hr_techgroup
Browse files- README.md +70 -0
- added_tokens.json +3 -0
- config.json +214 -0
- model.safetensors +3 -0
- runs/Jul23_07-52-02_9cdcb57939d9/events.out.tfevents.1721721130.9cdcb57939d9.2051.0 +3 -0
- runs/Jul23_07-52-02_9cdcb57939d9/events.out.tfevents.1721721844.9cdcb57939d9.2051.1 +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: tangminhanh/hr_cate
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
model-index:
|
| 12 |
+
- name: hr_subcate
|
| 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 |
+
# hr_subcate
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [tangminhanh/hr_cate](https://huggingface.co/tangminhanh/hr_cate) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.0156
|
| 24 |
+
- Accuracy: 0.7103
|
| 25 |
+
- F1: 0.8021
|
| 26 |
+
- Precision: 0.9213
|
| 27 |
+
- Recall: 0.7103
|
| 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: 2e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 32
|
| 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 |
+
| No log | 1.0 | 453 | 0.0316 | 0.4588 | 0.6210 | 0.9640 | 0.4581 |
|
| 59 |
+
| 0.0998 | 2.0 | 906 | 0.0212 | 0.5843 | 0.7185 | 0.9338 | 0.5839 |
|
| 60 |
+
| 0.0248 | 3.0 | 1359 | 0.0174 | 0.6827 | 0.7868 | 0.9293 | 0.6821 |
|
| 61 |
+
| 0.0184 | 4.0 | 1812 | 0.0162 | 0.7009 | 0.7942 | 0.9163 | 0.7009 |
|
| 62 |
+
| 0.0152 | 5.0 | 2265 | 0.0156 | 0.7103 | 0.8021 | 0.9213 | 0.7103 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.42.4
|
| 68 |
+
- Pytorch 2.3.1+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 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "tangminhanh/hr_cate",
|
| 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": "Viewing of pay slip in HRIS",
|
| 12 |
+
"1": "TaaS | Sprout - Change in Personal Information",
|
| 13 |
+
"2": "HRIS Log in Issue",
|
| 14 |
+
"3": "ID/Badge Card Request",
|
| 15 |
+
"4": "HRIS - Approver Account Creation\u00a0",
|
| 16 |
+
"5": "HRIS - Offboarding\u00a0",
|
| 17 |
+
"6": "HRIS - Work Information Update",
|
| 18 |
+
"7": "EAA Updates\u00a0",
|
| 19 |
+
"8": "Other HRIS Concerns",
|
| 20 |
+
"9": "Inaccurate Data Correction",
|
| 21 |
+
"10": "Personal Data Updating",
|
| 22 |
+
"11": "Complicated Report",
|
| 23 |
+
"12": "Simple Report",
|
| 24 |
+
"13": "Exit Management Concern",
|
| 25 |
+
"14": "Employement Verification",
|
| 26 |
+
"15": "OT Allowance reimbursement",
|
| 27 |
+
"16": "Reimbursable allowance (part of compensation)",
|
| 28 |
+
"17": "Endorsement for Salary Increase",
|
| 29 |
+
"18": "Endorsement for Promotion",
|
| 30 |
+
"19": "Endorsement for Lateral Movement",
|
| 31 |
+
"20": "Endorsement for Communication Allowance",
|
| 32 |
+
"21": "Other movement endorsement/process inquiries",
|
| 33 |
+
"22": "Certificate of Employment Request",
|
| 34 |
+
"23": "Non-Disclosure Agreement Request",
|
| 35 |
+
"24": "Memo Request",
|
| 36 |
+
"25": "Employment Contract / Consultancy Agreement request",
|
| 37 |
+
"26": "Personal information update",
|
| 38 |
+
"27": "Marriage Certificate/Birth Certificate/Death Certificate/Solo Parent ID upload",
|
| 39 |
+
"28": "HRIS unlock request",
|
| 40 |
+
"29": "HRIS approver change request",
|
| 41 |
+
"30": "HRIS work schedule change request",
|
| 42 |
+
"31": "HRIS filing error / system glitch",
|
| 43 |
+
"32": "Cancellation of Leave/Schedule Adjustment/Official Business",
|
| 44 |
+
"33": "Access level change",
|
| 45 |
+
