Hugging Face's logo

visolex
/
emotion-vit5

Text Classification
Safetensors
t5
vietnamese
emotion-recognition
VSMEC
Eval Results (legacy)
Model card Files
xet
 Community
AnnyNguyen commited on
Commit
8ad49c5
·
verified ·
1 Parent(s): a9af2c5

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +162 -0
trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1218,
3
+ "best_metric": 0.541471444081587,
4
+ "best_model_checkpoint": "outputs/vit5/checkpoint-1218",
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1218,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9942528735632183,
14
+ "grad_norm": 58.274559020996094,
15
+ "learning_rate": 6.88e-06,
16
+ "loss": 1.9914,
17
+ "step": 173
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.3206997084548105,
22
+ "eval_loss": 1.7322026491165161,
23
+ "eval_macro_f1": 0.14803455259181977,
24
+ "eval_runtime": 2.6376,
25
+ "eval_samples_per_second": 260.08,
26
+ "eval_steps_per_second": 8.341,
27
+ "step": 174
28
+ },
29
+ {
30
+ "epoch": 1.9885057471264367,
31
+ "grad_norm": 18.986042022705078,
32
+ "learning_rate": 1.38e-05,
33
+ "loss": 1.6725,
34
+ "step": 346
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.521865889212828,
39
+ "eval_loss": 1.3959580659866333,
40
+ "eval_macro_f1": 0.3094694125241264,
41
+ "eval_runtime": 2.6511,
42
+ "eval_samples_per_second": 258.757,
43
+ "eval_steps_per_second": 8.298,
44
+ "step": 348
45
+ },
46
+ {
47
+ "epoch": 2.9827586206896552,
48
+ "grad_norm": 15.519329071044922,
49
+ "learning_rate": 1.999994401896218e-05,
50
+ "loss": 1.2986,
51
+ "step": 519
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.5714285714285714,
56
+ "eval_loss": 1.1622083187103271,
57
+ "eval_macro_f1": 0.434315370257316,
58
+ "eval_runtime": 2.6503,
59
+ "eval_samples_per_second": 258.838,
60
+ "eval_steps_per_second": 8.301,
61
+ "step": 522
62
+ },
63
+ {
64
+ "epoch": 3.9770114942528734,
65
+ "grad_norm": 33.60322189331055,
66
+ "learning_rate": 1.9993697433304146e-05,
67
+ "loss": 1.0153,
68
+ "step": 692
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_accuracy": 0.5626822157434402,
73
+ "eval_loss": 1.1611000299453735,
74
+ "eval_macro_f1": 0.48082332945066447,
75
+ "eval_runtime": 2.6538,
76
+ "eval_samples_per_second": 258.499,
77
+ "eval_steps_per_second": 8.29,
78
+ "step": 696
79
+ },
80
+ {
81
+ "epoch": 4.971264367816092,
82
+ "grad_norm": 14.145572662353516,
83
+ "learning_rate": 1.9977115923137912e-05,
84
+ "loss": 0.7927,
85
+ "step": 865
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "eval_accuracy": 0.6034985422740525,
90
+ "eval_loss": 1.1552627086639404,
91
+ "eval_macro_f1": 0.52788220890471,
92
+ "eval_runtime": 2.6498,
93
+ "eval_samples_per_second": 258.886,
94
+ "eval_steps_per_second": 8.302,
95
+ "step": 870
96
+ },
97
+ {
98
+ "epoch": 5.9655172413793105,
99
+ "grad_norm": 19.387939453125,
100
+ "learning_rate": 1.995021663613649e-05,
101
+ "loss": 0.5873,
102
+ "step": 1038
103
+ },
104
+ {
105
+ "epoch": 6.0,
106
+ "eval_accuracy": 0.5860058309037901,
107
+ "eval_loss": 1.2505557537078857,
108
+ "eval_macro_f1": 0.5207841516451528,
109
+ "eval_runtime": 2.6525,
110
+ "eval_samples_per_second": 258.626,
111
+ "eval_steps_per_second": 8.294,
112
+ "step": 1044
113
+ },
114
+ {
115
+ "epoch": 6.959770114942529,
116
+ "grad_norm": 12.481695175170898,
117
+ "learning_rate": 1.991302739004225e-05,
118
+ "loss": 0.4349,
119
+ "step": 1211
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.607871720116618,
124
+ "eval_loss": 1.3485385179519653,
125
+ "eval_macro_f1": 0.541471444081587,
126
+ "eval_runtime": 2.653,
127
+ "eval_samples_per_second": 258.571,
128
+ "eval_steps_per_second": 8.292,
129
+ "step": 1218
130
+ }
131
+ ],
132
+ "logging_steps": 173,
133
+ "max_steps": 17400,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 100,
136
+ "save_steps": 500,
137
+ "stateful_callbacks": {
138
+ "EarlyStoppingCallback": {
139
+ "args": {
140
+ "early_stopping_patience": 5,
141
+ "early_stopping_threshold": 0.0
142
+ },
143
+ "attributes": {
144
+ "early_stopping_patience_counter": 0
145
+ }
146
+ },
147
+ "TrainerControl": {
148
+ "args": {
149
+ "should_epoch_stop": false,
150
+ "should_evaluate": false,
151
+ "should_log": false,
152
+ "should_save": true,
153
+ "should_training_stop": false
154
+ },
155
+ "attributes": {}
156
+ }
157
+ },
158
+ "total_flos": 8246611698717840.0,
159
+ "train_batch_size": 32,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }