Training in progress, epoch 1

config.json

@@ -7,7 +7,7 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "Financial",
     "1": "Arms",
@@ -21,7 +21,7 @@
     "9": "Porn"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "Arms": 1,
     "Crypto": 8,
@@ -37,8 +37,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1f7fc2c9c8b6a5181cf21ec40cdc96dd78e70486dee709c4ed0cae70a18c09
-size 437983256
+oid sha256:b693a0c4b24aafc38bfcf954ab946370583a7c36264ce089109595dba52dee60
+size 1340655568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783a6a12f67d9f1bd8f6f28ddd99760fa597056c04adc7de6cd9c5cdcd45bcfa
+oid sha256:76f53d51e766055bb938040a0538e182f5cf77eba70c947f29fde1132c9861c2
 size 5713