Hugging Face's logo

Lancelot53
/
flan-t5-base-xlsum

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
Lancelot53 commited on
Commit
7538355
·
1 Parent(s): d08fd02

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +167 -0
README.md ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/flan-t5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - xlsum
8
+ model-index:
9
+ - name: flan-t5-base-xlsum
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # flan-t5-base-xlsum
17
+
18
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the xlsum dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.3989
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 6
41
+ - eval_batch_size: 12
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 200
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 29.1967 | 0.05 | 100 | 4.4538 |
53
+ | 2.3457 | 0.09 | 200 | 0.4789 |
54
+ | 0.5064 | 0.14 | 300 | 0.4116 |
55
+ | 0.4857 | 0.18 | 400 | 0.4077 |
56
+ | 0.4749 | 0.23 | 500 | 0.4069 |
57
+ | 0.4695 | 0.28 | 600 | 0.4059 |
58
+ | 0.4754 | 0.32 | 700 | 0.4041 |
59
+ | 0.4609 | 0.37 | 800 | 0.4044 |
60
+ | 0.4703 | 0.42 | 900 | 0.4037 |
61
+ | 0.4656 | 0.46 | 1000 | 0.4025 |
62
+ | 0.464 | 0.51 | 1100 | 0.4020 |
63
+ | 0.4679 | 0.55 | 1200 | 0.4026 |
64
+ | 0.462 | 0.6 | 1300 | 0.4021 |
65
+ | 0.4665 | 0.65 | 1400 | 0.4006 |
66
+ | 0.4617 | 0.69 | 1500 | 0.4013 |
67
+ | 0.4541 | 0.74 | 1600 | 0.4000 |
68
+ | 0.4566 | 0.79 | 1700 | 0.3997 |
69
+ | 0.4646 | 0.83 | 1800 | 0.3995 |
70
+ | 0.4445 | 0.88 | 1900 | 0.3999 |
71
+ | 0.4733 | 0.92 | 2000 | 0.3993 |
72
+ | 0.4703 | 0.97 | 2100 | 0.3995 |
73
+ | 0.4412 | 1.02 | 2200 | 0.3998 |
74
+ | 0.4249 | 1.06 | 2300 | 0.4000 |
75
+ | 0.436 | 1.11 | 2400 | 0.3995 |
76
+ | 0.4333 | 1.16 | 2500 | 0.3989 |
77
+ | 0.4249 | 1.2 | 2600 | 0.3984 |
78
+ | 0.4312 | 1.25 | 2700 | 0.3988 |
79
+ | 0.4376 | 1.29 | 2800 | 0.3992 |
80
+ | 0.4276 | 1.34 | 2900 | 0.3990 |
81
+ | 0.4258 | 1.39 | 3000 | 0.3983 |
82
+ | 0.4411 | 1.43 | 3100 | 0.3986 |
83
+ | 0.4352 | 1.48 | 3200 | 0.3989 |
84
+ | 0.4429 | 1.53 | 3300 | 0.3974 |
85
+ | 0.4466 | 1.57 | 3400 | 0.3980 |
86
+ | 0.4311 | 1.62 | 3500 | 0.3977 |
87
+ | 0.427 | 1.66 | 3600 | 0.3976 |
88
+ | 0.4433 | 1.71 | 3700 | 0.3977 |
89
+ | 0.4228 | 1.76 | 3800 | 0.3984 |
90
+ | 0.4247 | 1.8 | 3900 | 0.3980 |
91
+ | 0.4275 | 1.85 | 4000 | 0.3980 |
92
+ | 0.4523 | 1.9 | 4100 | 0.3970 |
93
+ | 0.4258 | 1.94 | 4200 | 0.3976 |
94
+ | 0.4329 | 1.99 | 4300 | 0.3978 |
95
+ | 0.4146 | 2.03 | 4400 | 0.3988 |
96
+ | 0.4025 | 2.08 | 4500 | 0.3997 |
97
+ | 0.3944 | 2.13 | 4600 | 0.3989 |
98
+ | 0.4034 | 2.17 | 4700 | 0.3984 |
