Training in progress, epoch 1
Browse files- config.json +90 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-PER",
|
| 14 |
+
"2": "I-PER",
|
| 15 |
+
"3": "B-ORG",
|
| 16 |
+
"4": "I-ORG",
|
| 17 |
+
"5": "B-LOC",
|
| 18 |
+
"6": "I-LOC",
|
| 19 |
+
"7": "B-ANIM",
|
| 20 |
+
"8": "I-ANIM",
|
| 21 |
+
"9": "B-BIO",
|
| 22 |
+
"10": "I-BIO",
|
| 23 |
+
"11": "B-CEL",
|
| 24 |
+
"12": "I-CEL",
|
| 25 |
+
"13": "B-DIS",
|
| 26 |
+
"14": "I-DIS",
|
| 27 |
+
"15": "B-EVE",
|
| 28 |
+
"16": "I-EVE",
|
| 29 |
+
"17": "B-FOOD",
|
| 30 |
+
"18": "I-FOOD",
|
| 31 |
+
"19": "B-INST",
|
| 32 |
+
"20": "I-INST",
|
| 33 |
+
"21": "B-MEDIA",
|
| 34 |
+
"22": "I-MEDIA",
|
| 35 |
+
"23": "B-MYTH",
|
| 36 |
+
"24": "I-MYTH",
|
| 37 |
+
"25": "B-PLANT",
|
| 38 |
+
"26": "I-PLANT",
|
| 39 |
+
"27": "B-TIME",
|
| 40 |
+
"28": "I-TIME",
|
| 41 |
+
"29": "B-VEHI",
|
| 42 |
+
"30": "I-VEHI"
|
| 43 |
+
},
|
| 44 |
+
"initializer_range": 0.02,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"B-ANIM": 7,
|
| 47 |
+
"B-BIO": 9,
|
| 48 |
+
"B-CEL": 11,
|
| 49 |
+
"B-DIS": 13,
|
| 50 |
+
"B-EVE": 15,
|
| 51 |
+
"B-FOOD": 17,
|
| 52 |
+
"B-INST": 19,
|
| 53 |
+
"B-LOC": 5,
|
| 54 |
+
"B-MEDIA": 21,
|
| 55 |
+
"B-MYTH": 23,
|
| 56 |
+
"B-ORG": 3,
|
| 57 |
+
"B-PER": 1,
|
| 58 |
+
"B-PLANT": 25,
|
| 59 |
+
"B-TIME": 27,
|
| 60 |
+
"B-VEHI": 29,
|
| 61 |
+
"I-ANIM": 8,
|
| 62 |
+
"I-BIO": 10,
|
| 63 |
+
"I-CEL": 12,
|
| 64 |
+
"I-DIS": 14,
|
| 65 |
+
"I-EVE": 16,
|
| 66 |
+
"I-FOOD": 18,
|
| 67 |
+
"I-INST": 20,
|
| 68 |
+
"I-LOC": 6,
|
| 69 |
+
"I-MEDIA": 22,
|
| 70 |
+
"I-MYTH": 24,
|
| 71 |
+
"I-ORG": 4,
|
| 72 |
+
"I-PER": 2,
|
| 73 |
+
"I-PLANT": 26,
|
| 74 |
+
"I-TIME": 28,
|
| 75 |
+
"I-VEHI": 30,
|
| 76 |
+
"O": 0
|
| 77 |
+
},
|
| 78 |
+
"max_position_embeddings": 512,
|
| 79 |
+
"model_type": "distilbert",
|
| 80 |
+
"n_heads": 12,
|
| 81 |
+
"n_layers": 6,
|
| 82 |
+
"pad_token_id": 0,
|
| 83 |
+
"qa_dropout": 0.1,
|
| 84 |
+
"seq_classif_dropout": 0.2,
|
| 85 |
+
"sinusoidal_pos_embds": false,
|
| 86 |
+
"tie_weights_": true,
|
| 87 |
+
"torch_dtype": "float32",
|
| 88 |
+
"transformers_version": "4.35.2",
|
| 89 |
+
"vocab_size": 30522
|
| 90 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eef5bed1ea78439cf739ca32156e49759ffc2ec31564617fe7f57cd54c97470
|
| 3 |
+
size 265559228
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99fe09742eced6fd7266cc713f60834ca153fa248a9d823ec49cd4d4f207b175
|
| 3 |
+
size 4600
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|