Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
@@ -9,20 +9,20 @@
   "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,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b29d734fff54ec18e752662c6e0c6ea21f42f36de653149f2c19e91f5ed2aa8
-size 2239618672
+oid sha256:31d08a7288457c97d8fc53e51c20683658c0cd5344bf634c5a2f44adab9d77ee
+size 1112205008

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f76fe13d42f80dcee0cb86a1aeb5f14f8909bb8a8782f7a4a4ad76697ef164
-size 17083021
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c639d7ae795bdaeb75940c6e61249f1ae2d6da85f2d9ac5989b16c4d79c39d4f
-size 4856
+oid sha256:3340c228c18261b5ff40cbe01c818e2705e16804dc2a8a431238aab85f835eef
+size 4920