Hugging Face's logo

kpriyanshu256
/
distilgpt2-the_verge-linustechtips-two_min

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
2
kpriyanshu256 commited on
Commit
2bb02f1
·
1 Parent(s): 29bf1b1

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +15 -0
  2. eval_results.json +10 -0
  3. runs/Nov22_17-53-11_e50ed1e61975/events.out.tfevents.1669141999.e50ed1e61975.470.2 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +139 -0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.34066889097945724,
4
+ "eval_loss": 3.3777639865875244,
5
+ "eval_runtime": 172.1791,
6
+ "eval_samples": 20134,
7
+ "eval_samples_per_second": 116.936,
8
+ "eval_steps_per_second": 14.619,
9
+ "perplexity": 29.30517104379502,
10
+ "train_loss": 3.5289945189493994,
11
+ "train_runtime": 1832.9089,
12
+ "train_samples": 77229,
13
+ "train_samples_per_second": 42.135,
14
+ "train_steps_per_second": 5.267
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.34066889097945724,
4
+ "eval_loss": 3.3777639865875244,
5
+ "eval_runtime": 172.1791,
6
+ "eval_samples": 20134,
7
+ "eval_samples_per_second": 116.936,
8
+ "eval_steps_per_second": 14.619,
9
+ "perplexity": 29.30517104379502
10
+ }
runs/Nov22_17-53-11_e50ed1e61975/events.out.tfevents.1669141999.e50ed1e61975.470.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef86985b39e7625065d8771e5b40aed70b9891ff4528ea7cfa48caab0204a065
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 3.5289945189493994,
4
+ "train_runtime": 1832.9089,
5
+ "train_samples": 77229,
6
+ "train_samples_per_second": 42.135,
7
+ "train_steps_per_second": 5.267
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 9654,
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": 4.742075823492853e-05,
13
+ "loss": 3.736,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "learning_rate": 4.483115806919412e-05,
19
+ "loss": 3.6583,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.16,
24
+ "learning_rate": 4.224155790345971e-05,
25
+ "loss": 3.6089,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.21,
30
+ "learning_rate": 3.96519577377253e-05,
31
+ "loss": 3.5785,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.26,
36
+ "learning_rate": 3.706235757199089e-05,
37
+ "loss": 3.5712,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.31,
42
+ "learning_rate": 3.447275740625648e-05,
43
+ "loss": 3.5492,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.36,
48
+ "learning_rate": 3.188315724052207e-05,
49
+ "loss": 3.5441,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.41,
54
+ "learning_rate": 2.9293557074787652e-05,
55
+ "loss": 3.528,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.47,
60
+ "learning_rate": 2.6703956909053245e-05,
61
+ "loss": 3.5161,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.52,
66
+ "learning_rate": 2.4114356743318832e-05,
67
+ "loss": 3.4965,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.57,
72
+ "learning_rate": 2.1524756577584422e-05,
73
+ "loss": 3.502,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.62,
78
+ "learning_rate": 1.8935156411850012e-05,
79
+ "loss": 3.4984,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.67,
84
+ "learning_rate": 1.6345556246115602e-05,
85
+ "loss": 3.4832,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.73,
90
+ "learning_rate": 1.375595608038119e-05,
91
+ "loss": 3.4808,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.78,
96
+ "learning_rate": 1.116635591464678e-05,
97
+ "loss": 3.4683,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.83,
102
+ "learning_rate": 8.576755748912369e-06,
103
+ "loss": 3.4613,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.88,
108
+ "learning_rate": 5.992334783509427e-06,
109
+ "loss": 3.4763,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.93,
114
+ "learning_rate": 3.402734617775016e-06,
115
+ "loss": 3.4537,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.98,
120
+ "learning_rate": 8.131344520406049e-07,
121
+ "loss": 3.4605,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "step": 9654,
127
+ "total_flos": 5044921687867392.0,
128
+ "train_loss": 3.5289945189493994,
129
+ "train_runtime": 1832.9089,
130
+ "train_samples_per_second": 42.135,
131
+ "train_steps_per_second": 5.267
132
+ }
133
+ ],
134
+ "max_steps": 9654,
135
+ "num_train_epochs": 1,
136
+ "total_flos": 5044921687867392.0,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }