Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -9,14 +9,14 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2c093e0b3c419349ad649bd4d1535243129b0279a495efa90d27a238fb3540
-size 498612824
+oid sha256:d59ca79d90b2af0b0dbdfda76ce6a847f10a65edc23fa08ff0534f0db78b6b34
+size 1421495416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917ee3a7e9bf53b9314df684a802ce61041363dd6fd92052b7e0277c4258f12a
-size 5176
+oid sha256:fe14c10cb914b4b383f5f1fca421fe7be428c80fcf2de6eb33f7b1c865b9e0ed
+size 5240