Update to DS and training params

BatchSize_32_Metrics.txt

@@ -1,7 +1,7 @@
-Date:  11-21, 18:20
+Date:  01-02, 10:24
 Batch Size: 32
 Eval Strategy: epoch
 Early Stopping: epoch
 Early Stopping Patience: 5
 Best Model Metric: loss
-{'eval_loss': 0.17433641850948334, 'eval_accuracy': 0.9343434343434344, 'eval_f1': 0.880952380952381, 'eval_runtime': 46.2179, 'eval_samples_per_second': 42.841, 'eval_steps_per_second': 1.341, 'epoch': 7.0}
+{'eval_loss': 0.25912514328956604, 'eval_accuracy': 0.8928236397748592, 'eval_f1': 0.8110789582472095, 'eval_runtime': 242.0931, 'eval_samples_per_second': 17.613, 'eval_steps_per_second': 0.554, 'epoch': 7.0}

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 sha256:4fe18cc2cd00f7c2965e9c66fc628a5d0bfffe4eb37d118d6c269eb861cfcae2
-size 267854125
+oid sha256:00fb2f0fc0d8cdcd9c9dc92770a1b6dd9eadcabd9b18545297602766d49ea646
+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",