Hugging Face's logo

PuxAI
/
GenPII-framework-Data

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
3151e26
·
verified ·
1 Parent(s): 2d56693

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/gliner_config.json +105 -0
  2. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/optimizer.pt +3 -0
  3. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/pytorch_model.bin +3 -0
  4. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/rng_state.pth +3 -0
  5. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/scheduler.pt +3 -0
  6. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/tokenizer.json +0 -0
  7. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/tokenizer_config.json +24 -0
  8. pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/trainer_state.json +48 -0
  9. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/gliner_config.json +105 -0
  10. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/optimizer.pt +3 -0
  11. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/pytorch_model.bin +3 -0
  12. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/rng_state.pth +3 -0
  13. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/scheduler.pt +3 -0
  14. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/tokenizer.json +0 -0
  15. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/tokenizer_config.json +24 -0
  16. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/trainer_state.json +174 -0
  17. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/gliner_config.json +105 -0
  18. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/optimizer.pt +3 -0
  19. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/pytorch_model.bin +3 -0
  20. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/rng_state.pth +3 -0
  21. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/scheduler.pt +3 -0
  22. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/tokenizer.json +0 -0
  23. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/tokenizer_config.json +24 -0
  24. pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/trainer_state.json +181 -0
  25. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/gliner_config.json +105 -0
  26. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/optimizer.pt +3 -0
  27. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/pytorch_model.bin +3 -0
  28. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/rng_state.pth +3 -0
  29. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/scheduler.pt +3 -0
  30. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/tokenizer.json +0 -0
  31. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/tokenizer_config.json +24 -0
  32. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/trainer_state.json +188 -0
  33. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/gliner_config.json +105 -0
  34. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/optimizer.pt +3 -0
  35. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/pytorch_model.bin +3 -0
  36. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/rng_state.pth +3 -0
  37. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/scheduler.pt +3 -0
  38. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/tokenizer.json +0 -0
  39. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/tokenizer_config.json +24 -0
  40. pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/trainer_state.json +195 -0
  41. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/gliner_config.json +105 -0
  42. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/optimizer.pt +3 -0
  43. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/pytorch_model.bin +3 -0
  44. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/rng_state.pth +3 -0
  45. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/scheduler.pt +3 -0
  46. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/tokenizer.json +0 -0
  47. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/tokenizer_config.json +24 -0
  48. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/trainer_state.json +202 -0
  49. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12500/gliner_config.json +105 -0
  50. pii-masking-200k/gliner-PII-FineTuned/checkpoint-12500/optimizer.pt +3 -0
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2331dae248edbe0b59650366491ceef700f3b70a9a2f473c259652eb1c3957
3
+ size 2873
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839263d13e17a8ca08f030b532cec0f782b93805b5425ec968ca87f71065ae2a
3
+ size 14645
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbff5adec671c60eb30e3e96eea8365bc54b864f1c076d686c187203bc99c822
3
+ size 1529
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.04247727465805794,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02123863732902897,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.894019199728147e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.04247727465805794,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 9.787826013083002e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 47084,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 2,
31
+ "save_steps": 500,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": false
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 0.0,
45
+ "train_batch_size": 8,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af9d56eb784219dde0c00acbd5cc7a26e26222dfea6fe9b5718c3dbb29d23b8
3
+ size 2873
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a77bfcf652e5b0dd53ac957d76df4a00adcb9fcb42da0d2512ddf54b87eeee
3
+ size 14645
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d24c2ef1784867c8aa158ef3e1aee3d2ea865bdec156d0c87e0fb3718c6398a
3
+ size 1529
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4247727465805794,
6
+ "eval_steps": 500,
7
+ "global_step": 10000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02123863732902897,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.894019199728147e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.04247727465805794,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 9.787826013083002e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.06371591198708691,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 9.681632826437856e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.08495454931611587,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 9.575439639792711e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.10619318664514485,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 9.469246453147566e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.12743182397417382,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 9.363053266502422e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.1486704613032028,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 9.256860079857277e-06,
58
+ "loss": 0.0,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.16990909863223175,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 9.150666893212132e-06,
65
+ "loss": 0.0,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.19114773596126072,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 9.044473706566987e-06,
72
+ "loss": 0.0,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.2123863732902897,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 8.938280519921843e-06,
79
+ "loss": 0.0,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.23362501061931867,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 8.832087333276698e-06,
86
+ "loss": 0.0,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.25486364794834765,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 8.725894146631553e-06,
93
+ "loss": 0.0,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.2761022852773766,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 8.619700959986408e-06,
100
+ "loss": 0.0,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.2973409226064056,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 8.513507773341264e-06,
107
+ "loss": 0.0,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.3185795599354345,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 8.407314586696119e-06,
114
+ "loss": 0.0,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.3398181972644635,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 8.301121400050972e-06,
121
+ "loss": 0.0,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.36105683459349247,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 8.194928213405828e-06,
128
+ "loss": 0.0,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.38229547192252145,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 8.088735026760683e-06,
135
+ "loss": 0.0,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.4035341092515504,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 7.982541840115538e-06,
142
+ "loss": 0.0,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.4247727465805794,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 7.876348653470393e-06,
149
+ "loss": 0.0,
150
+ "step": 10000
151
+ }
152
+ ],
153
+ "logging_steps": 500,
154
+ "max_steps": 47084,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 2,
157
+ "save_steps": 500,
158
+ "stateful_callbacks": {
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": false
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 0.0,
171
+ "train_batch_size": 8,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023196821ad375c8859b101340c244d7b5a77578020653861d8648ab58e5b677
3
+ size 2873
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f910b023f08d65e666e822509c7ac29f819527f5b6ab775f1a0906332eed54
3
+ size 14645
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b958735966f04bc80e04f46ca5be997561579eaee6efe621ad5eb5cea9d79d2
3
+ size 1529
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-10500/trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.44601138390960837,
6
+ "eval_steps": 500,
7
+ "global_step": 10500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02123863732902897,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.894019199728147e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.04247727465805794,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 9.787826013083002e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.06371591198708691,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 9.681632826437856e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.08495454931611587,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 9.575439639792711e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.10619318664514485,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 9.469246453147566e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.12743182397417382,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 9.363053266502422e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.1486704613032028,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 9.256860079857277e-06,
58
+ "loss": 0.0,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.16990909863223175,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 9.150666893212132e-06,
65
+ "loss": 0.0,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.19114773596126072,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 9.044473706566987e-06,
72
+ "loss": 0.0,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.2123863732902897,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 8.938280519921843e-06,
79
+ "loss": 0.0,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.23362501061931867,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 8.832087333276698e-06,
86
+ "loss": 0.0,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.25486364794834765,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 8.725894146631553e-06,
93
+ "loss": 0.0,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.2761022852773766,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 8.619700959986408e-06,
100
+ "loss": 0.0,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.2973409226064056,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 8.513507773341264e-06,
107
+ "loss": 0.0,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.3185795599354345,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 8.407314586696119e-06,
114
+ "loss": 0.0,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.3398181972644635,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 8.301121400050972e-06,
121
+ "loss": 0.0,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.36105683459349247,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 8.194928213405828e-06,
128
+ "loss": 0.0,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.38229547192252145,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 8.088735026760683e-06,
135
+ "loss": 0.0,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.4035341092515504,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 7.982541840115538e-06,
142
+ "loss": 0.0,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.4247727465805794,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 7.876348653470393e-06,
149
+ "loss": 0.0,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 0.44601138390960837,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 7.770155466825249e-06,
156
+ "loss": 0.0,
157
+ "step": 10500
158
+ }
159
+ ],
160
+ "logging_steps": 500,
161
+ "max_steps": 47084,
162
+ "num_input_tokens_seen": 0,
163
+ "num_train_epochs": 2,
164
+ "save_steps": 500,
165
+ "stateful_callbacks": {
166
+ "TrainerControl": {
167
+ "args": {
168
+ "should_epoch_stop": false,
169
+ "should_evaluate": false,
170
+ "should_log": false,
171
+ "should_save": true,
172
+ "should_training_stop": false
173
+ },
174
+ "attributes": {}
175
+ }
176
+ },
177
+ "total_flos": 0.0,
178
+ "train_batch_size": 8,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ac899f17ef221566d3af9bb49f7db69eb0fb09e2cc6de2f041761664dbfa6a
3
+ size 2873
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9f650e45fdc70cf5ca66934beed1bb649b71e67cc63cf9edfb545dabe84b5a
3
+ size 14645
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e03ac760a4b0c2ac5679161d6df20218fb10d92556e5dbfe2191cd45af5ed9
3
+ size 1529
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11000/trainer_state.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.46725002123863735,
