Training in progress, epoch 1

config.json

@@ -1,12 +1,13 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "Crypto",
     "1": "Porn",
@@ -20,6 +21,7 @@
     "9": "Gambling"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Arms": 2,
     "Crypto": 0,
@@ -32,17 +34,22 @@
     "Porn": 1,
     "Violence": 3
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
   "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": "4.55.4",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564d09105181a72b0d59d62616436decf61abe3a7535af6cf99cb11b8621496a
-size 267857176
+oid sha256:d91e945703871024e9df2857d9c09ac6531bc81ea1669410e1ce64aead93ca6b
+size 711468072

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7809cb5ba37a6e4afbd24084dfcba30e34c33ab1c7e545dfee7326fd1245da
+oid sha256:95930ed7c92437370b06ad103c31c474e75d8f8ff7da9e3edb140f3648865e81
 size 5713