Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "gpt2-large",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2ForSequenceClassification"
@@ -9,14 +9,14 @@
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "id2label": {
-    "0": "Sonstiges",
-    "1": "Sexualdelikt",
-    "2": "K\u00f6rperverletzung",
-    "3": "Diebstahl",
-    "4": "Raub",
-    "5": "Bedrohung",
-    "6": "T\u00f6tungsdelikt",
-    "7": "Drogendelikt"
+    "0": "Sexualdelikt",
+    "1": "T\u00f6tungsdelikt",
+    "2": "Raub",
+    "3": "Drogendelikt",
+    "4": "Sonstiges",
+    "5": "Diebstahl",
+    "6": "K\u00f6rperverletzung",
+    "7": "Bedrohung"
   },
   "initializer_range": 0.02,
   "label2id": {
@@ -32,10 +32,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 36,
   "n_positions": 1024,
   "pad_token_id": 50258,
   "problem_type": "multi_label_classification",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c857d7c69d7056aab99011cd2543da5d3478c05f228c4c991b4c22789d743056
-size 510425857
+oid sha256:e65cdd15353ef1b30542741d4757aab077880c2c45ece4cdd3dfc1d9e48f38f8
+size 3134081281

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03ef07774b644b912e98648caee133a4c370de85c025c85774f1220f85d618a
+oid sha256:9991d00045d5a91f6a180548506f235897ec3e2bfbfddc5870ca6e330b93379f
 size 3515