subcate_cs
Browse files- README.md +70 -0
- added_tokens.json +3 -0
- config.json +120 -0
- model.safetensors +3 -0
- runs/Jul10_06-01-50_49a3fa77351e/events.out.tfevents.1720591317.49a3fa77351e.25532.1 +3 -0
- runs/Jul10_06-02-16_49a3fa77351e/events.out.tfevents.1720591341.49a3fa77351e.25532.2 +3 -0
- runs/Jul10_06-03-07_49a3fa77351e/events.out.tfevents.1720591395.49a3fa77351e.25532.3 +3 -0
- runs/Jul10_06-03-07_49a3fa77351e/events.out.tfevents.1720592102.49a3fa77351e.25532.4 +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/deberta-v3-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
model-index:
|
| 12 |
+
- name: subcate-cs
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# subcate-cs
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.0437
|
| 24 |
+
- Accuracy: 0.6014
|
| 25 |
+
- F1: 0.6753
|
| 26 |
+
- Precision: 0.7656
|
| 27 |
+
- Recall: 0.6040
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 3e-05
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 8
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 5
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 58 |
+
| 0.135 | 1.0 | 779 | 0.0751 | 0.1393 | 0.2430 | 0.9731 | 0.1388 |
|
| 59 |
+
| 0.0671 | 2.0 | 1558 | 0.0570 | 0.3389 | 0.4840 | 0.8453 | 0.3391 |
|
| 60 |
+
| 0.0573 | 3.0 | 2337 | 0.0486 | 0.5045 | 0.6208 | 0.8059 | 0.5048 |
|
| 61 |
+
| 0.0453 | 4.0 | 3116 | 0.0444 | 0.5738 | 0.6610 | 0.7759 | 0.5758 |
|
| 62 |
+
| 0.041 | 5.0 | 3895 | 0.0437 | 0.6014 | 0.6753 | 0.7656 | 0.6040 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.41.2
|
| 68 |
+
- Pytorch 2.3.0+cu121
|
| 69 |
+
- Datasets 2.20.0
|
| 70 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Messengerial /Courier Service Request",
|
| 12 |
+
"1": "Client Viewing Request",
|
| 13 |
+
"2": "Planned activities",
|
| 14 |
+
"3": "Checklists & Reports",
|
| 15 |
+
"4": "Assistance",
|
| 16 |
+
"5": "Parking / Car pass Requests",
|
| 17 |
+
"6": "Reservation (Rooms & Event Space)",
|
| 18 |
+
"7": "Cleaning request",
|
| 19 |
+
"8": "Gatepass Request",
|
| 20 |
+
"9": "Info or Document Request",
|
| 21 |
+
"10": "Office Set-up",
|
| 22 |
+
"11": "Photo / Video Request",
|
| 23 |
+
"12": "Supplies Request",
|
| 24 |
+
"13": "Visitor Access Request",
|
| 25 |
+
"14": "Access Cards / Room or Office Access Requests",
|
| 26 |
+
"15": "Checklists and Reports",
|
| 27 |
+
"16": "Storage Request",
|
| 28 |
+
"17": "AC Concerns",
|
| 29 |
+
"18": "New Office Transfer",
|
| 30 |
+
"19": "Repairs and Maintenance Request",
|
| 31 |
+
"20": "Phone / Sim Requests",
|
| 32 |
+
"21": "Move In Request",
|
| 33 |
+
"22": "Invoices",
|
| 34 |
+
"23": "Work Permit",
|
| 35 |
+
"24": "Medical Certificate Validation",
|
| 36 |
+
"25": "Move Out Request",
|
| 37 |
+
"26": "Furniture Move",
|
| 38 |
+
"27": "Security Breach/ Theft",
|
| 39 |
+
"28": "Safety Concerns",
|
| 40 |
+
"29": "Other Medical Concerns",
|
| 41 |
+
"30": "New Hire Kit Request",
|
| 42 |
+
"31": "Approval Request",
|
| 43 |
+
"32": "Shuttle Booking",
|
| 44 |
+
"33": "Costing Request",
|
| 45 |
+
"34": "Gate Pass Request",
|
| 46 |
+
"35": "HMO Account Update",
|
| 47 |
+
"36": "Van Repairs & Maintenance",
|
| 48 |
+
"37": "Power Outage",
|
| 49 |
+
"38": "Printing/Scan request",
|
| 50 |
+
"39": "Orientation / Training Request"
|
| 51 |
+
},
|
| 52 |
+
"initializer_range": 0.02,
|
| 53 |
+
"intermediate_size": 3072,
|
| 54 |
+
"label2id": {
|
| 55 |
+
"AC Concerns": 17,
|
| 56 |
+
"Access Cards / Room or Office Access Requests": 14,
|
| 57 |
