Upload folder using huggingface_hub
Browse files- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/config.json +61 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/model.safetensors +3 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/optimizer.pt +3 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/rng_state.pth +3 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/scheduler.pt +3 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer.json +0 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer_config.json +23 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/trainer_state.json +33 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/training_args.bin +3 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/config.json +61 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/pytorch_model.bin +3 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/tokenizer.json +0 -0
- financial-pii-ready/SpanBased-CustomDeBERTa/tokenizer_config.json +23 -0
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaStandardSpanClassifier"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "ADDRESS",
|
| 15 |
+
"2": "COMPANY",
|
| 16 |
+
"3": "CREDIT_CARD",
|
| 17 |
+
"4": "EMAIL",
|
| 18 |
+
"5": "NAME",
|
| 19 |
+
"6": "PHONE",
|
| 20 |
+
"7": "SSN",
|
| 21 |
+
"8": "URL"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"ADDRESS": 1,
|
| 27 |
+
"COMPANY": 2,
|
| 28 |
+
"CREDIT_CARD": 3,
|
| 29 |
+
"EMAIL": 4,
|
| 30 |
+
"NAME": 5,
|
| 31 |
+
"O": 0,
|
| 32 |
+
"PHONE": 6,
|
| 33 |
+
"SSN": 7,
|
| 34 |
+
"URL": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"legacy": true,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"max_relative_positions": -1,
|
| 40 |
+
"model_type": "deberta-v2",
|
| 41 |
+
"norm_rel_ebd": "layer_norm",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pooler_dropout": 0,
|
| 46 |
+
"pooler_hidden_act": "gelu",
|
| 47 |
+
"pooler_hidden_size": 768,
|
| 48 |
+
"pos_att_type": [
|
| 49 |
+
"p2c",
|
| 50 |
+
"c2p"
|
| 51 |
+
],
|
| 52 |
+
"position_biased_input": false,
|
| 53 |
+
"position_buckets": 256,
|
| 54 |
+
"relative_attention": true,
|
| 55 |
+
"share_att_key": true,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.3.0",
|
| 58 |
+
"type_vocab_size": 0,
|
| 59 |
+
"use_cache": false,
|
| 60 |
+
"vocab_size": 128100
|
| 61 |
+
}
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb0643a7d4a1b1424d979e3c8c0c6f9bc7e014cda75bb8a921845af3d3e7970
|
| 3 |
+
size 735405916
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:431745e4fed0e129935abb462961e9645e35855816f0ad3b916d0e31f93a212f
|
| 3 |
+
size 1470933579
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9537521fe0d7b866ee4ad64e1094289cdfdf40b43c276f3b560843d13a790ac2
|
| 3 |
+
size 14645
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b04611bea80597dee677a377375d057cf3fa3437fb4ed8809d4662285b8811b
|
| 3 |
+
size 1465
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"[PAD]",
|
| 10 |
+
"[CLS]",
|
| 11 |
+
"[SEP]"
|
| 12 |
+
],
|
| 13 |
+
"is_local": false,
|
| 14 |
+
"mask_token": "[MASK]",
|
| 15 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
+
"pad_token": "[PAD]",
|
| 17 |
+
"sep_token": "[SEP]",
|
| 18 |
+
"split_by_punct": false,
|
| 19 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 20 |
+
"unk_id": 3,
|
| 21 |
+
"unk_token": "[UNK]",
|
| 22 |
+
"vocab_type": "spm"
|
| 23 |
+
}
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [],
|
| 12 |
+
"logging_steps": 500,
|
| 13 |
+
"max_steps": 250,
|
| 14 |
+
"num_input_tokens_seen": 0,
|
| 15 |
+
"num_train_epochs": 1,
|
| 16 |
+
"save_steps": 500,
|
| 17 |
+
"stateful_callbacks": {
|
| 18 |
+
"TrainerControl": {
|
| 19 |
+
"args": {
|
| 20 |
+
"should_epoch_stop": false,
|
| 21 |
+
"should_evaluate": false,
|
| 22 |
+
"should_log": false,
|
| 23 |
+
"should_save": true,
|
| 24 |
+
"should_training_stop": true
|
| 25 |
+
},
|
| 26 |
+
"attributes": {}
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"total_flos": 64291496122584.0,
|
| 30 |
+
"train_batch_size": 2,
|
| 31 |
+
"trial_name": null,
|
| 32 |
+
"trial_params": null
|
| 33 |
+
}
|
financial-pii-ready/SpanBased-CustomDeBERTa/checkpoint-250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac7c7ac7bf936199b8020a8f042c125b85073157100a913cd9ec9b85217e1954
|
| 3 |
+
size 5201
|
financial-pii-ready/SpanBased-CustomDeBERTa/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaStandardSpanClassifier"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "ADDRESS",
|
| 15 |
+
"2": "COMPANY",
|
| 16 |
+
"3": "CREDIT_CARD",
|
| 17 |
+
"4": "EMAIL",
|
| 18 |
+
"5": "NAME",
|
| 19 |
+
"6": "PHONE",
|
| 20 |
+
"7": "SSN",
|
| 21 |
+
"8": "URL"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"ADDRESS": 1,
|
| 27 |
+
"COMPANY": 2,
|
| 28 |
+
"CREDIT_CARD": 3,
|
| 29 |
+
"EMAIL": 4,
|
| 30 |
+
"NAME": 5,
|
| 31 |
+
"O": 0,
|
| 32 |
+
"PHONE": 6,
|
| 33 |
+
"SSN": 7,
|
| 34 |
+
"URL": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"legacy": true,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"max_relative_positions": -1,
|
| 40 |
+
"model_type": "deberta-v2",
|
| 41 |
+
"norm_rel_ebd": "layer_norm",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pooler_dropout": 0,
|
| 46 |
+
"pooler_hidden_act": "gelu",
|
| 47 |
+
"pooler_hidden_size": 768,
|
| 48 |
+
"pos_att_type": [
|
| 49 |
+
"p2c",
|
| 50 |
+
"c2p"
|
| 51 |
+
],
|
| 52 |
+
"position_biased_input": false,
|
| 53 |
+
"position_buckets": 256,
|
| 54 |
+
"relative_attention": true,
|
| 55 |
+
"share_att_key": true,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.3.0",
|
| 58 |
+
"type_vocab_size": 0,
|
| 59 |
+
"use_cache": false,
|
| 60 |
+
"vocab_size": 128100
|
| 61 |
+
}
|
financial-pii-ready/SpanBased-CustomDeBERTa/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc594c166ab46120276b8dcd69d33cb891adb868ed0184612ac3f5b9c13e0178
|
| 3 |
+
size 735467011
|
financial-pii-ready/SpanBased-CustomDeBERTa/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
financial-pii-ready/SpanBased-CustomDeBERTa/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"[PAD]",
|
| 10 |
+
"[CLS]",
|
| 11 |
+
"[SEP]"
|
| 12 |
+
],
|
| 13 |
+
"is_local": false,
|
| 14 |
+
"mask_token": "[MASK]",
|
| 15 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
+
"pad_token": "[PAD]",
|
| 17 |
+
"sep_token": "[SEP]",
|
| 18 |
+
"split_by_punct": false,
|
| 19 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 20 |
+
"unk_id": 3,
|
| 21 |
+
"unk_token": "[UNK]",
|
| 22 |
+
"vocab_type": "spm"
|
| 23 |
+
}
|