fin_subcate

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: fin_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. -->
+
+# fin_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: 0.0671
+- Accuracy: 0.6825
+- F1: 0.7671
+- Precision: 0.8756
+- Recall: 0.6825
+
+## 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: 64
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 64   | 0.1875          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 128  | 0.1179          | 0.5134   | 0.6578 | 0.9153    | 0.5134 |
+| No log        | 3.0   | 192  | 0.0931          | 0.5124   | 0.6680 | 0.9593    | 0.5124 |
+| No log        | 4.0   | 256  | 0.0798          | 0.6231   | 0.7343 | 0.8936    | 0.6231 |
+| No log        | 5.0   | 320  | 0.0717          | 0.6508   | 0.7550 | 0.8989    | 0.6508 |
+| No log        | 6.0   | 384  | 0.0684          | 0.6746   | 0.7629 | 0.8777    | 0.6746 |
+| No log        | 7.0   | 448  | 0.0671          | 0.6825   | 0.7671 | 0.8756    | 0.6825 |
+
+
+### 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 +1,80 @@
+{
+  "_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": "Other Request",
+    "1": "Below 20k invoices (No PO)",
+    "2": "Client Cash advance",
+    "3": "Client Refund",
+    "4": "Confidential Payments Requests",
+    "5": "Complicated Report",
+    "6": "FORMS (Reimbursement, PCF, Credit Card Liquidation)",
+    "7": "Internal & External reimb request",
+    "8": "Petty Cash Request",
+    "9": "PO invoices",
+    "10": "Recurring bills (rentals, utilities, telco, etc.)",
+    "11": "Simple Report",
+    "12": "Urgent requests (Business permits, other taxes etc.)",
+    "13": "Bank Request",
+    "14": "Cash Advance",
+    "15": "Client Request",
+    "16": "Government Statutory",
+    "17": "Last Pay",
+    "18": "Operations",
+    "19": "Taxes / BOC / LGU Payment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Bank Request": 13,
+    "Below 20k invoices (No PO)": 1,
+    "Cash Advance": 14,
+    "Client Cash advance": 2,
+    "Client Refund": 3,
+    "Client Request": 15,
+    "Complicated Report": 5,
+    "Confidential Payments Requests": 4,
+    "FORMS (Reimbursement, PCF, Credit Card Liquidation)": 6,
+    "Government Statutory": 16,
+    "Internal & External reimb request": 7,
+    "Last Pay": 17,
+    "Operations": 18,
+    "Other Request": 0,
+    "PO invoices": 9,
+    "Petty Cash Request": 8,
+    "Recurring bills (rentals, utilities, telco, etc.)": 10,
+    "Simple Report": 11,
+    "Taxes / BOC / LGU Payment": 19,
+    "Urgent requests (Business permits, other taxes etc.)": 12
+  },
+  "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 sha256:268552d53863bcf892b3ecf81605436ad6bdca5bc06645b6070869e069511cc4
+size 567653928

runs/Jul19_07-32-49_caf7575f2689/events.out.tfevents.1721374382.caf7575f2689.10048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432bc51f3df8291ccddbecc2cea3ba009179fac8d5ef5766f876f4397f05a123
+size 10097

runs/Jul19_07-32-49_caf7575f2689/events.out.tfevents.1721374877.caf7575f2689.10048.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a985235243bbd641c80b724f08de9cc0e79261525f6ae9e038d87d636c3f20
+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 sha256:6d85915cb4cf9411d4d1778f4950a390e7df63857eb086a0fad5d2cde4996e4e
+size 5112