Hugging Face's logo

nlp04
/
sentiment_roberta_large_with_diary

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
YeRyeongLee commited on
Commit
0c0982c
•
1 Parent(s): 7f29cb6

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. train_results.txt +6 -0
  4. trainer_state.json +144 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6395634657499806,
4
+ "train_runtime": 1631.1404,
5
+ "train_samples": 48328,
6
+ "train_samples_per_second": 29.628,
7
+ "train_steps_per_second": 0.463
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6395634657499806,
4
+ "train_runtime": 1631.1404,
5
+ "train_samples": 48328,
6
+ "train_samples_per_second": 29.628,
7
+ "train_steps_per_second": 0.463
8
+ }
train_results.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch = 1.0
2
+ train_loss = 0.6395634657499806
3
+ train_runtime = 1631.1404
4
+ train_samples = 48328
5
+ train_samples_per_second = 29.628
6
+ train_steps_per_second = 0.463
trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9996689837802052,
5
+ "global_step": 755,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.13,
12
+ "learning_rate": 9.646539027982328e-06,
13
+ "loss": 1.6198,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "eval_accuracy": 0.48936170212765956,
19
+ "eval_auprc": 55.57425088347365,
20
+ "eval_loss": 1.3871960639953613,
21
+ "eval_micro f1 score": 48.93617021276596,
22
+ "eval_runtime": 2.5438,
23
+ "eval_samples_per_second": 92.382,
24
+ "eval_steps_per_second": 5.897,
25
+ "step": 100
26
+ },
27
+ {
28
+ "epoch": 0.26,
29
+ "learning_rate": 8.17378497790869e-06,
30
+ "loss": 0.6603,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.26,
35
+ "eval_accuracy": 0.6595744680851063,
36
+ "eval_auprc": 62.87589308944976,
37
+ "eval_loss": 0.9248737692832947,
38
+ "eval_micro f1 score": 65.95744680851064,
39
+ "eval_runtime": 2.5393,
40
+ "eval_samples_per_second": 92.545,
41
+ "eval_steps_per_second": 5.907,
42
+ "step": 200
43
+ },
44
+ {
45
+ "epoch": 0.4,
46
+ "learning_rate": 6.701030927835052e-06,
47
+ "loss": 0.5387,
48
+ "step": 300
49
+ },
50
+ {
51
+ "epoch": 0.4,
52
+ "eval_accuracy": 0.7319148936170212,
53
+ "eval_auprc": 71.1935721229021,
54
+ "eval_loss": 0.7262066602706909,
55
+ "eval_micro f1 score": 73.19148936170212,
56
+ "eval_runtime": 2.5398,
57
+ "eval_samples_per_second": 92.525,
58
+ "eval_steps_per_second": 5.906,
59
+ "step": 300
60
+ },
61
+ {
62
+ "epoch": 0.53,
63
+ "learning_rate": 5.228276877761414e-06,
64
+ "loss": 0.4801,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.53,
69
+ "eval_accuracy": 0.7404255319148936,
70
+ "eval_auprc": 68.860583531235,
71
+ "eval_loss": 0.6623471975326538,
72
+ "eval_micro f1 score": 74.04255319148936,
73
+ "eval_runtime": 2.5388,
74
+ "eval_samples_per_second": 92.563,
75
+ "eval_steps_per_second": 5.908,
76
+ "step": 400
77
+ },
78
+ {
79
+ "epoch": 0.66,
80
+ "learning_rate": 3.7555228276877766e-06,
81
+ "loss": 0.4597,
82
+ "step": 500
83
+ },
84
+ {
85
+ "epoch": 0.66,
86
+ "eval_accuracy": 0.7617021276595745,
87
+ "eval_auprc": 75.73457801993634,
88
+ "eval_loss": 0.6092124581336975,
89
+ "eval_micro f1 score": 76.17021276595744,
90
+ "eval_runtime": 2.5484,
91
+ "eval_samples_per_second": 92.215,
92
+ "eval_steps_per_second": 5.886,
93
+ "step": 500
94
+ },
95
+ {
96
+ "epoch": 0.79,
97
+ "learning_rate": 2.2827687776141384e-06,
98
+ "loss": 0.4217,
99
+ "step": 600
100
+ },
101
+ {
102
+ "epoch": 0.79,
103
+ "eval_accuracy": 0.7872340425531915,
104
+ "eval_auprc": 76.87089001906547,
105
+ "eval_loss": 0.5928928852081299,
106
+ "eval_micro f1 score": 78.72340425531915,
107
+ "eval_runtime": 2.5389,
108
+ "eval_samples_per_second": 92.559,
109
+ "eval_steps_per_second": 5.908,
110
+ "step": 600
111
+ },
112
+ {
113
+ "epoch": 0.93,
114
+ "learning_rate": 8.100147275405009e-07,
115
+ "loss": 0.4148,
116
+ "step": 700
117
+ },
118
+ {
119
+ "epoch": 0.93,
120
+ "eval_accuracy": 0.8,
121
+ "eval_auprc": 77.0281671357332,
122
+ "eval_loss": 0.5671084523200989,
123
+ "eval_micro f1 score": 80.00000000000001,
124
+ "eval_runtime": 2.5376,
125
+ "eval_samples_per_second": 92.609,
126
+ "eval_steps_per_second": 5.911,
127
+ "step": 700
128
+ },
129
+ {
130
+ "epoch": 1.0,
131
+ "step": 755,
132
+ "total_flos": 4.503229282615296e+16,
133
+ "train_loss": 0.6395634657499806,
134
+ "train_runtime": 1631.1404,
135
+ "train_samples_per_second": 29.628,
136
+ "train_steps_per_second": 0.463
137
+ }
138
+ ],
139
+ "max_steps": 755,
140
+ "num_train_epochs": 1,
141
+ "total_flos": 4.503229282615296e+16,
142
+ "trial_name": null,
143
+ "trial_params": null
144
+ }