ayshi
/

undersampling_distil

Text Classification

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

ayshi commited on Oct 9, 2023

Commit

0e64a01

•

1 Parent(s): ecfd4d4

Training in progress epoch 0

Files changed (2) hide show

README.md +6 -15
tf_model.h5 +2 -2

README.md CHANGED Viewed

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.8703
-- Validation Loss: 1.1425
-- Train Accuracy: 0.5699
-- Epoch: 9
 ## Model description
@@ -44,16 +44,7 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.7819     | 1.7485          | 0.3226         | 0     |
-| 1.7198     | 1.6716          | 0.4086         | 1     |
-| 1.6087     | 1.5410          | 0.4731         | 2     |
-| 1.4486     | 1.4143          | 0.4731         | 3     |
-| 1.2997     | 1.3131          | 0.5054         | 4     |
-| 1.1630     | 1.2415          | 0.5376         | 5     |
-| 1.0576     | 1.2065          | 0.5591         | 6     |
-| 0.9664     | 1.1588          | 0.6022         | 7     |
-| 0.9016     | 1.1525          | 0.5699         | 8     |
-| 0.8703     | 1.1425          | 0.5699         | 9     |
 ### Framework versions
@@ -61,4 +52,4 @@ The following hyperparameters were used during training:
 - Transformers 4.34.0
 - TensorFlow 2.13.0
 - Datasets 2.14.5
-- Tokenizers 0.14.0

 This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 1.7867
+- Validation Loss: 1.7551
+- Train Accuracy: 0.4176
+- Epoch: 0
 ## Model description
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
+| 1.7867     | 1.7551          | 0.4176         | 0     |
 ### Framework versions
 - Transformers 4.34.0
 - TensorFlow 2.13.0
 - Datasets 2.14.5
+- Tokenizers 0.14.1

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d6c43f879c8cc557b96edbd9a6324dad72f1423d5fc0699b42fd5b0eddd456
-size 541448896

 version https://git-lfs.github.com/spec/v1
+oid sha256:fe003f738885072b7234ac9ff014e94775a14542b2ed4b92cb316cc286534073
+size 541452232