+
"Approval Request": 31,
|
| 58 |
+
"Assistance": 4,
|
| 59 |
+
"Checklists & Reports": 3,
|
| 60 |
+
"Checklists and Reports": 15,
|
| 61 |
+
"Cleaning request": 7,
|
| 62 |
+
"Client Viewing Request": 1,
|
| 63 |
+
"Costing Request": 33,
|
| 64 |
+
"Furniture Move": 26,
|
| 65 |
+
"Gate Pass Request": 34,
|
| 66 |
+
"Gatepass Request": 8,
|
| 67 |
+
"HMO Account Update": 35,
|
| 68 |
+
"Info or Document Request": 9,
|
| 69 |
+
"Invoices": 22,
|
| 70 |
+
"Medical Certificate Validation": 24,
|
| 71 |
+
"Messengerial /Courier Service Request": 0,
|
| 72 |
+
"Move In Request": 21,
|
| 73 |
+
"Move Out Request": 25,
|
| 74 |
+
"New Hire Kit Request": 30,
|
| 75 |
+
"New Office Transfer": 18,
|
| 76 |
+
"Office Set-up": 10,
|
| 77 |
+
"Orientation / Training Request": 39,
|
| 78 |
+
"Other Medical Concerns": 29,
|
| 79 |
+
"Parking / Car pass Requests": 5,
|
| 80 |
+
"Phone / Sim Requests": 20,
|
| 81 |
+
"Photo / Video Request": 11,
|
| 82 |
+
"Planned activities": 2,
|
| 83 |
+
"Power Outage": 37,
|
| 84 |
+
"Printing/Scan request": 38,
|
| 85 |
+
"Repairs and Maintenance Request": 19,
|
| 86 |
+
"Reservation (Rooms & Event Space)": 6,
|
| 87 |
+
"Safety Concerns": 28,
|
| 88 |
+
"Security Breach/ Theft": 27,
|
| 89 |
+
"Shuttle Booking": 32,
|
| 90 |
+
"Storage Request": 16,
|
| 91 |
+
"Supplies Request": 12,
|
| 92 |
+
"Van Repairs & Maintenance": 36,
|
| 93 |
+
"Visitor Access Request": 13,
|
| 94 |
+
"Work Permit": 23
|
| 95 |
+
},
|
| 96 |
+
"layer_norm_eps": 1e-07,
|
| 97 |
+
"max_position_embeddings": 512,
|
| 98 |
+
"max_relative_positions": -1,
|
| 99 |
+
"model_type": "deberta-v2",
|
| 100 |
+
"norm_rel_ebd": "layer_norm",
|
| 101 |
+
"num_attention_heads": 12,
|
| 102 |
+
"num_hidden_layers": 6,
|
| 103 |
+
"pad_token_id": 0,
|
| 104 |
+
"pooler_dropout": 0,
|
| 105 |
+
"pooler_hidden_act": "gelu",
|
| 106 |
+
"pooler_hidden_size": 768,
|
| 107 |
+
"pos_att_type": [
|
| 108 |
+
"p2c",
|
| 109 |
+
"c2p"
|
| 110 |
+
],
|
| 111 |
+
"position_biased_input": false,
|
| 112 |
+
"position_buckets": 256,
|
| 113 |
+
"problem_type": "multi_label_classification",
|
| 114 |
+
"relative_attention": true,
|
| 115 |
+
"share_att_key": true,
|
| 116 |
+
"torch_dtype": "float32",
|
| 117 |
+
"transformers_version": "4.41.2",
|
| 118 |
+
"type_vocab_size": 0,
|
| 119 |
+
"vocab_size": 128100
|
| 120 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:254e75a5d61ab7102add71229281cd07299bd7dc4970d4992ff4590a5b4e6dcc
|
| 3 |
+
size 567715456
|
runs/Jul10_06-01-50_49a3fa77351e/events.out.tfevents.1720591317.49a3fa77351e.25532.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9ea0ba4564666f7acb04201f4726a999a077ff40bbfcab29b001aa0d73dde07
|
| 3 |
+
size 8465
|
runs/Jul10_06-02-16_49a3fa77351e/events.out.tfevents.1720591341.49a3fa77351e.25532.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2bfed5ec5979e98446d81cbec0b5602846898a4dc501660e9e25f27c9f992d7
|
| 3 |
+
size 8465
|
runs/Jul10_06-03-07_49a3fa77351e/events.out.tfevents.1720591395.49a3fa77351e.25532.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f467a135cc2116fab909ddcf720d117cc2a909fff12189d6e576f1fdd3b25aab
|
| 3 |
+
size 11833
|
runs/Jul10_06-03-07_49a3fa77351e/events.out.tfevents.1720592102.49a3fa77351e.25532.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c4b340edb9e8a2c2325166d01c56d25e951fc1c0d74e8514455f3b9055b27ac
|
| 3 |
+
size 560
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:573c28c95c80f8954bd19618bc4f63ed94c1be66ec3f84992e2828d4618c7f18
|
| 3 |
+
size 5112
|