Training in progress, step 10000
Browse files- .gitignore +1 -0
- config.json +22 -0
- logs/1685660238.5242996/events.out.tfevents.1685660238.serv-9225.4169283.1 +3 -0
- logs/events.out.tfevents.1685660238.serv-9225.4169283.0 +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -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": "relu",
|
3 |
+
"architectures": [
|
4 |
+
"DistilBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.05,
|
7 |
+
"dim": 768,
|
8 |
+
"dropout": 0.05,
|
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": 0.1,
|
18 |
+
"sinusoidal_pos_embds": true,
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.29.2",
|
21 |
+
"vocab_size": 30522
|
22 |
+
}
|
logs/1685660238.5242996/events.out.tfevents.1685660238.serv-9225.4169283.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2760f741ce4fa8c0055dc804180fcbc2bfc229b40fed2685e17a7c98febf1f7b
|
3 |
+
size 6030
|
logs/events.out.tfevents.1685660238.serv-9225.4169283.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958742d4013c8ceb0470c82784f1ed940ebfb085c544a419dfd6e288dd46f42a
|
3 |
+
size 7359
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4029a2049206e0b9e0022844d48f69483dd35b5ea753837bc1161c2ebfcd0dd
|
3 |
+
size 481170113
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aae172059548f3852e0ed121a0f6c528c5d493230c27e55a3177dd5656c907d0
|
3 |
+
size 4603
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|