Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -0,0 +1,101 @@
+{
+  "_name_or_path": "microsoft/mdeberta-v3-base",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B_BRN",
+    "2": "B_DES",
+    "3": "B_DTM",
+    "4": "B_LOC",
+    "5": "B_MEA",
+    "6": "B_NUM",
+    "7": "B_ORG",
+    "8": "B_PER",
+    "9": "B_TRM",
+    "10": "B_TTL",
+    "11": "I_BRN",
+    "12": "I_DES",
+    "13": "I_DTM",
+    "14": "I_LOC",
+    "15": "I_MEA",
+    "16": "I_NUM",
+    "17": "I_ORG",
+    "18": "I_PER",
+    "19": "I_TRM",
+    "20": "I_TTL",
+    "21": "E_BRN",
+    "22": "E_DES",
+    "23": "E_DTM",
+    "24": "E_LOC",
+    "25": "E_MEA",
+    "26": "E_NUM",
+    "27": "E_ORG",
+    "28": "E_PER",
+    "29": "E_TRM",
+    "30": "E_TTL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B_BRN": 1,
+    "B_DES": 2,
+    "B_DTM": 3,
+    "B_LOC": 4,
+    "B_MEA": 5,
+    "B_NUM": 6,
+    "B_ORG": 7,
+    "B_PER": 8,
+    "B_TRM": 9,
+    "B_TTL": 10,
+    "E_BRN": 21,
+    "E_DES": 22,
+    "E_DTM": 23,
+    "E_LOC": 24,
+    "E_MEA": 25,
+    "E_NUM": 26,
+    "E_ORG": 27,
+    "E_PER": 28,
+    "E_TRM": 29,
+    "E_TTL": 30,
+    "I_BRN": 11,
+    "I_DES": 12,
+    "I_DTM": 13,
+    "I_LOC": 14,
+    "I_MEA": 15,
+    "I_NUM": 16,
+    "I_ORG": 17,
+    "I_PER": 18,
+    "I_TRM": 19,
+    "I_TTL": 20,
+    "O": 0
+  },
+  "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": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e2e7a3e96afa3f31a73de965d9642cbacd7fe18ddc9b79d5daf41aeeac791a
+size 1112994868

runs/Jun15_02-25-04_c9fbe0f11166/events.out.tfevents.1718418305.c9fbe0f11166.8123.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed6cd9b063cf70eced1f401cf845da24d6f47b7200e08bbf726a9ba0362c1e6
+size 4184

runs/Jun15_02-27-07_c9fbe0f11166/events.out.tfevents.1718418428.c9fbe0f11166.9124.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd60fa54229c1d99277aec6184c9e2eaf46c2aa4c7b8861ef1abbb01acc965cf
+size 7223

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 sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e26ec8cd2234df8edcc6e8c207b66b3162360f9fdc46ee4526a440d0d9d0bb9
+size 16331374

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    },
+    "250101": {
+      "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:de47fc9e20a431404f2cecb277e68ef90ab126bddab7bba0429c2d5b22ea4120
+size 5112