Hugging Face's logo

DunnBC22
/
squeezebert-uncased-News_About_Gold

Text Classification
Transformers
PyTorch
TensorBoard
English
squeezebert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
DunnBC22 commited on
Commit
83db6c2
•
1 Parent(s): 6000862

All Dunn!!!

Browse files
Files changed (3) hide show
  1. all_results.json +7 -0
  2. train_results.json +7 -0
  3. trainer_state.json +151 -0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.42408741363009117,
4
+ "train_runtime": 3111.9997,
5
+ "train_samples_per_second": 13.586,
6
+ "train_steps_per_second": 0.214
7
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.42408741363009117,
4
+ "train_runtime": 3111.9997,
5
+ "train_samples_per_second": 13.586,
6
+ "train_steps_per_second": 0.214
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 665,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.9969924812030075e-05,
13
+ "loss": 1.4231,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 1.6000000000000003e-05,
19
+ "loss": 0.8756,
20
+ "step": 133
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_Macro F1": 0.6559577437042121,
25
+ "eval_Macro Precision": 0.6414383471396911,
26
+ "eval_Macro Recall": 0.6726779588705305,
27
+ "eval_Micro F1": 0.869914853358562,
28
+ "eval_Micro Precision": 0.869914853358562,
29
+ "eval_Micro Recall": 0.869914853358562,
30
+ "eval_Weighted F1": 0.8557169411489111,
31
+ "eval_Weighted Precision": 0.8436710960059746,
32
+ "eval_Weighted Recall": 0.869914853358562,
33
+ "eval_accuracy": 0.869914853358562,
34
+ "eval_loss": 0.452942818403244,
35
+ "eval_runtime": 45.2965,
36
+ "eval_samples_per_second": 46.67,
37
+ "eval_steps_per_second": 0.751,
38
+ "step": 133
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "learning_rate": 1.2e-05,
43
+ "loss": 0.4097,
44
+ "step": 266
45
+ },
46
+ {
47
+ "epoch": 2.0,
48
+ "eval_Macro F1": 0.7826498896982309,
49
+ "eval_Macro Precision": 0.8743465956410477,
50
+ "eval_Macro Recall": 0.763545504951241,
51
+ "eval_Micro F1": 0.902554399243141,
52
+ "eval_Micro Precision": 0.902554399243141,
53
+ "eval_Micro Recall": 0.902554399243141,
54
+ "eval_Weighted F1": 0.8981990872046596,
55
+ "eval_Weighted Precision": 0.9058995948483624,
56
+ "eval_Weighted Recall": 0.902554399243141,
57
+ "eval_accuracy": 0.902554399243141,
58
+ "eval_loss": 0.31955790519714355,
59
+ "eval_runtime": 46.2695,
60
+ "eval_samples_per_second": 45.689,
61
+ "eval_steps_per_second": 0.735,
62
+ "step": 266
63
+ },
64
+ {
65
+ "epoch": 3.0,
66
+ "learning_rate": 8.000000000000001e-06,
67
+ "loss": 0.3147,
68
+ "step": 399
69
+ },
70
+ {
71
+ "epoch": 3.0,
72
+ "eval_Macro F1": 0.8469888698710597,
73
+ "eval_Macro Precision": 0.8751072643902021,
74
+ "eval_Macro Recall": 0.8318917244382616,
75
+ "eval_Micro F1": 0.9115421002838221,
76
+ "eval_Micro Precision": 0.9115421002838221,
77
+ "eval_Micro Recall": 0.9115421002838221,
78
+ "eval_Weighted F1": 0.9110995447372147,
79
+ "eval_Weighted Precision": 0.9138453932389957,
80
+ "eval_Weighted Recall": 0.9115421002838221,
81
+ "eval_accuracy": 0.9115421002838221,
82
+ "eval_loss": 0.2824004292488098,
83
+ "eval_runtime": 44.6739,
84
+ "eval_samples_per_second": 47.321,
85
+ "eval_steps_per_second": 0.761,
86
+ "step": 399
87
+ },
88
+ {
89
+ "epoch": 4.0,
90
+ "learning_rate": 4.000000000000001e-06,
91
+ "loss": 0.2685,
92
+ "step": 532
93
+ },
94
+ {
95
+ "epoch": 4.0,
96
+ "eval_Macro F1": 0.8681032986279441,
97
+ "eval_Macro Precision": 0.8797074213841205,
98
+ "eval_Macro Recall": 0.8601906345542645,
99
+ "eval_Micro F1": 0.9186376537369915,
100
+ "eval_Micro Precision": 0.9186376537369915,
101
+ "eval_Micro Recall": 0.9186376537369915,
102
+ "eval_Weighted F1": 0.918722301523608,
103
+ "eval_Weighted Precision": 0.9202617437649651,
104
+ "eval_Weighted Recall": 0.9186376537369915,
105
+ "eval_accuracy": 0.9186376537369915,
106
+ "eval_loss": 0.26486265659332275,
107
+ "eval_runtime": 44.116,
108
+ "eval_samples_per_second": 47.919,
109
+ "eval_steps_per_second": 0.771,
110
+ "step": 532
111
+ },
112
+ {
113
+ "epoch": 5.0,
114
+ "learning_rate": 0.0,
115
+ "loss": 0.2479,
116
+ "step": 665
117
+ },
118
+ {
119
+ "epoch": 5.0,
120
+ "eval_Macro F1": 0.8749369503373983,
121
+ "eval_Macro Precision": 0.8821869512033577,
122
+ "eval_Macro Recall": 0.8684302125750863,
123
+ "eval_Micro F1": 0.9167455061494797,
124
+ "eval_Micro Precision": 0.9167455061494797,
125
+ "eval_Micro Recall": 0.9167455061494797,
126
+ "eval_Weighted F1": 0.9165697427628363,
127
+ "eval_Weighted Precision": 0.9168439952197603,
128
+ "eval_Weighted Recall": 0.9167455061494797,
129
+ "eval_accuracy": 0.9167455061494797,
130
+ "eval_loss": 0.26428648829460144,
131
+ "eval_runtime": 44.094,
132
+ "eval_samples_per_second": 47.943,
133
+ "eval_steps_per_second": 0.771,
134
+ "step": 665
135
+ },
136
+ {
137
+ "epoch": 5.0,
138
+ "step": 665,
139
+ "total_flos": 283497743040960.0,
140
+ "train_loss": 0.42408741363009117,
141
+ "train_runtime": 3111.9997,
142
+ "train_samples_per_second": 13.586,
143
+ "train_steps_per_second": 0.214
144
+ }
145
+ ],
146
+ "max_steps": 665,
147
+ "num_train_epochs": 5,
148
+ "total_flos": 283497743040960.0,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }