Hugging Face's logo

visolex
/
phobert-spam-binary

Text Classification
Safetensors
Vietnamese
roberta
spam-detection
vietnamese
phobert
Eval Results
Model card Files
xet
Community
AnnyNguyen commited on
Commit
5d0e36a
·
verified ·
1 Parent(s): e96b573

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +139 -0
trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2676,
3
+ "best_metric": 0.8966603654694392,
4
+ "best_model_checkpoint": "outputs/phobert-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
+ "grad_norm": 0.9173329472541809,
15
+ "learning_rate": 4.998771926094749e-05,
16
+ "loss": 0.3259,
17
+ "step": 446
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8815374921235035,
22
+ "eval_loss": 0.31694671511650085,
23
+ "eval_runtime": 5.9871,
24
+ "eval_samples_per_second": 265.072,
25
+ "eval_steps_per_second": 8.351,
26
+ "step": 446
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "grad_norm": 3.1561405658721924,
31
+ "learning_rate": 4.995077872180951e-05,
32
+ "loss": 0.2332,
33
+ "step": 892
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.8941398865784499,
38
+ "eval_loss": 0.28185954689979553,
39
+ "eval_runtime": 5.9876,
40
+ "eval_samples_per_second": 265.046,
41
+ "eval_steps_per_second": 8.351,
42
+ "step": 892
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "grad_norm": 7.922402858734131,
47
+ "learning_rate": 4.988921477641713e-05,
48
+ "loss": 0.1792,
49
+ "step": 1338
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.8922495274102079,
54
+ "eval_loss": 0.31757012009620667,
55
+ "eval_runtime": 5.9886,
56
+ "eval_samples_per_second": 265.006,
57
+ "eval_steps_per_second": 8.349,
58
+ "step": 1338
59
+ },
60
+ {
61
+ "epoch": 4.0,
62
+ "grad_norm": 0.4279385209083557,
63
+ "learning_rate": 4.980308818095173e-05,
64
+ "loss": 0.1372,
65
+ "step": 1784
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.8840579710144928,
70
+ "eval_loss": 0.4067457318305969,
71
+ "eval_runtime": 5.9908,
72
+ "eval_samples_per_second": 264.907,
73
+ "eval_steps_per_second": 8.346,
74
+ "step": 1784
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "grad_norm": 0.19143949449062347,
79
+ "learning_rate": 4.9692483931964865e-05,
80
+ "loss": 0.109,
81
+ "step": 2230
82
+ },
83
+ {
84
+ "epoch": 5.0,
85
+ "eval_accuracy": 0.8954001260239446,
86
+ "eval_loss": 0.417103111743927,
87
+ "eval_runtime": 5.9924,
88
+ "eval_samples_per_second": 264.834,
89
+ "eval_steps_per_second": 8.344,
90
+ "step": 2230
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "grad_norm": 0.09283456951379776,
95
+ "learning_rate": 4.9557511182496865e-05,
96
+ "loss": 0.0884,
97
+ "step": 2676
98
+ },
99
+ {
100
+ "epoch": 6.0,
101
+ "eval_accuracy": 0.8966603654694392,
102
+ "eval_loss": 0.4399544894695282,
103
+ "eval_runtime": 5.9927,
104
+ "eval_samples_per_second": 264.824,
105
+ "eval_steps_per_second": 8.344,
106
+ "step": 2676
107
+ }
108
+ ],
109
+ "logging_steps": 446,
110
+ "max_steps": 44600,
111
+ "num_input_tokens_seen": 0,
112
+ "num_train_epochs": 100,
113
+ "save_steps": 500,
114
+ "stateful_callbacks": {
115
+ "EarlyStoppingCallback": {
116
+ "args": {
117
+ "early_stopping_patience": 5,
118
+ "early_stopping_threshold": 0.0
119
+ },
120
+ "attributes": {
121
+ "early_stopping_patience_counter": 0
122
+ }
123
+ },
124
+ "TrainerControl": {
125
+ "args": {
126
+ "should_epoch_stop": false,
127
+ "should_evaluate": false,
128
+ "should_log": false,
129
+ "should_save": true,
130
+ "should_training_stop": false
131
+ },
132
+ "attributes": {}
133
+ }
134
+ },
135
+ "total_flos": 1.125431228196864e+16,
136
+ "train_batch_size": 32,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }