Training in progress, epoch 1
Browse files- checkpoints/checkpoint-50/config.json +91 -0
- checkpoints/checkpoint-50/model.safetensors +3 -0
- config.json +91 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoints/checkpoint-50/config.json
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NazaGara/NER-fine-tuned-BETO",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B_CANCER_CONCEPT",
|
14 |
+
"1": "B_CHEMOTHERAPY",
|
15 |
+
"2": "B_DATE",
|
16 |
+
"3": "B_DRUG",
|
17 |
+
"4": "B_FAMILY",
|
18 |
+
"5": "B_FREQ",
|
19 |
+
"6": "B_IMPLICIT_DATE",
|
20 |
+
"7": "B_INTERVAL",
|
21 |
+
"8": "B_METRIC",
|
22 |
+
"9": "B_OCURRENCE_EVENT",
|
23 |
+
"10": "B_QUANTITY",
|
24 |
+
"11": "B_RADIOTHERAPY",
|
25 |
+
"12": "B_SMOKER_STATUS",
|
26 |
+
"13": "B_STAGE",
|
27 |
+
"14": "B_SURGERY",
|
28 |
+
"15": "B_TNM",
|
29 |
+
"16": "I_CANCER_CONCEPT",
|
30 |
+
"17": "I_DATE",
|
31 |
+
"18": "I_DRUG",
|
32 |
+
"19": "I_FAMILY",
|
33 |
+
"20": "I_FREQ",
|
34 |
+
"21": "I_IMPLICIT_DATE",
|
35 |
+
"22": "I_INTERVAL",
|
36 |
+
"23": "I_METRIC",
|
37 |
+
"24": "I_OCURRENCE_EVENT",
|
38 |
+
"25": "I_SMOKER_STATUS",
|
39 |
+
"26": "I_STAGE",
|
40 |
+
"27": "I_SURGERY",
|
41 |
+
"28": "I_TNM",
|
42 |
+
"29": "O"
|
43 |
+
},
|
44 |
+
"initializer_range": 0.02,
|
45 |
+
"intermediate_size": 3072,
|
46 |
+
"label2id": {
|
47 |
+
"B_CANCER_CONCEPT": 0,
|
48 |
+
"B_CHEMOTHERAPY": 1,
|
49 |
+
"B_DATE": 2,
|
50 |
+
"B_DRUG": 3,
|
51 |
+
"B_FAMILY": 4,
|
52 |
+
"B_FREQ": 5,
|
53 |
+
"B_IMPLICIT_DATE": 6,
|
54 |
+
"B_INTERVAL": 7,
|
55 |
+
"B_METRIC": 8,
|
56 |
+
"B_OCURRENCE_EVENT": 9,
|
57 |
+
"B_QUANTITY": 10,
|
58 |
+
"B_RADIOTHERAPY": 11,
|
59 |
+
"B_SMOKER_STATUS": 12,
|
60 |
+
"B_STAGE": 13,
|
61 |
+
"B_SURGERY": 14,
|
62 |
+
"B_TNM": 15,
|
63 |
+
"I_CANCER_CONCEPT": 16,
|
64 |
+
"I_DATE": 17,
|
65 |
+
"I_DRUG": 18,
|
66 |
+
"I_FAMILY": 19,
|
67 |
+
"I_FREQ": 20,
|
68 |
+
"I_IMPLICIT_DATE": 21,
|
69 |
+
"I_INTERVAL": 22,
|
70 |
+
"I_METRIC": 23,
|
71 |
+
"I_OCURRENCE_EVENT": 24,
|
72 |
+
"I_SMOKER_STATUS": 25,
|
73 |
+
"I_STAGE": 26,
|
74 |
+
"I_SURGERY": 27,
|
75 |
+
"I_TNM": 28,
|
76 |
+
"O": 29
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-12,
|
79 |
+
"max_position_embeddings": 512,
|
80 |
+
"model_type": "bert",
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_hidden_layers": 12,
|
83 |
+
"output_past": true,
|
84 |
+
"pad_token_id": 1,
|
85 |
+
"position_embedding_type": "absolute",
|
86 |
+
"torch_dtype": "float32",
|
87 |
+
"transformers_version": "4.46.2",
|
88 |
+
"type_vocab_size": 2,
|
89 |
+
"use_cache": true,
|
90 |
+
"vocab_size": 31002
|
91 |
+
}
|
checkpoints/checkpoint-50/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c37c2ee7aedbfeb42cb5419ca4aea13ee103695dffcdcd276e86367cdd8f006
|
3 |
+
size 437156776
|
config.json
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NazaGara/NER-fine-tuned-BETO",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B_CANCER_CONCEPT",
|
14 |
+
"1": "B_CHEMOTHERAPY",
|
15 |
+
"2": "B_DATE",
|
16 |
+
"3": "B_DRUG",
|
17 |
+
"4": "B_FAMILY",
|
18 |
+
"5": "B_FREQ",
|
19 |
+