6
+ "eval_steps": 500,
7
+ "global_step": 11000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02123863732902897,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.894019199728147e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.04247727465805794,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 9.787826013083002e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.06371591198708691,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 9.681632826437856e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.08495454931611587,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 9.575439639792711e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.10619318664514485,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 9.469246453147566e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.12743182397417382,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 9.363053266502422e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.1486704613032028,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 9.256860079857277e-06,
58
+ "loss": 0.0,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.16990909863223175,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 9.150666893212132e-06,
65
+ "loss": 0.0,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.19114773596126072,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 9.044473706566987e-06,
72
+ "loss": 0.0,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.2123863732902897,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 8.938280519921843e-06,
79
+ "loss": 0.0,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.23362501061931867,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 8.832087333276698e-06,
86
+ "loss": 0.0,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.25486364794834765,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 8.725894146631553e-06,
93
+ "loss": 0.0,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.2761022852773766,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 8.619700959986408e-06,
100
+ "loss": 0.0,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.2973409226064056,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 8.513507773341264e-06,
107
+ "loss": 0.0,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.3185795599354345,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 8.407314586696119e-06,
114
+ "loss": 0.0,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.3398181972644635,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 8.301121400050972e-06,
121
+ "loss": 0.0,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.36105683459349247,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 8.194928213405828e-06,
128
+ "loss": 0.0,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.38229547192252145,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 8.088735026760683e-06,
135
+ "loss": 0.0,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.4035341092515504,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 7.982541840115538e-06,
142
+ "loss": 0.0,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.4247727465805794,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 7.876348653470393e-06,
149
+ "loss": 0.0,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 0.44601138390960837,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 7.770155466825249e-06,
156
+ "loss": 0.0,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 0.46725002123863735,
161
+ "grad_norm": 0.0,
162
+ "learning_rate": 7.663962280180104e-06,
163
+ "loss": 0.0,
164
+ "step": 11000
165
+ }
166
+ ],
167
+ "logging_steps": 500,
168
+ "max_steps": 47084,
169
+ "num_input_tokens_seen": 0,
170
+ "num_train_epochs": 2,
171
+ "save_steps": 500,
172
+ "stateful_callbacks": {
173
+ "TrainerControl": {
174
+ "args": {
175
+ "should_epoch_stop": false,
176
+ "should_evaluate": false,
177
+ "should_log": false,
178
+ "should_save": true,
179
+ "should_training_stop": false
180
+ },
181
+ "attributes": {}
182
+ }
183
+ },
184
+ "total_flos": 0.0,
185
+ "train_batch_size": 8,
186
+ "trial_name": null,
187
+ "trial_params": null
188
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6204493f98377dea7f13673fb726faa610d21870c5f7cdd0f5f8e502284c4867
3
+ size 2873
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e7aae940625a5e794acb9286023d61b0aefe3ec6578c96007ee4251489c558
3
+ size 14645
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733d5554cd260ea463d06ce9d7a4dfb25b4174f0ab9db582fd76a929f0f7f6af
3
+ size 1529
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-11500/trainer_state.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4884886585676663,
6
+ "eval_steps": 500,
7
+ "global_step": 11500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02123863732902897,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.894019199728147e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.04247727465805794,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 9.787826013083002e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.06371591198708691,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 9.681632826437856e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.08495454931611587,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 9.575439639792711e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.10619318664514485,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 9.469246453147566e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.12743182397417382,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 9.363053266502422e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.1486704613032028,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 9.256860079857277e-06,
58
+ "loss": 0.0,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.16990909863223175,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 9.150666893212132e-06,
65
+ "loss": 0.0,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.19114773596126072,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 9.044473706566987e-06,
72
+ "loss": 0.0,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.2123863732902897,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 8.938280519921843e-06,
79
+ "loss": 0.0,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.23362501061931867,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 8.832087333276698e-06,
86
+ "loss": 0.0,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.25486364794834765,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 8.725894146631553e-06,
93
+ "loss": 0.0,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.2761022852773766,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 8.619700959986408e-06,
100
+ "loss": 0.0,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.2973409226064056,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 8.513507773341264e-06,
107
+ "loss": 0.0,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.3185795599354345,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 8.407314586696119e-06,
114
