Hugging Face's logo

EricWesthoff
/
phi-1_5-finetuned-SQL

Text Generation
Transformers
PyTorch
mixformer-sequential
Generated from Trainer
custom_code
Model card Files
xet
Community
EricWesthoff commited on
Commit
0810f43
·
1 Parent(s): 558f36d

End of training

Browse files
Files changed (2) hide show
  1. README.md +184 -64
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3403
19
 
20
  ## Model description
21
 
@@ -40,72 +40,192 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
- - training_steps: 6000
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 2.4485 | 0.4 | 100 | 2.0478 |
50
- | 2.0521 | 0.8 | 200 | 1.9223 |
51
- | 1.9626 | 1.2 | 300 | 1.8386 |
52
- | 1.8707 | 1.6 | 400 | 1.7702 |
53
- | 1.79 | 2.0 | 500 | 1.7149 |
54
- | 1.7197 | 2.4 | 600 | 1.6567 |
55
- | 1.6904 | 2.8 | 700 | 1.6055 |
56
- | 1.6379 | 3.2 | 800 | 1.5583 |
57
- | 1.5794 | 3.6 | 900 | 1.5267 |
58
- | 1.5977 | 4.0 | 1000 | 1.4928 |
59
- | 1.4773 | 4.4 | 1100 | 1.4638 |
60
- | 1.5185 | 4.8 | 1200 | 1.4446 |
61
- | 1.4476 | 5.2 | 1300 | 1.4337 |
62
- | 1.4321 | 5.6 | 1400 | 1.4287 |
63
- | 1.4393 | 6.0 | 1500 | 1.4282 |
64
- | 1.4956 | 6.4 | 1600 | 1.4504 |
65
- | 1.5252 | 6.8 | 1700 | 1.4311 |
66
- | 1.4864 | 7.2 | 1800 | 1.3654 |
67
- | 1.4092 | 7.6 | 1900 | 1.3112 |
68
- | 1.4063 | 8.0 | 2000 | 1.2925 |
69
- | 1.2657 | 8.4 | 2100 | 1.2123 |
70
- | 1.312 | 8.8 | 2200 | 1.1824 |
71
- | 1.2451 | 9.2 | 2300 | 1.1223 |
72
- | 1.1777 | 9.6 | 2400 | 1.0857 |
73
- | 1.1913 | 10.0 | 2500 | 1.0422 |
74
- | 1.0452 | 10.4 | 2600 | 0.9842 |
75
- | 1.082 | 10.8 | 2700 | 0.9442 |
76
- | 0.9814 | 11.2 | 2800 | 0.9002 |
77
- | 0.9496 | 11.6 | 2900 | 0.8559 |
78
- | 0.9639 | 12.0 | 3000 | 0.8163 |
79
- | 0.823 | 12.4 | 3100 | 0.7827 |
80
- | 0.8395 | 12.8 | 3200 | 0.7384 |
81
- | 0.8038 | 13.2 | 3300 | 0.6971 |
82
- | 0.7458 | 13.6 | 3400 | 0.6641 |
83
- | 0.7495 | 14.0 | 3500 | 0.6328 |
84
- | 0.6575 | 14.4 | 3600 | 0.6017 |
85
- | 0.6448 | 14.8 | 3700 | 0.5829 |
86
- | 0.6268 | 15.2 | 3800 | 0.5412 |
87
- | 0.5738 | 15.6 | 3900 | 0.5233 |
88
- | 0.5989 | 16.0 | 4000 | 0.5008 |
89
- | 0.5033 | 16.4 | 4100 | 0.4781 |
90
- | 0.5343 | 16.8 | 4200 | 0.4572 |
91
- | 0.4881 | 17.2 | 4300 | 0.4390 |
92
- | 0.4676 | 17.6 | 4400 | 0.4254 |
93
- | 0.4683 | 18.0 | 4500 | 0.4171 |
94
- | 0.4188 | 18.4 | 4600 | 0.3987 |
95
- | 0.4245 | 18.8 | 4700 | 0.3869 |
96
- | 0.4136 | 19.2 | 4800 | 0.3777 |
97
- | 0.3938 | 19.6 | 4900 | 0.3694 |
98
- | 0.3986 | 20.0 | 5000 | 0.3627 |
99
- | 0.3661 | 20.4 | 5100 | 0.3571 |
100
- | 0.3743 | 20.8 | 5200 | 0.3516 |
101
- | 0.3668 | 21.2 | 5300 | 0.3482 |
102
- | 0.3613 | 21.6 | 5400 | 0.3455 |
103
- | 0.3542 | 22.0 | 5500 | 0.3430 |
104
- | 0.3505 | 22.4 | 5600 | 0.3419 |
105
- | 0.3495 | 22.8 | 5700 | 0.3410 |
106
- | 0.3396 | 23.2 | 5800 | 0.3405 |
107
- | 0.3481 | 23.6 | 5900 | 0.3403 |
108
- | 0.3444 | 24.0 | 6000 | 0.3403 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
 
