Training in progress, step 500

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "roberta-base",
   "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,
@@ -21,17 +22,17 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.32.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3c2e28939e2ca4b497a8477da5b8497fdf56c53554d8a185a20181419e0bc5
-size 433318705
+oid sha256:afcded809d1842d7bf4edcbe4d66d0bd1548c8d05592fc09d06763dc983198ba
+size 498660721

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f4d0deb8745217d3d23871ea2234cd11a25a3d8e5b1358b2d2632450d2f979
+oid sha256:bbfdeadc52d008942f27f56f135f16d08ef9b720e7b1fe5a2914551984647321
 size 4027