research-dump
/

bge-small-en-v1.5_wikinews_outcome_prediction_v1

Text Classification

sentence-transformers

generated_from_setfit_trainer

Model card Files Files and versions Community

hsuvaskakoty commited on about 20 hours ago

Commit

702248d

•

1 Parent(s): ca924a6

Push model using huggingface_hub.

Files changed (3) hide show

README.md +11 -11
model.safetensors +1 -1
model_head.pkl +1 -1

README.md CHANGED Viewed

@@ -202,8 +202,8 @@ preds = model("  Interviews: Interviews WN:Story preparation/Office hours:Frank
 - num_epochs: (10, 10)
 - max_steps: -1
 - sampling_strategy: oversampling
-- body_learning_rate: (0.01, 0.01)
-- head_learning_rate: 1e-05
 - loss: CosineSimilarityLoss
 - distance_metric: cosine_distance
 - margin: 0.25
@@ -219,15 +219,15 @@ preds = model("  Interviews: Interviews WN:Story preparation/Office hours:Frank
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
 | 0.0035 | 1    | 0.1819        | -               |
-| 1.0381 | 300  | 0.2871        | 0.5             |
-| 2.0761 | 600  | 0.2631        | 0.5             |
-| 3.1142 | 900  | 0.2592        | 0.5             |
-| 4.1522 | 1200 | 0.2589        | 0.5             |
-| 5.1903 | 1500 | 0.2578        | 0.5000          |
-| 6.2284 | 1800 | 0.2588        | 0.5             |
-| 7.2664 | 2100 | 0.253         | 0.5             |
-| 8.3045 | 2400 | 0.2581        | 0.5             |
-| 9.3426 | 2700 | 0.255         | 0.5             |
 ### Framework Versions
 - Python: 3.10.12

 - num_epochs: (10, 10)
 - max_steps: -1
 - sampling_strategy: oversampling
+- body_learning_rate: (1e-05, 1e-05)
+- head_learning_rate: 1e-07
 - loss: CosineSimilarityLoss
 - distance_metric: cosine_distance
 - margin: 0.25
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
 | 0.0035 | 1    | 0.1819        | -               |
+| 1.0381 | 300  | 0.2219        | 0.2548          |
+| 2.0761 | 600  | 0.0366        | 0.4080          |
+| 3.1142 | 900  | 0.0075        | 0.4389          |
+| 4.1522 | 1200 | 0.0037        | 0.4466          |
+| 5.1903 | 1500 | 0.0019        | 0.4511          |
+| 6.2284 | 1800 | 0.0015        | 0.4566          |
+| 7.2664 | 2100 | 0.0013        | 0.4649          |
+| 8.3045 | 2400 | 0.0011        | 0.4687          |
+| 9.3426 | 2700 | 0.0011        | 0.4683          |
 ### Framework Versions
 - Python: 3.10.12

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21474fbaa7211072acd430e63488bb184bc04b7093df50dac9c6da9bd4a3ffbe
 size 133462128

 version https://git-lfs.github.com/spec/v1
+oid sha256:befc2560c82231eb8ec6a1945f4d36ef0e6ad35126de905fa479469185a5aa68
 size 133462128

model_head.pkl CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b5dd10870230eb87f841ecf71fbe5072426aa1e0ba842d77f079573d0f031c
 size 13175

 version https://git-lfs.github.com/spec/v1
+oid sha256:497aee039ee3a1aa19b00610c7bc694c93ca39004b6f7d5c1ed9a0af70f90240
 size 13175