"34": "Location update",
|
| 46 |
+
"35": "Other HRIS requests and inquiries",
|
| 47 |
+
"36": "Incident Report template",
|
| 48 |
+
"37": "Incident Report submission / Notice to Explain (NTE) issuance request",
|
| 49 |
+
"38": "Return to Work Order Request",
|
| 50 |
+
"39": "Generic inquiries \u2013 individual contributor",
|
| 51 |
+
"40": "Team management-related inquiries \u2013 inquiries from people managers/leadership team (for People Managers only)",
|
| 52 |
+
"41": "Certificate of Partial Completion",
|
| 53 |
+
"42": "Certificate of Completion",
|
| 54 |
+
"43": "Internship allowance follow up",
|
| 55 |
+
"44": "Checking of current internship hours",
|
| 56 |
+
"45": "Other Internship Inquiries",
|
| 57 |
+
"46": "Paternity leave",
|
| 58 |
+
"47": "Bereavement benefit",
|
| 59 |
+
"48": "Solo parent leave",
|
| 60 |
+
"49": "Maternity benefit",
|
| 61 |
+
"50": "Company-initiated leave benefit",
|
| 62 |
+
"51": "Special leave for women and other leave benefits",
|
| 63 |
+
"52": "Compensatory Time Off",
|
| 64 |
+
"53": "All mental health-related inquiries/requests",
|
| 65 |
+
"54": "Request for Bonus / Incentive Computation",
|
| 66 |
+
"55": "Request for Sample Payout Computation",
|
| 67 |
+
"56": "Pay dispute/payroll concern",
|
| 68 |
+
"57": "Request for Computation of Final Pay",
|
| 69 |
+
"58": "Request for Computation of Intern Allowance",
|
| 70 |
+
"59": "Verification of Salary Range Status",
|
| 71 |
+
"60": "Request for Issuance of Authorization To Deduct",
|
| 72 |
+
"61": "Concerns Related to Sprout and Savii Loans",
|
| 73 |
+
"62": "Other Payroll-related concerns",
|
| 74 |
+
"63": "Submission of Reimbursement Form and Receipts",
|
| 75 |
+
"64": "3rd Month Performance Review upload",
|
| 76 |
+
"65": "5th Month Performance Review upload",
|
| 77 |
+
"66": "Coaching Logs upload",
|
| 78 |
+
"67": "Request for Coaching Logs Form",
|
| 79 |
+
"68": "Performance Improvement Plan Inquiry/Orientation",
|
| 80 |
+
"69": "Other performance-related inquiries",
|
| 81 |
+
"70": "Simple Reports",
|
| 82 |
+
"71": "Complex Reports / Reports Requiring Analytics",
|
| 83 |
+
"72": "Offboarding request (for People Managers only)",
|
| 84 |
+
"73": "Clearance follow up",
|
| 85 |
+
"74": "Offboarding-related inquiries",
|
| 86 |
+
"75": "Request for Online Certification of Government Loan Application",
|
| 87 |
+
"76": "Request for Continuation of Government Loan from Previous Employer",
|
| 88 |
+
"77": "Request for Certificate of Contribution - SSS|Philhealth|Pag-Ibig",
|
| 89 |
+
"78": "Request for Philhealth forms (for hospitalization purposes)",
|
| 90 |
+
"79": "Request for Increase in Pag-Ibig Contribution",
|
| 91 |
+
"80": "Request for Salary Deduction of MP2 savings",
|
| 92 |
+
"81": "Request for TIN Verification",
|
| 93 |
+
"82": "Other SSS, Philhealth, Pag-Ibig, and BIR Concerns",
|
| 94 |
+
"83": "Eligibility for Rehire (for Talent Acquisition Only)",
|
| 95 |
+
"84": "Credit Card/Cash Advance Limit (for Finance Only)",
|
| 96 |
+
"85": "All other concerns raised to C&B Internal that do not fall under the above categories",
|
| 97 |
+
"86": "PEX Pubmats/Collaterals Request"
|
| 98 |
+
},
|
| 99 |
+
"initializer_range": 0.02,
|
| 100 |
+
"intermediate_size": 3072,
|
| 101 |
+
"label2id": {
|
| 102 |
+
"3rd Month Performance Review upload": 64,
|
| 103 |
+
"5th Month Performance Review upload": 65,
|
| 104 |
+
