Hugging Face's logo

visolex
/
emotion-xlm-roberta

Text Classification
Safetensors
xlm-roberta
vietnamese
emotion-recognition
VSMEC
Eval Results (legacy)
Model card Files
xet
 Community
AnnyNguyen commited on
Commit
5340e8e
·
verified ·
1 Parent(s): cde6632

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": 0.5791211340127863,
4
+ "best_model_checkpoint": "outputs/xlm-roberta/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": 18.446226119995117,
15
+ "learning_rate": 6.88e-06,
16
+ "loss": 1.862,
17
+ "step": 173
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.35131195335276966,
22
+ "eval_loss": 1.7294005155563354,
23
+ "eval_macro_f1": 0.1305947465271508,
24
+ "eval_runtime": 2.5584,
25
+ "eval_samples_per_second": 268.135,
26
+ "eval_steps_per_second": 8.599,
27
+ "step": 174
28
+ },
29
+ {
30
+ "epoch": 1.9885057471264367,
31
+ "grad_norm": 13.695894241333008,
32
+ "learning_rate": 1.38e-05,
33
+ "loss": 1.5827,
34
+ "step": 346
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.4752186588921283,
39
+ "eval_loss": 1.4143601655960083,
40
+ "eval_macro_f1": 0.28267180164126793,
41
+ "eval_runtime": 2.5621,
42
+ "eval_samples_per_second": 267.745,
43
+ "eval_steps_per_second": 8.587,
44
+ "step": 348
45
+ },
46
+ {
47
+ "epoch": 2.9827586206896552,
48
+ "grad_norm": 17.38983917236328,
49
+ "learning_rate": 1.999994401896218e-05,
50
+ "loss": 1.255,
51
+ "step": 519
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.5583090379008746,
56
+ "eval_loss": 1.20831298828125,
57
+ "eval_macro_f1": 0.39994578519074936,
58
+ "eval_runtime": 2.574,
59
+ "eval_samples_per_second": 266.514,
60
+ "eval_steps_per_second": 8.547,
61
+ "step": 522
62
+ },
63
+ {
64
+ "epoch": 3.9770114942528734,
65
+ "grad_norm": 14.526453971862793,
66
+ "learning_rate": 1.9993697433304146e-05,
67
+ "loss": 1.0496,
68
+ "step": 692
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_accuracy": 0.5830903790087464,
73
+ "eval_loss": 1.165583610534668,
74
+ "eval_macro_f1": 0.4733848919733088,
75
+ "eval_runtime": 2.5683,
76
+ "eval_samples_per_second": 267.1,
77
+ "eval_steps_per_second": 8.566,
78
+ "step": 696
79
+ },
80
+ {
81
+ "epoch": 4.971264367816092,
82
+ "grad_norm": 21.57827377319336,
83
+ "learning_rate": 1.9977115923137912e-05,
84
+ "loss": 0.8598,
85
+ "step": 865
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "eval_accuracy": 0.6297376093294461,
90
+ "eval_loss": 1.1509721279144287,
91
+ "eval_macro_f1": 0.5534137222302774,
92
+ "eval_runtime": 2.5522,
93
+ "eval_samples_per_second": 268.787,
94
+ "eval_steps_per_second": 8.62,
95
+ "step": 870
96
+ },
97
+ {
98
+ "epoch": 5.9655172413793105,
99
+ "grad_norm": 25.143001556396484,
100
+ "learning_rate": 1.995021663613649e-05,
101
+ "loss": 0.6874,
102
+ "step": 1038
103
+ },
104
+ {
105
+ "epoch": 6.0,
106
+ "eval_accuracy": 0.6224489795918368,
107
+ "eval_loss": 1.2183538675308228,
108
+ "eval_macro_f1": 0.5459436407870719,
109
+ "eval_runtime": 2.5682,
110
+ "eval_samples_per_second": 267.115,
111
+ "eval_steps_per_second": 8.566,
112
+ "step": 1044
113
+ },
114
+ {
115
+ "epoch": 6.959770114942529,
116
+ "grad_norm": 26.58820915222168,
117
+ "learning_rate": 1.991302739004225e-05,
118
+ "loss": 0.5549,
119
+ "step": 1211
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.6239067055393586,
124
+ "eval_loss": 1.2362854480743408,
125
+ "eval_macro_f1": 0.5791211340127863,
126
+ "eval_runtime": 2.5663,
127
+ "eval_samples_per_second": 267.312,
128
+ "eval_steps_per_second": 8.573,
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": 3931781279500200.0,
159
+ "train_batch_size": 32,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }