Hugging Face's logo

DunnBC22
/
mega-base-wikitext-News_About_Gold

Text Classification
Transformers
PyTorch
TensorBoard
English
mega
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
DunnBC22 commited on
Commit
1cf9fa1
•
1 Parent(s): 7d73d6c

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": 1.1051450449721258,
4
+ "train_runtime": 307.9,
5
+ "train_samples_per_second": 137.317,
6
+ "train_steps_per_second": 2.16
7
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.1051450449721258,
4
+ "train_runtime": 307.9,
5
+ "train_samples_per_second": 137.317,
6
+ "train_steps_per_second": 2.16
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": 1.355,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 1.6000000000000003e-05,
19
+ "loss": 1.2255,
20
+ "step": 133
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_Macro F1": 0.14874720660368068,
25
+ "eval_Macro Precision": 0.22846464167062175,
26
+ "eval_Macro Recall": 0.2506841990271725,
27
+ "eval_Micro F1": 0.413434247871334,
28
+ "eval_Micro Precision": 0.413434247871334,
29
+ "eval_Micro Recall": 0.413434247871334,
30
+ "eval_Weighted F1": 0.24374830457829116,
31
+ "eval_Weighted Precision": 0.2652376477201957,
32
+ "eval_Weighted Recall": 0.413434247871334,
33
+ "eval_accuracy": 0.413434247871334,
34
+ "eval_loss": 1.1365216970443726,
35
+ "eval_runtime": 4.9797,
36
+ "eval_samples_per_second": 424.526,
37
+ "eval_steps_per_second": 6.828,
38
+ "step": 133
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "learning_rate": 1.2e-05,
43
+ "loss": 1.1337,
44
+ "step": 266
45
+ },
46
+ {
47
+ "epoch": 2.0,
48
+ "eval_Macro F1": 0.2539122945315465,
49
+ "eval_Macro Precision": 0.27045292732351167,
50
+ "eval_Macro Recall": 0.31610570012534067,
51
+ "eval_Micro F1": 0.4531693472090823,
52
+ "eval_Micro Precision": 0.4531693472090823,
53
+ "eval_Micro Recall": 0.4531693472090823,
54
+ "eval_Weighted F1": 0.3257022348814709,
55
+ "eval_Weighted Precision": 0.3014929354313833,
56
+ "eval_Weighted Recall": 0.4531693472090823,
57
+ "eval_accuracy": 0.4531693472090823,
58
+ "eval_loss": 1.0851175785064697,
59
+ "eval_runtime": 5.0249,
60
+ "eval_samples_per_second": 420.706,
61
+ "eval_steps_per_second": 6.766,
62
+ "step": 266
63
+ },
64
+ {
65
+ "epoch": 3.0,
66
+ "learning_rate": 8.000000000000001e-06,
67
+ "loss": 1.0847,
68
+ "step": 399
69
+ },
70
+ {
71
+ "epoch": 3.0,
72
+ "eval_Macro F1": 0.29146318011221783,
73
+ "eval_Macro Precision": 0.4941561809223257,
74
+ "eval_Macro Recall": 0.3519927370002771,
75
+ "eval_Micro F1": 0.47587511825922424,
76
+ "eval_Micro Precision": 0.47587511825922424,
77
+ "eval_Micro Recall": 0.47587511825922424,
78
+ "eval_Weighted F1": 0.35909819845877977,
79
+ "eval_Weighted Precision": 0.6351629101542547,
80
+ "eval_Weighted Recall": 0.47587511825922424,
81
+ "eval_accuracy": 0.47587511825922424,
82
+ "eval_loss": 1.0384365320205688,
83
+ "eval_runtime": 5.0385,
84
+ "eval_samples_per_second": 419.567,
85
+ "eval_steps_per_second": 6.748,
86
+ "step": 399
87
+ },
88
+ {
89
+ "epoch": 4.0,
90
+ "learning_rate": 4.000000000000001e-06,
91
+ "loss": 1.05,
92
+ "step": 532
93
+ },
94
+ {
95
+ "epoch": 4.0,
96
+ "eval_Macro F1": 0.3205588999330816,
97
+ "eval_Macro Precision": 0.4596183152865385,
98
+ "eval_Macro Recall": 0.3782911164189696,
99
+ "eval_Micro F1": 0.49621570482497634,
100
+ "eval_Micro Precision": 0.49621570482497634,
101
+ "eval_Micro Recall": 0.49621570482497634,
102
+ "eval_Weighted F1": 0.3917006514214786,
103
+ "eval_Weighted Precision": 0.584561005399218,
104
+ "eval_Weighted Recall": 0.49621570482497634,
105
+ "eval_accuracy": 0.49621570482497634,
106
+ "eval_loss": 1.0111591815948486,
107
+ "eval_runtime": 5.0498,
108
+ "eval_samples_per_second": 418.628,
109
+ "eval_steps_per_second": 6.733,
110
+ "step": 532
111
+ },
112
+ {
113
+ "epoch": 5.0,
114
+ "learning_rate": 0.0,
115
+ "loss": 1.0309,
116
+ "step": 665
117
+ },
118
+ {
119
+ "epoch": 5.0,
120
+ "eval_Macro F1": 0.3282454852143253,
121
+ "eval_Macro Precision": 0.4547967339236757,
122
+ "eval_Macro Recall": 0.3834764306870363,
123
+ "eval_Micro F1": 0.5014191106906338,
124
+ "eval_Micro Precision": 0.5014191106906338,
125
+ "eval_Micro Recall": 0.5014191106906338,
126
+ "eval_Weighted F1": 0.4022689273065864,
127
+ "eval_Weighted Precision": 0.5783027384112047,
128
+ "eval_Weighted Recall": 0.5014191106906338,
129
+ "eval_accuracy": 0.5014191106906338,
130
+ "eval_loss": 1.003102421760559,
131
+ "eval_runtime": 5.016,
132
+ "eval_samples_per_second": 421.451,
133
+ "eval_steps_per_second": 6.778,
134
+ "step": 665
135
+ },
136
+ {
137
+ "epoch": 5.0,
138
+ "step": 665,
139
+ "total_flos": 9687083333760.0,
140
+ "train_loss": 1.1051450449721258,
141
+ "train_runtime": 307.9,
142
+ "train_samples_per_second": 137.317,
143
+ "train_steps_per_second": 2.16
144
+ }
145
+ ],
146
+ "max_steps": 665,
147
+ "num_train_epochs": 5,
148
+ "total_flos": 9687083333760.0,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }