Hugging Face's logo

whitedevil0089devil
/
roberta_base_1

Text Classification
Transformers
Safetensors
PyTorch
English
roberta
question-answering
Model card Files
xet
 Community
whitedevil0089devil commited on
Commit
7e328f9
·
verified ·
1 Parent(s): d9fff33

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": 0.9943728018757327,
4
+ "best_model_checkpoint": "/content/drive/MyDrive/model/roberta_model/checkpoint-200",
5
+ "epoch": 0.18757327080890973,
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": 0.00023446658851113716,
14
+ "grad_norm": 7.900483131408691,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.2285,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.023446658851113716,
21
+ "grad_norm": 2.4035584926605225,
22
+ "learning_rate": 2.9015240328253227e-06,
23
+ "loss": 0.9217,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.04689331770222743,
28
+ "grad_norm": 0.31396016478538513,
29
+ "learning_rate": 5.832356389214537e-06,
30
+ "loss": 0.073,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.04689331770222743,
35
+ "eval_accuracy": 0.9943728018757327,
36
+ "eval_f1_macro": 0.24929461556548319,
37
+ "eval_f1_weighted": 0.9915671414895327,
38
+ "eval_loss": 0.04064385965466499,
39
+ "eval_runtime": 57.486,
40
+ "eval_samples_per_second": 148.384,
41
+ "eval_steps_per_second": 9.289,
42
+ "step": 200
43
+ },
44
+ {
45
+ "epoch": 0.07033997655334115,
46
+ "grad_norm": 0.14905625581741333,
47
+ "learning_rate": 8.763188745603752e-06,
48
+ "loss": 0.0474,
49
+ "step": 300
50
+ },
51
+ {
52
+ "epoch": 0.09378663540445487,
53
+ "grad_norm": 0.08281561732292175,
54
+ "learning_rate": 1.1694021101992966e-05,
55
+ "loss": 0.0334,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.09378663540445487,
60
+ "eval_accuracy": 0.9943728018757327,
61
+ "eval_f1_macro": 0.24929461556548319,
62
+ "eval_f1_weighted": 0.9915671414895327,
63
+ "eval_loss": 0.04262762889266014,
64
+ "eval_runtime": 54.8606,
65
+ "eval_samples_per_second": 155.485,
66
+ "eval_steps_per_second": 9.734,
67
+ "step": 400
68
+ },
69
+ {
70
+ "epoch": 0.11723329425556858,
71
+ "grad_norm": 0.04056438058614731,
72
+ "learning_rate": 1.4624853458382182e-05,
73
+ "loss": 0.04,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.1406799531066823,
78
+ "grad_norm": 0.04737967997789383,
79
+ "learning_rate": 1.7555685814771398e-05,
80
+ "loss": 0.0502,
81
+ "step": 600
82
+ },
83
+ {
84
+ "epoch": 0.1406799531066823,
85
+ "eval_accuracy": 0.9943728018757327,
86
+ "eval_f1_macro": 0.24929461556548319,
87
+ "eval_f1_weighted": 0.9915671414895327,
88
+ "eval_loss": 0.04288283362984657,
89
+ "eval_runtime": 54.7704,
90
+ "eval_samples_per_second": 155.741,
91
+ "eval_steps_per_second": 9.75,
92
+ "step": 600
93
+ },
94
+ {
95
+ "epoch": 0.16412661195779601,
96
+ "grad_norm": 0.14134405553340912,
97
+ "learning_rate": 2.048651817116061e-05,
98
+ "loss": 0.0605,
99
+ "step": 700
100
+ },
101
+ {
102
+ "epoch": 0.18757327080890973,
103
+ "grad_norm": 0.11066514253616333,
104
+ "learning_rate": 2.3417350527549826e-05,
105
+ "loss": 0.0325,
106
+ "step": 800
107
+ },
108
+ {
109
+ "epoch": 0.18757327080890973,
110
+ "eval_accuracy": 0.9943728018757327,
111
+ "eval_f1_macro": 0.24929461556548319,
112
+ "eval_f1_weighted": 0.9915671414895327,
113
+ "eval_loss": 0.04036899656057358,
114
+ "eval_runtime": 54.8996,
115
+ "eval_samples_per_second": 155.375,
116
+ "eval_steps_per_second": 9.727,
117
+ "step": 800
118
+ }
119
+ ],
120
+ "logging_steps": 100,
121
+ "max_steps": 17060,
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
+ }