Upload 10 files

README.md

@@ -1,3 +1,58 @@
 ---
 license: apache-2.0
+base_model: bmd1905/vietnamese-correction
+tags:
+- generated_from_trainer
+model-index:
+- name: my-vietnamese-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. -->
+
+# my-vietnamese-correction
+
+This model is a fine-tuned version of [bmd1905/vietnamese-correction](https://huggingface.co/bmd1905/vietnamese-correction) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7591
+- Cer: 0.1234
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.99,
+    "eval_cer": 0.12337560670111164,
+    "eval_loss": 0.7591257095336914,
+    "eval_runtime": 172.1415,
+    "eval_samples": 1999,
+    "eval_samples_per_second": 11.613,
+    "eval_steps_per_second": 2.905,
+    "train_loss": 0.23782958757521502,
+    "train_runtime": 525.475,
+    "train_samples": 8599,
+    "train_samples_per_second": 32.728,
+    "train_steps_per_second": 0.255
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "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>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.99,
+    "train_loss": 0.23782958757521502,
+    "train_runtime": 525.475,
+    "train_samples": 8599,
+    "train_samples_per_second": 32.728,
+    "train_steps_per_second": 0.255
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.994418604651163,
+  "eval_steps": 10000,
+  "global_step": 134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.033292770385742,
+      "learning_rate": 9.253731343283582e-05,
+      "loss": 1.2697,
+      "step": 10
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.4899826049804688,
+      "learning_rate": 8.507462686567164e-05,
+      "loss": 0.3049,
+      "step": 20
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.5415112972259521,
+      "learning_rate": 7.761194029850747e-05,
+      "loss": 0.2733,
+      "step": 30
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.638880968093872,
+      "learning_rate": 7.014925373134329e-05,
+      "loss": 0.2333,
+      "step": 40
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1440837383270264,
+      "learning_rate": 6.268656716417911e-05,
+      "loss": 0.1867,
+      "step": 50
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.1239829063415527,
+      "learning_rate": 5.5223880597014934e-05,
+      "loss": 0.192,
+      "step": 60
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.2518362998962402,
+      "learning_rate": 4.7761194029850745e-05,
+      "loss": 0.1704,
+      "step": 70
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.8198823928833008,
+      "learning_rate": 4.029850746268657e-05,
+      "loss": 0.0894,
+      "step": 80
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.8759316205978394,
+      "learning_rate": 3.283582089552239e-05,
+      "loss": 0.1051,
+      "step": 90
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.0815106630325317,
+      "learning_rate": 2.537313432835821e-05,
+      "loss": 0.0918,
+      "step": 100
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.6786580085754395,
+      "learning_rate": 1.791044776119403e-05,
+      "loss": 0.0828,
+      "step": 110
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.5591555833816528,
+      "learning_rate": 1.0447761194029851e-05,
+      "loss": 0.0796,
+      "step": 120
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.9764952659606934,
+      "learning_rate": 2.9850746268656716e-06,
+      "loss": 0.0783,
+      "step": 130
+    },
+    {
+      "epoch": 1.99,
+      "step": 134,
+      "total_flos": 708532919205888.0,
+      "train_loss": 0.23782958757521502,
+      "train_runtime": 525.475,
+      "train_samples_per_second": 32.728,
+      "train_steps_per_second": 0.255
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 134,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 708532919205888.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79714b4283c43871bdb862f10df6f362f15c585840b5895dabf27d5fbde1a07
+size 5048