Update to DS

BatchSize_32_Metrics.txt

@@ -1,7 +1,7 @@
-Date:  11-08, 22:06
+Date:  11-08, 21:52
 Batch Size: 32
 Eval Strategy: no
 Early Stopping: steps
 Early Stopping Patience: 5
 Best Model Metric: None
-{'eval_loss': 0.264784038066864, 'eval_accuracy': 0.8947368421052632, 'eval_f1': 0.8467432950191571, 'eval_runtime': 17.3527, 'eval_samples_per_second': 43.797, 'eval_steps_per_second': 1.383, 'epoch': 12.22}
+{'eval_loss': 0.28202134370803833, 'eval_accuracy': 0.8762886597938144, 'eval_f1': 0.8732394366197183, 'eval_runtime': 50.7452, 'eval_samples_per_second': 11.469, 'eval_steps_per_second': 0.374, 'epoch': 12.14}

added_tokens.json

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

config.json

@@ -28,6 +28,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.27.1",
+  "transformers_version": "4.34.0",
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d4699c4cdd22c8ebee131914a197c75833f6fabde51f77ae688812ccb6488c
-size 267854125
+oid sha256:976471419ab946b4b807cf6e1d0c63d6dc2180637597e9bdbcab395c0185c9ab
+size 267854570

tokenizer_config.json

@@ -1,11 +1,54 @@
 {
+  "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": 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",