Hugging Face's logo

lvkaokao
/
bert-base-uncased-teacher-preparation-pretrain

Transformers
PyTorch
bert
pretraining
Inference Endpoints
Model card Files Community
root commited on
Commit
e904c00
•
1 Parent(s): 9cf8be7

upload teacher pretrained model on wikipedia.

Browse files
Files changed (11) hide show
  1. all_results.json +8 -0
  2. args.bin +3 -0
  3. config.json +29 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +14 -0
  8. train_results.json +8 -0
  9. trainer_state.json +0 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.5,
3
+ "train_loss": 1.5298656570243836,
4
+ "train_runtime": 127603.5055,
5
+ "train_samples": 17029620,
6
+ "train_samples_per_second": 200.621,
7
+ "train_steps_per_second": 0.784
8
+ }
args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662968bd62fcaf334d0da7002fa0368234228d4cf7efb570a02ebf9a4cd00017
3
+ size 4527
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForPreTraining"
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "keys_to_ignore_at_inference": [
15
+ "prediction_logits"
16
+ ],
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 0,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.21.2",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f765a2fd9209a8457d25cde443e51f667803fc883ce6a648f914d27fd7cea93
3
+ size 440501472
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.5,
3
+ "train_loss": 1.5298656570243836,
4
+ "train_runtime": 127603.5055,
5
+ "train_samples": 17029620,
6
+ "train_samples_per_second": 200.621,
7
+ "train_steps_per_second": 0.784
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92bb508666b5e7ec96c62e117300bbd54fff1f8bf6eeb5f26ebec3d4f0fcb47
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff