NER Training complete

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: roberta-large
+tags:
+- generated_from_trainer
+model-index:
+- name: roberta-lg-cased-ms-ner-full
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-lg-cased-ms-ner-full
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 1.12.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,97 @@
+{
+  "_name_or_path": "roberta-large",
+  "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": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-BOSS",
+    "2": "I-BOSS",
+    "3": "B-MOB",
+    "4": "I-MOB",
+    "5": "B-MAP",
+    "6": "I-MAP",
+    "7": "B-JOB",
+    "8": "I-JOB",
+    "9": "B-INGAME_ITEM",
+    "10": "I-INGAME_ITEM",
+    "11": "B-QUEST",
+    "12": "I-QUEST",
+    "13": "B-CHANNEL",
+    "14": "I-CHANNEL",
+    "15": "B-SALE_ITEM",
+    "16": "I-SALE_ITEM",
+    "17": "B-EVENT",
+    "18": "I-EVENT",
+    "19": "B-MECHANIC",
+    "20": "I-MECHANIC",
+    "21": "B-FEATURE",
+    "22": "I-FEATURE",
+    "23": "B-NPC",
+    "24": "I-NPC",
+    "25": "B-GAME",
+    "26": "I-GAME",
+    "27": "B-SKILL",
+    "28": "I-SKILL",
+    "29": "B-UPDATE",
+    "30": "I-UPDATE",
+    "31": "B-MISC",
+    "32": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-BOSS": 1,
+    "B-CHANNEL": 13,
+    "B-EVENT": 17,
+    "B-FEATURE": 21,
+    "B-GAME": 25,
+    "B-INGAME_ITEM": 9,
+    "B-JOB": 7,
+    "B-MAP": 5,
+    "B-MECHANIC": 19,
+    "B-MISC": 31,
+    "B-MOB": 3,
+    "B-NPC": 23,
+    "B-QUEST": 11,
+    "B-SALE_ITEM": 15,
+    "B-SKILL": 27,
+    "B-UPDATE": 29,
+    "I-BOSS": 2,
+    "I-CHANNEL": 14,
+    "I-EVENT": 18,
+    "I-FEATURE": 22,
+    "I-GAME": 26,
+    "I-INGAME_ITEM": 10,
+    "I-JOB": 8,
+    "I-MAP": 6,
+    "I-MECHANIC": 20,
+    "I-MISC": 32,
+    "I-MOB": 4,
+    "I-NPC": 24,
+    "I-QUEST": 12,
+    "I-SALE_ITEM": 16,
+    "I-SKILL": 28,
+    "I-UPDATE": 30,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:538a52811fd0cd3273deaffe1a535ceb6522c4955ac7cd435c83f89a0c79513d
+size 1417423900

runs/Apr05_17-17-41_standardnc24adsa100v4al/events.out.tfevents.1712337596.standardnc24adsa100v4al.4769.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626196e6a1bb7a1453e3465654a3555f999f7b872ed025f5f20e13da3b67d531
+size 10108

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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": false,
+      "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 sha256:5ba0e91003f1d1d2af6f66ebfe3650e8c6d074355f699b168fac931926f2e426
+size 4527