Hugging Face's logo

visolex
/
bilstm-spam-multiclass

Text Classification
Safetensors
roberta
vietnamese
spam-detection
e-commerce
Eval Results (legacy)
Model card Files
xet
 Community
AnnyNguyen commited on
Commit
496bc06
·
verified ·
1 Parent(s): cd99526

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +176 -0
trainer_state.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3122,
3
+ "best_metric": 0.26706157640660244,
4
+ "best_model_checkpoint": "outputs/bilstm-spam-multiclass/checkpoint-3122",
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3122,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 0.797143280506134,
15
+ "learning_rate": 0.0009997543852189499,
16
+ "loss": 0.7942,
17
+ "step": 446
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7290485192186515,
22
+ "eval_f1": 0.21082361516034986,
23
+ "eval_loss": 0.8068332076072693,
24
+ "eval_precision": 0.1822621298046629,
25
+ "eval_recall": 0.25,
26
+ "eval_runtime": 6.2702,
27
+ "eval_samples_per_second": 253.101,
28
+ "eval_steps_per_second": 7.974,
29
+ "step": 446
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.6989365816116333,
34
+ "learning_rate": 0.0009990155744361903,
35
+ "loss": 0.7488,
36
+ "step": 892
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7290485192186515,
41
+ "eval_f1": 0.21082361516034986,
42
+ "eval_loss": 0.7541048526763916,
43
+ "eval_precision": 0.1822621298046629,
44
+ "eval_recall": 0.25,
45
+ "eval_runtime": 6.266,
46
+ "eval_samples_per_second": 253.271,
47
+ "eval_steps_per_second": 7.98,
48
+ "step": 892
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "grad_norm": 0.9377701878547668,
53
+ "learning_rate": 0.0009977842955283425,
54
+ "loss": 0.7286,
55
+ "step": 1338
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_accuracy": 0.7290485192186515,
60
+ "eval_f1": 0.21082361516034986,
61
+ "eval_loss": 0.7448248863220215,
62
+ "eval_precision": 0.1822621298046629,
63
+ "eval_recall": 0.25,
64
+ "eval_runtime": 6.2601,
65
+ "eval_samples_per_second": 253.511,
66
+ "eval_steps_per_second": 7.987,
67
+ "step": 1338
68
+ },
69
+ {
70
+ "epoch": 4.0,
71
+ "grad_norm": 1.436852216720581,
72
+ "learning_rate": 0.0009960617636190344,
73
+ "loss": 0.7228,
74
+ "step": 1784
75
+ },
76
+ {
77
+ "epoch": 4.0,
78
+ "eval_accuracy": 0.7296786389413988,
79
+ "eval_f1": 0.23500136448309822,
80
+ "eval_loss": 0.7346429824829102,
81
+ "eval_precision": 0.2942928298170524,
82
+ "eval_recall": 0.2605128413143665,
83
+ "eval_runtime": 6.2563,
84
+ "eval_samples_per_second": 253.663,
85
+ "eval_steps_per_second": 7.992,
86
+ "step": 1784
87
+ },
88
+ {
89
+ "epoch": 5.0,
90
+ "grad_norm": 1.0002644062042236,
91
+ "learning_rate": 0.0009938496786392973,
92
+ "loss": 0.7174,
93
+ "step": 2230
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "eval_accuracy": 0.7227473219911783,
98
+ "eval_f1": 0.2605779960514537,
99
+ "eval_loss": 0.7398474812507629,
100
+ "eval_precision": 0.2887123745819398,
101
+ "eval_recall": 0.27392437805977743,
102
+ "eval_runtime": 8.2774,
103
+ "eval_samples_per_second": 191.726,
104
+ "eval_steps_per_second": 6.041,
105
+ "step": 2230
106
+ },
107
+ {
108
+ "epoch": 6.0,
109
+ "grad_norm": 0.7430670857429504,
110
+ "learning_rate": 0.0009911502236499372,
111
+ "loss": 0.7166,
112
+ "step": 2676
113
+ },
114
+ {
115
+ "epoch": 6.0,
116
+ "eval_accuracy": 0.7315689981096408,
117
+ "eval_f1": 0.22160087719298247,
118
+ "eval_loss": 0.7539165616035461,
119
+ "eval_precision": 0.37036890436985437,
120
+ "eval_recall": 0.2549830103373283,
121
+ "eval_runtime": 8.322,
122
+ "eval_samples_per_second": 190.699,
123
+ "eval_steps_per_second": 6.008,
124
+ "step": 2676
125
+ },
126
+ {
127
+ "epoch": 7.0,
128
+ "grad_norm": 0.7684730887413025,
129
+ "learning_rate": 0.0009879660626871199,
130
+ "loss": 0.7173,
131
+ "step": 3122
132
+ },
133
+ {
134
+ "epoch": 7.0,
135
+ "eval_accuracy": 0.7334593572778828,
136
+ "eval_f1": 0.26706157640660244,
137
+ "eval_loss": 0.737380862236023,
138
+ "eval_precision": 0.3129218010274318,
139
+ "eval_recall": 0.2789705730929923,
140
+ "eval_runtime": 8.4068,
141
+ "eval_samples_per_second": 188.777,
142
+ "eval_steps_per_second": 5.948,
143
+ "step": 3122
144
+ }
145
+ ],
146
+ "logging_steps": 446,
147
+ "max_steps": 44600,
148
+ "num_input_tokens_seen": 0,
149
+ "num_train_epochs": 100,
150
+ "save_steps": 500,
151
+ "stateful_callbacks": {
152
+ "EarlyStoppingCallback": {
153
+ "args": {
154
+ "early_stopping_patience": 5,
155
+ "early_stopping_threshold": 0.0
156
+ },
157
+ "attributes": {
158
+ "early_stopping_patience_counter": 0
159
+ }
160
+ },
161
+ "TrainerControl": {
162
+ "args": {
163
+ "should_epoch_stop": false,
164
+ "should_evaluate": false,
165
+ "should_log": false,
166
+ "should_save": true,
167
+ "should_training_stop": false
168
+ },
169
+ "attributes": {}
170
+ }
171
+ },
172
+ "total_flos": 0.0,
173
+ "train_batch_size": 32,
174
+ "trial_name": null,
175
+ "trial_params": null
176
+ }