Commit 路
8a2388f
1
Parent(s): ade39aa
bert-cased
Browse files- README.md +2 -2
- pytorch_model.bin +1 -1
- special_tokens_map.json +7 -0
- tokenizer.json +2 -16
- tokenizer_config.json +14 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -33,11 +33,11 @@ More information needed
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 1e-05
|
| 36 |
-
- train_batch_size:
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
- gradient_accumulation_steps: 4
|
| 40 |
-
- total_train_batch_size:
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 2
|
|
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 1e-05
|
| 36 |
+
- train_batch_size: 8
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
- gradient_accumulation_steps: 4
|
| 40 |
+
- total_train_batch_size: 32
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 2
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 430952617
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:643efd0868ec2c3381285f6c61ec8b22059b8011320eb44f874ea2e8c4dd0463
|
| 3 |
size 430952617
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
|
|
|
| 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]",
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 384,
|
| 6 |
-
"strategy": "OnlySecond",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 384
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "[PAD]"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -41,19 +41,32 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_basic_tokenize": true,
|
| 48 |
"do_lower_case": false,
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"max_len": 512,
|
|
|
|
| 51 |
"model_max_length": 512,
|
| 52 |
"never_split": null,
|
|
|
|
| 53 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 54 |
"sep_token": "[SEP]",
|
|
|
|
| 55 |
"strip_accents": null,
|
| 56 |
"tokenize_chinese_chars": true,
|
| 57 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 58 |
"unk_token": "[UNK]"
|
| 59 |
}
|
|
|
|
| 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_basic_tokenize": true,
|
| 54 |
"do_lower_case": false,
|
| 55 |
"mask_token": "[MASK]",
|
| 56 |
"max_len": 512,
|
| 57 |
+
"max_length": 384,
|
| 58 |
"model_max_length": 512,
|
| 59 |
"never_split": null,
|
| 60 |
+
"pad_to_multiple_of": null,
|
| 61 |
"pad_token": "[PAD]",
|
| 62 |
+
"pad_token_type_id": 0,
|
| 63 |
+
"padding_side": "right",
|
| 64 |
"sep_token": "[SEP]",
|
| 65 |
+
"stride": 0,
|
| 66 |
"strip_accents": null,
|
| 67 |
"tokenize_chinese_chars": true,
|
| 68 |
"tokenizer_class": "BertTokenizer",
|
| 69 |
+
"truncation_side": "right",
|
| 70 |
+
"truncation_strategy": "only_second",
|
| 71 |
"unk_token": "[UNK]"
|
| 72 |
}
|
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:ca81de591346d781087219b5de01a889009697bbdb54b3a228ae0bda48b57796
|
| 3 |
size 4091
|