Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/alephbertgimmel/alephbertgimmel-base/ckpt_69200--Max128Seq",
+  "_name_or_path": "dicta-il/dictabert",
   "architectures": [
     "BertForMultiLabelTokenClassification"
   ],
@@ -10,70 +10,71 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "\"#",
-    "1": "#\u05d4",
-    "2": "#\u05d4\u05d5",
-    "3": "#\u05d4\u05dd",
-    "4": "#\u05d4\u05df",
-    "5": "#\u05d5",
-    "6": "#\u05d9",
-    "7": "#\u05d9\u05d4",
-    "8": "#\u05d9\u05d5",
-    "9": "#\u05da",
-    "10": "#\u05db\u05dd",
-    "11": "#\u05dd",
-    "12": "#\u05df",
-    "13": "#\u05e0\u05d5",
-    "14": "#\u05e0\u05d9",
-    "15": "'#",
-    "16": "\u05d1#",
-    "17": "\u05d4#",
-    "18": "\u05d5#",
-    "19": "\u05db#",
-    "20": "\u05db\u05e9#",
-    "21": "\u05dc#",
-    "22": "\u05de#",
-    "23": "\u05de\u05e9#",
-    "24": "\u05e9#"
+    "0": "\"_",
+    "1": "_\u05d4",
+    "2": "_\u05d4\u05d5",
+    "3": "_\u05d4\u05dd",
+    "4": "_\u05d4\u05df",
+    "5": "_\u05d5",
+    "6": "_\u05d9",
+    "7": "_\u05d9\u05d4",
+    "8": "_\u05d9\u05d5",
+    "9": "_\u05da",
+    "10": "_\u05db\u05dd",
+    "11": "_\u05dd",
+    "12": "_\u05df",
+    "13": "_\u05e0\u05d5",
+    "14": "_\u05e0\u05d9",
+    "15": "'_",
+    "16": "\u05d1_",
+    "17": "\u05d4_",
+    "18": "\u05d5_",
+    "19": "\u05db_",
+    "20": "\u05db\u05e9_",
+    "21": "\u05dc_",
+    "22": "\u05de_",
+    "23": "\u05de\u05e9_",
+    "24": "\u05e9_"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "\"#": 0,
-    "#\u05d4": 1,
-    "#\u05d4\u05d5": 2,
-    "#\u05d4\u05dd": 3,
-    "#\u05d4\u05df": 4,
-    "#\u05d5": 5,
-    "#\u05d9": 6,
-    "#\u05d9\u05d4": 7,
-    "#\u05d9\u05d5": 8,
-    "#\u05da": 9,
-    "#\u05db\u05dd": 10,
-    "#\u05dd": 11,
-    "#\u05df": 12,
-    "#\u05e0\u05d5": 13,
-    "#\u05e0\u05d9": 14,
-    "'#": 15,
-    "\u05d1#": 16,
-    "\u05d4#": 17,
-    "\u05d5#": 18,
-    "\u05db#": 19,
-    "\u05db\u05e9#": 20,
-    "\u05dc#": 21,
-    "\u05de#": 22,
-    "\u05de\u05e9#": 23,
-    "\u05e9#": 24
+    "\"_": 0,
+    "'_": 15,
+    "_\u05d4": 1,
+    "_\u05d4\u05d5": 2,
+    "_\u05d4\u05dd": 3,
+    "_\u05d4\u05df": 4,
+    "_\u05d5": 5,
+    "_\u05d9": 6,
+    "_\u05d9\u05d4": 7,
+    "_\u05d9\u05d5": 8,
+    "_\u05da": 9,
+    "_\u05db\u05dd": 10,
+    "_\u05dd": 11,
+    "_\u05df": 12,
+    "_\u05e0\u05d5": 13,
+    "_\u05e0\u05d9": 14,
+    "\u05d1_": 16,
+    "\u05d4_": 17,
+    "\u05d5_": 18,
+    "\u05db_": 19,
+    "\u05db\u05e9_": 20,
+    "\u05dc_": 21,
+    "\u05de_": 22,
+    "\u05de\u05e9_": 23,
+    "\u05e9_": 24
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
+  "newmodern": true,
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 3,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 128000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59632fc76e123148e48acf19385974914a620dd494006fcafccd92d766f034c2
+oid sha256:4ba6f823fcf23e199bef2bd088934755bbf15e68ac038e47124cd2b1662c64e8
 size 737481828

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c5bc0b21e3a45847eb7b2dff5d71bbfd6dcb14d93d3fefd1d06b922e1ab80e
-size 5112
+oid sha256:4b633f8af621f04c3059319313f56173bfef1681bc39f00ff7478e47c7caf7b2
+size 5176