Training in progress, epoch 1

config.json

@@ -1,21 +1,20 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "ltgoslo/norbert2",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a1cdf45da491fdc0da5774cbd4be118837434b07b82a9da941bba30d061307
-size 1420922485
+oid sha256:339905053d0d343626a29b23fb1297c27192eb420b3b70ed01ab45a2e5344474
+size 498161013

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64c6b93477356d3d3ddcf68cc48e903e648edbd0c149ec974dfda00882ff562
+oid sha256:2fc0664dd1f2ad8ece8df5c3e1e3b0dba135e84e90c703906e967bd857d8dca8
 size 3387