Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-CTRY",
+    "1": "B-NBHD",
+    "2": "B-HPOI",
+    "3": "I-DIST",
+    "4": "I-CNTY",
+    "5": "U-STAT",
+    "6": "L-DIST",
+    "7": "B-ST",
+    "8": "I-OTHR",
+    "9": "L-HPOI",
+    "10": "L-OTHR",
+    "11": "I-NPOI",
+    "12": "L-CNTY",
+    "13": "L-NBHD",
+    "14": "B-CITY",
+    "15": "I-NBHD",
+    "16": "L-CITY",
+    "17": "B-OTHR",
+    "18": "I-HPOI",
+    "19": "U-OTHR",
+    "20": "B-CONT",
+    "21": "I-CTRY",
+    "22": "I-CITY",
+    "23": "O",
+    "24": "U-HPOI",
+    "25": "B-STAT",
+    "26": "B-NPOI",
+    "27": "U-ST",
+    "28": "U-NPOI",
+    "29": "L-CONT",
+    "30": "U-CNTY",
+    "31": "U-DIST",
+    "32": "B-ISL",
+    "33": "U-ISL",
+    "34": "L-ST",
+    "35": "U-CTRY",
+    "36": "U-NBHD",
+    "37": "I-ST",
+    "38": "L-CTRY",
+    "39": "I-STAT",
+    "40": "B-CNTY",
+    "41": "U-CONT",
+    "42": "L-NPOI",
+    "43": "L-STAT",
+    "44": "B-DIST",
+    "45": "L-ISL",
+    "46": "I-ISL",
+    "47": "U-CITY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CITY": 14,
+    "B-CNTY": 40,
+    "B-CONT": 20,
+    "B-CTRY": 0,
+    "B-DIST": 44,
+    "B-HPOI": 2,
+    "B-ISL": 32,
+    "B-NBHD": 1,
+    "B-NPOI": 26,
+    "B-OTHR": 17,
+    "B-ST": 7,
+    "B-STAT": 25,
+    "I-CITY": 22,
+    "I-CNTY": 4,
+    "I-CTRY": 21,
+    "I-DIST": 3,
+    "I-HPOI": 18,
+    "I-ISL": 46,
+    "I-NBHD": 15,
+    "I-NPOI": 11,
+    "I-OTHR": 8,
+    "I-ST": 37,
+    "I-STAT": 39,
+    "L-CITY": 16,
+    "L-CNTY": 12,
+    "L-CONT": 29,
+    "L-CTRY": 38,
+    "L-DIST": 6,
+    "L-HPOI": 9,
+    "L-ISL": 45,
+    "L-NBHD": 13,
+    "L-NPOI": 42,
+    "L-OTHR": 10,
+    "L-ST": 34,
+    "L-STAT": 43,
+    "O": 23,
+    "U-CITY": 47,
+    "U-CNTY": 30,
+    "U-CONT": 41,
+    "U-CTRY": 35,
+    "U-DIST": 31,
+    "U-HPOI": 24,
+    "U-ISL": 33,
+    "U-NBHD": 36,
+    "U-NPOI": 28,
+    "U-OTHR": 19,
+    "U-ST": 27,
+    "U-STAT": 5
+  },
+  "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,
+  "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": "4.42.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b4dc83dff15db8a7b82e63caa2c43c361eca149f15a22ad96c9c250a42bbb3
+size 735498240

runs/Jul29_00-13-28_9a62380d3c0c/events.out.tfevents.1722212032.9a62380d3c0c.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee383e137b2d54bbaa5fafeb64a924f2ee59712a34a979d94de39c65ef99c4e
+size 7972

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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
+  }
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffccae601b389d436e6f425f4d9947f2c0390411f5cd7b64a09f37485b21f716
+size 5176