ayshi
/

undersampling_distil

Text Classification

generated_from_keras_callback

text-embeddings-inference

Model card Files Files and versions

ayshi commited on Oct 5, 2023

Commit

2e0ddf3

·

1 Parent(s): 217d261

Training in progress epoch 5

Files changed (2) hide show

README.md +6 -4
tf_model.h5 +1 -1

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: 1.4486
-- Validation Loss: 1.4143
-- Train Accuracy: 0.4731
-- Epoch: 3
 ## Model description
@@ -48,6 +48,8 @@ The following hyperparameters were used during training:
 | 1.7198     | 1.6716          | 0.4086         | 1     |
 | 1.6087     | 1.5410          | 0.4731         | 2     |
 | 1.4486     | 1.4143          | 0.4731         | 3     |
 ### Framework versions

 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: 1.1630
+- Validation Loss: 1.2415
+- Train Accuracy: 0.5376
+- Epoch: 5
 ## Model description
 | 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     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccfa6706a09df5f8a37f8bd49a5745288fb8cc524edbeb65f0741eb5c943b84b
 size 541448896

 version https://git-lfs.github.com/spec/v1
+oid sha256:a8ea480aeacbfe0dee4ef64daad9aff211edbe6d480b88dd539466eea7a19932
 size 541448896