Hugging Face's logo

Blaise-g
/
longt5_tglobal_large_sumpubmed

Summarization
Transformers
PyTorch
Safetensors
English
longt5
text2text-generation
biomedical papers
Inference Endpoints
Model card Files Community
2
Blaise-g commited on
Commit
a678832
·
1 Parent(s): 09a5e54

Upload 6 files

Browse files
Files changed (5) hide show
  1. optimizer.pt +3 -0
  2. rng_state.pth +3 -0
  3. scaler.pt +3 -0
  4. scheduler.pt +3 -0
  5. trainer_state.json +160 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672b4180c5ab3d87245e8be99342a4fa0cb2118cfd7b7c58ad0abfc9b8582b9b
3
+ size 5885590
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1574f8ccbf386d171d32f014f79f6a19ba2a64051071cbe14c59f288ef6ba85a
3
+ size 14503
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e87c9e29961faa708cc1fe7bcb86707a286c589286ca435b9daebaa7bedceb
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377aacc8c46cebc4da3b42ec8ea9c184fe5c9c8bf6a3e13663b6353c77d79195
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.43077864463821325,
5
+ "global_step": 88,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 0.000980392156862745,
13
+ "loss": 2.5451,
14
+ "step": 4
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 0.0009607843137254903,
19
+ "loss": 2.4286,
20
+ "step": 8
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 0.0009411764705882353,
25
+ "loss": 2.3441,
26
+ "step": 12
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 0.0009215686274509804,
31
+ "loss": 2.2542,
32
+ "step": 16
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 0.0009019607843137256,
37
+ "loss": 2.2205,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 0.0008823529411764706,
43
+ "loss": 2.294,
44
+ "step": 24
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 0.0008627450980392158,
49
+ "loss": 2.2184,
50
+ "step": 28
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 0.0008431372549019609,
55
+ "loss": 2.2811,
56
+ "step": 32
57
+ },
58
+ {
59
+ "epoch": 0.18,
60
+ "learning_rate": 0.0008235294117647058,
61
+ "loss": 2.2013,
62
+ "step": 36
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "learning_rate": 0.000803921568627451,
67
+ "loss": 2.2134,
68
+ "step": 40
69
+ },
70
+ {
71
+ "epoch": 0.22,
72
+ "learning_rate": 0.000784313725490196,
73
+ "loss": 2.1704,
74
+ "step": 44
75
+ },
76
+ {
77
+ "epoch": 0.23,
78
+ "learning_rate": 0.0007647058823529411,
79
+ "loss": 2.2088,
80
+ "step": 48
81
+ },
82
+ {
83
+ "epoch": 0.25,
84
+ "learning_rate": 0.0007450980392156863,
85
+ "loss": 2.1733,
86
+ "step": 52
87
+ },
88
+ {
89
+ "epoch": 0.27,
90
+ "learning_rate": 0.0007254901960784313,
91
+ "loss": 2.1753,
92
+ "step": 56
93
+ },
94
+ {
95
+ "epoch": 0.29,
96
+ "learning_rate": 0.0007058823529411765,
97
+ "loss": 2.1444,
98
+ "step": 60
99
+ },
100
+ {
101
+ "epoch": 0.31,
102
+ "learning_rate": 0.0006862745098039216,
103
+ "loss": 2.1432,
104
+ "step": 64
105
+ },
106
+ {
107
+ "epoch": 0.33,
108
+ "learning_rate": 0.0006666666666666666,
109
+ "loss": 2.1687,
110
+ "step": 68
111
+ },
112
+ {
113
+ "epoch": 0.35,
114
+ "learning_rate": 0.0006470588235294118,
115
+ "loss": 2.1211,
116
+ "step": 72
117
+ },
118
+ {
119
+ "epoch": 0.37,
120
+ "learning_rate": 0.0006274509803921569,
121
+ "loss": 2.1503,
122
+ "step": 76
123
+ },
124
+ {
125
+ "epoch": 0.39,
126
+ "learning_rate": 0.0006078431372549019,
127
+ "loss": 2.1357,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.4,
132
+ "learning_rate": 0.0005980392156862745,
133
+ "loss": 2.1429,
134
+ "step": 82
135
+ },
136
+ {
137
+ "epoch": 0.41,
138
+ "learning_rate": 0.0005882352941176471,
139
+ "loss": 2.0443,
140
+ "step": 84
141
+ },
142
+ {
143
+ "epoch": 0.42,
144
+ "learning_rate": 0.0005784313725490196,
145
+ "loss": 2.0832,
146
+ "step": 86
147
+ },
148
+ {
149
+ "epoch": 0.43,
150
+ "learning_rate": 0.0005686274509803922,
151
+ "loss": 2.1285,
152
+ "step": 88
153
+ }
154
+ ],
155
+ "max_steps": 204,
156
+ "num_train_epochs": 1,
157
+ "total_flos": 3.8867912194535424e+17,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }