Model save
Browse files- README.md +81 -0
- added_tokens.json +3 -0
- all_results.json +40 -0
- config.json +129 -0
- eval_results.json +34 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- train_results.json +9 -0
- trainer_state.json +148 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/deberta-v3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: deberta-v3-base_finetuned_bluegennx_run2.6
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# deberta-v3-base_finetuned_bluegennx_run2.6
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0968
|
19 |
+
- Overall Precision: 0.6921
|
20 |
+
- Overall Recall: 0.7279
|
21 |
+
- Overall F1: 0.7096
|
22 |
+
- Overall Accuracy: 0.9662
|
23 |
+
- Aadhar Card F1: 0.7499
|
24 |
+
- Age F1: 0.5816
|
25 |
+
- City F1: 0.7306
|
26 |
+
- Country F1: 0.6782
|
27 |
+
- Creditcardcvv F1: 0.7220
|
28 |
+
- Creditcardnumber F1: 0.7364
|
29 |
+
- Currency F1: 0.6681
|
30 |
+
- Currencyname F1: 0.0887
|
31 |
+
- Date F1: 0.6695
|
32 |
+
- Dateofbirth F1: 0.6437
|
33 |
+
- Email F1: 0.6486
|
34 |
+
- Expiry Date F1: 0.5623
|
35 |
+
- Organization F1: 0.7393
|
36 |
+
- Pan Card F1: 0.7191
|
37 |
+
- Person F1: 0.8088
|
38 |
+
- Phonenumber F1: 0.7218
|
39 |
+
- Secondary Address F1: 0.6801
|
40 |
+
- State F1: 0.7525
|
41 |
+
- Street F1: 0.8529
|
42 |
+
- Time F1: 0.7545
|
43 |
+
- Url F1: 0.5520
|
44 |
+
- Us Ssn F1: 0.9069
|
45 |
+
|
46 |
+
## Model description
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Intended uses & limitations
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training and evaluation data
|
55 |
+
|
56 |
+
More information needed
|
57 |
+
|
58 |
+
## Training procedure
|
59 |
+
|
60 |
+
### Training hyperparameters
|
61 |
+
|
62 |
+
The following hyperparameters were used during training:
|
63 |
+
- learning_rate: 5e-05
|
64 |
+
- train_batch_size: 36
|
65 |
+
- eval_batch_size: 8
|
66 |
+
- seed: 42
|
67 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
68 |
+
- lr_scheduler_type: cosine_with_restarts
|
69 |
+
- lr_scheduler_warmup_ratio: 0.2
|
70 |
+
- num_epochs: 3
|
71 |
+
|
72 |
+
### Training results
|
73 |
+
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.38.2
|
79 |
+
- Pytorch 2.1.0+cu118
|
80 |
+
- Datasets 2.18.0
|
81 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_AADHAR_CARD_f1": 0.7498692696531287,
|
4 |
+
"eval_AGE_f1": 0.5816216216216216,
|
5 |
+
"eval_CITY_f1": 0.7305788680869378,
|
6 |
+
"eval_COUNTRY_f1": 0.6781510192362905,
|
7 |
+
"eval_CREDITCARDCVV_f1": 0.7219837863614689,
|
8 |
+
"eval_CREDITCARDNUMBER_f1": 0.7364130434782609,
|
9 |
+
"eval_CURRENCYNAME_f1": 0.08870967741935484,
|
10 |
+
"eval_CURRENCY_f1": 0.6680805938494168,
|
11 |
+
"eval_DATEOFBIRTH_f1": 0.6437189496096523,
|
12 |
+
"eval_DATE_f1": 0.6695026178010473,
|
13 |
+