110
 
111
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1812
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
+ - training_steps: 18000
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 2.4485 | 0.4 | 100 | 2.0478 |
50
+ | 2.0521 | 0.8 | 200 | 1.9223 |
51
+ | 1.9626 | 1.2 | 300 | 1.8386 |
52
+ | 1.8707 | 1.6 | 400 | 1.7702 |
53
+ | 1.79 | 2.0 | 500 | 1.7149 |
54
+ | 1.7197 | 2.4 | 600 | 1.6567 |
55
+ | 1.6904 | 2.8 | 700 | 1.6055 |
56
+ | 1.6379 | 3.2 | 800 | 1.5583 |
57
+ | 1.5794 | 3.6 | 900 | 1.5267 |
58
+ | 1.5977 | 4.0 | 1000 | 1.4928 |
59
+ | 1.4773 | 4.4 | 1100 | 1.4638 |
60
+ | 1.5185 | 4.8 | 1200 | 1.4446 |
61
+ | 1.4476 | 5.2 | 1300 | 1.4337 |
62
+ | 1.4321 | 5.6 | 1400 | 1.4287 |
63
+ | 1.4393 | 6.0 | 1500 | 1.4282 |
64
+ | 1.4956 | 6.4 | 1600 | 1.4504 |
65
+ | 1.5252 | 6.8 | 1700 | 1.4311 |
66
+ | 1.4864 | 7.2 | 1800 | 1.3654 |
67
+ | 1.4092 | 7.6 | 1900 | 1.3112 |
68
+ | 1.4063 | 8.0 | 2000 | 1.2925 |
69
+ | 1.2657 | 8.4 | 2100 | 1.2123 |
70
+ | 1.312 | 8.8 | 2200 | 1.1824 |
71
+ | 1.2451 | 9.2 | 2300 | 1.1223 |
72
+ | 1.1777 | 9.6 | 2400 | 1.0857 |
73
+ | 1.1913 | 10.0 | 2500 | 1.0422 |
74
+ | 1.0452 | 10.4 | 2600 | 0.9842 |
75
+ | 1.082 | 10.8 | 2700 | 0.9442 |
76
+ | 0.9814 | 11.2 | 2800 | 0.9002 |
77
+ | 0.9496 | 11.6 | 2900 | 0.8559 |
78
+ | 0.9639 | 12.0 | 3000 | 0.8163 |
79
+ | 0.823 | 12.4 | 3100 | 0.7827 |
80
+ | 0.8395 | 12.8 | 3200 | 0.7384 |
81
+ | 0.8038 | 13.2 | 3300 | 0.6971 |
82
+ | 0.7458 | 13.6 | 3400 | 0.6641 |
83
+ | 0.7495 | 14.0 | 3500 | 0.6328 |
84
+ | 0.6575 | 14.4 | 3600 | 0.6017 |
85
+ | 0.6448 | 14.8 | 3700 | 0.5829 |
86
+ | 0.6268 | 15.2 | 3800 | 0.5412 |
87
+ | 0.5738 | 15.6 | 3900 | 0.5233 |
88
+ | 0.5989 | 16.0 | 4000 | 0.5008 |
89
+ | 0.5033 | 16.4 | 4100 | 0.4781 |
90
+ | 0.5343 | 16.8 | 4200 | 0.4572 |
91
+ | 0.4881 | 17.2 | 4300 | 0.4390 |
92
+ | 0.4676 | 17.6 | 4400 | 0.4254 |
93
+ | 0.4683 | 18.0 | 4500 | 0.4171 |
94
+ | 0.4188 | 18.4 | 4600 | 0.3987 |
95
+ | 0.4245 | 18.8 | 4700 | 0.3869 |
96
+ | 0.4136 | 19.2 | 4800 | 0.3777 |
97
+ | 0.3938 | 19.6 | 4900 | 0.3694 |
98
+ | 0.3986 | 20.0 | 5000 | 0.3627 |
99
+ | 0.3661 | 20.4 | 5100 | 0.3571 |
100
+ | 0.3743 | 20.8 | 5200 | 0.3516 |
101
+ | 0.3668 | 21.2 | 5300 | 0.3482 |
102
+ | 0.3613 | 21.6 | 5400 | 0.3455 |
103
+ | 0.3542 | 22.0 | 5500 | 0.3430 |
104
+ | 0.3505 | 22.4 | 5600 | 0.3419 |
105
+ | 0.3495 | 22.8 | 5700 | 0.3410 |
106
+ | 0.3396 | 23.2 | 5800 | 0.3405 |
107
+ | 0.3481 | 23.6 | 5900 | 0.3403 |
108
+ | 0.3444 | 24.0 | 6000 | 0.3403 |
109
+ | 0.4918 | 24.4 | 6100 | 0.4983 |
110
