Training complete

README.md

@@ -0,0 +1,59 @@
+---
+base_model: vinai/bartpho-syllable
+tags:
+- text2text-generation
+- generated_from_trainer
+metrics:
+- sacrebleu
+model-index:
+- name: vietnamese-correction-v2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vietnamese-correction-v2
+
+This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9331
+- Sacrebleu: 23.9554
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

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": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 40030
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429c515b83d2b64713bbfd069eae28807148837c29fa34bd95dfb2e6d2ebff79
+size 1583480280

runs/May21_21-06-55_8f4de844b6a5/events.out.tfevents.1716325616.8f4de844b6a5.682.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5492a5c0befe390b7b1164c6dd9e620f69acb24d76ba71954c1ca1094708f8
+size 5305

runs/May21_21-08-59_8f4de844b6a5/events.out.tfevents.1716325739.8f4de844b6a5.682.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e888df3bef1c45925d3a5b86ebc05ef8c0aae0e69f07630f8c5cfe792a365d
+size 5658

runs/May21_21-08-59_8f4de844b6a5/events.out.tfevents.1716326569.8f4de844b6a5.682.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039ae2c7ec8f319fa4c9ef6846ba2496f49d0231ea29fb5df7dc5c46cc99f529
+size 412

runs/May21_21-23-39_8f4de844b6a5/events.out.tfevents.1716326619.8f4de844b6a5.682.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4f0365b2bcf70459348e182e59f050a5df104d59be957fbdbcbd558ecbafb0
+size 5304

runs/May21_21-23-58_8f4de844b6a5/events.out.tfevents.1716326639.8f4de844b6a5.682.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc6198697397c7299ac8e273bf256d78d13166a7672185903a499ca2b4148f7
+size 5658

runs/May21_21-23-58_8f4de844b6a5/events.out.tfevents.1716327480.8f4de844b6a5.682.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63fb6c94bb28eaf68990602090ec2c9f5138ab471b31b16850271c98f7d82d5
+size 412

runs/May21_21-38-30_8f4de844b6a5/events.out.tfevents.1716327511.8f4de844b6a5.682.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957f28d72fda73b908b22ff46bde6c7b9c996ff998ea09201d5b1c4a00d852e0
+size 5658

runs/May21_21-38-30_8f4de844b6a5/events.out.tfevents.1716328355.8f4de844b6a5.682.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52bbb109df957d5f51357dd5d38a623ee4df3e954434c128ec1dce083656715
+size 736

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BartphoTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe641aa604ccc39c52026d0962a4daac630f644c6dc90cd6362a5dfeb497b7f1
+size 5240