Training in progress, epoch 1

.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 +1,87 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: model_gam_1809_viner2
+  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. -->
+
+# model_gam_1809_viner2
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.6808
+- eval_hiều cao khách hàng: {'precision': 0.9117647058823529, 'recall': 0.9393939393939394, 'f1': 0.9253731343283583, 'number': 33}
+- eval_hiều dài sản phẩm: {'precision': 0.7272727272727273, 'recall': 0.4444444444444444, 'f1': 0.5517241379310345, 'number': 18}
+- eval_hiều rộng sản phẩm: {'precision': 0.3157894736842105, 'recall': 0.6666666666666666, 'f1': 0.42857142857142855, 'number': 9}
+- eval_hong cách mua sắm: {'precision': 0.5925925925925926, 'recall': 0.7619047619047619, 'f1': 0.6666666666666666, 'number': 21}
+- eval_hong cách nhà cửa: {'precision': 0.7222222222222222, 'recall': 0.6190476190476191, 'f1': 0.6666666666666666, 'number': 21}
+- eval_hong cách thời trang: {'precision': 0.5416666666666666, 'recall': 0.7647058823529411, 'f1': 0.6341463414634146, 'number': 17}
+- eval_hất tóc: {'precision': 0.6896551724137931, 'recall': 0.7692307692307693, 'f1': 0.7272727272727274, 'number': 26}
+- eval_hối lượng sản phẩm: {'precision': 0.7894736842105263, 'recall': 0.8333333333333334, 'f1': 0.8108108108108109, 'number': 18}
+- eval_hời gian nhận hàng: {'precision': 0.6571428571428571, 'recall': 0.7931034482758621, 'f1': 0.71875, 'number': 29}
+- eval_iá sản phẩm: {'precision': 0.7777777777777778, 'recall': 0.8484848484848485, 'f1': 0.8115942028985507, 'number': 33}
+- eval_oại da: {'precision': 0.7586206896551724, 'recall': 0.9166666666666666, 'f1': 0.830188679245283, 'number': 24}
+- eval_ung hoàng đạo: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18}
+- eval_ung mệnh: {'precision': 0.9130434782608695, 'recall': 0.9130434782608695, 'f1': 0.9130434782608695, 'number': 23}
+- eval_àu da: {'precision': 0.7352941176470589, 'recall': 0.6756756756756757, 'f1': 0.7042253521126761, 'number': 37}
+- eval_àu sắc sản phẩm: {'precision': 0.782608695652174, 'recall': 0.7659574468085106, 'f1': 0.7741935483870968, 'number': 47}
+- eval_áng khuôn mặt: {'precision': 0.8095238095238095, 'recall': 0.85, 'f1': 0.8292682926829269, 'number': 20}
+- eval_áng người: {'precision': 0.9411764705882353, 'recall': 0.8888888888888888, 'f1': 0.9142857142857143, 'number': 18}
+- eval_ân nặng khách hàng: {'precision': 0.8888888888888888, 'recall': 0.9523809523809523, 'f1': 0.9195402298850575, 'number': 42}
+- eval_ã sản phẩm: {'precision': 0.6666666666666666, 'recall': 0.7692307692307693, 'f1': 0.7142857142857142, 'number': 26}
+- eval_ơn vị sản phẩm: {'precision': 0.726027397260274, 'recall': 0.6883116883116883, 'f1': 0.7066666666666667, 'number': 77}
+- eval_ản phẩm: {'precision': 0.8305921052631579, 'recall': 0.8790252393385553, 'f1': 0.854122621564482, 'number': 1149}
+- eval_ật độ tóc: {'precision': 0.8636363636363636, 'recall': 0.8260869565217391, 'f1': 0.8444444444444444, 'number': 23}
+- eval_ặc điểm khác của da: {'precision': 0.8571428571428571, 'recall': 0.8780487804878049, 'f1': 0.8674698795180722, 'number': 41}
+- eval_ịa chỉ nhận hàng: {'precision': 0.6285714285714286, 'recall': 0.7857142857142857, 'f1': 0.6984126984126985, 'number': 28}
+- eval_ố lượng sản phẩm: {'precision': 0.7642857142857142, 'recall': 0.7482517482517482, 'f1': 0.7561837455830388, 'number': 143}
+- eval_ố điện thoại nhận hàng: {'precision': 0.8994413407821229, 'recall': 1.0, 'f1': 0.9470588235294117, 'number': 161}
+- eval_ố đo vòng: {'precision': 0.952, 'recall': 0.9444444444444444, 'f1': 0.9482071713147411, 'number': 126}
