Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vinai/phobert-large",
+  "_name_or_path": "vinai/phobert-base",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -10,14 +10,14 @@
   "gradient_checkpointing": false,
   "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": 258,
   "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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 sha256:52ca0cc1e48a9e2fecf93fa831bb8428bb8ed874d4a8bdb808e3e9b5512f5883
-size 1476709528
+oid sha256:6a0e5f1c309f124cd28a959f6dba07aa444e3e8614d4a3c84b041f5b395be9c8
+size 540023384

runs/Apr17_09-45-46_b814bffdaab7/events.out.tfevents.1713347148.b814bffdaab7.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3cca9cf86072af22352f4bdadba9fb7431075d96a72623d88ab406c26fc109
+size 4928

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b737e406c005a3e617db50a6802d28360aa1e8ecaae316e2ae88e4406fd4c5
+oid sha256:15cb4fc51f7772ea4ace08e549ddc1d5f5186e06f61f415984f651d88a97190e
 size 4920