AG News Dataset. Training Completed

config.json

@@ -8,7 +8,6 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
-  "hidden_dropout_prob": 0.8,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -25,7 +24,7 @@
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
-  "n_layers": 2,
+  "n_layers": 6,
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
   "qa_dropout": 0.1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3be06288b75594e8eb4a235219baec1e6393ed5e6198cc3b6bd1bb407b9505
-size 154432877
+oid sha256:d4aa14f3db33957f31c329e1c50b5620c286cd0affcd17d7b4021248703e4d2f
+size 267860465

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1c37f2355ce21e59b6669f201ff59aafb7752481ae8c9b24cfa0af0544954b
+oid sha256:1916b37c91b2a664d30af4c7ee9a205f05aafb385d00c8102acf10a7d6a99622
 size 3439