Training in progress, epoch 1

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Pornography",
+    "1": "Erotica",
+    "2": "Adult Content",
+    "3": "Crime",
+    "4": "Sexual Assault",
+    "5": "Violent Crime",
+    "6": "Terrorist Attacks",
+    "7": "Counterterrorism",
+    "8": "Smoking",
+    "9": "Vaping",
+    "10": "Tobacco Use",
+    "11": "Military Conflict",
+    "12": "War",
+    "13": "International Relations",
+    "14": "Pandemic",
+    "15": "Vaccines",
+    "16": "Health Guidelines",
+    "17": "COVID-19 News",
+    "18": "Cybersecurity",
+    "19": "Hacking",
+    "20": "Malware",
+    "21": "Addiction",
+    "22": "Substance Abuse",
+    "23": "Rehabilitation",
+    "24": "Hate Speech",
+    "25": "Offensive Language",
+    "26": "Discrimination",
+    "27": "Racism",
+    "28": "Homophobia",
+    "29": "Accidents",
+    "30": "Disasters",
+    "31": "Public Safety",
+    "32": "Weapons",
+    "33": "Gun Control",
+    "34": "Accidents ",
+    "35": " Public Safety",
+    "36": "Firearms",
+    "37": "Weapons "
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    " Public Safety": 35,
+    "Accidents": 29,
+    "Accidents ": 34,
+    "Addiction": 21,
+    "Adult Content": 2,
+    "COVID-19 News": 17,
+    "Counterterrorism": 7,
+    "Crime": 3,
+    "Cybersecurity": 18,
+    "Disasters": 30,
+    "Discrimination": 26,
+    "Erotica": 1,
+    "Firearms": 36,
+    "Gun Control": 33,
+    "Hacking": 19,
+    "Hate Speech": 24,
+    "Health Guidelines": 16,
+    "Homophobia": 28,
+    "International Relations": 13,
+    "Malware": 20,
+    "Military Conflict": 11,
+    "Offensive Language": 25,
+    "Pandemic": 14,
+    "Pornography": 0,
+    "Public Safety": 31,
+    "Racism": 27,
+    "Rehabilitation": 23,
+    "Sexual Assault": 4,
+    "Smoking": 8,
+    "Substance Abuse": 22,
+    "Terrorist Attacks": 6,
+    "Tobacco Use": 10,
+    "Vaccines": 15,
+    "Vaping": 9,
+    "Violent Crime": 5,
+    "War": 12,
+    "Weapons": 32,
+    "Weapons ": 37
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a213500632f5325b98761e755ab6173ba6d56047da7dd8c0f2169ece030ca493
+size 541428120

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6d1ae0ec39c6e03bbc59d68fe10ea0fcf5df3462c0be2dcf3468fe1ba91dfd
+size 5240