Upload folder using huggingface_hub
Browse files- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/added_tokens.json +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/added_tokens.json +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/config.json +81 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/model.safetensors +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/optimizer.pt +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/rng_state.pth +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/scheduler.pt +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/special_tokens_map.json +15 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/spm.model +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/tokenizer.json +0 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/tokenizer_config.json +60 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/trainer_state.json +97 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/training_args.bin +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/config.json +81 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/pytorch_model.bin +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/special_tokens_map.json +15 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/spm.model +3 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/tokenizer.json +0 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/tokenizer_config.json +60 -0
- open-pii-masking-500k-ai4privacy/span-deberta-v3-base/training_meta.json +31 -0
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaAdvancedSpanClassifier"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "O",
|
| 12 |
+
"1": "AGE",
|
| 13 |
+
"2": "BUILDINGNUM",
|
| 14 |
+
"3": "CITY",
|
| 15 |
+
"4": "CREDITCARDNUMBER",
|
| 16 |
+
"5": "DATE",
|
| 17 |
+
"6": "DRIVERLICENSENUM",
|
| 18 |
+
"7": "EMAIL",
|
| 19 |
+
"8": "GENDER",
|
| 20 |
+
"9": "GIVENNAME",
|
| 21 |
+
"10": "IDCARDNUM",
|
| 22 |
+
"11": "PASSPORTNUM",
|
| 23 |
+
"12": "SEX",
|
| 24 |
+
"13": "SOCIALNUM",
|
| 25 |
+
"14": "STREET",
|
| 26 |
+
"15": "SURNAME",
|
| 27 |
+
"16": "TAXNUM",
|
| 28 |
+
"17": "TELEPHONENUM",
|
| 29 |
+
"18": "TIME",
|
| 30 |
+
"19": "TITLE",
|
| 31 |
+
"20": "ZIPCODE"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"AGE": 1,
|
| 37 |
+
"BUILDINGNUM": 2,
|
| 38 |
+
"CITY": 3,
|
| 39 |
+
"CREDITCARDNUMBER": 4,
|
| 40 |
+
"DATE": 5,
|
| 41 |
+
"DRIVERLICENSENUM": 6,
|
| 42 |
+
"EMAIL": 7,
|
| 43 |
+
"GENDER": 8,
|
| 44 |
+
"GIVENNAME": 9,
|
| 45 |
+
"IDCARDNUM": 10,
|
| 46 |
+
"O": 0,
|
| 47 |
+
"PASSPORTNUM": 11,
|
| 48 |
+
"SEX": 12,
|
| 49 |
+
"SOCIALNUM": 13,
|
| 50 |
+
"STREET": 14,
|
| 51 |
+
"SURNAME": 15,
|
| 52 |
+
"TAXNUM": 16,
|
| 53 |
+
"TELEPHONENUM": 17,
|
| 54 |
+
"TIME": 18,
|
| 55 |
+
"TITLE": 19,
|
| 56 |
+
"ZIPCODE": 20
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-07,
|
| 59 |
+
"legacy": true,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"max_relative_positions": -1,
|
| 62 |
+
"model_type": "deberta-v2",
|
| 63 |
+
"norm_rel_ebd": "layer_norm",
|
| 64 |
+
"num_attention_heads": 12,
|
| 65 |
+
"num_hidden_layers": 12,
|
| 66 |
+
"pad_token_id": 0,
|
| 67 |
+
"pooler_dropout": 0,
|
| 68 |
+
"pooler_hidden_act": "gelu",
|
| 69 |
+
"pooler_hidden_size": 768,
|
| 70 |
+
"pos_att_type": [
|
| 71 |
+
"p2c",
|
| 72 |
+
"c2p"
|
| 73 |
+
],
|
| 74 |
+
"position_biased_input": false,
|
| 75 |
+
"position_buckets": 256,
|
| 76 |
+
"relative_attention": true,
|
| 77 |
+
"share_att_key": true,
|
| 78 |
+
"transformers_version": "4.57.6",
|
| 79 |
+
"type_vocab_size": 0,
|
| 80 |
+
"vocab_size": 128100
|
| 81 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc382cbc62c876e60c28589ea611948521f70cc59bab7ea767fc38c45bbdfc25
|
| 3 |
+
size 741362860
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96526d609db1e038e1d4cb81deb67c7f9a315ee99b6aa23a5c199902d14b80e8
|
| 3 |
+