+- eval_ộ dài tóc: {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 20}
+- eval_ộ tuổi khách hàng: {'precision': 0.8888888888888888, 'recall': 0.8888888888888888, 'f1': 0.8888888888888888, 'number': 18}
+- eval_overall_precision: 0.8164
+- eval_overall_recall: 0.8592
+- eval_overall_f1: 0.8372
+- eval_overall_accuracy: 0.9167
+- eval_runtime: 3.2923
+- eval_samples_per_second: 196.821
+- eval_steps_per_second: 49.205
+- epoch: 8.0
+- step: 7960
+
+## 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: 2.5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "/workspace/nmquy/GHTK/GAM/example/model_1709",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": "O",
+    "1": "S\u1ea3n ph\u1ea9m",
+    "2": "\u0110\u1ecba ch\u1ec9 nh\u1eadn h\u00e0ng",
+    "3": "S\u1ed1 l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m",
+    "4": "\u0110\u1eb7c \u0111i\u1ec3m kh\u00e1c c\u1ee7a da",
+    "5": "\u0110\u01a1n v\u1ecb s\u1ea3n ph\u1ea9m",
+    "6": "D\u00e1ng ng\u01b0\u1eddi",
+    "7": "Phong c\u00e1ch mua s\u1eafm",
+    "8": "M\u00e0u s\u1eafc s\u1ea3n ph\u1ea9m",
+    "9": "M\u00e0u da",
+    "10": "Th\u1eddi gian nh\u1eadn h\u00e0ng",
+    "11": "C\u00e2n n\u1eb7ng kh\u00e1ch h\u00e0ng",
+    "12": "Ch\u1ea5t t\u00f3c",
+    "13": "Phong c\u00e1ch th\u1eddi trang",
+    "14": "Phong c\u00e1ch nh\u00e0 c\u1eeda",
+    "15": "Cung m\u1ec7nh",
+    "16": "Cung ho\u00e0ng \u0111\u1ea1o",
+    "17": "Lo\u1ea1i da",
+    "18": "\u0110\u1ed9 tu\u1ed5i kh\u00e1ch h\u00e0ng",
+    "19": "S\u1ed1 \u0111i\u1ec7n tho\u1ea1i nh\u1eadn h\u00e0ng",
+    "20": "Gi\u00e1 s\u1ea3n ph\u1ea9m",
+    "21": "D\u00e1ng khu\u00f4n m\u1eb7t",
+    "22": "\u0110\u1ed9 d\u00e0i t\u00f3c",
+    "23": "M\u1eadt \u0111\u1ed9 t\u00f3c",
+    "24": "Chi\u1ec1u cao kh\u00e1ch h\u00e0ng",
+    "25": "M\u00e3 s\u1ea3n ph\u1ea9m",
+    "26": "Kh\u1ed1i l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m",
+    "27": "S\u1ed1 \u0111o v\u00f2ng",
+    "28": "Chi\u1ec1u d\u00e0i s\u1ea3n ph\u1ea9m",
+    "29": "Chi\u1ec1u r\u1ed9ng s\u1ea3n ph\u1ea9m"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Chi\u1ec1u cao kh\u00e1ch h\u00e0ng": 24,
+    "Chi\u1ec1u d\u00e0i s\u1ea3n ph\u1ea9m": 28,
+    "Chi\u1ec1u r\u1ed9ng s\u1ea3n ph\u1ea9m": 29,
+    "Ch\u1ea5t t\u00f3c": 12,
+    "Cung ho\u00e0ng \u0111\u1ea1o": 16,
+    "Cung m\u1ec7nh": 15,
+    "C\u00e2n n\u1eb7ng kh\u00e1ch h\u00e0ng": 11,
+    "D\u00e1ng khu\u00f4n m\u1eb7t": 21,
+    "D\u00e1ng ng\u01b0\u1eddi": 6,
+    "Gi\u00e1 s\u1ea3n ph\u1ea9m": 20,
+    "Kh\u1ed1i l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m": 26,
+    "Lo\u1ea1i da": 17,
+    "M\u00e0u da": 9,
+    "M\u00e0u s\u1eafc s\u1ea3n ph\u1ea9m": 8,
+    "M\u00e3 s\u1ea3n ph\u1ea9m": 25,
+    "M\u1eadt \u0111\u1ed9 t\u00f3c": 23,
+    "O": 0,
+    "Phong c\u00e1ch mua s\u1eafm": 7,
+    "Phong c\u00e1ch nh\u00e0 c\u1eeda": 14,
+    "Phong c\u00e1ch th\u1eddi trang": 13,
+    "S\u1ea3n ph\u1ea9m": 1,
+    "S\u1ed1 l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m": 3,
+    "S\u1ed1 \u0111i\u1ec7n tho\u1ea1i nh\u1eadn h\u00e0ng": 19,
+    "S\u1ed1 \u0111o v\u00f2ng": 27,
+    "Th\u1eddi gian nh\u1eadn h\u00e0ng": 10,
+    "\u0110\u01a1n v\u1ecb s\u1ea3n ph\u1ea9m": 5,
+    "\u0110\u1eb7c \u0111i\u1ec3m kh\u00e1c c\u1ee7a da": 4,
+    "\u0110\u1ecba ch\u1ec9 nh\u1eadn h\u00e0ng": 2,
+    "\u0110\u1ed9 d\u00e0i t\u00f3c": 22,
+    "\u0110\u1ed9 tu\u1ed5i kh\u00e1ch h\u00e0ng": 18
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "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 sha256:6f110aa6a4dbb6f0dcfadf28f8769592b9446f1920dc52814e012c7090ada5e9
+size 2235534864