"Access level change": 33,
|
| 105 |
+
"All mental health-related inquiries/requests": 53,
|
| 106 |
+
"All other concerns raised to C&B Internal that do not fall under the above categories": 85,
|
| 107 |
+
"Bereavement benefit": 47,
|
| 108 |
+
"Cancellation of Leave/Schedule Adjustment/Official Business": 32,
|
| 109 |
+
"Certificate of Completion": 42,
|
| 110 |
+
"Certificate of Employment Request": 22,
|
| 111 |
+
"Certificate of Partial Completion": 41,
|
| 112 |
+
"Checking of current internship hours": 44,
|
| 113 |
+
"Clearance follow up": 73,
|
| 114 |
+
"Coaching Logs upload": 66,
|
| 115 |
+
"Company-initiated leave benefit": 50,
|
| 116 |
+
"Compensatory Time Off": 52,
|
| 117 |
+
"Complex Reports / Reports Requiring Analytics": 71,
|
| 118 |
+
"Complicated Report": 11,
|
| 119 |
+
"Concerns Related to Sprout and Savii Loans": 61,
|
| 120 |
+
"Credit Card/Cash Advance Limit (for Finance Only)": 84,
|
| 121 |
+
"EAA Updates\u00a0": 7,
|
| 122 |
+
"Eligibility for Rehire (for Talent Acquisition Only)": 83,
|
| 123 |
+
"Employement Verification": 14,
|
| 124 |
+
"Employment Contract / Consultancy Agreement request": 25,
|
| 125 |
+
"Endorsement for Communication Allowance": 20,
|
| 126 |
+
"Endorsement for Lateral Movement": 19,
|
| 127 |
+
"Endorsement for Promotion": 18,
|
| 128 |
+
"Endorsement for Salary Increase": 17,
|
| 129 |
+
"Exit Management Concern": 13,
|
| 130 |
+
"Generic inquiries \u2013 individual contributor": 39,
|
| 131 |
+
"HRIS - Approver Account Creation\u00a0": 4,
|
| 132 |
+
"HRIS - Offboarding\u00a0": 5,
|
| 133 |
+
"HRIS - Work Information Update": 6,
|
| 134 |
+
"HRIS Log in Issue": 2,
|
| 135 |
+
"HRIS approver change request": 29,
|
| 136 |
+
"HRIS filing error / system glitch": 31,
|
| 137 |
+
"HRIS unlock request": 28,
|
| 138 |
+
"HRIS work schedule change request": 30,
|
| 139 |
+
"ID/Badge Card Request": 3,
|
| 140 |
+
"Inaccurate Data Correction": 9,
|
| 141 |
+
"Incident Report submission / Notice to Explain (NTE) issuance request": 37,
|
| 142 |
+
"Incident Report template": 36,
|
| 143 |
+
"Internship allowance follow up": 43,
|
| 144 |
+
"Location update": 34,
|
| 145 |
+
"Marriage Certificate/Birth Certificate/Death Certificate/Solo Parent ID upload": 27,
|
| 146 |
+
"Maternity benefit": 49,
|
| 147 |
+
"Memo Request": 24,
|
| 148 |
+
"Non-Disclosure Agreement Request": 23,
|
| 149 |
+
"OT Allowance reimbursement": 15,
|
| 150 |
+
"Offboarding request (for People Managers only)": 72,
|
| 151 |
+
"Offboarding-related inquiries": 74,
|
| 152 |
+
"Other HRIS Concerns": 8,
|
| 153 |
+
"Other HRIS requests and inquiries": 35,
|
| 154 |
+
"Other Internship Inquiries": 45,
|
| 155 |
+
"Other Payroll-related concerns": 62,
|
| 156 |
+
"Other SSS, Philhealth, Pag-Ibig, and BIR Concerns": 82,
|
| 157 |
+
"Other movement endorsement/process inquiries": 21,
|
| 158 |
+
"Other performance-related inquiries": 69,
|
| 159 |
+
"PEX Pubmats/Collaterals Request": 86,
|
| 160 |
+
"Paternity leave": 46,
|
| 161 |
+
"Pay dispute/payroll concern": 56,
|
| 162 |
+
"Performance Improvement Plan Inquiry/Orientation": 68,
|
| 163 |
+
"Personal Data Updating": 10,
|
| 164 |
+
"Personal information update": 26,
|
| 165 |
+
"Reimbursable allowance (part of compensation)": 16,
|
| 166 |
+
"Request for Bonus / Incentive Computation": 54,
|
| 167 |
+
"Request for Certificate of Contribution - SSS|Philhealth|Pag-Ibig": 77,
|
| 168 |
+
