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: 0.5260
-- Validation Loss: 0.6328
-- Train Accuracy: 0.7729
-- Epoch: 2
+- Train Loss: 2.8682
+- Validation Loss: 1.7635
+- Train Accuracy: 0.3021
+- Epoch: 0
 
 ## Model description
 
@@ -43,14 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.4520     | 0.9126          | 0.7146         | 0     |
-| 0.7577     | 0.6889          | 0.7708         | 1     |
-| 0.5260     | 0.6328          | 0.7729         | 2     |
+| 2.8682     | 1.7635          | 0.3021         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.28.0
+- Transformers 4.28.1
 - TensorFlow 2.12.0
 - Datasets 2.11.0
 - Tokenizers 0.13.3

config.json

@@ -34,6 +34,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.28.0",
+  "transformers_version": "4.28.1",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4f204d21119f3aad47ae58eb2d03712c1512e62192061831818b514693451b
+oid sha256:0cfac0b7052c9b6b193d51b55c94c7414a5e3e46fa61d5fd8c3adf11a1daf732
 size 267964096