Duplicate from tangminhanh/cs_subcate

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+base_model: tangminhanh/ts_subcate
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: cs_subcate
+  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. -->
+
+# cs_subcate
+
+This model is a fine-tuned version of [tangminhanh/ts_subcate](https://huggingface.co/tangminhanh/ts_subcate) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0517
+- Accuracy: 0.6283
+- F1: 0.6777
+- Precision: 0.7292
+- Recall: 0.6330
+
+## 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   | 195  | 0.0649          | 0.2715   | 0.4110 | 0.8554    | 0.2704 |
+| No log        | 2.0   | 390  | 0.0532          | 0.5113   | 0.6149 | 0.7639    | 0.5145 |
+| 0.0785        | 3.0   | 585  | 0.0515          | 0.5688   | 0.6404 | 0.7225    | 0.5750 |
+| 0.0785        | 4.0   | 780  | 0.0496          | 0.5979   | 0.6606 | 0.7225    | 0.6085 |
+| 0.0785        | 5.0   | 975  | 0.0492          | 0.6147   | 0.6753 | 0.7367    | 0.6233 |
+| 0.0386        | 6.0   | 1170 | 0.0499          | 0.6141   | 0.6701 | 0.7151    | 0.6304 |
+| 0.0386        | 7.0   | 1365 | 0.0503          | 0.6206   | 0.6754 | 0.7265    | 0.6310 |
+| 0.0283        | 8.0   | 1560 | 0.0512          | 0.6199   | 0.6717 | 0.7129    | 0.6349 |
+| 0.0283        | 9.0   | 1755 | 0.0515          | 0.6193   | 0.6720 | 0.7228    | 0.6278 |
+| 0.0283        | 10.0  | 1950 | 0.0517          | 0.6283   | 0.6777 | 0.7292    | 0.6330 |
+
+
+### 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 +1,116 @@
+{
+  "_name_or_path": "tangminhanh/ts_subcate",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Power Outage",
+    "1": "Security Breach/ Theft",
+    "2": "AC Concerns",
+    "3": "Work Permit",
+    "4": "Move Out Request",
+    "5": "Move In Request",
+    "6": "Furniture Move",
+    "7": "Office Set-up",
+    "8": "Supplies Request",
+    "9": "Photo / Video Request",
+    "10": "Client Viewing Request",
+    "11": "Printing/Scan request",
+    "12": "Storage Request",
+    "13": "Cleaning request",
+    "14": "Parking / Car pass Requests",
+    "15": "Planned activities",
+    "16": "Medical Certificate Validation",
+    "17": "HMO Account Update",
+    "18": "Messengerial /Courier Service Request",
+    "19": "New Office Transfer",
+    "20": "Reservation (Rooms & Event Space)",
+    "21": "Shuttle Booking",
+    "22": "Van Repairs & Maintenance",
+    "23": "Repairs and Maintenance Request",
+    "24": "Visitor Access Request",
+    "25": "Approval Request",
+    "26": "Costing Request",
+    "27": "Info or Document Request",
+    "28": "Phone / Sim Requests",
+    "29": "Orientation / Training Request",
+    "30": "Assistance",
+    "31": "Access Cards / Room or Office Access Requests",
+    "32": "Safety Concerns",
+    "33": "Other Medical Concerns",
+    "34": "Checklists & Reports",
+    "35": "New Hire Kit Request",
+    "36": "Invoices",
+    "37": "Gatepass Request"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AC Concerns": 2,
+    "Access Cards / Room or Office Access Requests": 31,
+    "Approval Request": 25,
+    "Assistance": 30,
+    "Checklists & Reports": 34,
+    "Cleaning request": 13,
+    "Client Viewing Request": 10,
+    "Costing Request": 26,
+    "Furniture Move": 6,
+    "Gatepass Request": 37,
+    "HMO Account Update": 17,
+    "Info or Document Request": 27,
+    "Invoices": 36,
+    "Medical Certificate Validation": 16,
+    "Messengerial /Courier Service Request": 18,
+    "Move In Request": 5,
+    "Move Out Request": 4,
+    "New Hire Kit Request": 35,
+    "New Office Transfer": 19,
+    "Office Set-up": 7,
+    "Orientation / Training Request": 29,
+    "Other Medical Concerns": 33,
+    "Parking / Car pass Requests": 14,
+    "Phone / Sim Requests": 28,
+    "Photo / Video Request": 9,
+    "Planned activities": 15,
+    "Power Outage": 0,
+    "Printing/Scan request": 11,
+    "Repairs and Maintenance Request": 23,
+    "Reservation (Rooms & Event Space)": 20,
+    "Safety Concerns": 32,
+    "Security Breach/ Theft": 1,
+    "Shuttle Booking": 21,
+    "Storage Request": 12,
+    "Supplies Request": 8,
+    "Van Repairs & Maintenance": 22,
+    "Visitor Access Request": 24,
+    "Work Permit": 3
+  },
+  "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:d190ce2f4c8b5a32ed86ab31689f27bdb450faf9f2a0549d2e35443b74996e1e
+size 567709304

runs/Aug06_16-19-05_8286c2bd2340/events.out.tfevents.1722961152.8286c2bd2340.1585.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1e598a68fdb128771f2f4e2b465eaaa3acb28a25e82d02a029c969827274e6
+size 13372

runs/Aug06_16-19-05_8286c2bd2340/events.out.tfevents.1722962285.8286c2bd2340.1585.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e694f6c4fe909cb8839eb8d2494c71019df3b74ff8972527cbe0eea747ba875
+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:d14a3d443acd097613a7c8eab12f47e482dac8a1997803c5ba1ddafa97bdf077
+size 5112