Hugging Face's logo

mpsb00
/
ECHR_test_2

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
mpsb00 commited on
Commit
27e73ea
•
1 Parent(s): 83d75b8

Model save

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +131 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 717876559872000.0,
4
+ "train_loss": 0.18599607192145454,
5
+ "train_runtime": 356.9797,
6
+ "train_samples_per_second": 50.423,
7
+ "train_steps_per_second": 6.303
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 717876559872000.0,
4
+ "train_loss": 0.18599607192145454,
5
+ "train_runtime": 356.9797,
6
+ "train_samples_per_second": 50.423,
7
+ "train_steps_per_second": 6.303
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 2250,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.18,
12
+ "learning_rate": 0.0009111111111111111,
13
+ "loss": 0.2592,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 0.0008222222222222222,
19
+ "loss": 0.2127,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 0.44,
24
+ "eval_loss": 0.3103792071342468,
25
+ "eval_macro-f1": 0.3107897037355991,
26
+ "eval_micro-f1": 0.44178454842219805,
27
+ "eval_runtime": 16.3051,
28
+ "eval_samples_per_second": 61.331,
29
+ "eval_steps_per_second": 7.666,
30
+ "step": 500
31
+ },
32
+ {
33
+ "epoch": 0.53,
34
+ "learning_rate": 0.0007333333333333333,
35
+ "loss": 0.201,
36
+ "step": 600
37
+ },
38
+ {
39
+ "epoch": 0.71,
40
+ "learning_rate": 0.0006444444444444444,
41
+ "loss": 0.1913,
42
+ "step": 800
43
+ },
44
+ {
45
+ "epoch": 0.89,
46
+ "learning_rate": 0.0005555555555555556,
47
+ "loss": 0.1808,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.89,
52
+ "eval_loss": 0.2961287200450897,
53
+ "eval_macro-f1": 0.3452123032410471,
54
+ "eval_micro-f1": 0.5021520803443329,
55
+ "eval_runtime": 17.2348,
56
+ "eval_samples_per_second": 58.022,
57
+ "eval_steps_per_second": 7.253,
58
+ "step": 1000
59
+ },
60
+ {
61
+ "epoch": 1.07,
62
+ "learning_rate": 0.00046666666666666666,
63
+ "loss": 0.1758,
64
+ "step": 1200
65
+ },
66
+ {
67
+ "epoch": 1.24,
68
+ "learning_rate": 0.00037777777777777777,
69
+ "loss": 0.1762,
70
+ "step": 1400
71
+ },
72
+ {
73
+ "epoch": 1.33,
74
+ "eval_loss": 0.2807115316390991,
75
+ "eval_macro-f1": 0.3945425420350508,
76
+ "eval_micro-f1": 0.527331189710611,
77
+ "eval_runtime": 14.5084,
78
+ "eval_samples_per_second": 68.925,
79
+ "eval_steps_per_second": 8.616,
80
+ "step": 1500
81
+ },
82
+ {
83
+ "epoch": 1.42,
84
+ "learning_rate": 0.0002888888888888889,
85
+ "loss": 0.1698,
86
+ "step": 1600
87
+ },
88
+ {
89
+ "epoch": 1.6,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.1622,
92
+ "step": 1800
93
+ },
94
+ {
95
+ "epoch": 1.78,
96
+ "learning_rate": 0.0001111111111111111,
97
+ "loss": 0.16,
98
+ "step": 2000
99
+ },
100
+ {
101
+ "epoch": 1.78,
102
+ "eval_loss": 0.2669467031955719,
103
+ "eval_macro-f1": 0.4193019540132512,
104
+ "eval_micro-f1": 0.5572842998585573,
105
+ "eval_runtime": 14.4979,
106
+ "eval_samples_per_second": 68.976,
107
+ "eval_steps_per_second": 8.622,
108
+ "step": 2000
109
+ },
110
+ {
111
+ "epoch": 1.96,
112
+ "learning_rate": 2.2222222222222223e-05,
113
+ "loss": 0.1648,
114
+ "step": 2200
115
+ },
116
+ {
117
+ "epoch": 2.0,
118
+ "step": 2250,
119
+ "total_flos": 717876559872000.0,
120
+ "train_loss": 0.18599607192145454,
121
+ "train_runtime": 356.9797,
122
+ "train_samples_per_second": 50.423,
123
+ "train_steps_per_second": 6.303
124
+ }
125
+ ],
126
+ "max_steps": 2250,
127
+ "num_train_epochs": 2,
128
+ "total_flos": 717876559872000.0,
129
+ "trial_name": null,
130
+ "trial_params": null
131
+ }