Training in progress, epoch 1

config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "NeoBERTForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "model.NeoBERTConfig",
+    "AutoModel": "model.NeoBERT",
+    "AutoModelForMaskedLM": "model.NeoBERTLMHead",
+    "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification"
+  },
+  "classifier_init_range": 0.02,
+  "decoder_init_range": 0.02,
+  "dim_head": 64,
+  "dtype": "float32",
+  "embedding_init_range": 0.02,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Hacking",
+    "1": "Gambling",
+    "2": "Financial",
+    "3": "Electronic",
+    "4": "Porn",
+    "5": "Arms",
+    "6": "Drugs",
+    "7": "Others",
+    "8": "Crypto",
+    "9": "Violence"
+  },
+  "intermediate_size": 3072,
+  "kwargs": {
+    "architectures": [
+      "NeoBERTLMHead"
+    ],
+    "attn_implementation": null,
+    "auto_map": {
+      "AutoConfig": "model.NeoBERTConfig",
+      "AutoModel": "model.NeoBERT",
+      "AutoModelForMaskedLM": "model.NeoBERTLMHead",
+      "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification"
+    },
+    "classifier_init_range": 0.02,
+    "dim_head": 64,
+    "kwargs": {
+      "classifier_init_range": 0.02,
+      "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
+      "trust_remote_code": true
+    },
+    "model_type": "neobert",
+    "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
+    "torch_dtype": "float32",
+    "transformers_version": "4.48.2",
+    "trust_remote_code": true
+  },
+  "label2id": {
+    "Arms": 5,
+    "Crypto": 8,
+    "Drugs": 6,
+    "Electronic": 3,
+    "Financial": 2,
+    "Gambling": 1,
+    "Hacking": 0,
+    "Others": 7,
+    "Porn": 4,
+    "Violence": 9
+  },
+  "max_length": 4096,
+  "model_type": "neobert",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "pad_token_id": 0,
+  "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.1",
+  "trust_remote_code": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad811006d1acfd8a6754cf871ef778ff52dee4a7eb3aae9cc1101a3b8b8116b2
+size 889075200

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_size": 30522
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed730031610c2cc65f894c811cc516093dd5f5932a4803909b7673a7c892dfb
+size 5841