"eval_EMAIL_f1": 0.6485573173901742,
|
14 |
+
"eval_EXPIRY_DATE_f1": 0.5622568093385214,
|
15 |
+
"eval_ORGANIZATION_f1": 0.7392519632636763,
|
16 |
+
"eval_PAN_CARD_f1": 0.7191325638335083,
|
17 |
+
"eval_PERSON_f1": 0.8087976183243211,
|
18 |
+
"eval_PHONENUMBER_f1": 0.7218013468013468,
|
19 |
+
"eval_SECONDARY_ADDRESS_f1": 0.6800595238095238,
|
20 |
+
"eval_STATE_f1": 0.7525204032645223,
|
21 |
+
"eval_STREET_f1": 0.8528925619834711,
|
22 |
+
"eval_TIME_f1": 0.7544524441076165,
|
23 |
+
"eval_URL_f1": 0.5520118422823308,
|
24 |
+
"eval_US_SSN_f1": 0.90694626474443,
|
25 |
+
"eval_loss": 0.09682328253984451,
|
26 |
+
"eval_overall_accuracy": 0.9661661821488446,
|
27 |
+
"eval_overall_f1": 0.7095774460143962,
|
28 |
+
"eval_overall_precision": 0.6921289148206536,
|
29 |
+
"eval_overall_recall": 0.727928482300053,
|
30 |
+
"eval_runtime": 151.236,
|
31 |
+
"eval_samples": 18463,
|
32 |
+
"eval_samples_per_second": 122.081,
|
33 |
+
"eval_steps_per_second": 15.261,
|
34 |
+
"total_flos": 4.250069188231039e+16,
|
35 |
+
"train_loss": 0.2043684836406844,
|
36 |
+
"train_runtime": 5455.8592,
|
37 |
+
"train_samples": 73849,
|
38 |
+
"train_samples_per_second": 40.607,
|
39 |
+
"train_steps_per_second": 1.128
|
40 |
+
}
|
config.json
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForTokenClassification"
|
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": "O",
|
12 |
+
"1": "B-CREDITCARDCVV",
|
13 |
+
"2": "I-CREDITCARDCVV",
|
14 |
+
"3": "B-CITY",
|
15 |
+
"4": "I-CITY",
|
16 |
+
"5": "B-CREDITCARDNUMBER",
|
17 |
+
"6": "I-CREDITCARDNUMBER",
|
18 |
+
"7": "B-PAN_CARD",
|
19 |
+
"8": "I-PAN_CARD",
|
20 |
+
"9": "B-PHONENUMBER",
|
21 |
+
"10": "I-PHONENUMBER",
|
22 |
+
"11": "B-TIME",
|
23 |
+
"12": "I-TIME",
|
24 |
+
"13": "B-SECONDARY_ADDRESS",
|
25 |
+
"14": "I-SECONDARY_ADDRESS",
|
26 |
+
"15": "B-STREET",
|
27 |
+
"16": "I-STREET",
|
28 |
+
"17": "B-STATE",
|
29 |
+
"18": "I-STATE",
|
30 |
+
"19": "B-COUNTRY",
|
31 |
+
"20": "I-COUNTRY",
|
32 |
+
"21": "B-ORGANIZATION",
|
33 |
+
"22": "I-ORGANIZATION",
|
34 |
+
"23": "B-AGE",
|
35 |
+
"24": "I-AGE",
|
36 |
+
"25": "B-DATEOFBIRTH",
|
37 |
+
"26": "I-DATEOFBIRTH",
|
38 |
+
"27": "B-URL",
|
39 |
+
"28": "I-URL",
|
40 |
+
"29": "B-PERSON",
|
41 |
+
"30": "I-PERSON",
|
42 |
+
"31": "B-DATE",
|
43 |
+
"32": "I-DATE",
|
44 |
+
"33": "B-AADHAR_CARD",
|
45 |
+
"34": "I-AADHAR_CARD",
|
46 |
+
"35": "B-US_SSN",
|
47 |
+
"36": "I-US_SSN",
|
48 |
+
"37": "B-EMAIL",
|
49 |
+
"38": "I-EMAIL",
|
50 |
+
"39": "B-CURRENCY",
|
51 |
+
"40": "I-CURRENCY",
|
52 |
+
"41": "B-EXPIRY_DATE",
|
53 |
+
"42": "I-EXPIRY_DATE",
|
54 |
+
"43": "B-CURRENCYNAME",
|
55 |
+
"44": "I-CURRENCYNAME"
|
56 |
+
},
|
57 |
+
"initializer_range": 0.02,
|
58 |
+
"intermediate_size": 3072,
|
59 |
+
"label2id": {
|
60 |
+
"B-AADHAR_CARD": 33,
|
61 |
+
"B-AGE": 23,
|
62 |
+
"B-CITY": 3,
|
63 |
+
"B-COUNTRY": 19,
|
64 |
+
"B-CREDITCARDCVV": 1,
|
65 |
+
"B-CREDITCARDNUMBER": 5,
|
66 |
+
"B-CURRENCY": 39,
|
67 |
+
"B-CURRENCYNAME": 43,
|
68 |
+
"B-DATE": 31,
|
69 |
+
"B-DATEOFBIRTH": 25,
|
70 |
+
"B-EMAIL": 37,
|
71 |
+
"B-EXPIRY_DATE": 41,
|
72 |
+
"B-ORGANIZATION": 21,
|
73 |
+
"B-PAN_CARD": 7,
|
74 |
+
"B-PERSON": 29,
|
75 |
+
"B-PHONENUMBER": 9,
|
76 |
+
"B-SECONDARY_ADDRESS": 13,
|
77 |
+
"B-STATE": 17,
|
78 |
+
"B-STREET": 15,
|
79 |
+
"B-TIME": 11,
|
80 |
+
"B-URL": 27,
|
81 |
+
"B-US_SSN": 35,
|
82 |
+
"I-AADHAR_CARD": 34,
|
83 |
+
"I-AGE": 24,
|
84 |
+
"I-CITY": 4,
|
85 |
+
"I-COUNTRY": 20,
|
86 |
+
"I-CREDITCARDCVV": 2,
|
87 |
+
"I-CREDITCARDNUMBER": 6,
|
88 |
+
"I-CURRENCY": 40,
|
89 |
+
"I-CURRENCYNAME": 44,
|
90 |
+
"I-DATE": 32,
|
91 |
+
"I-DATEOFBIRTH": 26,
|
92 |
+
"I-EMAIL": 38,
|
93 |
+
"I-EXPIRY_DATE": 42,
|
94 |
+
"I-ORGANIZATION": 22,
|
95 |
+
"I-PAN_CARD": 8,
|
96 |
+
"I-PERSON": 30,
|
97 |
+
"I-PHONENUMBER": 10,
|
98 |
+
"I-SECONDARY_ADDRESS": 14,
|
99 |
+
"I-STATE": 18,
|
100 |
+
"I-STREET": 16,
|
101 |
+
"I-TIME": 12,
|
102 |
+
"I-URL": 28,
|
103 |
+
"I-US_SSN": 36,
|
104 |
+
"O": 0
|
105 |
+
},
|
106 |
+
"layer_norm_eps": 1e-07,
|
107 |
+
"max_position_embeddings": 512,
|
108 |
+
"max_relative_positions": -1,
|
109 |
+
"model_type": "deberta-v2",
|
110 |
+
"norm_rel_ebd": "layer_norm",
|
111 |
+
"num_attention_heads": 12,
|
112 |
+
"num_hidden_layers": 12,
|
113 |
+
"pad_token_id": 0,
|
114 |
+
"pooler_dropout": 0,
|
115 |
+
"pooler_hidden_act": "gelu",
|
116 |
+
"pooler_hidden_size": 768,
|
117 |
+
"pos_att_type": [
|
118 |
+
"p2c",
|
119 |
+
"c2p"
|
120 |
+
],
|
121 |
+
"position_biased_input": false,
|
122 |
+
"position_buckets": 256,
|
123 |
+
"relative_attention": true,
|
124 |
+
"share_att_key": true,
|
125 |
+
"torch_dtype": "float32",
|
126 |
+
"transformers_version": "4.38.2",
|
127 |
+
"type_vocab_size": 0,
|
128 |
+
"vocab_size": 128100
|
129 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_AADHAR_CARD_f1": 0.7498692696531287,
|
4 |
+
"eval_AGE_f1": 0.5816216216216216,
|
5 |
+
"eval_CITY_f1": 0.7305788680869378,
|
6 |
+
"eval_COUNTRY_f1": 0.6781510192362905,
|
7 |
+
"eval_CREDITCARDCVV_f1": 0.7219837863614689,
|
8 |
+
"eval_CREDITCARDNUMBER_f1": 0.7364130434782609,
|
9 |
+
"eval_CURRENCYNAME_f1": 0.08870967741935484,
|
10 |
+
"eval_CURRENCY_f1": 0.6680805938494168,
|
11 |
+
"eval_DATEOFBIRTH_f1": 0.6437189496096523,
|
12 |
+
"eval_DATE_f1": 0.6695026178010473,
|
13 |
+
"eval_EMAIL_f1": 0.6485573173901742,
|
14 |
+
"eval_EXPIRY_DATE_f1": 0.5622568093385214,
|
15 |
+
"eval_ORGANIZATION_f1": 0.7392519632636763,
|
16 |
+
"eval_PAN_CARD_f1": 0.7191325638335083,
|
17 |
+
"eval_PERSON_f1": 0.8087976183243211,
|
18 |
+
"eval_PHONENUMBER_f1": 0.7218013468013468,
|
19 |
+
