Add SetFit model
Browse files- README.md +139 -15
- model.safetensors +1 -1
- model_head.pkl +1 -1
README.md
CHANGED
@@ -133,7 +133,7 @@ preds = model("Climate change is causing a significant rise in sea levels.")
|
|
133 |
|
134 |
### Training Hyperparameters
|
135 |
- batch_size: (16, 16)
|
136 |
-
- num_epochs: (
|
137 |
- max_steps: -1
|
138 |
- sampling_strategy: oversampling
|
139 |
- num_iterations: 20
|
@@ -152,20 +152,144 @@ preds = model("Climate change is causing a significant rise in sea levels.")
|
|
152 |
### Training Results
|
153 |
| Epoch | Step | Training Loss | Validation Loss |
|
154 |
|:------:|:----:|:-------------:|:---------------:|
|
155 |
-
| 0.0015 | 1 | 0.
|
156 |
-
| 0.0727 | 50 | 0.
|
157 |
-
| 0.1453 | 100 | 0.
|
158 |
-
| 0.2180 | 150 | 0.
|
159 |
-
| 0.2907 | 200 | 0.
|
160 |
-
| 0.3634 | 250 | 0.
|
161 |
-
| 0.4360 | 300 | 0.
|
162 |
-
| 0.5087 | 350 | 0.
|
163 |
-
| 0.5814 | 400 | 0.
|
164 |
-
| 0.6541 | 450 | 0.
|
165 |
-
| 0.7267 | 500 | 0.
|
166 |
-
| 0.7994 | 550 | 0.
|
167 |
-
| 0.8721 | 600 | 0.
|
168 |
-
| 0.9448 | 650 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
169 |
|
170 |
### Framework Versions
|
171 |
- Python: 3.10.12
|
|
|
133 |
|
134 |
### Training Hyperparameters
|
135 |
- batch_size: (16, 16)
|
136 |
+
- num_epochs: (10, 10)
|
137 |
- max_steps: -1
|
138 |
- sampling_strategy: oversampling
|
139 |
- num_iterations: 20
|
|
|
152 |
### Training Results
|
153 |
| Epoch | Step | Training Loss | Validation Loss |
|
154 |
|:------:|:----:|:-------------:|:---------------:|
|
155 |
+
| 0.0015 | 1 | 0.2748 | - |
|
156 |
+
| 0.0727 | 50 | 0.2537 | - |
|
157 |
+
| 0.1453 | 100 | 0.1734 | - |
|
158 |
+
| 0.2180 | 150 | 0.1086 | - |
|
159 |
+
| 0.2907 | 200 | 0.062 | - |
|
160 |
+
| 0.3634 | 250 | 0.046 | - |
|
161 |
+
| 0.4360 | 300 | 0.017 | - |
|
162 |
+
| 0.5087 | 350 | 0.0104 | - |
|
163 |
+
| 0.5814 | 400 | 0.006 | - |
|
164 |
+
| 0.6541 | 450 | 0.0021 | - |
|
165 |
+
| 0.7267 | 500 | 0.0052 | - |
|
166 |
+
| 0.7994 | 550 | 0.0045 | - |
|
167 |
+
| 0.8721 | 600 | 0.0012 | - |
|
168 |
+
| 0.9448 | 650 | 0.0007 | - |
|
169 |
+
| 1.0174 | 700 | 0.0006 | - |
|
170 |
+
| 1.0901 | 750 | 0.0006 | - |
|
171 |
+
| 1.1628 | 800 | 0.0006 | - |
|
172 |
+
| 1.2355 | 850 | 0.0005 | - |
|
173 |
+
| 1.3081 | 900 | 0.0004 | - |
|
174 |
+
| 1.3808 | 950 | 0.0003 | - |
|
175 |
+
| 1.4535 | 1000 | 0.0004 | - |
|
176 |
+
| 1.5262 | 1050 | 0.0004 | - |
|
177 |
+
| 1.5988 | 1100 | 0.0004 | - |
|
178 |
+
| 1.6715 | 1150 | 0.0003 | - |
|
179 |
+
| 1.7442 | 1200 | 0.0002 | - |
