Training in progress epoch 0

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: savasy/bert-base-turkish-sentiment-cased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,12 +12,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # Fryktlos/lets_try
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [savasy/bert-base-turkish-sentiment-cased](https://huggingface.co/savasy/bert-base-turkish-sentiment-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1526
-- Validation Loss: 0.9756
-- Train Accuracy: 0.6875
-- Epoch: 1
+- Train Loss: 0.3810
+- Validation Loss: 0.2831
+- Train Accuracy: 0.8702
+- Epoch: 0
 
 ## Model description
 
@@ -44,8 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.2363     | 0.7394          | 0.6923         | 0     |
-| 0.1526     | 0.9756          | 0.6875         | 1     |
+| 0.3810     | 0.2831          | 0.8702         | 0     |
 
 
 ### Framework versions

config.json

@@ -1,31 +1,33 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "savasy/bert-base-turkish-sentiment-cased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst-2",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "negatif",
     "1": "pozitif"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "negatif": 0,
     "pozitif": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "transformers_version": "4.35.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc1da4667c06c390a8e691611032c7336c105400fe6345d838bc85762c57d32
-size 267955144
+oid sha256:a5236483992822b08a513e5b0fe53aa80005738053b5b9094af101eb476a080e
+size 442763544

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "100": {
+    "1": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -43,13 +43,16 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_len": 512,
   "model_max_length": 512,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }