Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- Severian/Internal-Knowledge-Map
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
---
|
7 |
+
## This model has been trained for 2 epochs using Unsloth on the Internal Knowledge Map dataset.
|
8 |
+
|
9 |
+
```
|
10 |
+
==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1
|
11 |
+
\\ /| Num examples = 3,555 | Num Epochs = 2
|
12 |
+
O^O/ \_/ \ Batch size per device = 4 | Gradient Accumulation steps = 4
|
13 |
+
\ / Total batch size = 16 | Total steps = 444
|
14 |
+
"-____-" Number of trainable parameters = 83,886,080
|
15 |
+
[444/444 25:17, Epoch 1/2]
|
16 |
+
Step Training Loss
|
17 |
+
1 3.133100
|
18 |
+
2 3.086100
|
19 |
+
3 3.045000
|
20 |
+
4 3.075100
|
21 |
+
5 3.086000
|
22 |
+
6 3.042100
|
23 |
+
7 3.018100
|
24 |
+
8 3.036100
|
25 |
+
9 2.986900
|
26 |
+
10 2.990600
|
27 |
+
11 2.949400
|
28 |
+
12 2.933200
|
29 |
+
13 2.899800
|
30 |
+
14 2.885900
|
31 |
+
15 2.928400
|
32 |
+
16 2.855700
|
33 |
+
17 2.805000
|
34 |
+
18 2.787100
|
35 |
+
19 2.807400
|
36 |
+
20 2.765600
|
37 |
+
21 2.794500
|
38 |
+
22 2.758400
|
39 |
+
23 2.753700
|
40 |
+
24 2.757400
|
41 |
+
25 2.669900
|
42 |
+
26 2.653900
|
43 |
+
27 2.708400
|
44 |
+
28 2.705100
|
45 |
+
29 2.695900
|
46 |
+
30 2.590100
|
47 |
+
31 2.615900
|
48 |
+
32 2.577500
|
49 |
+
33 2.571700
|
50 |
+
34 2.596400
|
51 |
+
35 2.570700
|
52 |
+
36 2.558600
|
53 |
+
37 2.524600
|
54 |
+
38 2.640500
|
55 |
+
39 2.506400
|
56 |
+
40 2.521900
|
57 |
+
41 2.519800
|
58 |
+
42 2.459700
|
59 |
+
43 2.388900
|
60 |
+
44 2.425400
|
61 |
+
45 2.387800
|
62 |
+
46 2.360600
|
63 |
+
47 2.376000
|
64 |
+
48 2.391600
|
65 |
+
49 2.321100
|
66 |
+
50 2.357600
|
67 |
+
51 2.325800
|
68 |
+
52 2.311800
|
69 |
+
53 2.255600
|
70 |
+
54 2.313900
|
71 |
+
55 2.200900
|
72 |
+
56 2.250800
|
73 |
+
57 2.242500
|
74 |
+
58 2.173000
|
75 |
+
59 2.261000
|
76 |
+
60 2.150500
|
77 |
+
61 2.162500
|
78 |
+
62 2.086800
|
79 |
+
63 2.178500
|
80 |
+
64 2.085600
|
81 |
+
65 2.068800
|
82 |
+
66 2.146500
|
83 |
+
67 2.001800
|
84 |
+
68 2.037600
|
85 |
+
69 2.009000
|
86 |
+
70 1.983300
|
87 |
+
71 1.931400
|
88 |
+
72 1.990400
|
89 |
+
73 1.944700
|
90 |
+
74 1.972700
|
91 |
+
75 2.002400
|
92 |
+
76 2.022400
|
93 |
+
77 1.900500
|
94 |
+
78 1.843100
|
95 |
+
79 1.887400
|
96 |
+
80 1.970700
|
97 |
+
81 1.820800
|
98 |
+
82 1.853900
|
99 |
+
83 1.744200
|
100 |
+
84 1.831400
|
101 |
+
85 1.768900
|
102 |
+
86 2.006100
|
103 |
+
87 1.681900
|
104 |
+
88 1.750000
|
105 |
+
89 1.628100
|
106 |
+
90 1.586900
|
107 |
+
91 1.567900
|
108 |
+
92 1.554500
|
109 |
+
93 1.830800
|
110 |
+
94 1.512500
|
111 |
+
95 1.592400
|
112 |
+
96 1.518600
|
113 |
+
97 1.593700
|
114 |
+
98 1.454100
|
115 |
+
99 1.497200
|
116 |
+
100 1.319700
|
117 |
+
101 1.363300
|
118 |
+
102 1.414300
|
119 |
+
103 1.343900
|
120 |
+
104 1.363500
|
121 |
+
105 1.449000
|
122 |
+
106 1.510100
|
123 |
+
107 1.268600
|
124 |
+
108 1.156600
|
125 |
+
109 1.075100
|
126 |
+
110 1.137200
|
127 |
+
111 1.020700
|
128 |
+
112 0.993600
|
129 |
+
113 1.195200
|
130 |
+
114 0.993300
|
131 |
+
115 1.072100
|
132 |
+
116 1.116900
|
133 |
+
117 1.184100
|
134 |
+
118 1.102600
|
135 |
+
119 1.083800
|
136 |
+
120 0.852100
|
137 |
+
121 1.023600
|
138 |
+
122 1.051200
|
139 |
+
123 1.270500
|
140 |
+
124 0.856200
|
141 |
+
125 1.089500
|
142 |
+
126 0.686800
|
143 |
+
127 0.800300
|
144 |
+
128 0.662400
|
145 |
+
129 0.688000
|
146 |
+
130 0.554400
|
147 |
+
131 0.737200
|
148 |
+
132 0.802900
|
149 |
+
133 0.538200
|
150 |
+
134 0.562000
|
151 |
+
135 0.516800
|
152 |
+
136 0.497200
|
153 |
+
137 0.611100
|
154 |
+
138 0.581200
|
155 |
+
139 0.442000
|
156 |
+
140 0.355200
|
157 |
+
141 0.473200
|
158 |
+
142 0.559600
|
159 |
+
143 0.683700
|
160 |
+
144 0.355300
|
161 |
+
145 0.343000
|
162 |
+
146 0.525300
|
163 |
+
147 0.442100
|
164 |
+
148 0.452900
|
165 |
+
149 0.478800
|
166 |
+
150 0.311300
|
167 |
+
151 0.535500
|
168 |
+
152 0.552600
|
169 |
+
153 0.252800
|
170 |
+
154 0.479200
|
171 |
+
155 0.539500
|
172 |
+
156 0.477200
|
173 |
+
157 0.283000
|
174 |
+
158 0.265100
|
175 |
+
159 0.352000
|
176 |
+
160 0.268500
|
177 |
+
161 0.711900
|
178 |
+
162 0.411300
|
179 |
+
163 0.377100
|
180 |
+
164 0.360500
|
181 |
+
165 0.311000
|
182 |
+
166 0.490800
|
183 |
+
167 0.269300
|
184 |
+
168 0.409600
|
185 |
+
169 0.147800
|
186 |
+
170 0.144600
|
187 |
+
171 0.223600
|
188 |
+
172 0.615300
|
189 |
+
173 0.218900
|
190 |
+
174 0.136400
|
191 |
+
175 0.133200
|
192 |
+
176 0.263200
|
193 |
+
177 0.363600
|
194 |
+
178 0.127700
|
195 |
+
179 0.238900
|
196 |
+
180 0.276200
|
197 |
+
181 0.306400
|
198 |
+
182 0.122000
|
199 |
+
183 0.302400
|
200 |
+
184 0.049500
|
201 |
+
185 0.406500
|
202 |
+
186 0.246400
|
203 |
+
187 0.429900
|
204 |
+
188 0.216900
|
205 |
+
189 0.320700
|
206 |
+
190 0.472800
|
207 |
+
191 0.159900
|
208 |
+
192 0.287500
|
209 |
+
193 0.334400
|
210 |
+
194 0.136100
|
211 |
+
195 0.233400
|
212 |
+
196 0.164100
|
213 |
+
197 0.196100
|
214 |
+
198 0.153300
|
215 |
+
199 0.251000
|
216 |
+
200 0.087500
|
217 |
+
201 0.083000
|
218 |
+
202 0.104900
|
219 |
+
203 0.157700
|
220 |
+
204 0.080300
|
221 |
+
205 0.280500
|
222 |
+
206 0.372100
|
223 |
+
207 0.150400
|
224 |
+
208 0.112900
|
225 |
+
209 0.265400
|
226 |
+
210 0.075800
|
227 |
+
211 0.082700
|
228 |
+
212 0.343000
|
229 |
