hungphongtrn
commited on
Commit
•
e555da6
1
Parent(s):
0e76b0c
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +4 -4
- pytorch_model.bin +3 -0
- runs/May29_06-00-37_labserver/events.out.tfevents.1716962766.labserver.1429073.0 +3 -0
- special_tokens_map.json +7 -49
- tokenizer.json +3 -6
- tokenizer_config.json +0 -42
- training_args.bin +2 -2
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
CHANGED
@@ -31,7 +31,7 @@
|
|
31 |
"19": "I-PREVENTIVEMED",
|
32 |
"20": "I-TREATMENT",
|
33 |
"21": "I-ORGANIZATION",
|
34 |
-
"22": "
|
35 |
"23": "B-UNITCALIBRATOR",
|
36 |
"24": "B-MEDDEVICETECHNIQUE",
|
37 |
"25": "I-OCCUPATION",
|
@@ -50,6 +50,7 @@
|
|
50 |
"initializer_range": 0.02,
|
51 |
"intermediate_size": 3072,
|
52 |
"label2id": {
|
|
|
53 |
"B-AGE": 14,
|
54 |
"B-DATETIME": 15,
|
55 |
"B-DIAGNOSTICS": 32,
|
@@ -85,8 +86,7 @@
|
|
85 |
"I-SURGERY": 29,
|
86 |
"I-TRANSPORTATION": 36,
|
87 |
"I-TREATMENT": 20,
|
88 |
-
"I-UNITCALIBRATOR": 9
|
89 |
-
"O": 22
|
90 |
},
|
91 |
"layer_norm_eps": 1e-07,
|
92 |
"max_position_embeddings": 512,
|
@@ -108,7 +108,7 @@
|
|
108 |
"relative_attention": true,
|
109 |
"share_att_key": true,
|
110 |
"torch_dtype": "float32",
|
111 |
-
"transformers_version": "4.
|
112 |
"type_vocab_size": 0,
|
113 |
"vocab_size": 128000
|
114 |
}
|
|
|
31 |
"19": "I-PREVENTIVEMED",
|
32 |
"20": "I-TREATMENT",
|
33 |
"21": "I-ORGANIZATION",
|
34 |
+
"22": "0",
|
35 |
"23": "B-UNITCALIBRATOR",
|
36 |
"24": "B-MEDDEVICETECHNIQUE",
|
37 |
"25": "I-OCCUPATION",
|
|
|
50 |
"initializer_range": 0.02,
|
51 |
"intermediate_size": 3072,
|
52 |
"label2id": {
|
53 |
+
"0": 22,
|
54 |
"B-AGE": 14,
|
55 |
"B-DATETIME": 15,
|
56 |
"B-DIAGNOSTICS": 32,
|
|
|
86 |
"I-SURGERY": 29,
|
87 |
"I-TRANSPORTATION": 36,
|
88 |
"I-TREATMENT": 20,
|
89 |
+
"I-UNITCALIBRATOR": 9
|
|
|
90 |
},
|
91 |
"layer_norm_eps": 1e-07,
|
92 |
"max_position_embeddings": 512,
|
|
|
108 |
"relative_attention": true,
|
109 |
"share_att_key": true,
|
110 |
"torch_dtype": "float32",
|
111 |
+
"transformers_version": "4.32.0.dev0",
|
112 |
"type_vocab_size": 0,
|
113 |
"vocab_size": 128000
|
114 |
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b48b6658998698fdd5ec04d282edc72f5b7ecad3226c4e811f5d4f501437541
|
3 |
+
size 735202218
|
runs/May29_06-00-37_labserver/events.out.tfevents.1716962766.labserver.1429073.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3d9b4643acc908276e9f79d0c3ce3adf9ecceb6d9a50846bdac958468af140e
|
3 |
+
size 7678
|
special_tokens_map.json
CHANGED
@@ -1,51 +1,9 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"cls_token": {
|
10 |
-
"content": "[CLS]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "[SEP]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "[MASK]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "[PAD]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "[SEP]",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
-
"unk_token": {
|
45 |
-
"content": "[UNK]",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false
|
50 |
-
}
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
tokenizer.json
CHANGED
@@ -76,8 +76,7 @@
|
|
76 |
{
|
77 |
"type": "Metaspace",
|
78 |
"replacement": "▁",
|
79 |
-
"
|
80 |
-
"split": true
|
81 |
}
|
82 |
]
|
83 |
},
|
@@ -159,8 +158,7 @@
|
|
159 |
"decoder": {
|
160 |
"type": "Metaspace",
|
161 |
"replacement": "▁",
|
162 |
-
"
|
163 |
-
"split": true
|
164 |
},
|
165 |
"model": {
|
166 |
"type": "Unigram",
|
@@ -512166,7 +512164,6 @@
|
|
512166 |
"\u0000",
|
512167 |
-23.170761450958047
|
512168 |
]
|
512169 |
-
]
|
512170 |
-
"byte_fallback": false
|
512171 |
}
|
512172 |
}
|
|
|
76 |
{
|
77 |
"type": "Metaspace",
|
78 |
"replacement": "▁",
|
79 |
+
"add_prefix_space": true
|
|
|
80 |
}
|
81 |
]
|
82 |
},
|
|
|
158 |
"decoder": {
|
159 |
"type": "Metaspace",
|
160 |
"replacement": "▁",
|
161 |
+
"add_prefix_space": true
|
|
|
162 |
},
|
163 |
"model": {
|
164 |
"type": "Unigram",
|
|
|
512164 |
"\u0000",
|
512165 |
-23.170761450958047
|
512166 |
]
|
512167 |
+
]
|
|
|
512168 |
}
|
512169 |
}
|
tokenizer_config.json
CHANGED
@@ -1,46 +1,4 @@
|
|
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 |
-
"1": {
|
12 |
-
"content": "[CLS]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "[SEP]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "[UNK]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"4": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
"bos_token": "[CLS]",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "[CLS]",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "[CLS]",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2af6ea6d4d57e4793e3f886b60336e8d26ae99e1897974301996c3095f430da3
|
3 |
+
size 4472
|