Hugging Face's logo

shrinath-suresh
/
mariorossi

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
shrinath-suresh commited on
Commit
04a67cb
•
1 Parent(s): 1cb5301

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 +127 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.18795312819805166,
4
+ "train_runtime": 5486.4328,
5
+ "train_samples": 10763,
6
+ "train_samples_per_second": 19.617,
7
+ "train_steps_per_second": 1.635
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.18795312819805166,
4
+ "train_runtime": 5486.4328,
5
+ "train_samples": 10763,
6
+ "train_samples_per_second": 19.617,
7
+ "train_steps_per_second": 1.635
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 8970,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.56,
12
+ "learning_rate": 2.8327759197324414e-05,
13
+ "loss": 0.668,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.11,
18
+ "learning_rate": 2.665551839464883e-05,
19
+ "loss": 0.2947,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.67,
24
+ "learning_rate": 2.4983277591973243e-05,
25
+ "loss": 0.2293,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.23,
30
+ "learning_rate": 2.331103678929766e-05,
31
+ "loss": 0.2054,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.79,
36
+ "learning_rate": 2.1638795986622073e-05,
37
+ "loss": 0.1899,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 3.34,
42
+ "learning_rate": 1.996655518394649e-05,
43
+ "loss": 0.1676,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 3.9,
48
+ "learning_rate": 1.8294314381270902e-05,
49
+ "loss": 0.1608,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 4.46,
54
+ "learning_rate": 1.662207357859532e-05,
55
+ "loss": 0.1571,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 5.02,
60
+ "learning_rate": 1.4949832775919733e-05,
61
+ "loss": 0.1482,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 5.57,
66
+ "learning_rate": 1.3277591973244148e-05,
67
+ "loss": 0.141,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 6.13,
72
+ "learning_rate": 1.1605351170568563e-05,
73
+ "loss": 0.1377,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 6.69,
78
+ "learning_rate": 9.933110367892978e-06,
79
+ "loss": 0.1366,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 7.25,
84
+ "learning_rate": 8.260869565217392e-06,
85
+ "loss": 0.1257,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 7.8,
90
+ "learning_rate": 6.588628762541806e-06,
91
+ "loss": 0.1293,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 8.36,
96
+ "learning_rate": 4.916387959866221e-06,
97
+ "loss": 0.1217,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 8.92,
102
+ "learning_rate": 3.2441471571906356e-06,
103
+ "loss": 0.1231,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 9.48,
108
+ "learning_rate": 1.5719063545150504e-06,
109
+ "loss": 0.1221,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 10.0,
114
+ "step": 8970,
115
+ "total_flos": 6.55421377609728e+16,
116
+ "train_loss": 0.18795312819805166,
117
+ "train_runtime": 5486.4328,
118
+ "train_samples_per_second": 19.617,
119
+ "train_steps_per_second": 1.635
120
+ }
121
+ ],
122
+ "max_steps": 8970,
123
+ "num_train_epochs": 10,
124
+ "total_flos": 6.55421377609728e+16,
125
+ "trial_name": null,
126
+ "trial_params": null
127
+ }