+
213 0.081900
|
230 |
+
214 0.360400
|
231 |
+
215 0.261200
|
232 |
+
216 0.072000
|
233 |
+
217 0.249400
|
234 |
+
218 0.211600
|
235 |
+
219 0.304500
|
236 |
+
220 0.289300
|
237 |
+
221 0.209400
|
238 |
+
222 0.067800
|
239 |
+
223 0.144500
|
240 |
+
224 0.078600
|
241 |
+
225 0.143500
|
242 |
+
226 0.377800
|
243 |
+
227 0.222300
|
244 |
+
228 0.279800
|
245 |
+
229 0.063400
|
246 |
+
230 0.120400
|
247 |
+
231 0.214000
|
248 |
+
232 0.121600
|
249 |
+
233 0.360400
|
250 |
+
234 0.168600
|
251 |
+
235 0.206300
|
252 |
+
236 0.075800
|
253 |
+
237 0.033800
|
254 |
+
238 0.059700
|
255 |
+
239 0.227500
|
256 |
+
240 0.212800
|
257 |
+
241 0.186600
|
258 |
+
242 0.223400
|
259 |
+
243 0.033600
|
260 |
+
244 0.204600
|
261 |
+
245 0.033600
|
262 |
+
246 0.600600
|
263 |
+
247 0.105800
|
264 |
+
248 0.198400
|
265 |
+
249 0.255100
|
266 |
+
250 0.226500
|
267 |
+
251 0.104700
|
268 |
+
252 0.128700
|
269 |
+
253 0.088300
|
270 |
+
254 0.158600
|
271 |
+
255 0.033200
|
272 |
+
256 0.261900
|
273 |
+
257 0.320500
|
274 |
+
258 0.140100
|
275 |
+
259 0.266200
|
276 |
+
260 0.087300
|
277 |
+
261 0.085400
|
278 |
+
262 0.240300
|
279 |
+
263 0.308800
|
280 |
+
264 0.033000
|
281 |
+
265 0.120300
|
282 |
+
266 0.156400
|
283 |
+
267 0.083200
|
284 |
+
268 0.199200
|
285 |
+
269 0.052000
|
286 |
+
270 0.116600
|
287 |
+
271 0.144000
|
288 |
+
272 0.237700
|
289 |
+
273 0.214700
|
290 |
+
274 0.180600
|
291 |
+
275 0.334200
|
292 |
+
276 0.032800
|
293 |
+
277 0.101700
|
294 |
+
278 0.078800
|
295 |
+
279 0.163300
|
296 |
+
280 0.032700
|
297 |
+
281 0.098000
|
298 |
+
282 0.126500
|
299 |
+
283 0.032600
|
300 |
+
284 0.110000
|
301 |
+
285 0.063500
|
302 |
+
286 0.382900
|
303 |
+
287 0.193200
|
304 |
+
288 0.264400
|
305 |
+
289 0.119000
|
306 |
+
290 0.189500
|
307 |
+
291 0.274900
|
308 |
+
292 0.102100
|
309 |
+
293 0.101000
|
310 |
+
294 0.197300
|
311 |
+
295 0.083300
|
312 |
+
296 0.153000
|
313 |
+
297 0.057500
|
314 |
+
298 0.335000
|
315 |
+
299 0.150400
|
316 |
+
300 0.044300
|
317 |
+
301 0.317200
|
318 |
+
302 0.073700
|
319 |
+
303 0.217200
|
320 |
+
304 0.043100
|
321 |
+
305 0.061800
|
322 |
+
306 0.100500
|
323 |
+
307 0.088800
|
324 |
+
308 0.153700
|
325 |
+
309 0.157200
|
326 |
+
310 0.086700
|
327 |
+
311 0.114000
|
328 |
+
312 0.077200
|
329 |
+
313 0.092000
|
330 |
+
314 0.167700
|
331 |
+
315 0.237000
|
332 |
+
316 0.215800
|
333 |
+
317 0.058100
|
334 |
+
318 0.077200
|
335 |
+
319 0.162900
|
336 |
+
320 0.122400
|
337 |
+
321 0.171100
|
338 |
+
322 0.142000
|
339 |
+
323 0.032100
|
340 |
+
324 0.098500
|
341 |
+
325 0.059400
|
342 |
+
326 0.038500
|
343 |
+
327 0.089000
|
344 |
+
328 0.123200
|
345 |
+
