End of training

config.json

@@ -1,27 +1,28 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "roberta-large",
   "architectures": [
-    "BertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.32.0.dev0",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4eb0ad717cde5c767a14c08b13ed9fb1aa55b81f1eca00dae573538348dd15
-size 438003505
+oid sha256:6660dd551007fe996716e59101d33805a80f39e94838b4070d99895a007808c3
+size 1421582769

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3773317666a3940018f26fcbf8e8a2f192b80f5cfca33fa565de2a5e57660e1
+oid sha256:48c2ee98f839f38714997782c499de0ca9823fef2d93bd1de78bfb80f2c8e128
 size 4027