Training complete

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: Bartpho_spelling_correction
+  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. -->
+
+# Bartpho_spelling_correction
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0098
+- eval_runtime: 743.5931
+- eval_samples_per_second: 19.365
+- eval_steps_per_second: 4.841
+- epoch: 0.0278
+- step: 500
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vinai/bartpho-syllable",
+  "_name_or_path": "ShynBui/Bartpho_spelling_correction",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ef550b60bc093e9b12aa693fc4c54040c7b8d11723cc055bc4d87e53e51b9e
+oid sha256:189afec4581fc9f0dcc20eaf8247e2bb424998f9d88425c6ef16821b39e46817
 size 1583480280

runs/Aug07_05-16-29_173421f72ca0/events.out.tfevents.1723007803.173421f72ca0.1383.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bc474a5d0eacdc2381df148b19df18575a2f5ff6f9183b35a1fffc5d41ba03
+size 5851

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf63db5565228f58d2d104f0de5cae281a8664312808f6df860f92579a799290
+oid sha256:629d25ad516d3a93352d7c5fd07608c8ec489710c1e77dd9e62d737cb6bd3880
 size 5304