Hugging Face's logo

tae898
/
emoberta-large

Text Classification
Transformers
PyTorch
English
roberta
emoberta
Inference Endpoints
Model card Files Community
1
tae898 commited on
Commit
78cd140
•
1 Parent(s): 1a32090

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +118 -0
trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6281057228463983,
3
+ "best_model_checkpoint": "results/MELD_IEMOCAP/roberta-large/SEEDS/2022-03-14-19-06-40-speaker_mode-None-num_past_utterances-0-num_future_utterances-0-batch_size-16-seed-42/checkpoint-7086",
4
+ "epoch": 6.0,
5
+ "global_step": 7086,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.1135900346584852e-06,
13
+ "loss": 1.6941,
14
+ "step": 1181
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_f1_macro": 0.07791319292694036,
19
+ "eval_f1_micro": 0.35635123614663256,
20
+ "eval_f1_weighted": 0.19072939518738496,
21
+ "eval_loss": 1.5153617858886719,
22
+ "eval_runtime": 3.1794,
23
+ "eval_samples_per_second": 737.872,
24
+ "eval_steps_per_second": 23.275,
25
+ "step": 1181
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 2.2338198736122084e-06,
30
+ "loss": 1.298,
31
+ "step": 2362
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_f1_macro": 0.39258179738738447,
36
+ "eval_f1_micro": 0.5882352941176471,
37
+ "eval_f1_weighted": 0.570696903628535,
38
+ "eval_loss": 1.1774364709854126,
39
+ "eval_runtime": 3.1793,
40
+ "eval_samples_per_second": 737.903,
41
+ "eval_steps_per_second": 23.276,
42
+ "step": 2362
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 3.3540497125659314e-06,
47
+ "loss": 1.0976,
48
+ "step": 3543
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_f1_macro": 0.4195774350293237,
53
+ "eval_f1_micro": 0.6052855924978687,
54
+ "eval_f1_weighted": 0.5932857871930991,
55
+ "eval_loss": 1.0991432666778564,
56
+ "eval_runtime": 3.1785,
57
+ "eval_samples_per_second": 738.086,
58
+ "eval_steps_per_second": 23.281,
59
+ "step": 3543
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 3.0822920081965484e-06,
64
+ "loss": 0.9869,
65
+ "step": 4724
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_f1_macro": 0.4634417760566037,
70
+ "eval_f1_micro": 0.6287297527706734,
71
+ "eval_f1_weighted": 0.6211850773676282,
72
+ "eval_loss": 1.0642313957214355,
73
+ "eval_runtime": 3.1809,
74
+ "eval_samples_per_second": 737.537,
75
+ "eval_steps_per_second": 23.264,
76
+ "step": 4724
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 2.8022345484581173e-06,
81
+ "loss": 0.8638,
82
+ "step": 5905
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_f1_macro": 0.4789393979707725,
87
+ "eval_f1_micro": 0.6172208013640239,
88
+ "eval_f1_weighted": 0.6157912564989868,
89
+ "eval_loss": 1.0899823904037476,
90
+ "eval_runtime": 3.182,
91
+ "eval_samples_per_second": 737.269,
92
+ "eval_steps_per_second": 23.256,
93
+ "step": 5905
94
+ },
95
+ {
96
+ "epoch": 6.0,
97
+ "learning_rate": 2.522414224587374e-06,
98
+ "loss": 0.772,
99
+ "step": 7086
100
+ },
101
+ {
102
+ "epoch": 6.0,
103
+ "eval_f1_macro": 0.4957254043928597,
104
+ "eval_f1_micro": 0.6295822676896846,
105
+ "eval_f1_weighted": 0.6281057228463983,
106
+ "eval_loss": 1.120431661605835,
107
+ "eval_runtime": 3.1786,
108
+ "eval_samples_per_second": 738.072,
109
+ "eval_steps_per_second": 23.281,
110
+ "step": 7086
111
+ }
112
+ ],
113
+ "max_steps": 17715,
114
+ "num_train_epochs": 15,
115
+ "total_flos": 8224038236774502.0,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }