Hugging Face's logo

visolex
/
bartpho-spam-binary

Text Classification
Safetensors
Vietnamese
mbart
spam-detection
vietnamese
bartpho
Eval Results
Model card Files
xet
Community
AnnyNguyen commited on
Commit
3d0d4d5
·
verified ·
1 Parent(s): 9eef197

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +171 -0
trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3568,
3
+ "best_metric": 0.8764965343415249,
4
+ "best_model_checkpoint": "outputs/bartpho-spam-binary/checkpoint-3568",
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3568,
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": 5.2079925537109375,
15
+ "learning_rate": 4.998771926094749e-05,
16
+ "loss": 0.4627,
17
+ "step": 446
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8084436042848141,
22
+ "eval_loss": 0.4561808407306671,
23
+ "eval_runtime": 19.4902,
24
+ "eval_samples_per_second": 81.426,
25
+ "eval_steps_per_second": 2.565,
26
+ "step": 446
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "grad_norm": 5.896441459655762,
31
+ "learning_rate": 4.995077872180951e-05,
32
+ "loss": 0.3735,
33
+ "step": 892
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.8418399495904222,
38
+ "eval_loss": 0.3941121995449066,
39
+ "eval_runtime": 19.0372,
40
+ "eval_samples_per_second": 83.363,
41
+ "eval_steps_per_second": 2.626,
42
+ "step": 892
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "grad_norm": 2.555406332015991,
47
+ "learning_rate": 4.988921477641713e-05,
48
+ "loss": 0.3147,
49
+ "step": 1338
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.8613736609955892,
54
+ "eval_loss": 0.3282012343406677,
55
+ "eval_runtime": 19.0715,
56
+ "eval_samples_per_second": 83.213,
57
+ "eval_steps_per_second": 2.622,
58
+ "step": 1338
59
+ },
60
+ {
61
+ "epoch": 4.0,
62
+ "grad_norm": 2.6473870277404785,
63
+ "learning_rate": 4.980308818095173e-05,
64
+ "loss": 0.2677,
65
+ "step": 1784
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.8714555765595463,
70
+ "eval_loss": 0.29463911056518555,
71
+ "eval_runtime": 19.1426,
72
+ "eval_samples_per_second": 82.904,
73
+ "eval_steps_per_second": 2.612,
74
+ "step": 1784
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "grad_norm": 7.139180660247803,
79
+ "learning_rate": 4.9692483931964865e-05,
80
+ "loss": 0.2441,
81
+ "step": 2230
82
+ },
83
+ {
84
+ "epoch": 5.0,
85
+ "eval_accuracy": 0.868935097668557,
86
+ "eval_loss": 0.32677021622657776,
87
+ "eval_runtime": 19.0711,
88
+ "eval_samples_per_second": 83.215,
89
+ "eval_steps_per_second": 2.622,
90
+ "step": 2230
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "grad_norm": 1.7669497728347778,
95
+ "learning_rate": 4.9557511182496865e-05,
96
+ "loss": 0.2137,
97
+ "step": 2676
98
+ },
99
+ {
100
+ "epoch": 6.0,
101
+ "eval_accuracy": 0.8752362948960303,
102
+ "eval_loss": 0.37486177682876587,
103
+ "eval_runtime": 19.1107,
104
+ "eval_samples_per_second": 83.042,
105
+ "eval_steps_per_second": 2.616,
106
+ "step": 2676
107
+ },
108
+ {
109
+ "epoch": 7.0,
110
+ "grad_norm": 3.3637311458587646,
111
+ "learning_rate": 4.939830313435599e-05,
112
+ "loss": 0.1957,
113
+ "step": 3122
114
+ },
115
+ {
116
+ "epoch": 7.0,
117
+ "eval_accuracy": 0.8720856962822936,
118
+ "eval_loss": 0.43288952112197876,
119
+ "eval_runtime": 19.1972,
120
+ "eval_samples_per_second": 82.668,
121
+ "eval_steps_per_second": 2.605,
122
+ "step": 3122
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "grad_norm": 7.402363300323486,
127
+ "learning_rate": 4.9215016906664344e-05,
128
+ "loss": 0.1769,
129
+ "step": 3568
130
+ },
131
+ {
132
+ "epoch": 8.0,
133
+ "eval_accuracy": 0.8764965343415249,
134
+ "eval_loss": 0.4071377217769623,
135
+ "eval_runtime": 19.1521,
136
+ "eval_samples_per_second": 82.863,
137
+ "eval_steps_per_second": 2.611,
138
+ "step": 3568
139
+ }
140
+ ],
141
+ "logging_steps": 446,
142
+ "max_steps": 44600,
143
+ "num_input_tokens_seen": 0,
144
+ "num_train_epochs": 100,
145
+ "save_steps": 500,
146
+ "stateful_callbacks": {
147
+ "EarlyStoppingCallback": {
148
+ "args": {
149
+ "early_stopping_patience": 5,
150
+ "early_stopping_threshold": 0.0
151
+ },
152
+ "attributes": {
153
+ "early_stopping_patience_counter": 0
154
+ }
155
+ },
156
+ "TrainerControl": {
157
+ "args": {
158
+ "should_epoch_stop": false,
159
+ "should_evaluate": false,
160
+ "should_log": false,
161
+ "should_save": true,
162
+ "should_training_stop": false
163
+ },
164
+ "attributes": {}
165
+ }
166
+ },
167
+ "total_flos": 6.101365327850419e+16,
168
+ "train_batch_size": 32,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }