Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-multilingual-cased
+base_model: ayshi/basic_distil
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,12 +13,13 @@ probably proofread and complete it, then remove this comment. -->
 
 # ayshi/basic_distil
 
-This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
+This model is a fine-tuned version of [ayshi/basic_distil](https://huggingface.co/ayshi/basic_distil) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6225
-- Validation Loss: 0.8513
-- Train Accuracy: 0.7333
-- Epoch: 4
+- Train Loss: 0.6951
+- Validation Loss: 0.7997
+- Train Acc: {'accuracy': 0.7466666666666667}
+- Train F1: {'f1': 0.6052389245138363}
+- Epoch: 0
 
 ## Model description
 
@@ -42,18 +43,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Train Loss | Validation Loss | Train Accuracy | Epoch |
-|:----------:|:---------------:|:--------------:|:-----:|
-| 1.2657     | 1.1128          | 0.6667         | 0     |
-| 0.9980     | 1.0243          | 0.6667         | 1     |
-| 0.8564     | 0.9625          | 0.7067         | 2     |
-| 0.7175     | 0.8779          | 0.7289         | 3     |
-| 0.6225     | 0.8513          | 0.7333         | 4     |
+| Train Loss | Validation Loss | Train Acc                        | Train F1                   | Epoch |
+|:----------:|:---------------:|:--------------------------------:|:--------------------------:|:-----:|
+| 0.6951     | 0.7997          | {'accuracy': 0.7466666666666667} | {'f1': 0.6052389245138363} | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.34.0
 - TensorFlow 2.13.0
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-multilingual-cased",
+  "_name_or_path": "ayshi/basic_distil",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -35,6 +35,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.34.0",
   "vocab_size": 119547
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65861263d0afdcf8176df47e581d0a999e509623b8ba1ff43f6369aa7939317
+oid sha256:54286edd79a21b82e8edeb60df09aa570701d68e98b7223bcc8731c3f6d13556
 size 541448896

tokenizer_config.json

@@ -1,4 +1,47 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,