"6": "B_IMPLICIT_DATE",
|
20 |
+
"7": "B_INTERVAL",
|
21 |
+
"8": "B_METRIC",
|
22 |
+
"9": "B_OCURRENCE_EVENT",
|
23 |
+
"10": "B_QUANTITY",
|
24 |
+
"11": "B_RADIOTHERAPY",
|
25 |
+
"12": "B_SMOKER_STATUS",
|
26 |
+
"13": "B_STAGE",
|
27 |
+
"14": "B_SURGERY",
|
28 |
+
"15": "B_TNM",
|
29 |
+
"16": "I_CANCER_CONCEPT",
|
30 |
+
"17": "I_DATE",
|
31 |
+
"18": "I_DRUG",
|
32 |
+
"19": "I_FAMILY",
|
33 |
+
"20": "I_FREQ",
|
34 |
+
"21": "I_IMPLICIT_DATE",
|
35 |
+
"22": "I_INTERVAL",
|
36 |
+
"23": "I_METRIC",
|
37 |
+
"24": "I_OCURRENCE_EVENT",
|
38 |
+
"25": "I_SMOKER_STATUS",
|
39 |
+
"26": "I_STAGE",
|
40 |
+
"27": "I_SURGERY",
|
41 |
+
"28": "I_TNM",
|
42 |
+
"29": "O"
|
43 |
+
},
|
44 |
+
"initializer_range": 0.02,
|
45 |
+
"intermediate_size": 3072,
|
46 |
+
"label2id": {
|
47 |
+
"B_CANCER_CONCEPT": 0,
|
48 |
+
"B_CHEMOTHERAPY": 1,
|
49 |
+
"B_DATE": 2,
|
50 |
+
"B_DRUG": 3,
|
51 |
+
"B_FAMILY": 4,
|
52 |
+
"B_FREQ": 5,
|
53 |
+
"B_IMPLICIT_DATE": 6,
|
54 |
+
"B_INTERVAL": 7,
|
55 |
+
"B_METRIC": 8,
|
56 |
+
"B_OCURRENCE_EVENT": 9,
|
57 |
+
"B_QUANTITY": 10,
|
58 |
+
"B_RADIOTHERAPY": 11,
|
59 |
+
"B_SMOKER_STATUS": 12,
|
60 |
+
"B_STAGE": 13,
|
61 |
+
"B_SURGERY": 14,
|
62 |
+
"B_TNM": 15,
|
63 |
+
"I_CANCER_CONCEPT": 16,
|
64 |
+
"I_DATE": 17,
|
65 |
+
"I_DRUG": 18,
|
66 |
+
"I_FAMILY": 19,
|
67 |
+
"I_FREQ": 20,
|
68 |
+
"I_IMPLICIT_DATE": 21,
|
69 |
+
"I_INTERVAL": 22,
|
70 |
+
"I_METRIC": 23,
|
71 |
+
"I_OCURRENCE_EVENT": 24,
|
72 |
+
"I_SMOKER_STATUS": 25,
|
73 |
+
"I_STAGE": 26,
|
74 |
+
"I_SURGERY": 27,
|
75 |
+
"I_TNM": 28,
|
76 |
+
"O": 29
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-12,
|
79 |
+
"max_position_embeddings": 512,
|
80 |
+
"model_type": "bert",
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_hidden_layers": 12,
|
83 |
+
"output_past": true,
|
84 |
+
"pad_token_id": 1,
|
85 |
+
"position_embedding_type": "absolute",
|
86 |
+
"torch_dtype": "float32",
|
87 |
+
"transformers_version": "4.46.2",
|
88 |
+
"type_vocab_size": 2,
|
89 |
+
"use_cache": true,
|
90 |
+
"vocab_size": 31002
|
91 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be2be101fb674e38d4a2f6be8b8665f4349e61b326876ba77ebf3236a9550be5
|
3 |
+
size 437156776
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[MASK]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "[PAD]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"3": {
|
21 |
+
"content": "[UNK]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"4": {
|
29 |
+
"content": "[CLS]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"5": {
|
37 |
+
"content": "[SEP]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": false,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"num_labels": 9,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"strip_accents": false,
|
56 |
+
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "BertTokenizer",
|
58 |
+
"unk_token": "[UNK]"
|
59 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a8804d08e70be539646a18ceeb2102a556b1d2ff1cbb17add97980be89d35b
|
3 |
+
size 5368
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|