Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vinai/bartpho-syllable",
+  "_name_or_path": "vinai/bartpho-syllable-base",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [
@@ -8,17 +8,17 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 6,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -26,7 +26,7 @@
   "is_encoder_decoder": true,
   "max_position_embeddings": 1024,
   "model_type": "mbart",
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
   "tokenizer_class": "BartphoTokenizer",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4317c1dd08fcc3f97bdd8a0b778278c4fa5523c03d674f4ddc7ab534c43b75
-size 1583480280
+oid sha256:528155addeb64194e6c003b66729692f4d363e353fefd761bc0eeb91fe753fc3
+size 526442440

runs/Dec06_07-00-41_26ce95cce962/events.out.tfevents.1733468489.26ce95cce962.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1241f9c0e1c4b0d39ca128cef1b8fbccb9ada9d00533bbdd5a62051106fdae
+size 6603

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f05fc7e2e35cad259cd166ab51161649a628cb8a91556b427ecd62408d380a
+oid sha256:adc2df6d7264f238d3551bca4fa0c116cf019e730d2e44bf65489e7233982819
 size 5432