Hugging Face's logo

research-dump
/
bge-small-en-v1.5_wikinews_outcome_prediction_v1

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Model card Files Community
hsuvaskakoty commited on
Commit
944cad7
•
1 Parent(s): 49ad88d

Push model using huggingface_hub.

Browse files
Files changed (3) hide show
  1. README.md +8 -36
  2. model.safetensors +1 -1
  3. model_head.pkl +1 -1
README.md CHANGED
@@ -198,13 +198,12 @@ preds = model(" Interviews: Interviews WN:Story preparation/Office hours:Frank
198
  | 3 | 7 |
199
 
200
  ### Training Hyperparameters
201
- - batch_size: (4, 2)
202
- - num_epochs: (1, 16)
203
  - max_steps: -1
204
  - sampling_strategy: oversampling
205
- - num_iterations: 100
206
  - body_learning_rate: (1e-05, 1e-05)
207
- - head_learning_rate: 5e-05
208
  - loss: CosineSimilarityLoss
209
  - distance_metric: cosine_distance
210
  - margin: 0.25
@@ -219,38 +218,11 @@ preds = model(" Interviews: Interviews WN:Story preparation/Office hours:Frank
219
  ### Training Results
220
  | Epoch | Step | Training Loss | Validation Loss |
221
  |:------:|:----:|:-------------:|:---------------:|
222
- | 0.0003 | 1 | 0.2846 | - |
223
- | 0.0317 | 100 | 0.2624 | 0.2114 |
224
- | 0.0635 | 200 | 0.2433 | 0.2166 |
225
- | 0.0952 | 300 | 0.2075 | 0.2141 |
226
- | 0.1270 | 400 | 0.1335 | 0.3088 |
227
- | 0.1587 | 500 | 0.0647 | 0.3611 |
228
- | 0.1905 | 600 | 0.0357 | 0.4090 |
229
- | 0.2222 | 700 | 0.0239 | 0.4250 |
230
- | 0.2540 | 800 | 0.0117 | 0.4209 |
231
- | 0.2857 | 900 | 0.0176 | 0.4442 |
232
- | 0.3175 | 1000 | 0.0106 | 0.4505 |
233
- | 0.3492 | 1100 | 0.0059 | 0.4447 |
234
- | 0.3810 | 1200 | 0.0047 | 0.4502 |
235
- | 0.4127 | 1300 | 0.0056 | 0.4520 |
236
- | 0.4444 | 1400 | 0.0052 | 0.4549 |
237
- | 0.4762 | 1500 | 0.004 | 0.4545 |
238
- | 0.5079 | 1600 | 0.0021 | 0.4501 |
239
- | 0.5397 | 1700 | 0.0024 | 0.4509 |
240
- | 0.5714 | 1800 | 0.0024 | 0.4570 |
241
- | 0.6032 | 1900 | 0.0018 | 0.4546 |
242
- | 0.6349 | 2000 | 0.0017 | 0.4571 |
243
- | 0.6667 | 2100 | 0.0017 | 0.4528 |
244
- | 0.6984 | 2200 | 0.0013 | 0.4610 |
245
- | 0.7302 | 2300 | 0.0014 | 0.4538 |
246
- | 0.7619 | 2400 | 0.0015 | 0.4605 |
247
- | 0.7937 | 2500 | 0.0012 | 0.4594 |
248
- | 0.8254 | 2600 | 0.0013 | 0.4600 |
249
- | 0.8571 | 2700 | 0.0012 | 0.4601 |
250
- | 0.8889 | 2800 | 0.0011 | 0.4590 |
251
- | 0.9206 | 2900 | 0.001 | 0.4589 |
252
- | 0.9524 | 3000 | 0.0012 | 0.4603 |
253
- | 0.9841 | 3100 | 0.001 | 0.4595 |
254
 
255
  ### Framework Versions
256
  - Python: 3.10.12
 
198
  | 3 | 7 |
199
 
200
  ### Training Hyperparameters
201
+ - batch_size: (8, 2)
202
+ - num_epochs: (5, 5)
203
  - max_steps: -1
204
  - sampling_strategy: oversampling
 
205
  - body_learning_rate: (1e-05, 1e-05)
206
+ - head_learning_rate: 1e-05
207
  - loss: CosineSimilarityLoss
208
  - distance_metric: cosine_distance
209
  - margin: 0.25
 
218
  ### Training Results
219
  | Epoch | Step | Training Loss | Validation Loss |
220
  |:------:|:----:|:-------------:|:---------------:|
221
+ | 0.0035 | 1 | 0.1819 | - |
222
+ | 1.0381 | 300 | 0.1851 | 0.3881 |
223
+ | 2.0761 | 600 | 0.0269 | 0.4134 |
224
+ | 3.1142 | 900 | 0.0077 | 0.4345 |
225
+ | 4.1522 | 1200 | 0.005 | 0.4377 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
226
 
227
  ### Framework Versions
228
  - Python: 3.10.12
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f28c04cc5087911e90801cc0e4efe60def175173817f09e52474cd4893315b5
3
  size 133462128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fff781c8b433ef8156abbab6389370a998431e78bba555114a83726876223c
3
  size 133462128
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e99e5f5eb6859412fe50e314daa6328bd6fc0374a9816e3092f8252cd8c81348
3
  size 13175
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34e42a9f1da8845971f1e3a5812ff6bd8fdb8476b347ea7f1bcd072b67735d53
3
  size 13175