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: 0.0591
-- Validation Loss: 0.3201
-- Train Accuracy: 0.9037
-- Epoch: 2
+- Train Loss: 0.2130
+- Validation Loss: 0.2447
+- Train Accuracy: 0.8979
+- Epoch: 0
 
 ## Model description
 
@@ -43,14 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.2119     | 0.2864          | 0.8876         | 0     |
-| 0.1029     | 0.2479          | 0.9048         | 1     |
-| 0.0591     | 0.3201          | 0.9037         | 2     |
+| 0.2130     | 0.2447          | 0.8979         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.27.4
+- Transformers 4.28.0
 - TensorFlow 2.12.0
 - Datasets 2.11.0
-- Tokenizers 0.13.2
+- Tokenizers 0.13.3

config.json

@@ -26,6 +26,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.28.0",
   "vocab_size": 30522
 }

logs/train/events.out.tfevents.1681490854.ip-172-26-13-131.44582.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da96dd589f46e5a95dfab59a67bbd59c93d0cd96953b335898a145b4196c0635
+size 1788388

logs/validation/events.out.tfevents.1681492739.ip-172-26-13-131.44582.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12f9161c2e1ba02aebb850b609c09b4f3eabde8d871abc0dd626de5e553faae
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d182b2c6ec702422e6bbdae6c6dccb25bda048f690c18df3a84c2c32246e9cf
+oid sha256:04d7b674c66813a8dc0304fcadfadb57a4c7d978e859ba0b43e05a37c8909f6a
 size 267951808

tokenizer_config.json

@@ -1,11 +1,11 @@
 {
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",