+ | 0.5913 | 24.8 | 6200 | 0.4897 |
111
+ | 0.5565 | 25.2 | 6300 | 0.4776 |
112
+ | 0.5439 | 25.6 | 6400 | 0.4586 |
113
+ | 0.5586 | 26.0 | 6500 | 0.4355 |
114
+ | 0.4542 | 26.4 | 6600 | 0.4205 |
115
+ | 0.4895 | 26.8 | 6700 | 0.3966 |
116
+ | 0.4576 | 27.2 | 6800 | 0.3798 |
117
+ | 0.4252 | 27.6 | 6900 | 0.3597 |
118
+ | 0.4427 | 28.0 | 7000 | 0.3365 |
119
+ | 0.3589 | 28.4 | 7100 | 0.3258 |
120
+ | 0.3888 | 28.8 | 7200 | 0.3280 |
121
+ | 0.3662 | 29.2 | 7300 | 0.3129 |
122
+ | 0.3422 | 29.6 | 7400 | 0.2991 |
123
+ | 0.3604 | 30.0 | 7500 | 0.2811 |
124
+ | 0.3039 | 30.4 | 7600 | 0.2861 |
125
+ | 0.3268 | 30.8 | 7700 | 0.2752 |
126
+ | 0.3087 | 31.2 | 7800 | 0.2687 |
127
+ | 0.3067 | 31.6 | 7900 | 0.2662 |
128
+ | 0.3044 | 32.0 | 8000 | 0.2558 |
129
+ | 0.2737 | 32.4 | 8100 | 0.2558 |
130
+ | 0.2903 | 32.8 | 8200 | 0.2517 |
131
+ | 0.2744 | 33.2 | 8300 | 0.2482 |
132
+ | 0.2757 | 33.6 | 8400 | 0.2435 |
133
+ | 0.2771 | 34.0 | 8500 | 0.2360 |
134
+ | 0.2488 | 34.4 | 8600 | 0.2393 |
135
+ | 0.266 | 34.8 | 8700 | 0.2341 |
136
+ | 0.2536 | 35.2 | 8800 | 0.2312 |
137
+ | 0.2516 | 35.6 | 8900 | 0.2288 |
138
+ | 0.2575 | 36.0 | 9000 | 0.2242 |
139
+ | 0.2358 | 36.4 | 9100 | 0.2268 |
140
+ | 0.2489 | 36.8 | 9200 | 0.2204 |
141
+ | 0.2335 | 37.2 | 9300 | 0.2196 |
142
+ | 0.2381 | 37.6 | 9400 | 0.2170 |
143
+ | 0.2428 | 38.0 | 9500 | 0.2142 |
144
+ | 0.2235 | 38.4 | 9600 | 0.2158 |
145
+ | 0.2392 | 38.8 | 9700 | 0.2126 |
146
+ | 0.2221 | 39.2 | 9800 | 0.2113 |
147
+ | 0.2247 | 39.6 | 9900 | 0.2094 |
148
+ | 0.2341 | 40.0 | 10000 | 0.2067 |
149
+ | 0.2136 | 40.4 | 10100 | 0.2065 |
150
+ | 0.2256 | 40.8 | 10200 | 0.2046 |
151
+ | 0.22 | 41.2 | 10300 | 0.2034 |
152
+ | 0.2144 | 41.6 | 10400 | 0.2032 |
153
+ | 0.224 | 42.0 | 10500 | 0.2006 |
154
+ | 0.2101 | 42.4 | 10600 | 0.2006 |
155
+ | 0.2136 | 42.8 | 10700 | 0.1992 |
156
+ | 0.2171 | 43.2 | 10800 | 0.1982 |
157
+ | 0.2077 | 43.6 | 10900 | 0.2003 |
158
+ | 0.217 | 44.0 | 11000 | 0.1979 |
159
+ | 0.2036 | 44.4 | 11100 | 0.1983 |
160
+ | 0.2083 | 44.8 | 11200 | 0.1970 |
161
+ | 0.2134 | 45.2 | 11300 | 0.1961 |
162
+ | 0.2071 | 45.6 | 11400 | 0.1943 |
163
+ | 0.2115 | 46.0 | 11500 | 0.1937 |
164
+ | 0.1997 | 46.4 | 11600 | 0.1952 |
165
+ | 0.2055 | 46.8 | 11700 | 0.1932 |
166
+ | 0.2057 | 47.2 | 11800 | 0.1926 |
167
+ | 0.2011 | 47.6 | 11900 | 0.1932 |
168
+ | 0.2092 | 48.0 | 12000 | 0.1908 |
169
+ | 0.1934 | 48.4 | 12100 | 0.1918 |
170
+ | 0.2065 | 48.8 | 12200 | 0.1915 |
171
+ | 0.2009 | 49.2 | 12300 | 0.1911 |
172
+ | 0.1995 | 49.6 | 12400 | 0.1904 |
173
+ | 0.205 | 50.0 | 12500 | 0.1889 |
174
+ | 0.1925 | 50.4 | 12600 | 0.1892 |
175
+ | 0.2013 | 50.8 | 12700 | 0.1886 |
176
+ | 0.1955 | 51.2 | 12800 | 0.1883 |
177
+ | 0.1989 | 51.6 | 12900 | 0.1880 |
178
+ | 0.1982 | 52.0 | 13000 | 0.1872 |
179
+ | 0.1872 | 52.4 | 13100 | 0.1878 |
180
+ | 0.1984 | 52.8 | 13200 | 0.1868 |
181
+ | 0.1974 | 53.2 | 13300 | 0.1871 |
182
+ | 0.188 | 53.6 | 13400 | 0.1871 |
183
+ | 0.2026 | 54.0 | 13500 | 0.1860 |
184
+ | 0.1919 | 54.4 | 13600 | 0.1863 |
185
+ | 0.1946 | 54.8 | 13700 | 0.1852 |
186
+ | 0.19 | 55.2 | 13800 | 0.1851 |
187
+ | 0.1915 | 55.6 | 13900 | 0.1852 |
188
+ | 0.1962 | 56.0 | 14000 | 0.1845 |
189
+ | 0.1922 | 56.4 | 14100 | 0.1851 |
190
+ | 0.1901 | 56.8 | 14200 | 0.1851 |
191
+ | 0.1896 | 57.2 | 14300 | 0.1839 |
192
+ | 0.1888 | 57.6 | 14400 | 0.1840 |
193
+ | 0.1921 | 58.0 | 14500 | 0.1838 |
194
+ | 0.1856 | 58.4 | 14600 | 0.1836 |
195
+ | 0.1902 | 58.8 | 14700 | 0.1832 |
196
+ | 0.1879 | 59.2 | 14800 | 0.1830 |
197
+ | 0.1868 | 59.6 | 14900 | 0.1832 |
198
+ | 0.1931 | 60.0 | 15000 | 0.1827 |
199
+ | 0.1881 | 60.4 | 15100 | 0.1830 |
200
+ | 0.1856 | 60.8 | 15200 | 0.1825 |
201
+ | 0.1876 | 61.2 | 15300 | 0.1826 |
202
+ | 0.1851 | 61.6 | 15400 | 0.1823 |
203
+ | 0.1862 | 62.0 | 15500 | 0.1821 |
204
+ | 0.1844 | 62.4 | 15600 | 0.1824 |
205
+ | 0.1879 | 62.8 | 15700 | 0.1819 |
206
+ | 0.1826 | 63.2 | 15800 | 0.1819 |
207
+ | 0.1844 | 63.6 | 15900 | 0.1818 |
208
+ | 0.1861 | 64.0 | 16000 | 0.1816 |
209
+ | 0.1815 | 64.4 | 16100 | 0.1817 |
210
+ | 0.1822 | 64.8 | 16200 | 0.1816 |
211
+ | 0.1861 | 65.2 | 16300 | 0.1816 |
212
+ | 0.1828 | 65.6 | 16400 | 0.1815 |
213
+ | 0.1852 | 66.0 | 16500 | 0.1814 |
214
+ | 0.182 | 66.4 | 16600 | 0.1814 |
215
+ | 0.1843 | 66.8 | 16700 | 0.1814 |
216
+ | 0.181 | 67.2 | 16800 | 0.1813 |
217
+ | 0.1811 | 67.6 | 16900 | 0.1813 |
218
+ | 0.1846 | 68.0 | 17000 | 0.1813 |
219
+ | 0.1801 | 68.4 | 17100 | 0.1813 |
220
+ | 0.1837 | 68.8 | 17200 | 0.1813 |
221
+ | 0.1826 | 69.2 | 17300 | 0.1812 |
222
+ | 0.1831 | 69.6 | 17400 | 0.1812 |
223
+ | 0.1801 | 70.0 | 17500 | 0.1812 |
224
+ | 0.1789 | 70.4 | 17600 | 0.1812 |
225
+ | 0.1827 | 70.8 | 17700 | 0.1812 |
226
+ | 0.1832 | 71.2 | 17800 | 0.1812 |
227
+ | 0.1818 | 71.6 | 17900 | 0.1812 |
228
+ | 0.181 | 72.0 | 18000 | 0.1812 |
229
 
230
 
231
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a73f1697cdef76e8c2e7a8b134eba284542ee34cb67682b46573ab91a620868c
3
  size 18908110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50113307082b21eac3909f0b2a73cfff8931117464adef77930b743081562b0
3
  size 18908110