Hugging Face's logo

JeffreyLau
/
SikuGPT2-poem

Text Generation
Transformers
PyTorch
Chinese
gpt2
text-generation-inference
Inference Endpoints
Model card Files
JeffreyLau commited on
Commit
6df9f6f
•
1 Parent(s): 1af836d

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +147 -0
trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.929802894592285,
3
+ "best_model_checkpoint": "output/Chinese-poetry/SikuGPT2-POEM/checkpoint-5000",
4
+ "epoch": 3.0,
5
+ "global_step": 9810,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.15,
12
+ "learning_rate": 4.745158002038736e-05,
13
+ "loss": 4.361,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.31,
18
+ "learning_rate": 4.490316004077472e-05,
19
+ "loss": 4.2153,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.46,
24
+ "learning_rate": 4.235474006116208e-05,
25
+ "loss": 4.1768,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.61,
30
+ "learning_rate": 3.980632008154944e-05,
31
+ "loss": 4.1459,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.76,
36
+ "learning_rate": 3.72579001019368e-05,
37
+ "loss": 4.1214,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.92,
42
+ "learning_rate": 3.4709480122324164e-05,
43
+ "loss": 4.0975,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.07,
48
+ "learning_rate": 3.2161060142711516e-05,
49
+ "loss": 4.0607,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.22,
54
+ "learning_rate": 2.9612640163098882e-05,
55
+ "loss": 4.0215,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.38,
60
+ "learning_rate": 2.7064220183486238e-05,
61
+ "loss": 4.007,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.53,
66
+ "learning_rate": 2.45158002038736e-05,
67
+ "loss": 4.0004,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.53,
72
+ "eval_loss": 3.929802894592285,
73
+ "eval_runtime": 283.0836,
74
+ "eval_samples_per_second": 7.69,
75
+ "eval_steps_per_second": 0.964,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 1.68,
80
+ "learning_rate": 2.196738022426096e-05,
81
+ "loss": 3.9871,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 1.83,
86
+ "learning_rate": 1.9418960244648318e-05,
87
+ "loss": 3.9853,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.99,
92
+ "learning_rate": 1.6870540265035677e-05,
93
+ "loss": 3.9716,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 2.14,
98
+ "learning_rate": 1.4322120285423038e-05,
99
+ "loss": 3.9384,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 2.29,
104
+ "learning_rate": 1.1773700305810397e-05,
105
+ "loss": 3.928,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 2.45,
110
+ "learning_rate": 9.225280326197758e-06,
111
+ "loss": 3.9257,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 2.6,
116
+ "learning_rate": 6.676860346585118e-06,
117
+ "loss": 3.92,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 2.75,
122
+ "learning_rate": 4.128440366972477e-06,
123
+ "loss": 3.9186,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 2.91,
128
+ "learning_rate": 1.580020387359837e-06,
129
+ "loss": 3.9191,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 3.0,
134
+ "step": 9810,
135
+ "total_flos": 3.0753026998272e+16,
136
+ "train_loss": 4.032964795469387,
137
+ "train_runtime": 12111.7268,
138
+ "train_samples_per_second": 4.859,
139
+ "train_steps_per_second": 0.81
140
+ }
141
+ ],
142
+ "max_steps": 9810,
143
+ "num_train_epochs": 3,
144
+ "total_flos": 3.0753026998272e+16,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }