Training in progress, epoch 1

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": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 40030
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9498a2f43ad2191126ca24ab3015a7516aea5e560bab5dea8d4d120598d3f246
+size 1583480280

runs/May30_16-25-31_lab2/events.out.tfevents.1717086332.lab2.3565014.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72f43705d9156a76eb728ae094459222da66a2c7b9c8d3784de3d033aa9ec16
+size 7168

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0734468cd80061ac25fff5ae9a6a28d6a2d264193d654510c65884a638fe2b8b
+size 5304