runs/Sep18_23-48-06_nmtuet-serv/events.out.tfevents.1726678093.nmtuet-serv.1911358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d57fa9d7af3128a95d308355e7a905ec2380522e6ab904f4118f24a1318d45
+size 7697

runs/Sep18_23-53-12_nmtuet-serv/events.out.tfevents.1726678394.nmtuet-serv.2019645.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce11f0c24f9b3e22c3b7f8dfed188834259c76b4c219949681ecdea0e5bdcc
+size 10686

runs/Sep19_00-31-30_nmtuet-serv/events.out.tfevents.1726680704.nmtuet-serv.2106635.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a82aaa93c0a51742fec7c271c88c12198fdc8ac1ef1ad2d03f44d139f2a8c50
+size 15091

runs/Sep20_09-32-05_nmtuet-serv/events.out.tfevents.1726799598.nmtuet-serv.3995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2416f6573a783cd4b0dbc32512aea64d5ac11b389b9cf9fe25fdfce1ef4daff9
+size 7675

runs/Sep20_09-34-15_nmtuet-serv/events.out.tfevents.1726799659.nmtuet-serv.3995.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdaa823b555f869b5788cc35d2211ba5886ae84b21b8e69b8f9433d433171c3
+size 8390

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68342a8501ca5fc1f9a6736827ca79ebb1f38267c03edbb6c8d3a95719e38d9b
+size 5240