Training in progress, step 500

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "lakshyakh93/deberta_finetuned_pii",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "DebertaForTokenClassification"
+    "DebertaV2ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
@@ -42,7 +42,8 @@
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
-  "model_type": "deberta",
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
@@ -50,13 +51,15 @@
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 768,
   "pos_att_type": [
-    "c2p",
-    "p2c"
+    "p2c",
+    "c2p"
   ],
   "position_biased_input": false,
+  "position_buckets": 256,
   "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",
   "type_vocab_size": 0,
-  "vocab_size": 50265
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685e0734bbb9085bfffff53ae73473ff409ec40556f1470832dc3264d41e4e27
-size 554470860
+oid sha256:fbcec678037238add86033f25c42eb14dd60eb1ef696fd5a45396ff9f811ff28
+size 735390572

special_tokens_map.json

@@ -1,46 +1,10 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -1,11 +1,9 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +11,7 @@
     "1": {
       "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,7 +19,7 @@
     "2": {
       "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -34,27 +32,27 @@
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "128000": {
       "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",
-  "errors": "replace",
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "tokenizer_class": "DebertaTokenizer",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
   "unk_token": "[UNK]",
-  "vocab_type": "gpt2"
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b6028bea919006be9ad13fd6cba8ea1bf6d1e2ede0b44fafc34e7aa5ef0bcc
+oid sha256:36eaebafcaa405a4870d259d4be3467ac08fc2a7e955e976d0860e2d67c72fcc
 size 4283