Hugging Face's logo

Frikallo
/
Dodo82J-vgdunkey

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
Frikallo commited on
Commit
1cf1840
•
1 Parent(s): 1201315

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +133 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 4.058929084449686,
4
+ "train_runtime": 28.0555,
5
+ "train_samples": 93,
6
+ "train_samples_per_second": 3.315,
7
+ "train_steps_per_second": 3.315
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 4.058929084449686,
4
+ "train_runtime": 28.0555,
5
+ "train_samples": 93,
6
+ "train_samples_per_second": 3.315,
7
+ "train_steps_per_second": 3.315
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 93,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 0.0001298236559139785,
13
+ "loss": 5.2886,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 0.00012244731182795699,
19
+ "loss": 4.8484,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.16,
24
+ "learning_rate": 0.00011507096774193549,
25
+ "loss": 4.592,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.22,
30
+ "learning_rate": 0.00010769462365591397,
31
+ "loss": 4.3362,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.27,
36
+ "learning_rate": 0.00010031827956989248,
37
+ "loss": 4.3381,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.32,
42
+ "learning_rate": 9.294193548387097e-05,
43
+ "loss": 4.229,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.38,
48
+ "learning_rate": 8.556559139784946e-05,
49
+ "loss": 4.2006,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.43,
54
+ "learning_rate": 7.818924731182796e-05,
55
+ "loss": 3.8651,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.48,
60
+ "learning_rate": 7.081290322580646e-05,
61
+ "loss": 4.0792,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.54,
66
+ "learning_rate": 6.343655913978495e-05,
67
+ "loss": 3.8664,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.59,
72
+ "learning_rate": 5.606021505376345e-05,
73
+ "loss": 3.7922,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.65,
78
+ "learning_rate": 4.868387096774194e-05,
79
+ "loss": 3.727,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.7,
84
+ "learning_rate": 4.130752688172043e-05,
85
+ "loss": 3.565,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.75,
90
+ "learning_rate": 3.3931182795698924e-05,
91
+ "loss": 3.7849,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.81,
96
+ "learning_rate": 2.655483870967742e-05,
97
+ "loss": 3.7644,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.86,
102
+ "learning_rate": 1.9178494623655912e-05,
103
+ "loss": 3.6057,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.91,
108
+ "learning_rate": 1.1802150537634409e-05,
109
+ "loss": 3.648,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.97,
114
+ "learning_rate": 4.4258064516129036e-06,
115
+ "loss": 3.6404,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 1.0,
120
+ "step": 93,
121
+ "total_flos": 48600317952000.0,
122
+ "train_loss": 4.058929084449686,
123
+ "train_runtime": 28.0555,
124
+ "train_samples_per_second": 3.315,
125
+ "train_steps_per_second": 3.315
126
+ }
127
+ ],
128
+ "max_steps": 93,
129
+ "num_train_epochs": 1,
130
+ "total_flos": 48600317952000.0,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }