Training in progress, epoch 1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "vinai/bartpho-syllable-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "tokenizer_class": "BartphoTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 40030
+}

logs/events.out.tfevents.1703062012.264d4ec69400.597.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e541b3db16a55a74b4771fe58274676c639166a9a424a717b208ae8b9da2dc
+size 5624

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7861e669c87ef04d361bcd9a79ab8f054946ba1e3ea1ee9cc90dedd64e4dad43
+size 526442440

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9e0bf5f7116524b00ae7f96f4a659e72a65eccf47212d38ff26bc6caa2579c
+size 4920