Commit
•
feaac7a
1
Parent(s):
99e6ce5
End of training
Browse files- README.md +1 -1
- pytorch_model.bin +1 -1
- special_tokens_map.json +0 -7
- tokenizer.json +1 -8
- tokenizer_config.json +1 -14
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -47,4 +47,4 @@ The following hyperparameters were used during training:
|
|
| 47 |
- Transformers 4.34.0
|
| 48 |
- Pytorch 2.0.1+cu118
|
| 49 |
- Datasets 2.14.5
|
| 50 |
-
- Tokenizers 0.14.
|
|
|
|
| 47 |
- Transformers 4.34.0
|
| 48 |
- Pytorch 2.0.1+cu118
|
| 49 |
- Datasets 2.14.5
|
| 50 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437997617
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:878c385d24a1be17174212be0c4034afaab1cce39ef489ffc4bb98b684160836
|
| 3 |
size 437997617
|
special_tokens_map.json
CHANGED
|
@@ -1,11 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"[PAD]",
|
| 4 |
-
"[UNK]",
|
| 5 |
-
"[CLS]",
|
| 6 |
-
"[SEP]",
|
| 7 |
-
"[MASK]"
|
| 8 |
-
],
|
| 9 |
"cls_token": "[CLS]",
|
| 10 |
"mask_token": "[MASK]",
|
| 11 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
tokenizer.json
CHANGED
|
@@ -1,14 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
-
"padding":
|
| 5 |
-
"strategy": "BatchLongest",
|
| 6 |
-
"direction": "Right",
|
| 7 |
-
"pad_to_multiple_of": null,
|
| 8 |
-
"pad_id": 0,
|
| 9 |
-
"pad_type_id": 0,
|
| 10 |
-
"pad_token": "[PAD]"
|
| 11 |
-
},
|
| 12 |
"added_tokens": [
|
| 13 |
{
|
| 14 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -41,29 +41,16 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"additional_special_tokens": [
|
| 45 |
-
"[PAD]",
|
| 46 |
-
"[UNK]",
|
| 47 |
-
"[CLS]",
|
| 48 |
-
"[SEP]",
|
| 49 |
-
"[MASK]"
|
| 50 |
-
],
|
| 51 |
"clean_up_tokenization_spaces": true,
|
| 52 |
"cls_token": "[CLS]",
|
| 53 |
"do_lower_case": true,
|
| 54 |
"mask_token": "[MASK]",
|
| 55 |
-
"max_length": 512,
|
| 56 |
"model_max_length": 512,
|
| 57 |
-
"pad_to_multiple_of": null,
|
| 58 |
"pad_token": "[PAD]",
|
| 59 |
-
"pad_token_type_id": 0,
|
| 60 |
-
"padding_side": "right",
|
| 61 |
"sep_token": "[SEP]",
|
| 62 |
-
"stride": 0,
|
| 63 |
"strip_accents": null,
|
| 64 |
"tokenize_chinese_chars": true,
|
| 65 |
"tokenizer_class": "BertTokenizer",
|
| 66 |
-
"truncation_side": "right",
|
| 67 |
-
"truncation_strategy": "longest_first",
|
| 68 |
"unk_token": "[UNK]"
|
| 69 |
}
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
|
|
|
| 49 |
"model_max_length": 512,
|
|
|
|
| 50 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 51 |
"sep_token": "[SEP]",
|
|
|
|
| 52 |
"strip_accents": null,
|
| 53 |
"tokenize_chinese_chars": true,
|
| 54 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 55 |
"unk_token": "[UNK]"
|
| 56 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49f532a6011f5da796b3002cb53c290b57dc0de862f3ef9333a33f9ba113f2f1
|
| 3 |
size 4091
|