329 0.190200
|
346 |
+
330 0.051700
|
347 |
+
331 0.087400
|
348 |
+
332 0.198400
|
349 |
+
333 0.073500
|
350 |
+
334 0.073100
|
351 |
+
335 0.176600
|
352 |
+
336 0.186100
|
353 |
+
337 0.183000
|
354 |
+
338 0.106100
|
355 |
+
339 0.064700
|
356 |
+
340 0.136500
|
357 |
+
341 0.085600
|
358 |
+
342 0.115400
|
359 |
+
343 0.106000
|
360 |
+
344 0.065800
|
361 |
+
345 0.143100
|
362 |
+
346 0.137300
|
363 |
+
347 0.251000
|
364 |
+
348 0.067200
|
365 |
+
349 0.181600
|
366 |
+
350 0.084600
|
367 |
+
351 0.108800
|
368 |
+
352 0.114600
|
369 |
+
353 0.043200
|
370 |
+
354 0.241500
|
371 |
+
355 0.031800
|
372 |
+
356 0.150500
|
373 |
+
357 0.063700
|
374 |
+
358 0.036100
|
375 |
+
359 0.158100
|
376 |
+
360 0.045700
|
377 |
+
361 0.120200
|
378 |
+
362 0.035800
|
379 |
+
363 0.050200
|
380 |
+
364 0.031700
|
381 |
+
365 0.044000
|
382 |
+
366 0.035400
|
383 |
+
367 0.035300
|
384 |
+
368 0.162500
|
385 |
+
369 0.044400
|
386 |
+
370 0.132700
|
387 |
+
371 0.054300
|
388 |
+
372 0.049100
|
389 |
+
373 0.031500
|
390 |
+
374 0.038000
|
391 |
+
375 0.084900
|
392 |
+
376 0.059000
|
393 |
+
377 0.034500
|
394 |
+
378 0.049200
|
395 |
+
379 0.058100
|
396 |
+
380 0.122700
|
397 |
+
381 0.096400
|
398 |
+
382 0.034300
|
399 |
+
383 0.071700
|
400 |
+
384 0.059300
|
401 |
+
385 0.048500
|
402 |
+
386 0.051000
|
403 |
+
387 0.063000
|
404 |
+
388 0.131400
|
405 |
+
389 0.031100
|
406 |
+
390 0.076700
|
407 |
+
391 0.072200
|
408 |
+
392 0.146300
|
409 |
+
393 0.031000
|
410 |
+
394 0.031000
|
411 |
+
395 0.099200
|
412 |
+
396 0.049000
|
413 |
+
397 0.104100
|
414 |
+
398 0.087400
|
415 |
+
399 0.097100
|
416 |
+
400 0.069800
|
417 |
+
401 0.034900
|
418 |
+
402 0.035300
|
419 |
+
403 0.057400
|
420 |
+
404 0.058000
|
421 |
+
405 0.041100
|
422 |
+
406 0.083400
|
423 |
+
407 0.090000
|
424 |
+
408 0.098600
|
425 |
+
409 0.106100
|
426 |
+
410 0.052600
|
427 |
+
411 0.057800
|
428 |
+
412 0.085500
|
429 |
+
413 0.061600
|
430 |
+
414 0.034000
|
431 |
+
415 0.079700
|
432 |
+
416 0.036800
|
433 |
+
417 0.034600
|
434 |
+
418 0.073800
|
435 |
+
419 0.047900
|
436 |
+
420 0.041100
|
437 |
+
421 0.046300
|
438 |
+
422 0.030600
|
439 |
+
423 0.064200
|
440 |
+
424 0.045900
|
441 |
+
425 0.045600
|
442 |
+
426 0.032900
|
443 |
+
427 0.048800
|
444 |
+
428 0.041700
|
445 |
+
429 0.048200
|
446 |
+
430 0.035800
|
447 |
+
431 0.058200
|
448 |
+
432 0.044100
|
449 |
+
433 0.033400
|
450 |
+
434 0.046100
|
451 |
+
435 0.042800
|
452 |
+
436 0.034900
|
453 |
+
437 0.045800
|
454 |
+
438 0.055800
|
455 |
+
439 0.030300
|
456 |
+
440 0.059600
|
457 |
+
441 0.030200
|
458 |
+
442 0.052700
|
459 |
+
443 0.030200
|
460 |
+
444 0.035600
|
461 |
+
```
|