Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "xlm-roberta-large",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
@@ -9,24 +9,36 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
-    "0": "LABEL_0"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
-    "LABEL_0": 0
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "problem_type": "regression",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "type_vocab_size": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95593b07621e1733b97003b36ada4f2e935dd590f7943f8048a2618da80656c
-size 1112201932
+oid sha256:7d6415474dfbade5b97b7e9709c07f7fda57d57531e878cd87c714ed60c6de96
+size 2239639172

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bea3a35f0fa4c3725af3bd96ea621a1802038b1c7c7d73a5391a7b712c43473
+oid sha256:a1b173f37360e081bc1cded748f67c8f587d750188f8367bd558bb6700683027
 size 5304