"eval_SECONDARY_ADDRESS_f1": 0.6800595238095238,
|
20 |
+
"eval_STATE_f1": 0.7525204032645223,
|
21 |
+
"eval_STREET_f1": 0.8528925619834711,
|
22 |
+
"eval_TIME_f1": 0.7544524441076165,
|
23 |
+
"eval_URL_f1": 0.5520118422823308,
|
24 |
+
"eval_US_SSN_f1": 0.90694626474443,
|
25 |
+
"eval_loss": 0.09682328253984451,
|
26 |
+
"eval_overall_accuracy": 0.9661661821488446,
|
27 |
+
"eval_overall_f1": 0.7095774460143962,
|
28 |
+
"eval_overall_precision": 0.6921289148206536,
|
29 |
+
"eval_overall_recall": 0.727928482300053,
|
30 |
+
"eval_runtime": 151.236,
|
31 |
+
"eval_samples": 18463,
|
32 |
+
"eval_samples_per_second": 122.081,
|
33 |
+
"eval_steps_per_second": 15.261
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06d16af7890a027c488608a64bd943af86e69da4167538c29ed319b384622071
|
3 |
+
size 735489012
|
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 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 4.250069188231039e+16,
|
4 |
+
"train_loss": 0.2043684836406844,
|
5 |
+
"train_runtime": 5455.8592,
|
6 |
+
"train_samples": 73849,
|
7 |
+
"train_samples_per_second": 40.607,
|
8 |
+
"train_steps_per_second": 1.128
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6156,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.24,
|
13 |
+
"grad_norm": 1.4913195371627808,
|
14 |
+
"learning_rate": 2.0292207792207792e-05,
|
15 |
+
"loss": 1.0759,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.49,
|
20 |
+
"grad_norm": 0.7769107222557068,
|
21 |
+
"learning_rate": 4.0584415584415584e-05,
|
22 |
+
"loss": 0.2485,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.73,
|
27 |
+
"grad_norm": 0.9267131686210632,
|
28 |
+
"learning_rate": 4.963542668550149e-05,
|
29 |
+
"loss": 0.1884,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.97,
|
34 |
+
"grad_norm": 0.8767552971839905,
|
35 |
+
"learning_rate": 4.7058361708328026e-05,
|
36 |
+
"loss": 0.1553,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.22,
|
41 |
+
"grad_norm": 1.5689440965652466,
|
42 |
+
"learning_rate": 4.225547310225216e-05,
|
43 |
+
"loss": 0.133,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.46,
|
48 |
+
"grad_norm": 1.353319764137268,
|
49 |
+
"learning_rate": 3.5711401707230445e-05,
|
50 |
+
"loss": 0.1242,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.71,
|
55 |
+
"grad_norm": 0.7634446620941162,
|
56 |
+
"learning_rate": 2.808648435756026e-05,
|
57 |
+
"loss": 0.1157,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.95,
|
62 |
+
"grad_norm": 0.5596290826797485,
|
63 |
+
"learning_rate": 2.0150121855972848e-05,
|
64 |
+
"loss": 0.1079,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.19,
|
69 |
+
"grad_norm": 0.407377690076828,
|
70 |
+
"learning_rate": 1.2703141726159556e-05,
|
71 |
+
"loss": 0.0933,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.44,
