ekiprop commited on
Commit
b1fe1b7
·
verified ·
1 Parent(s): e9b3088

Model save

Browse files
Files changed (2) hide show
  1. README.md +115 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: roberta-base
5
+ tags:
6
+ - base_model:adapter:roberta-base
7
+ - lora
8
+ - transformers
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: SST-2-GLoRA-p40-seed62
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # SST-2-GLoRA-p40-seed62
20
+
21
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1907
24
+ - Accuracy: 0.9495
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.0003
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 5
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
55
+ | 0.3812 | 0.0950 | 200 | 0.2376 | 0.9209 |
56
+ | 0.2893 | 0.1900 | 400 | 0.1875 | 0.9255 |
57
+ | 0.2599 | 0.2850 | 600 | 0.1922 | 0.9266 |
58
+ | 0.2416 | 0.3800 | 800 | 0.2270 | 0.9323 |
59
+ | 0.2361 | 0.4751 | 1000 | 0.2757 | 0.9151 |
60
+ | 0.2242 | 0.5701 | 1200 | 0.2305 | 0.9289 |
61
+ | 0.2247 | 0.6651 | 1400 | 0.1974 | 0.9266 |
62
+ | 0.2214 | 0.7601 | 1600 | 0.2127 | 0.9312 |
63
+ | 0.2205 | 0.8551 | 1800 | 0.1843 | 0.9404 |
64
+ | 0.2122 | 0.9501 | 2000 | 0.2053 | 0.9358 |
65
+ | 0.2182 | 1.0451 | 2200 | 0.1874 | 0.9415 |
66
+ | 0.1876 | 1.1401 | 2400 | 0.2008 | 0.9392 |
67
+ | 0.1907 | 1.2352 | 2600 | 0.1867 | 0.9392 |
68
+ | 0.1866 | 1.3302 | 2800 | 0.2096 | 0.9392 |
69
+ | 0.1816 | 1.4252 | 3000 | 0.2020 | 0.9415 |
70
+ | 0.1843 | 1.5202 | 3200 | 0.1969 | 0.9358 |
71
+ | 0.186 | 1.6152 | 3400 | 0.1882 | 0.9427 |
72
+ | 0.1756 | 1.7102 | 3600 | 0.2128 | 0.9381 |
73
+ | 0.1752 | 1.8052 | 3800 | 0.2081 | 0.9450 |
74
+ | 0.1827 | 1.9002 | 4000 | 0.1900 | 0.9427 |
75
+ | 0.1692 | 1.9952 | 4200 | 0.2219 | 0.9415 |
76
+ | 0.1636 | 2.0903 | 4400 | 0.1869 | 0.9438 |
77
+ | 0.1526 | 2.1853 | 4600 | 0.1974 | 0.9438 |
78
+ | 0.159 | 2.2803 | 4800 | 0.2152 | 0.9392 |
79
+ | 0.1576 | 2.3753 | 5000 | 0.1954 | 0.9404 |
80
+ | 0.1581 | 2.4703 | 5200 | 0.2159 | 0.9415 |
81
+ | 0.1579 | 2.5653 | 5400 | 0.2106 | 0.9415 |
82
+ | 0.1676 | 2.6603 | 5600 | 0.1820 | 0.9450 |
83
+ | 0.1533 | 2.7553 | 5800 | 0.1956 | 0.9461 |
84
+ | 0.1441 | 2.8504 | 6000 | 0.2133 | 0.9415 |
85
+ | 0.1466 | 2.9454 | 6200 | 0.1948 | 0.9438 |
86
+ | 0.1469 | 3.0404 | 6400 | 0.2218 | 0.9381 |
87
+ | 0.1263 | 3.1354 | 6600 | 0.2035 | 0.9427 |
88
+ | 0.1365 | 3.2304 | 6800 | 0.1915 | 0.9461 |
89
+ | 0.1466 | 3.3254 | 7000 | 0.1851 | 0.9450 |
90
+ | 0.1389 | 3.4204 | 7200 | 0.1907 | 0.9495 |
91
+ | 0.1296 | 3.5154 | 7400 | 0.1989 | 0.9461 |
92
+ | 0.1336 | 3.6105 | 7600 | 0.1966 | 0.9472 |
93
+ | 0.1388 | 3.7055 | 7800 | 0.1984 | 0.9438 |
94
+ | 0.1353 | 3.8005 | 8000 | 0.2053 | 0.9427 |
95
+ | 0.1409 | 3.8955 | 8200 | 0.2072 | 0.9472 |
96
+ | 0.1352 | 3.9905 | 8400 | 0.1940 | 0.9461 |
97
+ | 0.1282 | 4.0855 | 8600 | 0.2006 | 0.9438 |
98
+ | 0.1195 | 4.1805 | 8800 | 0.2225 | 0.9438 |
99
+ | 0.129 | 4.2755 | 9000 | 0.2098 | 0.9461 |
100
+ | 0.1255 | 4.3705 | 9200 | 0.2020 | 0.9427 |
101
+ | 0.1228 | 4.4656 | 9400 | 0.2058 | 0.9427 |
102
+ | 0.1183 | 4.5606 | 9600 | 0.1987 | 0.9438 |
103
+ | 0.1216 | 4.6556 | 9800 | 0.2014 | 0.9438 |
104
+ | 0.1199 | 4.7506 | 10000 | 0.2008 | 0.9427 |
105
+ | 0.1267 | 4.8456 | 10200 | 0.1970 | 0.9404 |
106
+ | 0.1238 | 4.9406 | 10400 | 0.1972 | 0.9404 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - PEFT 0.16.0
112
+ - Transformers 4.54.1
113
+ - Pytorch 2.5.1+cu121
114
+ - Datasets 4.0.0
115
+ - Tokenizers 0.21.4
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1283e337ce30a47994d15750f403242355faf44914f45c586417badf86a7803
3
  size 4859088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b3e4b6f855ea1432adb4c98600898f235c2ca2f8a72f517163cab0f477f5a7
3
  size 4859088