|
180 |
+
| 1.8169 | 1250 | 0.0002 | - |
|
181 |
+
| 1.8895 | 1300 | 0.0005 | - |
|
182 |
+
| 1.9622 | 1350 | 0.0004 | - |
|
183 |
+
| 2.0349 | 1400 | 0.0002 | - |
|
184 |
+
| 2.1076 | 1450 | 0.0004 | - |
|
185 |
+
| 2.1802 | 1500 | 0.0002 | - |
|
186 |
+
| 2.2529 | 1550 | 0.0002 | - |
|
187 |
+
| 2.3256 | 1600 | 0.0004 | - |
|
188 |
+
| 2.3983 | 1650 | 0.0002 | - |
|
189 |
+
| 2.4709 | 1700 | 0.0002 | - |
|
190 |
+
| 2.5436 | 1750 | 0.0002 | - |
|
191 |
+
| 2.6163 | 1800 | 0.0002 | - |
|
192 |
+
| 2.6890 | 1850 | 0.0002 | - |
|
193 |
+
| 2.7616 | 1900 | 0.0003 | - |
|
194 |
+
| 2.8343 | 1950 | 0.0001 | - |
|
195 |
+
| 2.9070 | 2000 | 0.0002 | - |
|
196 |
+
| 2.9797 | 2050 | 0.0002 | - |
|
197 |
+
| 3.0523 | 2100 | 0.0003 | - |
|
198 |
+
| 3.125 | 2150 | 0.0002 | - |
|
199 |
+
| 3.1977 | 2200 | 0.0002 | - |
|
200 |
+
| 3.2703 | 2250 | 0.0001 | - |
|
201 |
+
| 3.3430 | 2300 | 0.0002 | - |
|
202 |
+
| 3.4157 | 2350 | 0.0002 | - |
|
203 |
+
| 3.4884 | 2400 | 0.0002 | - |
|
204 |
+
| 3.5610 | 2450 | 0.0001 | - |
|
205 |
+
| 3.6337 | 2500 | 0.0001 | - |
|
206 |
+
| 3.7064 | 2550 | 0.0001 | - |
|
207 |
+
| 3.7791 | 2600 | 0.0001 | - |
|
208 |
+
| 3.8517 | 2650 | 0.0001 | - |
|
209 |
+
| 3.9244 | 2700 | 0.0001 | - |
|
210 |
+
| 3.9971 | 2750 | 0.0001 | - |
|
211 |
+
| 4.0698 | 2800 | 0.0001 | - |
|
212 |
+
| 4.1424 | 2850 | 0.0001 | - |
|
213 |
+
| 4.2151 | 2900 | 0.0001 | - |
|
214 |
+
| 4.2878 | 2950 | 0.0001 | - |
|
215 |
+
| 4.3605 | 3000 | 0.0001 | - |
|
216 |
+
| 4.4331 | 3050 | 0.0001 | - |
|
217 |
+
| 4.5058 | 3100 | 0.0001 | - |
|
218 |
+
| 4.5785 | 3150 | 0.0001 | - |
|
219 |
+
| 4.6512 | 3200 | 0.0001 | - |
|
220 |
+
| 4.7238 | 3250 | 0.0001 | - |
|
221 |
+
| 4.7965 | 3300 | 0.0001 | - |
|
222 |
+
| 4.8692 | 3350 | 0.0001 | - |
|
223 |
+
| 4.9419 | 3400 | 0.0001 | - |
|
224 |
+
| 5.0145 | 3450 | 0.0001 | - |
|
225 |
+
| 5.0872 | 3500 | 0.0001 | - |
|
226 |
+
| 5.1599 | 3550 | 0.0001 | - |
|
227 |
+
| 5.2326 | 3600 | 0.0001 | - |
|
228 |
+
| 5.3052 | 3650 | 0.0001 | - |
|
229 |
+
| 5.3779 | 3700 | 0.0001 | - |
|
230 |
+
| 5.4506 | 3750 | 0.0001 | - |
|
231 |
+
| 5.5233 | 3800 | 0.0001 | - |
|
232 |
+
| 5.5959 | 3850 | 0.0001 | - |
|
233 |
+
| 5.6686 | 3900 | 0.0001 | - |
|
234 |
+
| 5.7413 | 3950 | 0.0001 | - |
|
235 |
+
| 5.8140 | 4000 | 0.0001 | - |
|
236 |
+
| 5.8866 | 4050 | 0.0001 | - |
|
237 |
+
| 5.9593 | 4100 | 0.0001 | - |
|
238 |
+
| 6.0320 | 4150 | 0.0001 | - |
|
239 |
+
| 6.1047 | 4200 | 0.0001 | - |
|
240 |
+
| 6.1773 | 4250 | 0.0001 | - |
|
241 |
+
| 6.25 | 4300 | 0.0001 | - |
