Training in progress, epoch 1

config.json

@@ -1,54 +1,33 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "HooshvareLab/bert-base-parsbert-uncased",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
-    "1": "B-corporation",
-    "2": "I-corporation",
-    "3": "B-creative-work",
-    "4": "I-creative-work",
-    "5": "B-group",
-    "6": "I-group",
-    "7": "B-location",
-    "8": "I-location",
-    "9": "B-person",
-    "10": "I-person",
-    "11": "B-product",
-    "12": "I-product"
+    "1": "halfspace"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
-    "B-corporation": 1,
-    "B-creative-work": 3,
-    "B-group": 5,
-    "B-location": 7,
-    "B-person": 9,
-    "B-product": 11,
-    "I-corporation": 2,
-    "I-creative-work": 4,
-    "I-group": 6,
-    "I-location": 8,
-    "I-person": 10,
-    "I-product": 12,
-    "O": 0
+    "O": 0,
+    "halfspace": 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",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5507690bcfa33cd13305d5cbb387d28a4a0ed509d6a10de751e43004fd3db39
-size 265503852
+oid sha256:91632129e1f23af32363dfded6f84f4c1a8f1f4f9a06492c85746d9ba2f6627a
+size 649032520

runs/Jun11_14-47-24_c84076364e1d/events.out.tfevents.1718117248.c84076364e1d.3930.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02de6ea6c7dbe47644f2fd114863e71528002595670631871aed47da46c8f038
+size 5380

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,
@@ -24,16 +24,16 @@
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "4": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -43,13 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "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]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9dec810982d94348422cefe1e5bf158445963bffc6e47757e8292867a6db2c
+oid sha256:fe19e2a2eb4cc72a2a2a3d68a58ed10a36f8164b6b76cfecf1dd10dca5be7eec
 size 4655