99
+ | 0.4099 | 2.22 | 4800 | 0.3987 |
100
+ | 0.3989 | 2.27 | 4900 | 0.3983 |
101
+ | 0.4269 | 2.31 | 5000 | 0.3990 |
102
+ | 0.4273 | 2.36 | 5100 | 0.3988 |
103
+ | 0.4117 | 2.4 | 5200 | 0.3981 |
104
+ | 0.4117 | 2.45 | 5300 | 0.3984 |
105
+ | 0.4037 | 2.5 | 5400 | 0.3978 |
106
+ | 0.4158 | 2.54 | 5500 | 0.3981 |
107
+ | 0.4081 | 2.59 | 5600 | 0.3982 |
108
+ | 0.4125 | 2.64 | 5700 | 0.3982 |
109
+ | 0.4086 | 2.68 | 5800 | 0.3988 |
110
+ | 0.4143 | 2.73 | 5900 | 0.3986 |
111
+ | 0.4025 | 2.77 | 6000 | 0.3981 |
112
+ | 0.4141 | 2.82 | 6100 | 0.3979 |
113
+ | 0.4239 | 2.87 | 6200 | 0.3975 |
114
+ | 0.4217 | 2.91 | 6300 | 0.3979 |
115
+ | 0.4099 | 2.96 | 6400 | 0.3972 |
116
+ | 0.4008 | 3.01 | 6500 | 0.3977 |
117
+ | 0.4092 | 3.05 | 6600 | 0.3998 |
118
+ | 0.3898 | 3.1 | 6700 | 0.4000 |
119
+ | 0.3978 | 3.14 | 6800 | 0.3985 |
120
+ | 0.4004 | 3.19 | 6900 | 0.3996 |
121
+ | 0.3998 | 3.24 | 7000 | 0.3996 |
122
+ | 0.3908 | 3.28 | 7100 | 0.3993 |
123
+ | 0.4021 | 3.33 | 7200 | 0.3994 |
124
+ | 0.3889 | 3.37 | 7300 | 0.3993 |
125
+ | 0.4009 | 3.42 | 7400 | 0.3984 |
126
+ | 0.3835 | 3.47 | 7500 | 0.3988 |
127
+ | 0.3999 | 3.51 | 7600 | 0.3986 |
128
+ | 0.409 | 3.56 | 7700 | 0.3985 |
129
+ | 0.3927 | 3.61 | 7800 | 0.3984 |
130
+ | 0.407 | 3.65 | 7900 | 0.3980 |
131
+ | 0.389 | 3.7 | 8000 | 0.3989 |
132
+ | 0.3976 | 3.74 | 8100 | 0.3981 |
133
+ | 0.4075 | 3.79 | 8200 | 0.3982 |
134
+ | 0.3897 | 3.84 | 8300 | 0.3981 |
135
+ | 0.3805 | 3.88 | 8400 | 0.3983 |
136
+ | 0.393 | 3.93 | 8500 | 0.3983 |
137
+ | 0.398 | 3.98 | 8600 | 0.3980 |
138
+ | 0.3832 | 4.02 | 8700 | 0.3985 |
139
+ | 0.384 | 4.07 | 8800 | 0.3989 |
140
+ | 0.3787 | 4.11 | 8900 | 0.3989 |
141
+ | 0.3816 | 4.16 | 9000 | 0.3994 |
142
+ | 0.3857 | 4.21 | 9100 | 0.3991 |
143
+ | 0.3909 | 4.25 | 9200 | 0.3990 |
144
+ | 0.3858 | 4.3 | 9300 | 0.3993 |
145
+ | 0.4021 | 4.35 | 9400 | 0.3993 |
146
+ | 0.3879 | 4.39 | 9500 | 0.3991 |
147
+ | 0.3752 | 4.44 | 9600 | 0.3994 |
148
+ | 0.3882 | 4.48 | 9700 | 0.3994 |
149
+ | 0.3881 | 4.53 | 9800 | 0.3992 |
150
+ | 0.4089 | 4.58 | 9900 | 0.3988 |
151
+ | 0.3801 | 4.62 | 10000 | 0.3989 |
152
+ | 0.3925 | 4.67 | 10100 | 0.3989 |
153
+ | 0.3858 | 4.72 | 10200 | 0.3990 |
154
+ | 0.3883 | 4.76 | 10300 | 0.3988 |
155
+ | 0.3808 | 4.81 | 10400 | 0.3989 |
156
+ | 0.4012 | 4.85 | 10500 | 0.3989 |
157
+ | 0.384 | 4.9 | 10600 | 0.3989 |
158
+ | 0.3828 | 4.95 | 10700 | 0.3989 |
159
+ | 0.3899 | 4.99 | 10800 | 0.3989 |
160
+
161
+
162
+ ### Framework versions
163
+
164
+ - Transformers 4.31.0
165
+ - Pytorch 2.0.1+cu117
166
+ - Datasets 2.13.1
167
+ - Tokenizers 0.13.3