|
242 |
+
| 6.3227 | 4350 | 0.0001 | - |
|
243 |
+
| 6.3953 | 4400 | 0.0001 | - |
|
244 |
+
| 6.4680 | 4450 | 0.0001 | - |
|
245 |
+
| 6.5407 | 4500 | 0.0001 | - |
|
246 |
+
| 6.6134 | 4550 | 0.0001 | - |
|
247 |
+
| 6.6860 | 4600 | 0.0001 | - |
|
248 |
+
| 6.7587 | 4650 | 0.0001 | - |
|
249 |
+
| 6.8314 | 4700 | 0.0001 | - |
|
250 |
+
| 6.9041 | 4750 | 0.0001 | - |
|
251 |
+
| 6.9767 | 4800 | 0.0 | - |
|
252 |
+
| 7.0494 | 4850 | 0.0001 | - |
|
253 |
+
| 7.1221 | 4900 | 0.0001 | - |
|
254 |
+
| 7.1948 | 4950 | 0.0001 | - |
|
255 |
+
| 7.2674 | 5000 | 0.0001 | - |
|
256 |
+
| 7.3401 | 5050 | 0.0001 | - |
|
257 |
+
| 7.4128 | 5100 | 0.0001 | - |
|
258 |
+
| 7.4855 | 5150 | 0.0001 | - |
|
259 |
+
| 7.5581 | 5200 | 0.0001 | - |
|
260 |
+
| 7.6308 | 5250 | 0.0001 | - |
|
261 |
+
| 7.7035 | 5300 | 0.0001 | - |
|
262 |
+
| 7.7762 | 5350 | 0.0001 | - |
|
263 |
+
| 7.8488 | 5400 | 0.0001 | - |
|
264 |
+
| 7.9215 | 5450 | 0.0001 | - |
|
265 |
+
| 7.9942 | 5500 | 0.0 | - |
|
266 |
+
| 8.0669 | 5550 | 0.0001 | - |
|
267 |
+
| 8.1395 | 5600 | 0.0001 | - |
|
268 |
+
| 8.2122 | 5650 | 0.0001 | - |
|
269 |
+
| 8.2849 | 5700 | 0.0 | - |
|
270 |
+
| 8.3576 | 5750 | 0.0001 | - |
|
271 |
+
| 8.4302 | 5800 | 0.0001 | - |
|
272 |
+
| 8.5029 | 5850 | 0.0001 | - |
|
273 |
+
| 8.5756 | 5900 | 0.0001 | - |
|
274 |
+
| 8.6483 | 5950 | 0.0001 | - |
|
275 |
+
| 8.7209 | 6000 | 0.0001 | - |
|
276 |
+
| 8.7936 | 6050 | 0.0001 | - |
|
277 |
+
| 8.8663 | 6100 | 0.0 | - |
|
278 |
+
| 8.9390 | 6150 | 0.0 | - |
|
279 |
+
| 9.0116 | 6200 | 0.0001 | - |
|
280 |
+
| 9.0843 | 6250 | 0.0001 | - |
|
281 |
+
| 9.1570 | 6300 | 0.0 | - |
|
282 |
+
| 9.2297 | 6350 | 0.0 | - |
|
283 |
+
| 9.3023 | 6400 | 0.0 | - |
|
284 |
+
| 9.375 | 6450 | 0.0001 | - |
|
285 |
+
| 9.4477 | 6500 | 0.0001 | - |
|
286 |
+
| 9.5203 | 6550 | 0.0001 | - |
|
287 |
+
| 9.5930 | 6600 | 0.0001 | - |
|
288 |
+
| 9.6657 | 6650 | 0.0001 | - |
|
289 |
+
| 9.7384 | 6700 | 0.0001 | - |
|
290 |
+
| 9.8110 | 6750 | 0.0001 | - |
|
291 |
+
| 9.8837 | 6800 | 0.0001 | - |
|
292 |
+
| 9.9564 | 6850 | 0.0 | - |
|
293 |
|
294 |
### Framework Versions
|
295 |
- Python: 3.10.12
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437967672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:961b45a0c6ea5c0d470e3e4cf9f4ce05ac1adf1c2c7aed84ea5914712ffef4c3
|
3 |
size 437967672
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 75287
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fde232400d37cd4c504bfd6f32a75b7c864969cfc24261146a5761c0ca5c4bfc
|
3 |
size 75287
|