"Request for Coaching Logs Form": 67,
|
| 169 |
+
"Request for Computation of Final Pay": 57,
|
| 170 |
+
"Request for Computation of Intern Allowance": 58,
|
| 171 |
+
"Request for Continuation of Government Loan from Previous Employer": 76,
|
| 172 |
+
"Request for Increase in Pag-Ibig Contribution": 79,
|
| 173 |
+
"Request for Issuance of Authorization To Deduct": 60,
|
| 174 |
+
"Request for Online Certification of Government Loan Application": 75,
|
| 175 |
+
"Request for Philhealth forms (for hospitalization purposes)": 78,
|
| 176 |
+
"Request for Salary Deduction of MP2 savings": 80,
|
| 177 |
+
"Request for Sample Payout Computation": 55,
|
| 178 |
+
"Request for TIN Verification": 81,
|
| 179 |
+
"Return to Work Order Request": 38,
|
| 180 |
+
"Simple Report": 12,
|
| 181 |
+
"Simple Reports": 70,
|
| 182 |
+
"Solo parent leave": 48,
|
| 183 |
+
"Special leave for women and other leave benefits": 51,
|
| 184 |
+
"Submission of Reimbursement Form and Receipts": 63,
|
| 185 |
+
"TaaS | Sprout - Change in Personal Information": 1,
|
| 186 |
+
"Team management-related inquiries \u2013 inquiries from people managers/leadership team (for People Managers only)": 40,
|
| 187 |
+
"Verification of Salary Range Status": 59,
|
| 188 |
+
"Viewing of pay slip in HRIS": 0
|
| 189 |
+
},
|
| 190 |
+
"layer_norm_eps": 1e-07,
|
| 191 |
+
"max_position_embeddings": 512,
|
| 192 |
+
"max_relative_positions": -1,
|
| 193 |
+
"model_type": "deberta-v2",
|
| 194 |
+
"norm_rel_ebd": "layer_norm",
|
| 195 |
+
"num_attention_heads": 12,
|
| 196 |
+
"num_hidden_layers": 6,
|
| 197 |
+
"pad_token_id": 0,
|
| 198 |
+
"pooler_dropout": 0,
|
| 199 |
+
"pooler_hidden_act": "gelu",
|
| 200 |
+
"pooler_hidden_size": 768,
|
| 201 |
+
"pos_att_type": [
|
| 202 |
+
"p2c",
|
| 203 |
+
"c2p"
|
| 204 |
+
],
|
| 205 |
+
"position_biased_input": false,
|
| 206 |
+
"position_buckets": 256,
|
| 207 |
+
"problem_type": "multi_label_classification",
|
| 208 |
+
"relative_attention": true,
|
| 209 |
+
"share_att_key": true,
|
| 210 |
+
"torch_dtype": "float32",
|
| 211 |
+
"transformers_version": "4.42.4",
|
| 212 |
+
"type_vocab_size": 0,
|
| 213 |
+
"vocab_size": 128100
|
| 214 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16a8b2bc7ba60db08d1b2200f6315c0abbec83ca4d3a64e635a56f7878bbbc62
|
| 3 |
+
size 567860028
|
runs/Jul23_07-52-02_9cdcb57939d9/events.out.tfevents.1721721130.9cdcb57939d9.2051.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c3fda114962c9cc14cfb848ea8699bfeba9e7d405efcee78525a1bbd9e40f1f
|
| 3 |
+
size 17132
|
runs/Jul23_07-52-02_9cdcb57939d9/events.out.tfevents.1721721844.9cdcb57939d9.2051.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c293d2284c58422acc6452b4d78cac7130e707e5445e2f1b3b6f8e2273351e92
|
| 3 |
+
size 560
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
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 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 512,
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sep_token": "[SEP]",
|
| 57 |
+
"sp_model_kwargs": {},
|
| 58 |
+
"split_by_punct": false,
|
| 59 |
+
"stride": 0,
|
| 60 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"truncation_strategy": "longest_first",
|
| 63 |
+
"unk_token": "[UNK]",
|
| 64 |
+
"vocab_type": "spm"
|
| 65 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:addaf7285b3097e25b8d3ec757399e5fdd02969ef6ec0d83ac7d1741e20e007f
|
| 3 |
+
size 5112
|