Hugging Face's logo

visolex
/
phobert-v2-spam-multiclass

Text Classification
Safetensors
roberta
vietnamese
spam-detection
e-commerce
Eval Results (legacy)
Model card Files
xet
 Community
AnnyNguyen commited on
Commit
555c61b
·
verified ·
1 Parent(s): c50e45a

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +119 -0
trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1784,
3
+ "best_metric": 0.7556884604610913,
4
+ "best_model_checkpoint": "outputs/phobert-v2-spam-multiclass/checkpoint-1784",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1784,
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": 0.4952254891395569,
15
+ "learning_rate": 4.998771926094749e-05,
16
+ "loss": 0.3797,
17
+ "step": 446
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8991808443604284,
22
+ "eval_f1": 0.731437578554798,
23
+ "eval_loss": 0.32099807262420654,
24
+ "eval_precision": 0.7906199246241619,
25
+ "eval_recall": 0.6906560700315657,
26
+ "eval_runtime": 6.0884,
27
+ "eval_samples_per_second": 260.66,
28
+ "eval_steps_per_second": 8.212,
29
+ "step": 446
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 7.687873363494873,
34
+ "learning_rate": 4.995077872180951e-05,
35
+ "loss": 0.2543,
36
+ "step": 892
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8979206049149339,
41
+ "eval_f1": 0.731081078121833,
42
+ "eval_loss": 0.3287402093410492,
43
+ "eval_precision": 0.7898720982969423,
44
+ "eval_recall": 0.6907625233762491,
45
+ "eval_runtime": 6.0984,
46
+ "eval_samples_per_second": 260.233,
47
+ "eval_steps_per_second": 8.199,
48
+ "step": 892
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "grad_norm": 0.808912456035614,
53
+ "learning_rate": 4.988921477641713e-05,
54
+ "loss": 0.1899,
55
+ "step": 1338
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_accuracy": 0.8783868935097668,
60
+ "eval_f1": 0.7244610762250314,
61
+ "eval_loss": 0.4272703528404236,
62
+ "eval_precision": 0.7676076400572929,
63
+ "eval_recall": 0.6972846955844025,
64
+ "eval_runtime": 6.0861,
65
+ "eval_samples_per_second": 260.758,
66
+ "eval_steps_per_second": 8.215,
67
+ "step": 1338
68
+ },
69
+ {
70
+ "epoch": 4.0,
71
+ "grad_norm": 1.4541220664978027,
72
+ "learning_rate": 4.980308818095173e-05,
73
+ "loss": 0.1417,
74
+ "step": 1784
75
+ },
76
+ {
77
+ "epoch": 4.0,
78
+ "eval_accuracy": 0.8878386893509767,
79
+ "eval_f1": 0.7556884604610913,
80
+ "eval_loss": 0.36974188685417175,
81
+ "eval_precision": 0.8502751264037481,
82
+ "eval_recall": 0.7261916079618785,
83
+ "eval_runtime": 6.085,
84
+ "eval_samples_per_second": 260.803,
85
+ "eval_steps_per_second": 8.217,
86
+ "step": 1784
87
+ }
88
+ ],
89
+ "logging_steps": 446,
90
+ "max_steps": 44600,
91
+ "num_input_tokens_seen": 0,
92
+ "num_train_epochs": 100,
93
+ "save_steps": 500,
94
+ "stateful_callbacks": {
95
+ "EarlyStoppingCallback": {
96
+ "args": {
97
+ "early_stopping_patience": 5,
98
+ "early_stopping_threshold": 0.0
99
+ },
100
+ "attributes": {
101
+ "early_stopping_patience_counter": 0
102
+ }
103
+ },
104
+ "TrainerControl": {
105
+ "args": {
106
+ "should_epoch_stop": false,
107
+ "should_evaluate": false,
108
+ "should_log": false,
109
+ "should_save": true,
110
+ "should_training_stop": false
111
+ },
112
+ "attributes": {}
113
+ }
114
+ },
115
+ "total_flos": 0.0,
116
+ "train_batch_size": 32,
117
+ "trial_name": null,
118
+ "trial_params": null
119
+ }