ts_cate

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+base_model: tangminhanh/ts_tg
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: ts_cate
+  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. -->
+
+# ts_cate
+
+This model is a fine-tuned version of [tangminhanh/ts_tg](https://huggingface.co/tangminhanh/ts_tg) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0263
+- Accuracy: 0.8555
+- F1: 0.8736
+- Precision: 0.8824
+- Recall: 0.8649
+
+## 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: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 404  | 0.0458          | 0.6802   | 0.7650 | 0.8750    | 0.6796 |
+| 0.1001        | 2.0   | 808  | 0.0318          | 0.7717   | 0.8259 | 0.8817    | 0.7767 |
+| 0.0321        | 3.0   | 1212 | 0.0278          | 0.8251   | 0.8564 | 0.8862    | 0.8286 |
+| 0.0215        | 4.0   | 1616 | 0.0256          | 0.8322   | 0.8627 | 0.8909    | 0.8363 |
+| 0.0161        | 5.0   | 2020 | 0.0256          | 0.8455   | 0.8679 | 0.8812    | 0.8551 |
+| 0.0161        | 6.0   | 2424 | 0.0259          | 0.8499   | 0.8711 | 0.8831    | 0.8594 |
+| 0.0124        | 7.0   | 2828 | 0.0255          | 0.8536   | 0.8713 | 0.8836    | 0.8594 |
+| 0.0105        | 8.0   | 3232 | 0.0262          | 0.8533   | 0.8723 | 0.8836    | 0.8612 |
+| 0.0087        | 9.0   | 3636 | 0.0261          | 0.8567   | 0.8746 | 0.8838    | 0.8656 |
+| 0.0078        | 10.0  | 4040 | 0.0263          | 0.8555   | 0.8736 | 0.8824    | 0.8649 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "tangminhanh/ts_tg",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Biometric",
+    "1": "Document",
+    "2": "On Boarding",
+    "3": "Ticketing Support",
+    "4": "Asset Management",
+    "5": "Off Boarding",
+    "6": "CCTV",
+    "7": "Checklist",
+    "8": "Hardware",
+    "9": "General Assistance",
+    "10": "TV Advertisement",
+    "11": "Network",
+    "12": "Network and Infrastructure Design",
+    "13": "Circuit",
+    "14": "Outage",
+    "15": "Network Security",
+    "16": "Notification",
+    "17": "System Security",
+    "18": "Server Management",
+    "19": "Server Projects",
+    "20": "Services Management",
+    "21": "User Account",
+    "22": "Deployment / Movement",
+    "23": "Email",
+    "24": "Printer",
+    "25": "Software",
+    "26": "Telephony",
+    "27": "Development",
+    "28": "Web/Application Security",
+    "29": "CASA",
+    "30": "Compliance",
+    "31": "Email Security",
+    "32": "Procurement",
+    "33": "TPMO",
+    "34": "BCP Activation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Asset Management": 4,
+    "BCP Activation": 34,
+    "Biometric": 0,
+    "CASA": 29,
+    "CCTV": 6,
+    "Checklist": 7,
+    "Circuit": 13,
+    "Compliance": 30,
+    "Deployment / Movement": 22,
+    "Development": 27,
+    "Document": 1,
+    "Email": 23,
+    "Email Security": 31,
+    "General Assistance": 9,
+    "Hardware": 8,
+    "Network": 11,
+    "Network Security": 15,
+    "Network and Infrastructure Design": 12,
+    "Notification": 16,
+    "Off Boarding": 5,
+    "On Boarding": 2,
+    "Outage": 14,
+    "Printer": 24,
+    "Procurement": 32,
+    "Server Management": 18,
+    "Server Projects": 19,
+    "Services Management": 20,
+    "Software": 25,
+    "System Security": 17,
+    "TPMO": 33,
+    "TV Advertisement": 10,
+    "Telephony": 26,
+    "Ticketing Support": 3,
+    "User Account": 21,
+    "Web/Application Security": 28
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60de420a12559e4f2438f215dee42e52e271b4958b8d10c34d0ac8d81a907235
+size 567700076

runs/Aug06_13-56-19_8286c2bd2340/events.out.tfevents.1722952587.8286c2bd2340.1585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5e7eb0e2673ac1c1267ba9646201ce195ed477c57f1df8d939f361defecd24
+size 13638

runs/Aug06_13-56-19_8286c2bd2340/events.out.tfevents.1722954943.8286c2bd2340.1585.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fdeb544359d45cc8260242ec175ef25a91fd6e1db5dc992375e36e92fecefc
+size 560

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca84d62247c72ad432ded3ebcdee7f00790f5426695f6f3210f998157fdea73b
+size 5112