size 1482849419
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa7c961931834e93c9c9b588b061136887e4aa9e54c9ddcd465a02bb4057a05c
|
| 3 |
+
size 14645
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07f62f5489b3009352c2691236646292c9fa02eb6b1bc0f345366615fca35cc7
|
| 3 |
+
size 1465
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/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 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "[CLS]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "[SEP]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "[UNK]",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"128000": {
|
| 37 |
+
"content": "[MASK]",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "[CLS]",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "[CLS]",
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "[MASK]",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"split_by_punct": false,
|
| 57 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 58 |
+
"unk_token": "[UNK]",
|
| 59 |
+
"vocab_type": "spm"
|
| 60 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/trainer_state.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4836,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.20682523267838676,
|
| 14 |
+
"grad_norm": 0.017236677929759026,
|
| 15 |
+
"learning_rate": 4.9827665441176475e-06,
|
| 16 |
+
"loss": 0.0278,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.4136504653567735,
|
| 21 |
+
"grad_norm": 0.00843733549118042,
|
| 22 |
+
"learning_rate": 4.408318014705883e-06,
|
| 23 |
+
"loss": 0.0043,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6204756980351603,
|
| 28 |
+
"grad_norm": 0.006669110152870417,
|
| 29 |
+
"learning_rate": 3.833869485294118e-06,
|
| 30 |
+
"loss": 0.002,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.827300930713547,
|
| 35 |
+
"grad_norm": 0.00830770656466484,
|
| 36 |
+
"learning_rate": 3.259420955882353e-06,
|
| 37 |
+
"loss": 0.0014,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0339193381592555,
|
| 42 |
+
"grad_norm": 0.0074545168317854404,
|
| 43 |
+
"learning_rate": 2.6849724264705885e-06,
|
| 44 |
+
"loss": 0.0012,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.2407445708376421,
|
| 49 |
+
"grad_norm": 0.006495707668364048,
|
| 50 |
+
"learning_rate": 2.1105238970588236e-06,
|
| 51 |
+
"loss": 0.001,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.447569803516029,
|
| 56 |
+
"grad_norm": 0.005083563271909952,
|
| 57 |
+
"learning_rate": 1.5360753676470587e-06,
|
| 58 |
+
"loss": 0.0009,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.6543950361944157,
|
| 63 |
+
"grad_norm": 0.004685825668275356,
|
| 64 |
+
"learning_rate": 9.61626838235294e-07,
|
| 65 |
+
"loss": 0.0009,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.8612202688728026,
|
| 70 |
+
"grad_norm": 0.005011296831071377,
|
| 71 |
+
"learning_rate": 3.8717830882352943e-07,
|
| 72 |
+
"loss": 0.0009,
|
| 73 |
+
"step": 4500
|
| 74 |
+
}
|
| 75 |
+
],
|
| 76 |
+
"logging_steps": 500,
|
| 77 |
+
"max_steps": 4836,
|
| 78 |
+
"num_input_tokens_seen": 0,
|
| 79 |
+
"num_train_epochs": 2,
|
| 80 |
+
"save_steps": 500,
|
| 81 |
+
"stateful_callbacks": {
|
| 82 |
+
"TrainerControl": {
|
| 83 |
+
"args": {
|
| 84 |
+
"should_epoch_stop": false,
|
| 85 |
+
"should_evaluate": false,
|
| 86 |
+
"should_log": false,
|
| 87 |
+
"should_save": true,
|
| 88 |
+
"should_training_stop": true
|
| 89 |
+
},
|
| 90 |
+
"attributes": {}
|
| 91 |
+
}
|
| 92 |
+
},
|
| 93 |
+
"total_flos": 4.282386863824843e+16,
|
| 94 |
+
"train_batch_size": 32,
|
| 95 |
+
"trial_name": null,
|
| 96 |
+
"trial_params": null
|
| 97 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/checkpoint-4836/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03022649e3755d4897de2c5ea16b3bf40a2e5c3e53ea7ae25ecde49bc7ef5180
|
| 3 |
+
size 5905
