PuxAI commited on
Commit
9fc1f1d
·
verified ·
1 Parent(s): 1bb796a

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. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/gliner_config.json +105 -0
  2. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/optimizer.pt +3 -0
  3. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/pytorch_model.bin +3 -0
  4. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/rng_state.pth +3 -0
  5. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/scheduler.pt +3 -0
  6. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/tokenizer.json +0 -0
  7. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/tokenizer_config.json +24 -0
  8. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/trainer_state.json +48 -0
  9. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/gliner_config.json +105 -0
  10. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/optimizer.pt +3 -0
  11. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/pytorch_model.bin +3 -0
  12. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/rng_state.pth +3 -0
  13. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/scheduler.pt +3 -0
  14. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/tokenizer.json +0 -0
  15. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/tokenizer_config.json +24 -0
  16. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/trainer_state.json +55 -0
  17. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/gliner_config.json +105 -0
  18. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/optimizer.pt +3 -0
  19. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/pytorch_model.bin +3 -0
  20. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/rng_state.pth +3 -0
  21. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/scheduler.pt +3 -0
  22. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/tokenizer.json +0 -0
  23. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/tokenizer_config.json +24 -0
  24. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/trainer_state.json +62 -0
  25. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/gliner_config.json +105 -0
  26. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/optimizer.pt +3 -0
  27. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/pytorch_model.bin +3 -0
  28. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/rng_state.pth +3 -0
  29. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/scheduler.pt +3 -0
  30. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/tokenizer.json +0 -0
  31. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/tokenizer_config.json +24 -0
  32. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/trainer_state.json +69 -0
  33. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/gliner_config.json +105 -0
  34. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/optimizer.pt +3 -0
  35. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/pytorch_model.bin +3 -0
  36. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/rng_state.pth +3 -0
  37. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/scheduler.pt +3 -0
  38. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/tokenizer.json +0 -0
  39. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/tokenizer_config.json +24 -0
  40. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/trainer_state.json +76 -0
  41. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/gliner_config.json +105 -0
  42. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/optimizer.pt +3 -0
  43. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/pytorch_model.bin +3 -0
  44. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/rng_state.pth +3 -0
  45. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/scheduler.pt +3 -0
  46. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/tokenizer.json +0 -0
  47. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/tokenizer_config.json +24 -0
  48. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/trainer_state.json +83 -0
  49. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-4000/gliner_config.json +105 -0
  50. nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-4000/optimizer.pt +3 -0
nemotron-pii-ready/GLiNER-NVIDIA/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750db1db7b4a265df197f5ad731f07d1b358c4706727bed81ae5546decf1f3da
3
+ size 2873
nemotron-pii-ready/GLiNER-NVIDIA/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
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4da2d09a7f58448572e1e03dac261cf8ae927f72d9d8862f13c9d130299724
3
+ size 14645
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1958b18ed1fc6f653d87274ec2f130d0527b11dd31f70c85910541b9315affe
3
+ size 1529
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/GLiNER-NVIDIA/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/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": 0.16,
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": 0.08,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.2016e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 8.401600000000001e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 6250,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 1,
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": 16,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e2419c98de35a8f5b49f703a898bc8047d5b52f5278d548c614f0d416aef4d
3
+ size 2873
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc025aa5dbbdda6a5aa0998da6a30b0f55ffd06a122c4ad2519217741401a061
3
+ size 14645
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e9466b9f5a55568d896a688e06434750e2f84492cdb6e9b72b6d761ed7d073
3
+ size 1529
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.24,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.2016e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 8.401600000000001e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.24,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 7.6016e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ }
33
+ ],
34
+ "logging_steps": 500,
35
+ "max_steps": 6250,
36
+ "num_input_tokens_seen": 0,
37
+ "num_train_epochs": 1,
38
+ "save_steps": 500,
39
+ "stateful_callbacks": {
40
+ "TrainerControl": {
41
+ "args": {
42
+ "should_epoch_stop": false,
43
+ "should_evaluate": false,
44
+ "should_log": false,
45
+ "should_save": true,
46
+ "should_training_stop": false
47
+ },
48
+ "attributes": {}
49
+ }
50
+ },
51
+ "total_flos": 0.0,
52
+ "train_batch_size": 16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34627c298ffdb286ee8880369bc996e913b9b2d071f81e3a9aee85c259f241c6
3
+ size 2873
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae3d39a0e9c1d492ef7c7b446a6f126e99fe89cbedd6221042e0050a6984f13
3
+ size 14645
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9009fa78be2826a79e0bf65af983602bec4d66fbb025d00bb454bfeff1f15e5b
3
+ size 1529
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.32,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.2016e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 8.401600000000001e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.24,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 7.6016e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.32,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 6.8016e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ }
40
+ ],
41
+ "logging_steps": 500,
42
+ "max_steps": 6250,
43
+ "num_input_tokens_seen": 0,
44
+ "num_train_epochs": 1,
45
+ "save_steps": 500,
46
+ "stateful_callbacks": {
47
+ "TrainerControl": {
48
+ "args": {
49
+ "should_epoch_stop": false,
50
+ "should_evaluate": false,
51
+ "should_log": false,
52
+ "should_save": true,
53
+ "should_training_stop": false
54
+ },
55
+ "attributes": {}
56
+ }
57
+ },
58
+ "total_flos": 0.0,
59
+ "train_batch_size": 16,
60
+ "trial_name": null,
61
+ "trial_params": null
62
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70df23370e715ef52f70c788f5fdc2727ca3b9251e03c8da20564f506346423a
3
+ size 2873
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e14448576d833906dbe18a18ba023c7af629eb96ce53e8838d17fb05b6d2e9
3
+ size 14709
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2a50cc313f1c8a356bb4c7781c9fa4ddc4bdf531aac1079e003dccc1246f94
3
+ size 1529
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4,
6
+ "eval_steps": 500,
7
+ "global_step": 2500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.2016e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 8.401600000000001e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.24,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 7.6016e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.32,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 6.8016e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 6.001600000000001e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 6250,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 1,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": false
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 0.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4fdf9a023bdbd3c816a1c918c63418ed5f74f927a333c50edccb0dd03e6e09
3
+ size 2873
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0a3a67a5c15e6ca296838d8b2b9c283ec8707aebdf82a8f69ce582305f6dcb
3
+ size 14581
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1be9c43f3a2bed8f7dc3a3709936e5fe86d88e6ea6876b6b15dbe694be0b0c6
3
+ size 1529
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.48,
6
+ "eval_steps": 500,
7
+ "global_step": 3000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.2016e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 8.401600000000001e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.24,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 7.6016e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.32,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 6.8016e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 6.001600000000001e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.48,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 5.2016e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 6250,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 1,
59
+ "save_steps": 500,
60
+ "stateful_callbacks": {
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": false
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 0.0,
73
+ "train_batch_size": 16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262cbf1014e0302de492fd314afabd295b63bce060e287550968e1b29e25c235
3
+ size 2873
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d9619b394f9e4cf40119464716eb97ca3d3210341a4aeaa366fe3cc9f48617
3
+ size 14645
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6be909ee1b030127657170b3a480f548991a66b636a9b0e605182beabf6e6bb
3
+ size 1529
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.56,
6
+ "eval_steps": 500,
7
+ "global_step": 3500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 9.2016e-06,
16
+ "loss": 0.0,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 8.401600000000001e-06,
23
+ "loss": 0.0,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.24,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 7.6016e-06,
30
+ "loss": 0.0,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.32,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 6.8016e-06,
37
+ "loss": 0.0,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 6.001600000000001e-06,
44
+ "loss": 0.0,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.48,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 5.2016e-06,
51
+ "loss": 0.0,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.56,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 4.4016e-06,
58
+ "loss": 0.0,
59
+ "step": 3500
60
+ }
61
+ ],
62
+ "logging_steps": 500,
63
+ "max_steps": 6250,
64
+ "num_input_tokens_seen": 0,
65
+ "num_train_epochs": 1,
66
+ "save_steps": 500,
67
+ "stateful_callbacks": {
68
+ "TrainerControl": {
69
+ "args": {
70
+ "should_epoch_stop": false,
71
+ "should_evaluate": false,
72
+ "should_log": false,
73
+ "should_save": true,
74
+ "should_training_stop": false
75
+ },
76
+ "attributes": {}
77
+ }
78
+ },
79
+ "total_flos": 0.0,
80
+ "train_batch_size": 16,
81
+ "trial_name": null,
82
+ "trial_params": null
83
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-4000/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
+ }
nemotron-pii-ready/GLiNER-NVIDIA/checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b292b9bb3be1d4fb66f17b5be44bd143434dab0faec216ddb049c042c98b8a3
3
+ size 2873