Hugging Face's logo

research-dump
/
all-roberta-large-v1_wikinews_outcome_prediction_v1

Text Classification
setfit
Safetensors
sentence-transformers
roberta
generated_from_setfit_trainer
Model card Files Community
hsuvaskakoty commited on
Commit
f91c955
·
verified ·
1 Parent(s): bf6d211

Push model using huggingface_hub.

Browse files
Files changed (3) hide show
  1. README.md +8 -20
  2. model.safetensors +1 -1
  3. model_head.pkl +1 -1
README.md CHANGED
@@ -198,13 +198,13 @@ preds = model(" Interviews: Interviews WN:Story preparation/Office hours:Frank
198
  | 3 | 7 |
199
 
200
  ### Training Hyperparameters
201
- - batch_size: (8, 2)
202
  - num_epochs: (1, 16)
203
  - max_steps: -1
204
  - sampling_strategy: oversampling
205
- - num_iterations: 100
206
- - body_learning_rate: (0.0001, 0.0001)
207
- - head_learning_rate: 0.0004
208
  - loss: CosineSimilarityLoss
209
  - distance_metric: cosine_distance
210
  - margin: 0.25
@@ -219,22 +219,10 @@ preds = model(" Interviews: Interviews WN:Story preparation/Office hours:Frank
219
  ### Training Results
220
  | Epoch | Step | Training Loss | Validation Loss |
221
  |:------:|:----:|:-------------:|:---------------:|
222
- | 0.0006 | 1 | 0.3439 | - |
223
- | 0.0635 | 100 | 0.1135 | 0.3697 |
224
- | 0.1270 | 200 | 0.0552 | 0.3815 |
225
- | 0.1905 | 300 | 0.0432 | 0.3861 |
226
- | 0.2540 | 400 | 0.0309 | 0.3646 |
227
- | 0.3175 | 500 | 0.0403 | 0.2130 |
228
- | 0.3810 | 600 | 0.036 | 0.2965 |
229
- | 0.4444 | 700 | 0.1352 | 0.3006 |
230
- | 0.5079 | 800 | 0.4312 | 0.5 |
231
- | 0.5714 | 900 | 0.3482 | 0.5 |
232
- | 0.6349 | 1000 | 0.355 | 0.5 |
233
- | 0.6984 | 1100 | 0.3365 | 0.5 |
234
- | 0.7619 | 1200 | 0.3177 | 0.5 |
235
- | 0.8254 | 1300 | 0.3374 | 0.5 |
236
- | 0.8889 | 1400 | 0.31 | 0.5 |
237
- | 0.9524 | 1500 | 0.337 | 0.5 |
238
 
239
  ### Framework Versions
240
  - Python: 3.10.12
 
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: 10
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
  ### Training Results
220
  | Epoch | Step | Training Loss | Validation Loss |
221
  |:------:|:----:|:-------------:|:---------------:|
222
+ | 0.0032 | 1 | 0.6701 | - |
223
+ | 0.3175 | 100 | 0.1951 | 0.2339 |
224
+ | 0.6349 | 200 | 0.0536 | 0.2513 |
225
+ | 0.9524 | 300 | 0.0228 | 0.2661 |
 
 
 
 
 
 
 
 
 
 
 
 
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 sha256:2be0fc28a2e184aac7cb4820bee0390f9461e842625bd393a5f3f7472d659052
3
  size 1421483904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f195c11a542b42f51fe864b5825bfd37e5cb443f25eaa1da5f7c5363281f02b7
3
  size 1421483904
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7de3106dfbf8deb461a76d201d9874158fe0431ca7920c69d64478541daee1f0
3
  size 33655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d995994ae42710059e9d6b767637f0d68f02d68211232691dc76a0552e6b46
3
  size 33655