Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -1,12 +1,9 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "DebertaV2ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -66,17 +63,27 @@
     "U-PERSON": 4,
     "U-USERID": 16
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eda920096efe7a4df65b179be762adf02fdc25ad7b10a2fc74b94d39c2784c6
-size 1109913172
+oid sha256:bf58456c0f5e26416569440d19eed316a2873d9303f271e37275b43f47db902f
+size 735427484

special_tokens_map.json

@@ -1,15 +1,15 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": 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,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  }
 }

spm.model

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
-size 17082854
+oid sha256:05402ffae6dd382a8491b1d29bfc139bec5d332662e86a026f433ce54c25c202
+size 8656646

tokenizer_config.json

@@ -2,7 +2,7 @@
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,7 +18,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,30 +26,34 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64541c40b165b585c1f39109f4f9770d81896d7917e03cca41e8545d91e1f506
+oid sha256:031102c84f45276cc9774d691319bbf84040a13fc03701221e3935114d9eb63f
 size 4856