lc_subcate

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: lc_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. -->
+
+# lc_subcate
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0705
+- Accuracy: 0.6794
+- F1: 0.7121
+- Precision: 0.7468
+- Recall: 0.6805
+
+## 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: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 64   | 0.2032          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 128  | 0.1115          | 0.3026   | 0.4699 | 0.9936    | 0.3077 |
+| No log        | 3.0   | 192  | 0.0883          | 0.6613   | 0.6775 | 0.6950    | 0.6607 |
+| No log        | 4.0   | 256  | 0.0777          | 0.6613   | 0.7015 | 0.7450    | 0.6627 |
+| No log        | 5.0   | 320  | 0.0740          | 0.5912   | 0.6802 | 0.7963    | 0.5937 |
+| No log        | 6.0   | 384  | 0.0715          | 0.6754   | 0.7138 | 0.7555    | 0.6765 |
+| No log        | 7.0   | 448  | 0.0711          | 0.6854   | 0.7153 | 0.7468    | 0.6864 |
+| 0.1388        | 8.0   | 512  | 0.0705          | 0.6794   | 0.7121 | 0.7468    | 0.6805 |
+
+
+### 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 +1,90 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "OTHERS - LEGAL & COMPLIANCE RELATED",
+    "1": "GENERAL LEGAL/COMPLIANCE ADVICE",
+    "2": "VISA PROCESSING (REQUIREMENTS)",
+    "3": "CONTRACT REVIEW",
+    "4": "INTELLECTUAL PROPERTY CONCERNS",
+    "5": "AMLA CONCERNS",
+    "6": "DATA PRIVACY CONCERNS",
+    "7": "OTHER ADVISORY/INQUIRY - LEGAL MATTERS / OPINIONS",
+    "8": "OTHER ADVISORY/INQUIRY - COMPLIANCE RELATED",
+    "9": "INQUIRY/ADVISORY FOR PEZA - CLIENTS",
+    "10": "BIR/PEZA/LGU/FSIC/DOLE/INSURANCE RELATED INQUIRIES FOR",
+    "11": "SEC/CORPORATE DOCUMENTS",
+    "12": "LETTER DRAFTING REQUESTS",
+    "13": "BUSINESS & OTHER LGU PERMITS FOR",
+    "14": "BIR/DOLE/FSIC/INSURANCE/BUILDING ADMIN CERTIFICATES/PERMITS FOR :",
+    "15": "PEZA CERTIFICATIONS FOR CLIENTS",
+    "16": "OFFSHORE (FOREIGN) CLIENT DOCUMENT REQUESTS",
+    "17": "OTHER DOCUMENT REQUESTS",
+    "18": "KYC",
+    "19": "VENDOR ACCREDITATION/DUE DILIGENCE",
+    "20": "BUSINESS REGISTRATION PROCESSING FOR",
+    "21": "PEZA REGISTRATION",
+    "22": "PEZA CERTIFICATIONS/INCENTIVES PROCESSING FOR CLIENTS",
+    "23": "OTHER PROCESSING REQUESTS RELATED TO LGU, BIR, PEZA, DOLE, BOC COMPLIANCE",
+    "24": "REQUEST FOR COPIES OF CONTRACTS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AMLA CONCERNS": 5,
+    "BIR/DOLE/FSIC/INSURANCE/BUILDING ADMIN CERTIFICATES/PERMITS FOR :": 14,
+    "BIR/PEZA/LGU/FSIC/DOLE/INSURANCE RELATED INQUIRIES FOR": 10,
+    "BUSINESS & OTHER LGU PERMITS FOR": 13,
+    "BUSINESS REGISTRATION PROCESSING FOR": 20,
+    "CONTRACT REVIEW": 3,
+    "DATA PRIVACY CONCERNS": 6,
+    "GENERAL LEGAL/COMPLIANCE ADVICE": 1,
+    "INQUIRY/ADVISORY FOR PEZA - CLIENTS": 9,
+    "INTELLECTUAL PROPERTY CONCERNS": 4,
+    "KYC": 18,
+    "LETTER DRAFTING REQUESTS": 12,
+    "OFFSHORE (FOREIGN) CLIENT DOCUMENT REQUESTS": 16,
+    "OTHER ADVISORY/INQUIRY - COMPLIANCE RELATED": 8,
+    "OTHER ADVISORY/INQUIRY - LEGAL MATTERS / OPINIONS": 7,
+    "OTHER DOCUMENT REQUESTS": 17,
+    "OTHER PROCESSING REQUESTS RELATED TO LGU, BIR, PEZA, DOLE, BOC COMPLIANCE": 23,
+    "OTHERS - LEGAL & COMPLIANCE RELATED": 0,
+    "PEZA CERTIFICATIONS FOR CLIENTS": 15,
+    "PEZA CERTIFICATIONS/INCENTIVES PROCESSING FOR CLIENTS": 22,
+    "PEZA REGISTRATION": 21,
+    "REQUEST FOR COPIES OF CONTRACTS": 24,
+    "SEC/CORPORATE DOCUMENTS": 11,
+    "VENDOR ACCREDITATION/DUE DILIGENCE": 19,
+    "VISA PROCESSING (REQUIREMENTS)": 2
+  },
+  "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 sha256:44dbb9cd7ebee3ca133084c7848cc735b0772989ceb466b666cb885c7e61d40d
+size 567669308

runs/Jul30_03-16-11_80170deff950/events.out.tfevents.1722309373.80170deff950.996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a2e2afb7352dabc822617bb2ced18839b2a7d30c73250c25c3ff8f84070b3b
+size 7370

runs/Jul30_03-16-30_80170deff950/events.out.tfevents.1722309395.80170deff950.996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968c80a07f7a19132ccd14a3906162656efbe9274d8d4327d748d4bfcf1c2874
+size 7368

runs/Jul30_03-16-52_80170deff950/events.out.tfevents.1722309419.80170deff950.996.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa35b670b7ba5f38cb35287d9fe7b448937a765fc9f0837131168170759cac98
+size 11700

runs/Jul30_03-16-52_80170deff950/events.out.tfevents.1722310175.80170deff950.996.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3861491c92c603d66d6f9dae4b7a72f13d869b1311241d7b045d6101fc2d31f6
+size 560

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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 +1,58 @@
+{
+  "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]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8dfff85136886cb06be25dbfaf03b8fdeb097ef6e7e058a06e4b100e3557d11
+size 5112