Training completed!

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: vinai/phobert-base-v2
+base_model: vinai/phobert-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # PhoBERT-cls-detail-in-Non_OCR
 
-This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
+This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3171
+- Loss: 0.2965
 - Accuracy: 0.95
 - F1: 0.9359
 
@@ -44,25 +44,24 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 1.5232        | 1.0   | 25   | 1.1976          | 0.79     | 0.7209 |
-| 1.0392        | 2.0   | 50   | 0.7550          | 0.91     | 0.8830 |
-| 0.6986        | 3.0   | 75   | 0.5119          | 0.92     | 0.8928 |
-| 0.5144        | 4.0   | 100  | 0.4181          | 0.92     | 0.8928 |
-| 0.4265        | 5.0   | 125  | 0.3602          | 0.95     | 0.9359 |
-| 0.3618        | 6.0   | 150  | 0.3394          | 0.95     | 0.9359 |
-| 0.3196        | 7.0   | 175  | 0.3218          | 0.95     | 0.9359 |
-| 0.2982        | 8.0   | 200  | 0.3171          | 0.95     | 0.9359 |
+| 1.5312        | 1.0   | 25   | 1.2681          | 0.55     | 0.4060 |
+| 1.1478        | 2.0   | 50   | 0.8709          | 0.82     | 0.7465 |
+| 0.7779        | 3.0   | 75   | 0.5259          | 0.92     | 0.8928 |
+| 0.528         | 4.0   | 100  | 0.3918          | 0.92     | 0.8928 |
+| 0.4236        | 5.0   | 125  | 0.3363          | 0.94     | 0.9254 |
+| 0.3641        | 6.0   | 150  | 0.3035          | 0.95     | 0.9359 |
+| 0.3356        | 7.0   | 175  | 0.2965          | 0.95     | 0.9359 |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.1

added_tokens.json

@@ -1,3 +1,7 @@
 {
-  "<mask>": 64000
+  "</s>": 2,
+  "<mask>": 64000,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vinai/phobert-base-v2",
+  "_name_or_path": "vinai/phobert-base",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -7,6 +7,7 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -38,7 +39,7 @@
   "problem_type": "single_label_classification",
   "tokenizer_class": "PhobertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 64001

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf04b61da97934148142f76be9fc1dfc13a8f705c4f1fefca4614ef4ed0c8594
+oid sha256:de5997667b22f35807f1161d74db16beeed56c23089220f192420e7fcf5a28f5
 size 540080497

tokenizer_config.json

@@ -1,4 +1,47 @@
 {
+  "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
+    }
+  },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
@@ -8,5 +51,6 @@
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "PhobertTokenizer",
+  "tokenizer_file": "/root/.cache/huggingface/hub/models--vinai--phobert-large/snapshots/9ce4eafcd8e601d798295b17c75c5f5f1b1509b9/tokenizer.json",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92cd65c70df121f6e89d516f162c48afdb626e0109cbfd5d3595e5fa6bd261b6
-size 4027
+oid sha256:a6af8aa3f9b6974a88282861a87312175519579d399c4620e4914bc3a1801f07
+size 4091