Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ 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: 0.6865
-- Validation Loss: 0.6978
+- Train Loss: 0.6882
+- Validation Loss: 0.6969
 - Train Accuracy: 0.4908
-- Epoch: 1
+- Epoch: 0
 
 ## Model description
 
@@ -43,13 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6879     | 0.6976          | 0.4908         | 0     |
-| 0.6865     | 0.6978          | 0.4908         | 1     |
+| 0.6882     | 0.6969          | 0.4908         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.16.1
+- Transformers 4.16.2
 - TensorFlow 2.7.0
 - Datasets 1.18.2
 - Tokenizers 0.11.0

config.json

@@ -18,6 +18,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.16.1",
+  "transformers_version": "4.16.2",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0760740dc8facb2e46b985a334f6fb2bc2410e42cd8aa9439777416cb7e5865d
+oid sha256:02d14da9433700fd6e36558964116e02992cfc93aa1dcb625e97c6ba83bcdf0d
 size 267951896