,
66
+ "learning_rate": 1.08675799086758e-05,
67
+ "loss": 0.7586,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.0,
72
+ "eval_loss": 0.8747021555900574,
73
+ "eval_runtime": 251.8476,
74
+ "eval_samples_per_second": 41.97,
75
+ "eval_steps_per_second": 2.625,
76
+ "step": 5475
77
+ },
78
+ {
79
+ "epoch": 1.0,
80
+ "learning_rate": 9.95433789954338e-06,
81
+ "loss": 0.737,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 1.1,
86
+ "learning_rate": 9.04109589041096e-06,
87
+ "loss": 0.5544,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.19,
92
+ "learning_rate": 8.127853881278539e-06,
93
+ "loss": 0.5876,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 1.28,
98
+ "learning_rate": 7.214611872146119e-06,
99
+ "loss": 0.5841,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 1.37,
104
+ "learning_rate": 6.301369863013699e-06,
105
+ "loss": 0.5772,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 1.46,
110
+ "learning_rate": 5.388127853881279e-06,
111
+ "loss": 0.5743,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 1.55,
116
+ "learning_rate": 4.4748858447488585e-06,
117
+ "loss": 0.5722,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 1.64,
122
+ "learning_rate": 3.5616438356164386e-06,
123
+ "loss": 0.5506,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 1.74,
128
+ "learning_rate": 2.6484018264840183e-06,
129
+ "loss": 0.5588,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 1.83,
134
+ "learning_rate": 1.7351598173515982e-06,
135
+ "loss": 0.5428,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 1.92,
140
+ "learning_rate": 8.219178082191781e-07,
141
+ "loss": 0.563,
142
+ "step": 10500
143
+ }
144
+ ],
145
+ "max_steps": 10950,
146
+ "num_train_epochs": 2,
147
+ "total_flos": 3.292319537616845e+16,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }