sqllama-V0 / res2.txt
matt-tries-dl's picture
second pass
ce91638
Output exceeds the size limit. Open the full output data in a text editor
table: 2-1137692-1
columns: Entrant,Constructor,Chassis,Engine †,Tyre,Driver,Rounds
Q: What were the rounds on the Engine † of the Ferrari 048?
A: SELECT Rounds FROM 2-1137692-1 WHERE Engine † = 'ferrari 048'
END
table: 1-21530474-1
columns: Chassis code,Model no.,Production years,Drivetrain,Transmission,Engine type,Engine code,Region(s)
Q: Name the drivetrain for 1ur-fse for usf41
A: SELECT Drivetrain FROM 1-21530474-1 WHERE Engine code = '1UR-FSE' AND Chassis code = 'USF41'
END
table: 2-14155087-1
columns: Callsign,Area served,Frequency,Band,On-air ID,Purpose
Q: What is the Callsign with an Area of tamworth and frequency of 0 88.9?
A: SELECT Callsign FROM 2-14155087-1 WHERE Area served = 'tamworth' AND Frequency = '0 88.9'
END
table: 2-17580726-2
columns: Date,Opponent,Venue,Score,Attendance,Scorers
Q: What is the number of people in attendance when Tonbridge Angels is the opponent?
...
Q: What were the match points when Bordeaux-Bègles was eliminated from competition?
A: SELECT Match points FROM 1-27986200-3 WHERE Eliminated from competition = 'Bordeaux-Bègles'
END
/home/matt/hf/sqllama-V0/.venv/lib/python3.7/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: /opt/conda did not contain libcudart.so as expected! Searching further paths...
warn(msg)
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'LLaMATokenizer'.
The class this function is called from is 'LlamaTokenizer'.
===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 113
CUDA SETUP: Loading binary /home/matt/hf/sqllama-V0/.venv/lib/python3.7/site-packages/bitsandbytes/libbitsandbytes_cuda113.so...
True
92
0
count 56355.000000
mean 101.219519
std 21.740325
min 63.000000
25% 87.500000
50% 97.000000
75% 109.000000
max 461.000000
32084
[250/250 3:49:26, Epoch 0/1]
Step Training Loss
1 2.748800
2 2.699100
3 2.670200
4 2.600500
5 2.560100
6 2.556800
7 2.498100
8 2.515400
9 2.436100
10 2.411700
11 2.346400
12 2.276300
13 2.238000
14 2.189100
15 2.109200
16 2.058000
17 1.983900
18 1.928600
19 1.824100
20 1.794700
21 1.681200
22 1.598900
23 1.562000
24 1.527200
25 1.518700
26 1.493100
27 1.500500
28 1.464000
29 1.386900
30 1.373400
31 1.362200
32 1.360800
33 1.321000
34 1.310500
35 1.302600
36 1.256100
37 1.252500
38 1.202300
39 1.249100
40 1.188600
41 1.203200
42 1.150000
43 1.182000
44 1.192300
45 1.133100
46 1.119600
47 1.097000
48 1.142100
49 1.117200
50 1.129200
51 1.087300
52 1.098700
53 1.135400
54 1.071700
55 1.087300
56 1.051400
57 1.068300
58 1.092500
59 1.068600
60 1.072800
61 1.074000
62 1.060400
63 1.065800
64 1.075900
65 1.059500
66 1.039600
67 1.051400
68 1.049500
69 1.023800
70 1.071900
71 1.051000
72 1.034700
73 1.041600
74 1.030900
75 1.010800
76 1.019800
77 1.005000
78 1.043800
79 1.009200
80 1.017100
81 1.044600
82 1.022600
83 1.011400
84 0.996600
85 1.029900
86 0.988200
87 1.005600
88 0.986600
89 1.025300
90 1.012500
91 0.988100
92 1.001800
93 0.987100
94 1.017600
95 0.998500
96 0.966600
97 0.983700
98 0.961800
99 0.969000
100 0.989200
101 0.956400
102 0.976000
103 1.000100
104 1.001500
105 0.995900
106 0.989700
107 0.965700
108 0.968400
109 1.019600
110 1.000100
111 0.978500
112 0.978900
113 0.952600
114 0.975400
115 0.989400
116 0.968500
117 0.960100
118 0.979100
119 0.955100
120 0.934800
121 0.943600
122 0.976700
123 0.998700
124 0.930500
125 0.953500
126 0.978000
127 0.967300
128 0.929400
129 0.963100
130 0.961500
131 0.978500
132 0.937200
133 0.953400
134 0.962000
135 0.950700
136 0.925100
137 0.958800
138 0.926200
139 0.930600
140 0.968900
141 0.970400
142 0.927100
143 0.911800
144 0.953200
145 0.907100
146 0.935900
147 0.970600
148 0.920400
149 0.930200
150 0.926700
151 0.913400
152 0.926800
153 0.967200
154 0.939500
155 0.910600
156 0.926400
157 0.935400
158 0.967700
159 0.899000
160 0.916600
161 0.961600
162 0.898200
163 0.944600
164 0.935700
165 0.922500
166 0.897600
167 0.968600
168 0.927400
169 0.910900
170 0.904700
171 0.899800
172 0.896400
173 0.862100
174 0.909100
175 0.903200
176 0.958600
177 0.902500
178 0.894900
179 0.937900
180 0.900700
181 0.922300
182 0.939300
183 0.932600
184 0.913300
185 0.941700
186 0.886300
187 0.918000
188 0.884000
189 0.947400
190 0.894500
191 0.929300
192 0.877300
193 0.894300
194 0.867800
195 0.913500
196 0.908100
197 0.931200
198 0.911000
199 0.941800
200 0.913000
201 0.921800
202 0.921700
203 0.914500
204 0.910500
205 0.906600
206 0.915100
207 0.881600
208 0.884700
209 0.902900
210 0.882600
211 0.891000
212 0.914400
213 0.930400
214 0.891100
215 0.859300
216 0.891800
217 0.873000
218 0.925900
219 0.905700
220 0.921200
221 0.890200
222 0.915800
223 0.887300
224 0.898300
225 0.865600
226 0.873900
227 0.904800
228 0.917900
229 0.923400
230 0.939700
231 0.913400
232 0.873100
233 0.896700
234 0.892100
235 0.902100
236 0.927200
237 0.912900
238 0.872900
239 0.904700
240 0.879600
241 0.879800
242 0.908800
243 0.909800
244 0.838400
245 0.889200
246 0.912900
247 0.879700
248 0.910700
249 0.845400
250 0.882200
/home/matt/hf/sqllama-V0/.venv/lib/python3.7/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Output exceeds the size limit. Open the full output data in a text editor
from model
<unk>table: 1-12028543-3
columns: Season,Cup FinalDate,WinningTeam,Score,LosingTeam,Location,Cup Final Attendance
Q: Who was the winning team in the 1989 season?
A: SELECT WinningTeam FROM 1-12028543-3 WHERE Season = '1989'
END
END
END
END
expected answer
SELECT WinningTeam FROM 1-12028543-3 WHERE Season = '1989'
END
from model
<unk>table: 2-18096431-5
columns: Place,Player,Country,Score,To par
Q: What is To par, when Country is "United States", and when Player is "Mark Brooks"?
A: 18-1
END
expected answer
SELECT To par FROM 2-18096431-5 WHERE Country = 'united states' AND Player = 'mark brooks'
END
...
expected answer
SELECT Score FROM 2-17978030-6 WHERE Set 3 = '26–28'
END