TasmiaAzmi
commited on
Commit
•
5534b6c
1
Parent(s):
ef0a8df
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: masked-sentence-generation-t5-base
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# masked-sentence-generation-t5-base
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.7392
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 4
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 4
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| 2.9984 | 0.05 | 80 | 2.7041 |
|
49 |
+
| 2.8752 | 0.1 | 160 | 2.7021 |
|
50 |
+
| 2.9314 | 0.15 | 240 | 2.6966 |
|
51 |
+
| 2.8541 | 0.2 | 320 | 2.6968 |
|
52 |
+
| 2.8674 | 0.25 | 400 | 2.6900 |
|
53 |
+
| 2.8706 | 0.3 | 480 | 2.6886 |
|
54 |
+
| 2.7718 | 0.34 | 560 | 2.6908 |
|
55 |
+
| 2.8503 | 0.39 | 640 | 2.6877 |
|
56 |
+
| 2.8195 | 0.44 | 720 | 2.6902 |
|
57 |
+
| 2.8569 | 0.49 | 800 | 2.6893 |
|
58 |
+
| 2.8372 | 0.54 | 880 | 2.6859 |
|
59 |
+
| 2.8915 | 0.59 | 960 | 2.6898 |
|
60 |
+
| 2.9687 | 0.64 | 1040 | 2.6909 |
|
61 |
+
| 2.832 | 0.69 | 1120 | 2.6841 |
|
62 |
+
| 2.8425 | 0.74 | 1200 | 2.6842 |
|
63 |
+
| 2.8114 | 0.79 | 1280 | 2.6766 |
|
64 |
+
| 2.8101 | 0.84 | 1360 | 2.6783 |
|
65 |
+
| 2.8837 | 0.89 | 1440 | 2.6781 |
|
66 |
+
| 2.894 | 0.94 | 1520 | 2.6754 |
|
67 |
+
| 2.9183 | 0.99 | 1600 | 2.6762 |
|
68 |
+
| 2.6916 | 1.03 | 1680 | 2.6889 |
|
69 |
+
| 2.5812 | 1.08 | 1760 | 2.6896 |
|
70 |
+
| 2.5522 | 1.13 | 1840 | 2.6943 |
|
71 |
+
| 2.5368 | 1.18 | 1920 | 2.6928 |
|
72 |
+
| 2.5987 | 1.23 | 2000 | 2.6927 |
|
73 |
+
| 2.5625 | 1.28 | 2080 | 2.6899 |
|
74 |
+
| 2.4946 | 1.33 | 2160 | 2.6942 |
|
75 |
+
| 2.5902 | 1.38 | 2240 | 2.6900 |
|
76 |
+
| 2.5415 | 1.43 | 2320 | 2.6897 |
|
77 |
+
| 2.5767 | 1.48 | 2400 | 2.6858 |
|
78 |
+
| 2.6262 | 1.53 | 2480 | 2.6825 |
|
79 |
+
| 2.6066 | 1.58 | 2560 | 2.6818 |
|
80 |
+
| 2.5387 | 1.63 | 2640 | 2.6840 |
|
81 |
+
| 2.5795 | 1.67 | 2720 | 2.6828 |
|
82 |
+
| 2.5521 | 1.72 | 2800 | 2.6871 |
|
83 |
+
| 2.5477 | 1.77 | 2880 | 2.6836 |
|
84 |
+
| 2.587 | 1.82 | 2960 | 2.6824 |
|
85 |
+
| 2.529 | 1.87 | 3040 | 2.6871 |
|
86 |
+
| 2.6221 | 1.92 | 3120 | 2.6838 |
|
87 |
+
| 2.6353 | 1.97 | 3200 | 2.6803 |
|
88 |
+
| 2.5419 | 2.02 | 3280 | 2.6879 |
|
89 |
+
| 2.4521 | 2.07 | 3360 | 2.7027 |
|
90 |
+
| 2.3415 | 2.12 | 3440 | 2.7105 |
|
91 |
+
| 2.3483 | 2.17 | 3520 | 2.7140 |
|
92 |
+
| 2.3493 | 2.22 | 3600 | 2.7144 |
|
93 |
+
| 2.3967 | 2.27 | 3680 | 2.7134 |
|
94 |
+
| 2.3544 | 2.32 | 3760 | 2.7122 |
|
95 |
+
| 2.3192 | 2.36 | 3840 | 2.7175 |
|
96 |
+
| 2.3381 | 2.41 | 3920 | 2.7166 |
|
97 |
+
| 2.3667 | 2.46 | 4000 | 2.7165 |
|
98 |
+
| 2.3997 | 2.51 | 4080 | 2.7106 |
|
99 |
+
| 2.3178 | 2.56 | 4160 | 2.7154 |
|
100 |
+
| 2.4036 | 2.61 | 4240 | 2.7144 |
|
101 |
+
| 2.3797 | 2.66 | 4320 | 2.7129 |
|
102 |
+
| 2.3354 | 2.71 | 4400 | 2.7136 |
|
103 |
+
| 2.4109 | 2.76 | 4480 | 2.7118 |
|
104 |
+
| 2.387 | 2.81 | 4560 | 2.7097 |
|
105 |
+
| 2.3934 | 2.86 | 4640 | 2.7103 |
|
106 |
+
| 2.3956 | 2.91 | 4720 | 2.7103 |
|
107 |
+
| 2.4086 | 2.96 | 4800 | 2.7111 |
|
108 |
+
| 2.4083 | 3.0 | 4880 | 2.7110 |
|
109 |
+
| 2.3121 | 3.05 | 4960 | 2.7230 |
|
110 |
+
| 2.263 | 3.1 | 5040 | 2.7252 |
|
111 |
+
| 2.2722 | 3.15 | 5120 | 2.7296 |
|
112 |
+
| 2.2053 | 3.2 | 5200 | 2.7309 |
|
113 |
+
| 2.1969 | 3.25 | 5280 | 2.7363 |
|
114 |
+
| 2.2684 | 3.3 | 5360 | 2.7396 |
|
115 |
+
| 2.2789 | 3.35 | 5440 | 2.7376 |
|
116 |
+
| 2.2227 | 3.4 | 5520 | 2.7384 |
|
117 |
+
| 2.2886 | 3.45 | 5600 | 2.7390 |
|
118 |
+
| 2.2182 | 3.5 | 5680 | 2.7376 |
|
119 |
+
| 2.2738 | 3.55 | 5760 | 2.7394 |
|
120 |
+
| 2.1687 | 3.6 | 5840 | 2.7386 |
|
121 |
+
| 2.2548 | 3.65 | 5920 | 2.7371 |
|
122 |
+
| 2.2391 | 3.69 | 6000 | 2.7372 |
|
123 |
+
| 2.2031 | 3.74 | 6080 | 2.7391 |
|
124 |
+
| 2.1885 | 3.79 | 6160 | 2.7400 |
|
125 |
+
| 2.216 | 3.84 | 6240 | 2.7406 |
|
126 |
+
| 2.272 | 3.89 | 6320 | 2.7401 |
|
127 |
+
| 2.3455 | 3.94 | 6400 | 2.7395 |
|
128 |
+
| 2.2889 | 3.99 | 6480 | 2.7392 |
|
129 |
+
|
130 |
+
|
131 |
+
### Framework versions
|
132 |
+
|
133 |
+
- Transformers 4.28.1
|
134 |
+
- Pytorch 2.0.0
|
135 |
+
- Datasets 2.12.0
|
136 |
+
- Tokenizers 0.11.0
|