soumya13
/

GPT2_CleanDesc_MAKE_v1.5

Text Classification

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

soumya13 commited on May 2, 2023

Commit

a22a836

·

1 Parent(s): 02f009c

Training in progress epoch 2

Files changed (2) hide show

README.md +5 -4
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.5028
-- Validation Loss: 0.9649
-- Train Accuracy: 0.6923
-- Epoch: 1
 ## Model description
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:--------------:|:-----:|
 | 4.0208     | 1.7346          | 0.3590         | 0     |
 | 1.5028     | 0.9649          | 0.6923         | 1     |
 ### Framework versions

 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.8469
+- Validation Loss: 0.4756
+- Train Accuracy: 0.9231
+- Epoch: 2
 ## Model description
 |:----------:|:---------------:|:--------------:|:-----:|
 | 4.0208     | 1.7346          | 0.3590         | 0     |
 | 1.5028     | 0.9649          | 0.6923         | 1     |
+| 0.8469     | 0.4756          | 0.9231         | 2     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eadc82b9ecddc486b917445d5815add0d4c9df1243e85a0d9a887f307c59f3d8
 size 497983984

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5cd52e0d8ee80d42045c603272b02f2794ff925e910f57e574c8ff1b3bb7be5
 size 497983984