Upload credit options FinBERT system - 20250918_095039
Browse files- level_0/config.json +45 -0
- level_0/model.safetensors +3 -0
- metadata.json +87 -0
- tokenizer/special_tokens_map.json +7 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +58 -0
- tokenizer/vocab.txt +0 -0
level_0/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "CDX EM",
|
| 13 |
+
"1": "CDX NA HY",
|
| 14 |
+
"2": "CDX NA IG",
|
| 15 |
+
"3": "Underlying not identified",
|
| 16 |
+
"4": "iTraxx Europe",
|
| 17 |
+
"5": "iTraxx Europe Crossover",
|
| 18 |
+
"6": "iTraxx Europe Snr Financials",
|
| 19 |
+
"7": "x"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"CDX EM": 0,
|
| 25 |
+
"CDX NA HY": 1,
|
| 26 |
+
"CDX NA IG": 2,
|
| 27 |
+
"Underlying not identified": 3,
|
| 28 |
+
"iTraxx Europe": 4,
|
| 29 |
+
"iTraxx Europe Crossover": 5,
|
| 30 |
+
"iTraxx Europe Snr Financials": 6,
|
| 31 |
+
"x": 7
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-12,
|
| 34 |
+
"max_position_embeddings": 512,
|
| 35 |
+
"model_type": "bert",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"pad_token_id": 0,
|
| 39 |
+
"position_embedding_type": "absolute",
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"transformers_version": "4.56.1",
|
| 42 |
+
"type_vocab_size": 2,
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"vocab_size": 30873
|
| 45 |
+
}
|
level_0/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df7c608b1b4974a4eba37d508320f9cc15141b99c8ab7162e106f26c48458bd6
|
| 3 |
+
size 439055376
|
metadata.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"timestamp": "20250918_095039",
|
| 3 |
+
"model_name": "yiyanghkust/finbert-tone",
|
| 4 |
+
"max_length": 128,
|
| 5 |
+
"hierarchy": {
|
| 6 |
+
"level_0": [
|
| 7 |
+
"CDX NA HY",
|
| 8 |
+
"iTraxx Europe Crossover",
|
| 9 |
+
"x",
|
| 10 |
+
"Underlying not identified",
|
| 11 |
+
"CDX EM",
|
| 12 |
+
"iTraxx Europe",
|
| 13 |
+
"iTraxx Europe Sub Financials",
|
| 14 |
+
"iTraxx Europe Snr Financials",
|
| 15 |
+
"CDX NA IG"
|
| 16 |
+
]
|
| 17 |
+
},
|
| 18 |
+
"label_mappings": {
|
| 19 |
+
"level_0": {
|
| 20 |
+
"label2id": {
|
| 21 |
+
"CDX EM": 0,
|
| 22 |
+
"CDX NA HY": 1,
|
| 23 |
+
"CDX NA IG": 2,
|
| 24 |
+
"Underlying not identified": 3,
|
| 25 |
+
"iTraxx Europe": 4,
|
| 26 |
+
"iTraxx Europe Crossover": 5,
|
| 27 |
+
"iTraxx Europe Snr Financials": 6,
|
| 28 |
+
"x": 7
|
| 29 |
+
},
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "CDX EM",
|
| 32 |
+
"1": "CDX NA HY",
|
| 33 |
+
"2": "CDX NA IG",
|
| 34 |
+
"3": "Underlying not identified",
|
| 35 |
+
"4": "iTraxx Europe",
|
| 36 |
+
"5": "iTraxx Europe Crossover",
|
| 37 |
+
"6": "iTraxx Europe Snr Financials",
|
| 38 |
+
"7": "x"
|
| 39 |
+
},
|
| 40 |
+
"num_labels": 8
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"cleaning_stats": {
|
| 44 |
+
"original_samples": 3022,
|
| 45 |
+
"after_dropna": 3019,
|
| 46 |
+
"after_empty_removal_raw": 3019,
|
| 47 |
+
"after_text_cleaning": 2980,
|
| 48 |
+
"empty_after_cleaning": 39,
|
| 49 |
+
"classes_removed": 1,
|
| 50 |
+
"samples_removed": 1,
|
| 51 |
+
"data_retention_rate_after_class_filter": 0.9996644295302013,
|
| 52 |
+
"original_classes": 9,
|
| 53 |
+
"levels_prepared": [
|
| 54 |
+
"level_0"
|
| 55 |
+
],
|
| 56 |
+
"api_enrichment_enabled": true,
|
| 57 |
+
"api_enrichment_stats": {
|
| 58 |
+
"total_companies": 1817,
|
| 59 |
+
"enriched_companies": 1,
|
| 60 |
+
"enrichment_rate": 0.000550357732526142,
|
| 61 |
+
"api_database_size": 28997,
|
| 62 |
+
"match_method": "exact"
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
+
"levels_trained": [
|
| 66 |
+
"level_0"
|
| 67 |
+
],
|
| 68 |
+
"model_type": "credit_options_finbert",
|
| 69 |
+
"api_enrichment_stats": {
|
| 70 |
+
"total_companies": 1817,
|
| 71 |
+
"enriched_companies": 1,
|
| 72 |
+
"enrichment_rate": 0.000550357732526142,
|
| 73 |
+
"api_database_size": 28997,
|
| 74 |
+
"match_method": "exact"
|
| 75 |
+
},
|
| 76 |
+
"performance": {
|
| 77 |
+
"level_0": {
|
| 78 |
+
"val_accuracy": 0.9932885906040269,
|
| 79 |
+
"test_accuracy": 0.9865771812080537,
|
| 80 |
+
"training_info": {
|
| 81 |
+
"steps_per_epoch": 130,
|
| 82 |
+
"total_steps": 650,
|
| 83 |
+
"total_train_samples": 2085
|
| 84 |
+
}
|
| 85 |
+
}
|
| 86 |
+
}
|
| 87 |
+
}
|
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"2": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"3": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"4": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"5": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
tokenizer/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|