Training in progress, step 500

config.json

@@ -1,75 +1,37 @@
 {
-  "_name_or_path": "GuysTrans/bart-base-vn-ehealth",
-  "activation_dropout": 0.1,
+  "_name_or_path": "vinai/bartpho-syllable",
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
   "architectures": [
-    "BartForConditionalGeneration"
+    "MBartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
   "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 4,
-  "num_hidden_layers": 6,
+  "model_type": "mbart",
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": false,
-  "task_specific_params": {
-    "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
-      "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "num_beams": 4
-    },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
-    }
-  },
+  "tokenizer_class": "BartphoTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 40030
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5734565b7b882aaeace390c5a6673c07e4bc9d61f9b6cd3d465a21df85c5121
-size 557971229
+oid sha256:6c1e124c933c59cd3ac4963cfb6b8579d70a11adfe78464a80c3c3be00cb7a53
+size 1583596058

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -5,7 +5,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer_config.json

@@ -1,19 +1,55 @@
 {
-  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40029": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "errors": "replace",
   "mask_token": "<mask>",
-  "max_length": 512,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "stride": 0,
-  "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BartphoTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd98bf074615d11b5dd8442b0a3bb5319f27486214318030c3937dedf971ed3e
-size 4219
+oid sha256:c8742674ae5f2eeedc4a2e9fa6b40457494e09b9b14641712fb44ae87d593403
+size 4664