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaAdvancedSpanClassifier"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "O",
|
| 12 |
+
"1": "AGE",
|
| 13 |
+
"2": "BUILDINGNUM",
|
| 14 |
+
"3": "CITY",
|
| 15 |
+
"4": "CREDITCARDNUMBER",
|
| 16 |
+
"5": "DATE",
|
| 17 |
+
"6": "DRIVERLICENSENUM",
|
| 18 |
+
"7": "EMAIL",
|
| 19 |
+
"8": "GENDER",
|
| 20 |
+
"9": "GIVENNAME",
|
| 21 |
+
"10": "IDCARDNUM",
|
| 22 |
+
"11": "PASSPORTNUM",
|
| 23 |
+
"12": "SEX",
|
| 24 |
+
"13": "SOCIALNUM",
|
| 25 |
+
"14": "STREET",
|
| 26 |
+
"15": "SURNAME",
|
| 27 |
+
"16": "TAXNUM",
|
| 28 |
+
"17": "TELEPHONENUM",
|
| 29 |
+
"18": "TIME",
|
| 30 |
+
"19": "TITLE",
|
| 31 |
+
"20": "ZIPCODE"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"AGE": 1,
|
| 37 |
+
"BUILDINGNUM": 2,
|
| 38 |
+
"CITY": 3,
|
| 39 |
+
"CREDITCARDNUMBER": 4,
|
| 40 |
+
"DATE": 5,
|
| 41 |
+
"DRIVERLICENSENUM": 6,
|
| 42 |
+
"EMAIL": 7,
|
| 43 |
+
"GENDER": 8,
|
| 44 |
+
"GIVENNAME": 9,
|
| 45 |
+
"IDCARDNUM": 10,
|
| 46 |
+
"O": 0,
|
| 47 |
+
"PASSPORTNUM": 11,
|
| 48 |
+
"SEX": 12,
|
| 49 |
+
"SOCIALNUM": 13,
|
| 50 |
+
"STREET": 14,
|
| 51 |
+
"SURNAME": 15,
|
| 52 |
+
"TAXNUM": 16,
|
| 53 |
+
"TELEPHONENUM": 17,
|
| 54 |
+
"TIME": 18,
|
| 55 |
+
"TITLE": 19,
|
| 56 |
+
"ZIPCODE": 20
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-07,
|
| 59 |
+
"legacy": true,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"max_relative_positions": -1,
|
| 62 |
+
"model_type": "deberta-v2",
|
| 63 |
+
"norm_rel_ebd": "layer_norm",
|
| 64 |
+
"num_attention_heads": 12,
|
| 65 |
+
"num_hidden_layers": 12,
|
| 66 |
+
"pad_token_id": 0,
|
| 67 |
+
"pooler_dropout": 0,
|
| 68 |
+
"pooler_hidden_act": "gelu",
|
| 69 |
+
"pooler_hidden_size": 768,
|
| 70 |
+
"pos_att_type": [
|
| 71 |
+
"p2c",
|
| 72 |
+
"c2p"
|
| 73 |
+
],
|
| 74 |
+
"position_biased_input": false,
|
| 75 |
+
"position_buckets": 256,
|
| 76 |
+
"relative_attention": true,
|
| 77 |
+
"share_att_key": true,
|
| 78 |
+
"transformers_version": "4.57.6",
|
| 79 |
+
"type_vocab_size": 0,
|
| 80 |
+
"vocab_size": 128100
|
| 81 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:989b2ac28b620845f1b70a9f019bb3875eace85d532e94a07aa0eeb021c0b5de
|
| 3 |
+
size 741424783
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/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 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "[CLS]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "[SEP]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "[UNK]",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"128000": {
|
| 37 |
+
"content": "[MASK]",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "[CLS]",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "[CLS]",
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "[MASK]",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"split_by_punct": false,
|
| 57 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 58 |
+
"unk_token": "[UNK]",
|
| 59 |
+
"vocab_type": "spm"
|
| 60 |
+
}
|
open-pii-masking-500k-ai4privacy/span-deberta-v3-base/training_meta.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "span_based",
|
| 3 |
+
"base_model": "microsoft/deberta-v3-base",
|
| 4 |
+
"dataset": "open-pii-masking-500k-ai4privacy",
|
| 5 |
+
"label_list": [
|
| 6 |
+
"O",
|
| 7 |
+
"AGE",
|
| 8 |
+
"BUILDINGNUM",
|
| 9 |
+
"CITY",
|
| 10 |
+
"CREDITCARDNUMBER",
|
| 11 |
+
"DATE",
|
| 12 |
+
"DRIVERLICENSENUM",
|
| 13 |
+
"EMAIL",
|
| 14 |
+
"GENDER",
|
| 15 |
+
"GIVENNAME",
|
| 16 |
+
"IDCARDNUM",
|
| 17 |
+
"PASSPORTNUM",
|
| 18 |
+
"SEX",
|
| 19 |
+
"SOCIALNUM",
|
| 20 |
+
"STREET",
|
| 21 |
+
"SURNAME",
|
| 22 |
+
"TAXNUM",
|
| 23 |
+
"TELEPHONENUM",
|
| 24 |
+
"TIME",
|
| 25 |
+
"TITLE",
|
| 26 |
+
"ZIPCODE"
|
| 27 |
+
],
|
| 28 |
+
"max_seq_length": 512,
|
| 29 |
+
"max_span_width": 30,
|
| 30 |
+
"timestamp": "2026-04-07T02:35:27.258435"
|
| 31 |
+
}
|