Hugging Face's logo

visolex
/
bartpho-hsd-span

Token Classification
Safetensors
t5
vietnamese
hate-speech
span-detection
nlp
Eval Results
Model card Files
xet
Community
AnnyNguyen commited on
Commit
66284f9
·
verified ·
1 Parent(s): 6c2225a

Upload checkpoint-2205/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-2205/trainer_state.json +176 -0
checkpoint-2205/trainer_state.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2205,
3
+ "best_metric": 0.8215573432280139,
4
+ "best_model_checkpoint": "outputs/runs/bartpho/checkpoint-2205",
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2205,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9968253968253968,
14
+ "grad_norm": 3.099806785583496,
15
+ "learning_rate": 4.999432333543028e-06,
16
+ "loss": 0.5217,
17
+ "step": 314
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.5575607044846632,
22
+ "eval_f1": 0.5515728094561057,
23
+ "eval_loss": 1.320883870124817,
24
+ "eval_precision": 0.6356662607616385,
25
+ "eval_recall": 0.613408724428726,
26
+ "eval_runtime": 5.7255,
27
+ "eval_samples_per_second": 227.228,
28
+ "eval_steps_per_second": 7.161,
29
+ "step": 315
30
+ },
31
+ {
32
+ "epoch": 1.9936507936507937,
33
+ "grad_norm": 1.9128671884536743,
34
+ "learning_rate": 4.996525669931999e-06,
35
+ "loss": 0.3798,
36
+ "step": 628
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7966790565185674,
41
+ "eval_f1": 0.7727173370771165,
42
+ "eval_loss": 0.47158923745155334,
43
+ "eval_precision": 0.8049817216732861,
44
+ "eval_recall": 0.7621576186595547,
45
+ "eval_runtime": 5.7417,
46
+ "eval_samples_per_second": 226.586,
47
+ "eval_steps_per_second": 7.141,
48
+ "step": 630
49
+ },
50
+ {
51
+ "epoch": 2.9904761904761905,
52
+ "grad_norm": 2.9943490028381348,
53
+ "learning_rate": 4.991155236893945e-06,
54
+ "loss": 0.3319,
55
+ "step": 942
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_accuracy": 0.821516656824261,
60
+ "eval_f1": 0.8026111791478101,
61
+ "eval_loss": 0.4115768074989319,
62
+ "eval_precision": 0.8293916217775468,
63
+ "eval_recall": 0.7918328303886295,
64
+ "eval_runtime": 5.7518,
65
+ "eval_samples_per_second": 226.191,
66
+ "eval_steps_per_second": 7.128,
67
+ "step": 945
68
+ },
69
+ {
70
+ "epoch": 3.9873015873015873,
71
+ "grad_norm": 3.69238543510437,
72
+ "learning_rate": 4.983326334397891e-06,
73
+ "loss": 0.3164,
74
+ "step": 1256
75
+ },
76
+ {
77
+ "epoch": 4.0,
78
+ "eval_accuracy": 0.8272310417896968,
79
+ "eval_f1": 0.8089149421105615,
80
+ "eval_loss": 0.39312005043029785,
81
+ "eval_precision": 0.8362205682758683,
82
+ "eval_recall": 0.7978148005325525,
83
+ "eval_runtime": 5.7808,
84
+ "eval_samples_per_second": 225.054,
85
+ "eval_steps_per_second": 7.092,
86
+ "step": 1260
87
+ },
88
+ {
89
+ "epoch": 4.984126984126984,
90
+ "grad_norm": 20.970905303955078,
91
+ "learning_rate": 4.97304668862541e-06,
92
+ "loss": 1.1543,
93
+ "step": 1570
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "eval_accuracy": 0.6326814186959392,
98
+ "eval_f1": 0.43821110851496803,
99
+ "eval_loss": 0.6246408224105835,
100
+ "eval_precision": 0.8027087477481067,
101
+ "eval_recall": 0.5281280484111368,
102
+ "eval_runtime": 5.7608,
103
+ "eval_samples_per_second": 225.837,
104
+ "eval_steps_per_second": 7.117,
105
+ "step": 1575
106
+ },
107
+ {
108
+ "epoch": 5.980952380952381,
109
+ "grad_norm": 7.541131019592285,
110
+ "learning_rate": 4.9603264443458e-06,
111
+ "loss": 0.7372,
112
+ "step": 1884
113
+ },
114
+ {
115
+ "epoch": 6.0,
116
+ "eval_accuracy": 0.8111994997742036,
117
+ "eval_f1": 0.7970220873127174,
118
+ "eval_loss": 0.38770145177841187,
119
+ "eval_precision": 0.8059464877876692,
120
+ "eval_recall": 0.7915295487509866,
121
+ "eval_runtime": 5.7788,
122
+ "eval_samples_per_second": 225.131,
123
+ "eval_steps_per_second": 7.095,
124
+ "step": 1890
125
+ },
126
+ {
127
+ "epoch": 6.977777777777778,
128
+ "grad_norm": 3.5747125148773193,
129
+ "learning_rate": 4.945178154904432e-06,
130
+ "loss": 0.3252,
131
+ "step": 2198
132
+ },
133
+ {
134
+ "epoch": 7.0,
135
+ "eval_accuracy": 0.8378782089137458,
136
+ "eval_f1": 0.8215573432280139,
137
+ "eval_loss": 0.3621535897254944,
138
+ "eval_precision": 0.846152402138612,
139
+ "eval_recall": 0.8106876687211231,
140
+ "eval_runtime": 5.775,
141
+ "eval_samples_per_second": 225.28,
142
+ "eval_steps_per_second": 7.1,
143
+ "step": 2205
144
+ }
145
+ ],
146
+ "logging_steps": 314,
147
+ "max_steps": 31500,
148
+ "num_input_tokens_seen": 0,
149
+ "num_train_epochs": 100,
150
+ "save_steps": 500,
151
+ "stateful_callbacks": {
152
+ "EarlyStoppingCallback": {
153
+ "args": {
154
+ "early_stopping_patience": 5,
155
+ "early_stopping_threshold": 0.0
156
+ },
157
+ "attributes": {
158
+ "early_stopping_patience_counter": 0
159
+ }
160
+ },
161
+ "TrainerControl": {
162
+ "args": {
163
+ "should_epoch_stop": false,
164
+ "should_evaluate": false,
165
+ "should_log": false,
166
+ "should_save": true,
167
+ "should_training_stop": false
168
+ },
169
+ "attributes": {}
170
+ }
171
+ },
172
+ "total_flos": 0.0,
173
+ "train_batch_size": 32,
174
+ "trial_name": null,
175
+ "trial_params": null
176
+ }