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: 1.1312
-- Validation Loss: 1.9314
-- Train Accuracy: 0.5027
-- Epoch: 4
+- Train Loss: 2.1059
+- Validation Loss: 1.8323
+- Train Accuracy: 0.4978
+- Epoch: 0
 
 ## Model description
 
@@ -43,16 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.1159     | 1.8381          | 0.4997         | 0     |
-| 1.6862     | 1.7809          | 0.5137         | 1     |
-| 1.4767     | 1.8153          | 0.5131         | 2     |
-| 1.2870     | 1.8708          | 0.5088         | 3     |
-| 1.1312     | 1.9314          | 0.5027         | 4     |
+| 2.1059     | 1.8323          | 0.4978         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.30.1
+- Transformers 4.30.2
 - TensorFlow 2.12.0
 - Datasets 2.12.0
 - Tokenizers 0.13.3

config.json

@@ -94,6 +94,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.30.1",
+  "transformers_version": "4.30.2",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c9494bd702649efd65e4a7ba1a7cd8d8de4193adfc4f675fc8aa98e4a0b674
+oid sha256:f3d237a5cb3ec8409d473ad69ea727f3c813b8da774d3d20dc7a7d6350c7be45
 size 268056256