Hugging Face's logo

tae898
/
emoberta-base

Text Classification
Transformers
PyTorch
English
roberta
emoberta
Inference Endpoints
Model card Files Community
1
tae898 commited on
Commit
12d2240
·
1 Parent(s): 42745ab

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": 0.61800263898399,
3
+ "best_model_checkpoint": "results/MELD_IEMOCAP/roberta-base/SEEDS/2022-03-14-18-51-04-speaker_mode-None-num_past_utterances-0-num_future_utterances-0-batch_size-64-seed-42/checkpoint-1776",
4
+ "epoch": 6.0,
5
+ "global_step": 1776,
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": 4.4394239954278034e-06,
13
+ "loss": 1.6701,
14
+ "step": 296
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_f1_macro": 0.30985777176910967,
19
+ "eval_f1_micro": 0.5323955669224212,
20
+ "eval_f1_weighted": 0.4859489120974787,
21
+ "eval_loss": 1.2982797622680664,
22
+ "eval_runtime": 1.2188,
23
+ "eval_samples_per_second": 1924.802,
24
+ "eval_steps_per_second": 15.589,
25
+ "step": 296
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 8.878847990855607e-06,
30
+ "loss": 1.2179,
31
+ "step": 592
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_f1_macro": 0.3839732358130102,
36
+ "eval_f1_micro": 0.5775788576300085,
37
+ "eval_f1_weighted": 0.5574500829748503,
38
+ "eval_loss": 1.200979471206665,
39
+ "eval_runtime": 1.2192,
40
+ "eval_samples_per_second": 1924.226,
41
+ "eval_steps_per_second": 15.584,
42
+ "step": 592
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 1.3333320881183167e-05,
47
+ "loss": 1.1013,
48
+ "step": 888
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_f1_macro": 0.4087266861454327,
53
+ "eval_f1_micro": 0.5971867007672634,
54
+ "eval_f1_weighted": 0.5871017027301386,
55
+ "eval_loss": 1.1074929237365723,
56
+ "eval_runtime": 1.2154,
57
+ "eval_samples_per_second": 1930.208,
58
+ "eval_steps_per_second": 15.633,
59
+ "step": 888
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 1.2257324895850666e-05,
64
+ "loss": 0.9993,
65
+ "step": 1184
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_f1_macro": 0.43350041604945594,
70
+ "eval_f1_micro": 0.613384484228474,
71
+ "eval_f1_weighted": 0.6060947860828556,
72
+ "eval_loss": 1.1003719568252563,
73
+ "eval_runtime": 1.2215,
74
+ "eval_samples_per_second": 1920.649,
75
+ "eval_steps_per_second": 15.555,
76
+ "step": 1184
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 1.1147468896993714e-05,
81
+ "loss": 0.8819,
82
+ "step": 1480
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_f1_macro": 0.44292548050475483,
87
+ "eval_f1_micro": 0.5980392156862745,
88
+ "eval_f1_weighted": 0.59795700581851,
89
+ "eval_loss": 1.1594799757003784,
90
+ "eval_runtime": 1.2178,
91
+ "eval_samples_per_second": 1926.363,
92
+ "eval_steps_per_second": 15.601,
93
+ "step": 1480
94
+ },
95
+ {
96
+ "epoch": 6.0,
97
+ "learning_rate": 1.0033850674411826e-05,
98
+ "loss": 0.7848,
99
+ "step": 1776
100
+ },
101
+ {
102
+ "epoch": 6.0,
103
+ "eval_f1_macro": 0.47229721194417307,
104
+ "eval_f1_micro": 0.6231884057971014,
105
+ "eval_f1_weighted": 0.61800263898399,
106
+ "eval_loss": 1.1640219688415527,
107
+ "eval_runtime": 1.2206,
108
+ "eval_samples_per_second": 1922.025,
109
+ "eval_steps_per_second": 15.566,
110
+ "step": 1776
111
+ }
112
+ ],
113
+ "max_steps": 4440,
114
+ "num_train_epochs": 15,
115
+ "total_flos": 3164590543786950.0,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }