Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +22 -0
- logs/1677581822.90313/events.out.tfevents.1677581822.serv-3332.3411920.1 +3 -0
- logs/events.out.tfevents.1677581822.serv-3332.3411920.0 +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"DistilBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"dim": 768,
|
8 |
+
"dropout": 0.1,
|
9 |
+
"hidden_dim": 3072,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"max_position_embeddings": 512,
|
12 |
+
"model_type": "hybridbert",
|
13 |
+
"n_heads": 12,
|
14 |
+
"n_layers": 12,
|
15 |
+
"pad_token_id": 0,
|
16 |
+
"qa_dropout": 0.1,
|
17 |
+
"seq_classif_dropout": 0.2,
|
18 |
+
"sinusoidal_pos_embds": true,
|
19 |
+
"torch_dtype": "float16",
|
20 |
+
"transformers_version": "4.26.1",
|
21 |
+
"vocab_size": 30522
|
22 |
+
}
|
logs/1677581822.90313/events.out.tfevents.1677581822.serv-3332.3411920.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1246aa7263b80bb2ed6b7752cfdcd5680d5ecbb0da4a3c3662211d7ad1f4fe75
|
3 |
+
size 5776
|
logs/events.out.tfevents.1677581822.serv-3332.3411920.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6f4faf633dc565404877da33808d2335db21773150a2ce6a0ca8afa00ceb13b
|
3 |
+
size 4157
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f92d6138560e1ff08567ce863af1f5737e6095aca3e1f6712895772f7622aa52
|
3 |
+
size 212235391
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5022fece8be2fb181795456e132b45dce15bb600da38c5561cac44d8ead373cd
|
3 |
+
size 4603
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|