End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: xlm-roberta-large_product_classifier
+  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. -->
+
+# xlm-roberta-large_product_classifier
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3981
+- Accuracy: 0.8169
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 490  | 0.8869          | 0.7423   |
+| 1.3297        | 2.0   | 980  | 0.7796          | 0.7798   |
+| 0.7265        | 3.0   | 1470 | 0.7592          | 0.7872   |
+| 0.5509        | 4.0   | 1960 | 0.8112          | 0.7949   |
+| 0.4258        | 5.0   | 2450 | 0.8498          | 0.7875   |
+| 0.3307        | 6.0   | 2940 | 0.8326          | 0.8036   |
+| 0.2702        | 7.0   | 3430 | 0.8833          | 0.8066   |
+| 0.2078        | 8.0   | 3920 | 0.9260          | 0.8066   |
+| 0.1571        | 9.0   | 4410 | 0.9800          | 0.8087   |
+| 0.1242        | 10.0  | 4900 | 1.0725          | 0.8043   |
+| 0.0962        | 11.0  | 5390 | 1.2147          | 0.7946   |
+| 0.0857        | 12.0  | 5880 | 1.1705          | 0.8123   |
+| 0.0667        | 13.0  | 6370 | 1.2551          | 0.8041   |
+| 0.052         | 14.0  | 6860 | 1.2762          | 0.8184   |
+| 0.0414        | 15.0  | 7350 | 1.3442          | 0.8115   |
+| 0.0313        | 16.0  | 7840 | 1.3510          | 0.8130   |
+| 0.0247        | 17.0  | 8330 | 1.3754          | 0.8133   |
+| 0.0158        | 18.0  | 8820 | 1.3915          | 0.8135   |
+| 0.0162        | 19.0  | 9310 | 1.3975          | 0.8186   |
+| 0.0109        | 20.0  | 9800 | 1.3981          | 0.8169   |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,89 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Th\u1eddi Trang Nam",
+    "1": "Th\u1eddi Trang N\u1eef",
+    "2": "Th\u1eddi Trang Tr\u1ebb Em",
+    "3": "Gi\u00e0y D\u00e9p N\u1eef",
+    "4": "Gi\u00e0y D\u00e9p Nam",
+    "5": "T\u00fai V\u00ed N\u1eef",
+    "6": "Balo & T\u00fai V\u00ed Nam",
+    "7": "Ph\u1ee5 Ki\u1ec7n & Trang S\u1ee9c N\u1eef",
+    "8": "\u0110i\u1ec7n Tho\u1ea1i & Ph\u1ee5 Ki\u1ec7n",
+    "9": "Thi\u1ebft B\u1ecb \u0110i\u1ec7n T\u1eed",
+    "10": "M\u00e1y T\u00ednh & Laptop",
+    "11": "M\u00e1y \u1ea2nh & M\u00e1y Quay Phim",
+    "12": "Thi\u1ebft B\u1ecb \u0110i\u1ec7n Gia D\u1ee5ng",
+    "13": "Nh\u00e0 C\u1eeda & \u0110\u1eddi S\u1ed1ng",
+    "14": "Gi\u1eb7t Gi\u0169 & Ch\u0103m S\u00f3c Nh\u00e0 C\u1eeda",
+    "15": "D\u1ee5ng C\u1ee5 & Thi\u1ebft B\u1ecb Ti\u1ec7n \u00cdch",
+    "16": "S\u1eafc \u0110\u1eb9p",
+    "17": "S\u1ee9c Kh\u1ecfe",
+    "18": "M\u1eb9 & B\u00e9",
+    "19": "\u0110\u1ed3 Ch\u01a1i",
+    "20": "Th\u1ec3 Thao & Du L\u1ecbch",
+    "21": "\u00d4 T\u00f4",
+    "22": "Xe M\u00e1y",
+    "23": "Xe \u0110\u1ea1p",
+    "24": "B\u00e1ch H\u00f3a Online",
+    "25": "Voucher & D\u1ecbch V\u1ee5",
+    "26": "Nh\u00e0 S\u00e1ch Online",
+    "27": "Ch\u0103m S\u00f3c Th\u00fa C\u01b0ng"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Balo & T\u00fai V\u00ed Nam": 6,
+    "B\u00e1ch H\u00f3a Online": 24,
+    "Ch\u0103m S\u00f3c Th\u00fa C\u01b0ng": 27,
+    "D\u1ee5ng C\u1ee5 & Thi\u1ebft B\u1ecb Ti\u1ec7n \u00cdch": 15,
+    "Gi\u00e0y D\u00e9p Nam": 4,
+    "Gi\u00e0y D\u00e9p N\u1eef": 3,
+    "Gi\u1eb7t Gi\u0169 & Ch\u0103m S\u00f3c Nh\u00e0 C\u1eeda": 14,
+    "M\u00e1y T\u00ednh & Laptop": 10,
+    "M\u00e1y \u1ea2nh & M\u00e1y Quay Phim": 11,
+    "M\u1eb9 & B\u00e9": 18,
+    "Nh\u00e0 C\u1eeda & \u0110\u1eddi S\u1ed1ng": 13,
+    "Nh\u00e0 S\u00e1ch Online": 26,
+    "Ph\u1ee5 Ki\u1ec7n & Trang S\u1ee9c N\u1eef": 7,
+    "S\u1eafc \u0110\u1eb9p": 16,
+    "S\u1ee9c Kh\u1ecfe": 17,
+    "Thi\u1ebft B\u1ecb \u0110i\u1ec7n Gia D\u1ee5ng": 12,
+    "Thi\u1ebft B\u1ecb \u0110i\u1ec7n T\u1eed": 9,
+    "Th\u1ec3 Thao & Du L\u1ecbch": 20,
+    "Th\u1eddi Trang Nam": 0,
+    "Th\u1eddi Trang N\u1eef": 1,
+    "Th\u1eddi Trang Tr\u1ebb Em": 2,
+    "T\u00fai V\u00ed N\u1eef": 5,
+    "Voucher & D\u1ecbch V\u1ee5": 25,
+    "Xe M\u00e1y": 22,
+    "Xe \u0110\u1ea1p": 23,
+    "\u00d4 T\u00f4": 21,
+    "\u0110i\u1ec7n Tho\u1ea1i & Ph\u1ee5 Ki\u1ec7n": 8,
+    "\u0110\u1ed3 Ch\u01a1i": 19
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059ca498e603aeebc26b26cb83d7cc5de36752936034492cd04f0480900b6797
+size 2239725272

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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
+size 17082987

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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc94f565ef6c257d649a54d69efa6e13ff8c33bc5dcf5e2511f203d0999a9f4
+size 5304