Commit
•
26a438f
1
Parent(s):
bf77c27
End of training
Browse files- added_tokens.json +28 -0
- pytorch_model.bin +1 -1
- runs/Aug04_23-18-38_b64a65d64683/events.out.tfevents.1659655138.b64a65d64683.75.0 +2 -2
- special_tokens_map.json +7 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"''": 31116,
|
| 3 |
+
"``": 31117,
|
| 4 |
+
"fw": 31118,
|
| 5 |
+
"jjr": 31119,
|
| 6 |
+
"jjs": 31120,
|
| 7 |
+
"md": 31121,
|
| 8 |
+
"nnp": 31122,
|
| 9 |
+
"nnps": 31123,
|
| 10 |
+
"nns": 31124,
|
| 11 |
+
"nn|sym": 31125,
|
| 12 |
+
"pdt": 31126,
|
| 13 |
+
"prp": 31127,
|
| 14 |
+
"prp$": 31128,
|
| 15 |
+
"rbr": 31129,
|
| 16 |
+
"rbs": 31130,
|
| 17 |
+
"uh": 31131,
|
| 18 |
+
"vb": 31132,
|
| 19 |
+
"vbd": 31133,
|
| 20 |
+
"vbg": 31134,
|
| 21 |
+
"vbn": 31135,
|
| 22 |
+
"vbp": 31136,
|
| 23 |
+
"vbz": 31137,
|
| 24 |
+
"wdt": 31138,
|
| 25 |
+
"wp": 31139,
|
| 26 |
+
"wp$": 31140,
|
| 27 |
+
"wrb": 31141
|
| 28 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535828715
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc0e563d2c94b7cb5d6f04193868b0a65355c94f10607761d1d842f58965211
|
| 3 |
size 535828715
|
runs/Aug04_23-18-38_b64a65d64683/events.out.tfevents.1659655138.b64a65d64683.75.0
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 sha256:850c39b9db103ef00e6a1da8670ff53ece41bb8b0131fc8fa4b2c502cce1ce8e
|
| 3 |
+
size 12627
|
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_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"name_or_path": "allenai/scibert_scivocab_cased",
|
| 7 |
+
"never_split": null,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"special_tokens_map_file": null,
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|