Hugging Face's logo

visolex
/
xlm-r-spam-binary

Text Classification
PyTorch
xlm-roberta
vietnamese
spam-detection
e-commerce
Eval Results
Model card Files
xet
Community
1
AnnyNguyen commited on
Commit
dbf9872
·
verified ·
1 Parent(s): c446e36

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +122 -0
trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2676,
3
+ "best_metric": 0.8785521354799841,
4
+ "best_model_checkpoint": "outputs/xlm-r-spam-binary/checkpoint-2676",
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2676,
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
+ "eval_accuracy": 0.8380592312539382,
15
+ "eval_f1": 0.7446043097893572,
16
+ "eval_loss": 0.4673084318637848,
17
+ "eval_precision": 0.8814136508052441,
18
+ "eval_recall": 0.7099304536592229,
19
+ "eval_runtime": 6.2961,
20
+ "eval_samples_per_second": 252.06,
21
+ "eval_steps_per_second": 31.607,
22
+ "step": 446
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "eval_accuracy": 0.8954001260239446,
27
+ "eval_f1": 0.8581815245478036,
28
+ "eval_loss": 0.2860272526741028,
29
+ "eval_precision": 0.8911766356713877,
30
+ "eval_recall": 0.8362022873912083,
31
+ "eval_runtime": 6.3092,
32
+ "eval_samples_per_second": 251.537,
33
+ "eval_steps_per_second": 31.541,
34
+ "step": 892
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.9017013232514177,
39
+ "eval_f1": 0.8763134439910312,
40
+ "eval_loss": 0.2545902132987976,
41
+ "eval_precision": 0.8741907793554848,
42
+ "eval_recall": 0.8785170147333722,
43
+ "eval_runtime": 6.3097,
44
+ "eval_samples_per_second": 251.517,
45
+ "eval_steps_per_second": 31.539,
46
+ "step": 1338
47
+ },
48
+ {
49
+ "epoch": 3.9960740325294446,
50
+ "grad_norm": 6.024568557739258,
51
+ "learning_rate": 2.98821174647605e-05,
52
+ "loss": 0.3102,
53
+ "step": 1782
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_accuracy": 0.8966603654694392,
58
+ "eval_f1": 0.8620397933999949,
59
+ "eval_loss": 0.3537818491458893,
60
+ "eval_precision": 0.8863547186830534,
61
+ "eval_recall": 0.8443729774275894,
62
+ "eval_runtime": 6.3034,
63
+ "eval_samples_per_second": 251.771,
64
+ "eval_steps_per_second": 31.57,
65
+ "step": 1784
66
+ },
67
+ {
68
+ "epoch": 5.0,
69
+ "eval_accuracy": 0.8758664146187776,
70
+ "eval_f1": 0.8526447810662267,
71
+ "eval_loss": 0.33958056569099426,
72
+ "eval_precision": 0.8369464036375354,
73
+ "eval_recall": 0.8783341038371089,
74
+ "eval_runtime": 6.3052,
75
+ "eval_samples_per_second": 251.696,
76
+ "eval_steps_per_second": 31.561,
77
+ "step": 2230
78
+ },
79
+ {
80
+ "epoch": 6.0,
81
+ "eval_accuracy": 0.906112161310649,
82
+ "eval_f1": 0.8785521354799841,
83
+ "eval_loss": 0.3098773956298828,
84
+ "eval_precision": 0.8876659531609425,
85
+ "eval_recall": 0.8705825008542543,
86
+ "eval_runtime": 6.3101,
87
+ "eval_samples_per_second": 251.503,
88
+ "eval_steps_per_second": 31.537,
89
+ "step": 2676
90
+ }
91
+ ],
92
+ "logging_steps": 1782,
93
+ "max_steps": 44600,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 100,
96
+ "save_steps": 500,
97
+ "stateful_callbacks": {
98
+ "EarlyStoppingCallback": {
99
+ "args": {
100
+ "early_stopping_patience": 5,
101
+ "early_stopping_threshold": 0.0
102
+ },
103
+ "attributes": {
104
+ "early_stopping_patience_counter": 0
105
+ }
106
+ },
107
+ "TrainerControl": {
108
+ "args": {
109
+ "should_epoch_stop": false,
110
+ "should_evaluate": false,
111
+ "should_log": false,
112
+ "should_save": true,
113
+ "should_training_stop": false
114
+ },
115
+ "attributes": {}
116
+ }
117
+ },
118
+ "total_flos": 0.0,
119
+ "train_batch_size": 8,
120
+ "trial_name": null,
121
+ "trial_params": null
122
+ }