Hugging Face's logo

visolex
/
bilstm-spam-binary

Text Classification
Safetensors
roberta
vietnamese
spam-detection
e-commerce
Eval Results
Model card Files
xet
Community
AnnyNguyen commited on
Commit
d6c59f7
·
verified ·
1 Parent(s): 2d53e71

Delete trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -176
trainer_state.json DELETED
@@ -1,176 +0,0 @@
1
- {
2
- "best_global_step": 3122,
3
- "best_metric": 0.5257779194390215,
4
- "best_model_checkpoint": "outputs/bilstm-spam-binary/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": 0.4966887831687927,
15
- "learning_rate": 0.0009997543852189499,
16
- "loss": 0.5757,
17
- "step": 446
18
- },
19
- {
20
- "epoch": 1.0,
21
- "eval_accuracy": 0.7290485192186515,
22
- "eval_f1": 0.42164723032069973,
23
- "eval_loss": 0.5851318836212158,
24
- "eval_precision": 0.3645242596093258,
25
- "eval_recall": 0.5,
26
- "eval_runtime": 6.2523,
27
- "eval_samples_per_second": 253.825,
28
- "eval_steps_per_second": 7.997,
29
- "step": 446
30
- },
31
- {
32
- "epoch": 2.0,
33
- "grad_norm": 0.35379767417907715,
34
- "learning_rate": 0.0009990155744361903,
35
- "loss": 0.5739,
36
- "step": 892
37
- },
38
- {
39
- "epoch": 2.0,
40
- "eval_accuracy": 0.7290485192186515,
41
- "eval_f1": 0.42164723032069973,
42
- "eval_loss": 0.5852128267288208,
43
- "eval_precision": 0.3645242596093258,
44
- "eval_recall": 0.5,
45
- "eval_runtime": 6.2531,
46
- "eval_samples_per_second": 253.796,
47
- "eval_steps_per_second": 7.996,
48
- "step": 892
49
- },
50
- {
51
- "epoch": 3.0,
52
- "grad_norm": 0.5833616256713867,
53
- "learning_rate": 0.0009977842955283425,
54
- "loss": 0.5726,
55
- "step": 1338
56
- },
57
- {
58
- "epoch": 3.0,
59
- "eval_accuracy": 0.7290485192186515,
60
- "eval_f1": 0.42164723032069973,
61
- "eval_loss": 0.5832122564315796,
62
- "eval_precision": 0.3645242596093258,
63
- "eval_recall": 0.5,
64
- "eval_runtime": 6.2546,
65
- "eval_samples_per_second": 253.734,
66
- "eval_steps_per_second": 7.994,
67
- "step": 1338
68
- },
69
- {
70
- "epoch": 4.0,
71
- "grad_norm": 0.9242071509361267,
72
- "learning_rate": 0.0009960617636190344,
73
- "loss": 0.5606,
74
- "step": 1784
75
- },
76
- {
77
- "epoch": 4.0,
78
- "eval_accuracy": 0.7290485192186515,
79
- "eval_f1": 0.42164723032069973,
80
- "eval_loss": 0.5644996762275696,
81
- "eval_precision": 0.3645242596093258,
82
- "eval_recall": 0.5,
83
- "eval_runtime": 6.2529,
84
- "eval_samples_per_second": 253.801,
85
- "eval_steps_per_second": 7.996,
86
- "step": 1784
87
- },
88
- {
89
- "epoch": 5.0,
90
- "grad_norm": 0.6944896578788757,
91
- "learning_rate": 0.0009938496786392973,
92
- "loss": 0.5453,
93
- "step": 2230
94
- },
95
- {
96
- "epoch": 5.0,
97
- "eval_accuracy": 0.7321991178323881,
98
- "eval_f1": 0.4810744810744811,
99
- "eval_loss": 0.563392698764801,
100
- "eval_precision": 0.6428808639393865,
101
- "eval_recall": 0.5233492794114691,
102
- "eval_runtime": 6.2646,
103
- "eval_samples_per_second": 253.33,
104
- "eval_steps_per_second": 7.981,
105
- "step": 2230
106
- },
107
- {
108
- "epoch": 6.0,
109
- "grad_norm": 0.42335620522499084,
110
- "learning_rate": 0.0009911502236499372,
111
- "loss": 0.5441,
112
- "step": 2676
113
- },
114
- {
115
- "epoch": 6.0,
116
- "eval_accuracy": 0.7284183994959043,
117
- "eval_f1": 0.4236885275598579,
118
- "eval_loss": 0.5696581602096558,
119
- "eval_precision": 0.53125,
120
- "eval_recall": 0.5002984864625837,
121
- "eval_runtime": 6.2683,
122
- "eval_samples_per_second": 253.179,
123
- "eval_steps_per_second": 7.977,
124
- "step": 2676
125
- },
126
- {
127
- "epoch": 7.0,
128
- "grad_norm": 0.6146748661994934,
129
- "learning_rate": 0.0009879660626871199,
130
- "loss": 0.5431,
131
- "step": 3122
132
- },
133
- {
134
- "epoch": 7.0,
135
- "eval_accuracy": 0.7353497164461248,
136
- "eval_f1": 0.5257779194390215,
137
- "eval_loss": 0.5626002550125122,
138
- "eval_precision": 0.6485838779956428,
139
- "eval_recall": 0.5452372816626802,
140
- "eval_runtime": 6.2648,
141
- "eval_samples_per_second": 253.32,
142
- "eval_steps_per_second": 7.981,
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
- }