pd_subcate

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: tangminhanh/pd_cate
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: pd_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. -->
+
+# pd_subcate
+
+This model is a fine-tuned version of [tangminhanh/pd_cate](https://huggingface.co/tangminhanh/pd_cate) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0817
+- Accuracy: 0.0626
+- F1: 0.1103
+- Precision: 0.4717
+- Recall: 0.0624
+
+## 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   | 100  | 0.1179          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 200  | 0.1039          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 3.0   | 300  | 0.0949          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 4.0   | 400  | 0.0888          | 0.0      | 0.0    | 0.0       | 0.0    |
+| 0.1312        | 5.0   | 500  | 0.0852          | 0.0113   | 0.0217 | 0.3333    | 0.0112 |
+| 0.1312        | 6.0   | 600  | 0.0838          | 0.0413   | 0.0758 | 0.4714    | 0.0412 |
+| 0.1312        | 7.0   | 700  | 0.0820          | 0.0601   | 0.1062 | 0.4660    | 0.0599 |
+| 0.1312        | 8.0   | 800  | 0.0817          | 0.0626   | 0.1103 | 0.4717    | 0.0624 |
+
+
+### 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 +1,120 @@
+{
+  "_name_or_path": "tangminhanh/pd_cate",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "RFA/RFI/Techinical Coordination",
+    "1": "Initial Testfit (Office Modification)",
+    "2": "Revise Testfit (Office Modification)",
+    "3": "Floorplan / Evacuation Plan Updating",
+    "4": "Urgent: RFA/RFI Response for Builds",
+    "5": "OSM Checklist/Internal Dept Design Coordination Tasks",
+    "6": "Render (2 to 3 views)",
+    "7": "Office Area / Floorplan Copy / PEZA Info (Subject for Verification of P&D)",
+    "8": "Sourcing/Shopping/Site Accessorizing",
+    "9": "Floorplan Copy Request",
+    "10": "Canvassing OSM Alternatives",
+    "11": "Site Check",
+    "12": "Initial Testfit (Existing BTS or Service Office Modification)",
+    "13": "Technical Detail Drawing Request",
+    "14": "Furniture / Joinery Details",
+    "15": "Furniture and Material Specifications",
+    "16": "OSM Checklist & Coordination",
+    "17": "PEZA As-built print signed and sealed",
+    "18": "Revise Testfit (New Build/ Refresh)",
+    "19": "Initial Testfit (New Build / Refresh)",
+    "20": "Site Coordination Meetings",
+    "21": "Canvass approval / Vendor Cost Approval (under 20k)",
+    "22": "Floorplan/As-built Review & Approval (Audit/BP/OP/)",
+    "23": "Non-Urgent: Info/Coordination Request",
+    "24": "Revise Testfit (Existing BTS or Service Office Modification)",
+    "25": "PEZA Office Areas",
+    "26": "Project Scoping / Client Meeting",
+    "27": "Design Pegs & Cost Guide",
+    "28": "Site Handover Acceptance (Pre & Post Construction)",
+    "29": "Initial Testfit (New BTS or KMC Suites) >1000 to 5000 sqm",
+    "30": "Initial Testfit (New BTS or KMC Suites) <1000 sqm",
+    "31": "Canvassing OSM Alternatives / Vendor Costing Request",
+    "32": "Engineering Consultation",
+    "33": "Around Metro Manila - BTS / KMC Suites / SO",
+    "34": "3d Modeling + Rendering (minimum of 5 areas)",
+    "35": "3D Walkthrough",
+    "36": "Client Presentation",
+    "37": "Revise Testfit (New BTS or KMC Suites) >1000 to 5000 sqm",
+    "38": "Site Punchlist Walkthrough/ Handover Assessment",
+    "39": "Revise Testfit (New BTS or KMC Suites) <1000 sqm"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "3D Walkthrough": 35,
+    "3d Modeling + Rendering (minimum of 5 areas)": 34,
+    "Around Metro Manila - BTS / KMC Suites / SO": 33,
+    "Canvass approval / Vendor Cost Approval (under 20k)": 21,
+    "Canvassing OSM Alternatives": 10,
+    "Canvassing OSM Alternatives / Vendor Costing Request": 31,
+    "Client Presentation": 36,
+    "Design Pegs & Cost Guide": 27,
+    "Engineering Consultation": 32,
+    "Floorplan / Evacuation Plan Updating": 3,
+    "Floorplan Copy Request": 9,
+    "Floorplan/As-built Review & Approval (Audit/BP/OP/)": 22,
+    "Furniture / Joinery Details": 14,
+    "Furniture and Material Specifications": 15,
+    "Initial Testfit (Existing BTS or Service Office Modification)": 12,
+    "Initial Testfit (New BTS or KMC Suites) <1000 sqm": 30,
+    "Initial Testfit (New BTS or KMC Suites) >1000 to 5000 sqm": 29,
+    "Initial Testfit (New Build / Refresh)": 19,
+    "Initial Testfit (Office Modification)": 1,
+    "Non-Urgent: Info/Coordination Request": 23,
+    "OSM Checklist & Coordination": 16,
+    "OSM Checklist/Internal Dept Design Coordination Tasks": 5,
+    "Office Area / Floorplan Copy / PEZA Info (Subject for Verification of P&D)": 7,
+    "PEZA As-built print signed and sealed": 17,
+    "PEZA Office Areas": 25,
+    "Project Scoping / Client Meeting": 26,
+    "RFA/RFI/Techinical Coordination": 0,
+    "Render (2 to 3 views)": 6,
+    "Revise Testfit (Existing BTS or Service Office Modification)": 24,
+    "Revise Testfit (New BTS or KMC Suites) <1000 sqm": 39,
+    "Revise Testfit (New BTS or KMC Suites) >1000 to 5000 sqm": 37,
+    "Revise Testfit (New Build/ Refresh)": 18,
+    "Revise Testfit (Office Modification)": 2,
+    "Site Check": 11,
+    "Site Coordination Meetings": 20,
+    "Site Handover Acceptance (Pre & Post Construction)": 28,
+    "Site Punchlist Walkthrough/ Handover Assessment": 38,
+    "Sourcing/Shopping/Site Accessorizing": 8,
+    "Technical Detail Drawing Request": 13,
+    "Urgent: RFA/RFI Response for Builds": 4
+  },
+  "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:ab6d9dea6bcc8234ea0e9586ff72937f9132f990e24ffa94c3421a776047304a
+size 567715456

runs/Jul30_08-16-37_06a218ada6c5/events.out.tfevents.1722327404.06a218ada6c5.1464.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbabaa9b7dd024bd6ec922965eb0db8747c521bd91986c8c6b13437afb1b543
+size 13516

runs/Jul30_08-16-37_06a218ada6c5/events.out.tfevents.1722327875.06a218ada6c5.1464.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd83be34e14c6aa1f79cc2723448eb7a6e2a45bb2982a54d212d4f904ab6f48
+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:b6d010bb16801620c6961fb37783d5d000e18a7fea314d8eacbc2c4b29391018
+size 5112