|
76 |
+
"grad_norm": 0.9677791595458984,
|
77 |
+
"learning_rate": 6.496989816913732e-06,
|
78 |
+
"loss": 0.086,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.68,
|
83 |
+
"grad_norm": 1.0203440189361572,
|
84 |
+
"learning_rate": 2.157904819340964e-06,
|
85 |
+
"loss": 0.0836,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.92,
|
90 |
+
"grad_norm": 0.48467525839805603,
|
91 |
+
"learning_rate": 1.2372695218094142e-07,
|
92 |
+
"loss": 0.0787,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.0,
|
97 |
+
"step": 6156,
|
98 |
+
"total_flos": 4.250069188231039e+16,
|
99 |
+
"train_loss": 0.2043684836406844,
|
100 |
+
"train_runtime": 5455.8592,
|
101 |
+
"train_samples_per_second": 40.607,
|
102 |
+
"train_steps_per_second": 1.128
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 3.0,
|
106 |
+
"eval_AADHAR_CARD_f1": 0.7498692696531287,
|
107 |
+
"eval_AGE_f1": 0.5816216216216216,
|
108 |
+
"eval_CITY_f1": 0.7305788680869378,
|
109 |
+
"eval_COUNTRY_f1": 0.6781510192362905,
|
110 |
+
"eval_CREDITCARDCVV_f1": 0.7219837863614689,
|
111 |
+
"eval_CREDITCARDNUMBER_f1": 0.7364130434782609,
|
112 |
+
"eval_CURRENCYNAME_f1": 0.08870967741935484,
|
113 |
+
"eval_CURRENCY_f1": 0.6680805938494168,
|
114 |
+
"eval_DATEOFBIRTH_f1": 0.6437189496096523,
|
115 |
+
"eval_DATE_f1": 0.6695026178010473,
|
116 |
+
"eval_EMAIL_f1": 0.6485573173901742,
|
117 |
+
"eval_EXPIRY_DATE_f1": 0.5622568093385214,
|
118 |
+
"eval_ORGANIZATION_f1": 0.7392519632636763,
|
119 |
+
"eval_PAN_CARD_f1": 0.7191325638335083,
|
120 |
+
"eval_PERSON_f1": 0.8087976183243211,
|
121 |
+
"eval_PHONENUMBER_f1": 0.7218013468013468,
|
122 |
+
"eval_SECONDARY_ADDRESS_f1": 0.6800595238095238,
|
123 |
+
"eval_STATE_f1": 0.7525204032645223,
|
124 |
+
"eval_STREET_f1": 0.8528925619834711,
|
125 |
+
"eval_TIME_f1": 0.7544524441076165,
|
126 |
+
"eval_URL_f1": 0.5520118422823308,
|
127 |
+
"eval_US_SSN_f1": 0.90694626474443,
|
128 |
+
"eval_loss": 0.09682328253984451,
|
129 |
+
"eval_overall_accuracy": 0.9661661821488446,
|
130 |
+
"eval_overall_f1": 0.7095774460143962,
|
131 |
+
"eval_overall_precision": 0.6921289148206536,
|
132 |
+
"eval_overall_recall": 0.727928482300053,
|
133 |
+
"eval_runtime": 151.236,
|
134 |
+
"eval_samples_per_second": 122.081,
|
135 |
+
"eval_steps_per_second": 15.261,
|
136 |
+
"step": 6156
|
137 |
+
}
|
138 |
+
],
|
139 |
+
"logging_steps": 500,
|
140 |
+
"max_steps": 6156,
|
141 |
+
"num_input_tokens_seen": 0,
|
142 |
+
"num_train_epochs": 3,
|
143 |
+
"save_steps": 500,
|
144 |
+
"total_flos": 4.250069188231039e+16,
|
145 |
+
"train_batch_size": 36,
|
146 |
+
"trial_name": null,
|
147 |
+
"trial_params": null
|
148 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b067ec7a0347c3f22a47adc9fe0d8549e99bc78d5aceaf663bded3995dfbe37
|
3 |
+
size 4984
|