Hugging Face's logo

whitedevil0089devil
/
Cyber_Bot

Text Classification
Transformers
Safetensors
PyTorch
English
roberta
question-answering
Model card Files
xet
 Community
whitedevil0089devil commited on
Commit
23f93e3
·
verified ·
1 Parent(s): 050d191

Upload checkpoint-800/trainer_state.json

Browse files
Files changed (1) hide show
  1. checkpoint-800/trainer_state.json +150 -0
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 200,
3
+ "best_metric": 0.9943516121440339,
4
+ "best_model_checkpoint": "/content/drive/MyDrive/model/roberta_model/checkpoint-200",
5
+ "epoch": 0.3651300775901415,
6
+ "eval_steps": 200,
7
+ "global_step": 800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00045641259698767686,
14
+ "grad_norm": 10.173584938049316,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.9445,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.045641259698767686,
21
+ "grad_norm": 1.0232760906219482,
22
+ "learning_rate": 5.5872291904218926e-06,
23
+ "loss": 1.2613,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.09128251939753537,
28
+ "grad_norm": 0.08294256031513214,
29
+ "learning_rate": 1.1288483466362599e-05,
30
+ "loss": 0.0782,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.09128251939753537,
35
+ "eval_accuracy": 0.9943516121440339,
36
+ "eval_f1_macro": 0.24929195185272598,
37
+ "eval_f1_weighted": 0.9915354168771638,
38
+ "eval_loss": 0.041581232100725174,
39
+ "eval_runtime": 27.4281,
40
+ "eval_samples_per_second": 154.914,
41
+ "eval_steps_per_second": 9.698,
42
+ "step": 200
43
+ },
44
+ {
45
+ "epoch": 0.13692377909630304,
46
+ "grad_norm": 0.3370012044906616,
47
+ "learning_rate": 1.6875712656784493e-05,
48
+ "loss": 0.0881,
49
+ "step": 300
50
+ },
51
+ {
52
+ "epoch": 0.18256503879507074,
53
+ "grad_norm": 0.047330956906080246,
54
+ "learning_rate": 2.2576966932725198e-05,
55
+ "loss": 0.0638,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.18256503879507074,
60
+ "eval_accuracy": 0.9943516121440339,
61
+ "eval_f1_macro": 0.24929195185272598,
62
+ "eval_f1_weighted": 0.9915354168771638,
63
+ "eval_loss": 0.04604693129658699,
64
+ "eval_runtime": 26.999,
65
+ "eval_samples_per_second": 157.376,
66
+ "eval_steps_per_second": 9.852,
67
+ "step": 400
68
+ },
69
+ {
70
+ "epoch": 0.22820629849383842,
71
+ "grad_norm": 0.10343942046165466,
72
+ "learning_rate": 2.8278221208665906e-05,
73
+ "loss": 0.0685,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.2738475581926061,
78
+ "grad_norm": 1.5386130809783936,
79
+ "learning_rate": 3.397947548460662e-05,
80
+ "loss": 0.0983,
81
+ "step": 600
82
+ },
83
+ {
84
+ "epoch": 0.2738475581926061,
85
+ "eval_accuracy": 0.9943516121440339,
86
+ "eval_f1_macro": 0.24929195185272598,
87
+ "eval_f1_weighted": 0.9915354168771638,
88
+ "eval_loss": 0.038662198930978775,
89
+ "eval_runtime": 26.7411,
90
+ "eval_samples_per_second": 158.894,
91
+ "eval_steps_per_second": 9.947,
92
+ "step": 600
93
+ },
94
+ {
95
+ "epoch": 0.3194888178913738,
96
+ "grad_norm": 0.0841965451836586,
97
+ "learning_rate": 3.9680729760547326e-05,
98
+ "loss": 0.0629,
99
+ "step": 700
100
+ },
101
+ {
102
+ "epoch": 0.3651300775901415,
103
+ "grad_norm": 0.15497300028800964,
104
+ "learning_rate": 4.538198403648803e-05,
105
+ "loss": 0.0914,
106
+ "step": 800
107
+ },
108
+ {
109
+ "epoch": 0.3651300775901415,
110
+ "eval_accuracy": 0.9943516121440339,
111
+ "eval_f1_macro": 0.24929195185272598,
112
+ "eval_f1_weighted": 0.9915354168771638,
113
+ "eval_loss": 0.039651524275541306,
114
+ "eval_runtime": 26.6349,
115
+ "eval_samples_per_second": 159.528,
116
+ "eval_steps_per_second": 9.987,
117
+ "step": 800
118
+ }
119
+ ],
120
+ "logging_steps": 100,
121
+ "max_steps": 8764,
122
+ "num_input_tokens_seen": 0,
123
+ "num_train_epochs": 4,
124
+ "save_steps": 200,
125
+ "stateful_callbacks": {
126
+ "EarlyStoppingCallback": {
127
+ "args": {
128
+ "early_stopping_patience": 3,
129
+ "early_stopping_threshold": 0.001
130
+ },
131
+ "attributes": {
132
+ "early_stopping_patience_counter": 3
133
+ }
134
+ },
135
+ "TrainerControl": {
136
+ "args": {
137
+ "should_epoch_stop": false,
138
+ "should_evaluate": false,
139
+ "should_log": false,
140
+ "should_save": true,
141
+ "should_training_stop": true
142
+ },
143
+ "attributes": {}
144
+ }
145
+ },
146
+ "total_flos": 2525934167654400.0,
147
+ "train_batch_size": 16,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }