Training in progress, step 39

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "vinai/bartpho-syllable",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "tokenizer_class": "BartphoTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 40030
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffc744cbee4b99b4a4e68013a31fde946dd6262457e5c946b49db1d18733206
+size 1583480280

runs/Nov19_12-00-48_74a4efb5ef56/events.out.tfevents.1732018264.74a4efb5ef56.2346.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac1f3e809074934d56f22739c8d942e918e865cc28ba5631cddccd95e55e041
+size 5939

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6730ae2c3dfb02815fe52394040ea10be68de10a1d5263239a8ecd30bd6810ee
+size 5304