Training in progress, epoch 1

config.json

@@ -0,0 +1,165 @@
+{
+  "_name_or_path": "numind/NuNER-v2.0",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "O",
+    "1": "art-broadcastprogram",
+    "2": "art-film",
+    "3": "art-music",
+    "4": "art-other",
+    "5": "art-painting",
+    "6": "art-writtenart",
+    "7": "building-airport",
+    "8": "building-hospital",
+    "9": "building-hotel",
+    "10": "building-library",
+    "11": "building-other",
+    "12": "building-restaurant",
+    "13": "building-sportsfacility",
+    "14": "building-theater",
+    "15": "event-attack/battle/war/militaryconflict",
+    "16": "event-disaster",
+    "17": "event-election",
+    "18": "event-other",
+    "19": "event-protest",
+    "20": "event-sportsevent",
+    "21": "location-GPE",
+    "22": "location-bodiesofwater",
+    "23": "location-island",
+    "24": "location-mountain",
+    "25": "location-other",
+    "26": "location-park",
+    "27": "location-road/railway/highway/transit",
+    "28": "organization-company",
+    "29": "organization-education",
+    "30": "organization-government/governmentagency",
+    "31": "organization-media/newspaper",
+    "32": "organization-other",
+    "33": "organization-politicalparty",
+    "34": "organization-religion",
+    "35": "organization-showorganization",
+    "36": "organization-sportsleague",
+    "37": "organization-sportsteam",
+    "38": "other-astronomything",
+    "39": "other-award",
+    "40": "other-biologything",
+    "41": "other-chemicalthing",
+    "42": "other-currency",
+    "43": "other-disease",
+    "44": "other-educationaldegree",
+    "45": "other-god",
+    "46": "other-language",
+    "47": "other-law",
+    "48": "other-livingthing",
+    "49": "other-medical",
+    "50": "person-actor",
+    "51": "person-artist/author",
+    "52": "person-athlete",
+    "53": "person-director",
+    "54": "person-other",
+    "55": "person-politician",
+    "56": "person-scholar",
+    "57": "person-soldier",
+    "58": "product-airplane",
+    "59": "product-car",
+    "60": "product-food",
+    "61": "product-game",
+    "62": "product-other",
+    "63": "product-ship",
+    "64": "product-software",
+    "65": "product-train",
+    "66": "product-weapon"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "art-broadcastprogram": 1,
+    "art-film": 2,
+    "art-music": 3,
+    "art-other": 4,
+    "art-painting": 5,
+    "art-writtenart": 6,
+    "building-airport": 7,
+    "building-hospital": 8,
+    "building-hotel": 9,
+    "building-library": 10,
+    "building-other": 11,
+    "building-restaurant": 12,
+    "building-sportsfacility": 13,
+    "building-theater": 14,
+    "event-attack/battle/war/militaryconflict": 15,
+    "event-disaster": 16,
+    "event-election": 17,
+    "event-other": 18,
+    "event-protest": 19,
+    "event-sportsevent": 20,
+    "location-GPE": 21,
+    "location-bodiesofwater": 22,
+    "location-island": 23,
+    "location-mountain": 24,
+    "location-other": 25,
+    "location-park": 26,
+    "location-road/railway/highway/transit": 27,
+    "organization-company": 28,
+    "organization-education": 29,
+    "organization-government/governmentagency": 30,
+    "organization-media/newspaper": 31,
+    "organization-other": 32,
+    "organization-politicalparty": 33,
+    "organization-religion": 34,
+    "organization-showorganization": 35,
+    "organization-sportsleague": 36,
+    "organization-sportsteam": 37,
+    "other-astronomything": 38,
+    "other-award": 39,
+    "other-biologything": 40,
+    "other-chemicalthing": 41,
+    "other-currency": 42,
+    "other-disease": 43,
+    "other-educationaldegree": 44,
+    "other-god": 45,
+    "other-language": 46,
+    "other-law": 47,
+    "other-livingthing": 48,
+    "other-medical": 49,
+    "person-actor": 50,
+    "person-artist/author": 51,
+    "person-athlete": 52,
+    "person-director": 53,
+    "person-other": 54,
+    "person-politician": 55,
+    "person-scholar": 56,
+    "person-soldier": 57,
+    "product-airplane": 58,
+    "product-car": 59,
+    "product-food": 60,
+    "product-game": 61,
+    "product-other": 62,
+    "product-ship": 63,
+    "product-software": 64,
+    "product-train": 65,
+    "product-weapon": 66
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a364c096a67a4789ec840477c867506d70ac49fb24d9f9842803989a17c9f7
+size 496450188

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b7f42704888662b15a04d948332c8113a2139889ceae24d75894b78f7937f1
+size 5048