Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vinai/phobert-base",
+  "_name_or_path": "vinai/phobert-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -10,14 +10,14 @@
   "gradient_checkpointing": false,
   "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": 258,
   "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:d72363bc4612bc269cb8105b82c167ed4bb793d8ca4019238c5fc7b9f10f4aad
-size 540023384
+oid sha256:71255375100935457e514bbf7facc1cebeca210c2d2f57a0bef6565992f340b1
+size 1476709528

runs/Apr17_05-44-38_f1659026a288/events.out.tfevents.1713332678.f1659026a288.361.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f42e21c3149a4a34885cc60b1ec442fa27c5714c43e0fe26eda70c5d069ce6
+size 4917

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07492824d6c2a0c97bceca5104530a9fc54d4a4b1aad48c7c058b489347da729
+oid sha256:09b737e406c005a3e617db50a6802d28360aa1e8ecaae316e2ae88e4406fd4c5
 size 4920