+ "loss": 0.0,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.3398181972644635,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 8.301121400050972e-06,
121
+ "loss": 0.0,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.36105683459349247,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 8.194928213405828e-06,
128
+ "loss": 0.0,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.38229547192252145,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 8.088735026760683e-06,
135
+ "loss": 0.0,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.4035341092515504,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 7.982541840115538e-06,
142
+ "loss": 0.0,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.4247727465805794,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 7.876348653470393e-06,
149
+ "loss": 0.0,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 0.44601138390960837,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 7.770155466825249e-06,
156
+ "loss": 0.0,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 0.46725002123863735,
161
+ "grad_norm": 0.0,
162
+ "learning_rate": 7.663962280180104e-06,
163
+ "loss": 0.0,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 0.4884886585676663,
168
+ "grad_norm": 0.0,
169
+ "learning_rate": 7.557769093534959e-06,
170
+ "loss": 0.0,
171
+ "step": 11500
172
+ }
173
+ ],
174
+ "logging_steps": 500,
175
+ "max_steps": 47084,
176
+ "num_input_tokens_seen": 0,
177
+ "num_train_epochs": 2,
178
+ "save_steps": 500,
179
+ "stateful_callbacks": {
180
+ "TrainerControl": {
181
+ "args": {
182
+ "should_epoch_stop": false,
183
+ "should_evaluate": false,
184
+ "should_log": false,
185
+ "should_save": true,
186
+ "should_training_stop": false
187
+ },
188
+ "attributes": {}
189
+ }
190
+ },
191
+ "total_flos": 0.0,
192
+ "train_batch_size": 8,
193
+ "trial_name": null,
194
+ "trial_params": null
195
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91680f250708b349c36892699a8ed8b766033faafef32862272798104ffb305e
3
+ size 2873
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc3b0087bc9bc5f9eb8a50b990ceebe1ac320746ba80c6b371d4f3cd4ea8ba1
3
+ size 14645
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf4590d2d5fc34dcd8eee06cdef1b362051b2637ecdb5b39a6a577947544e71
3
+ size 1529
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12000/trainer_state.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.5097272958966953,
6
+ "eval_steps": 500,
7
+ "global_step": 12000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02123863732902897,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.894019199728147e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.04247727465805794,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 9.787826013083002e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.06371591198708691,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 9.681632826437856e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.08495454931611587,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 9.575439639792711e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.10619318664514485,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 9.469246453147566e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.12743182397417382,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 9.363053266502422e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.1486704613032028,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 9.256860079857277e-06,
58
+ "loss": 0.0,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.16990909863223175,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 9.150666893212132e-06,
65
+ "loss": 0.0,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.19114773596126072,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 9.044473706566987e-06,
72
+ "loss": 0.0,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.2123863732902897,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 8.938280519921843e-06,
79
+ "loss": 0.0,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.23362501061931867,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 8.832087333276698e-06,
86
+ "loss": 0.0,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.25486364794834765,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 8.725894146631553e-06,
93
+ "loss": 0.0,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.2761022852773766,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 8.619700959986408e-06,
100
+ "loss": 0.0,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.2973409226064056,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 8.513507773341264e-06,
107
+ "loss": 0.0,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.3185795599354345,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 8.407314586696119e-06,
114
+ "loss": 0.0,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.3398181972644635,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 8.301121400050972e-06,
121
+ "loss": 0.0,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.36105683459349247,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 8.194928213405828e-06,
128
+ "loss": 0.0,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.38229547192252145,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 8.088735026760683e-06,
135
+ "loss": 0.0,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.4035341092515504,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 7.982541840115538e-06,
142
+ "loss": 0.0,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.4247727465805794,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 7.876348653470393e-06,
149
+ "loss": 0.0,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 0.44601138390960837,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 7.770155466825249e-06,
156
+ "loss": 0.0,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 0.46725002123863735,
161
+ "grad_norm": 0.0,
162
+ "learning_rate": 7.663962280180104e-06,
163
+ "loss": 0.0,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 0.4884886585676663,
168
+ "grad_norm": 0.0,
169
+ "learning_rate": 7.557769093534959e-06,
170
+ "loss": 0.0,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 0.5097272958966953,
175
+ "grad_norm": 0.0,
176
+ "learning_rate": 7.4515759068898145e-06,
177
+ "loss": 0.0,
178
+ "step": 12000
179
+ }
180
+ ],
181
+ "logging_steps": 500,
182
+ "max_steps": 47084,
183
+ "num_input_tokens_seen": 0,
184
+ "num_train_epochs": 2,
185
+ "save_steps": 500,
186
+ "stateful_callbacks": {
187
+ "TrainerControl": {
188
+ "args": {
189
+ "should_epoch_stop": false,
190
+ "should_evaluate": false,
191
+ "should_log": false,
192
+ "should_save": true,
193
+ "should_training_stop": false
194
+ },
195
+ "attributes": {}
196
+ }
197
+ },
198
+ "total_flos": 0.0,
199
+ "train_batch_size": 8,
200
+ "trial_name": null,
201
+ "trial_params": null
202
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12500/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
pii-masking-200k/gliner-PII-FineTuned/checkpoint-12500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3227d35e6e1bfbc32cf0fe0e1d9cbf892124237a010ef8dbbc656a864e343947
3
+ size 2873