End of training

config.json

@@ -1,27 +1,26 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "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,
+  "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,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.32.0.dev0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85afcf2f66f22733e319c6647dd1db641842e8fcf7c2dce7fef7024253252a32
-size 923120440
+oid sha256:af33b870bbaba4fa84fb0850cd030d80138ecafeb29cfda7ce4d30b3f9732f77
+size 438003505

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e137d15032e1c2fb6ef5ca8efc103ab85e83c4c0a3bb62b1c4b0b89ae966bf
+oid sha256:de02baa11cb822cabaf8ed62310d39d9a560a0c04f9f9ae3823b8d19207703d2
 size 4027