Training in progress, epoch 1

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -9,15 +9,14 @@
   "eos_token_id": 2,
   "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-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -25,5 +24,5 @@
   "transformers_version": "4.44.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ea74dbe4a4548747e58de7b6348f8622298c166bad93e511672ac24f2196b6
-size 2239618672
+oid sha256:9b4a9a07ee172b7d8e49ad3d893a5be6bc5e66c698306a99175635c2c46b1329
+size 498612824

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8a4f45a26ec13b94d429d8d87dcdea14cb1028d9f77380bf3c0d604ccfb099
+oid sha256:f73697be84cd9a4d55f2ef4a47c86072e82dff31636d5a0693cee0105665af86
 size 4719