Finished contrastive learning stage 1

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -23,16 +23,16 @@
     "no": 0
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "transformers_version": "4.56.0",
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "4.56.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 64001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52dcc26e87dad78ab47dfef42640fee3329746696b73c9acbc5818139c96e7a2
-size 1112208084
+oid sha256:87de3ce39b471bac9f961bb8d7ca4ea169b8f2ebe38ef936bb57218f7b7abb40
+size 540026460