Chessmen
/

TF_fine_tune_distilbert-base-uncased

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

Chessmen commited on 25 days ago

Commit

d5781af

•

1 Parent(s): 28da12d

Training in progress epoch 1

Files changed (2) hide show

README.md +4 -3
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.7036
-- Validation Loss: 2.4365
-- Epoch: 0
 ## Model description
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 2.7036     | 2.4365          | 0     |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 2.5098
+- Validation Loss: 2.3908
+- Epoch: 1
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 2.7036     | 2.4365          | 0     |
+| 2.5098     | 2.3908          | 1     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98d4ae5ca3c697bc55141504f9f1f839f6fc16e1ab65a3ff9f55dc041ce19c4
 size 363423648

 version https://git-lfs.github.com/spec/v1
+oid sha256:f653bcc3bdf6536e57d2d966e0b5a78161dfedab0c110c7e949e835f8956d295
 size 363423648