Training in progress, step 10000
Browse files- .gitignore +1 -0
- config.json +22 -0
- logs/1685332474.4806716/events.out.tfevents.1685332474.serv-9225.2835589.1 +3 -0
- logs/1685334707.0584376/events.out.tfevents.1685334707.serv-3318.2100951.1 +3 -0
- logs/1685335746.4493518/events.out.tfevents.1685335746.serv-3318.2102972.1 +3 -0
- logs/events.out.tfevents.1685332474.serv-9225.2835589.0 +3 -0
- logs/events.out.tfevents.1685334707.serv-3318.2100951.0 +3 -0
- logs/events.out.tfevents.1685335746.serv-3318.2102972.0 +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/1685332474.4806716/events.out.tfevents.1685332474.serv-9225.2835589.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb99077267cc30aec03088a2b29a3cada059f902a42670685291048663175e41
|
3 |
+
size 5994
|
logs/1685334707.0584376/events.out.tfevents.1685334707.serv-3318.2100951.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19d8f51bd7453f885bb29a16a7086b4538adac16ecefb587819a47d0834bfa3b
|
3 |
+
size 5994
|
logs/1685335746.4493518/events.out.tfevents.1685335746.serv-3318.2102972.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25977bfff2adf20c1d960b23a40708537edd73a6a1d80779f61b972d27a342c1
|
3 |
+
size 5981
|
logs/events.out.tfevents.1685332474.serv-9225.2835589.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19b7b9bb06c6f4695f46735024d607632e6e8e63a1fbb48e5bc2116848f5a76e
|
3 |
+
size 4173
|
logs/events.out.tfevents.1685334707.serv-3318.2100951.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f8741ba251d235241602dc8b1060d1e0d82197da90055f64eaf65614f48d31f
|
3 |
+
size 4017
|
logs/events.out.tfevents.1685335746.serv-3318.2102972.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:283d24f6a3baf3810fdd71f1fc0430f78cd9801ee76c41d76b676d80d87409a9
|
3 |
+
size 7308
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed18d83ad01e2b30d949052b865ded1efc7943e70db8f524b20a64e1e7d5bad3
|
3 |
+
size 467494353
|
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 sha256:9da920c8e17bf24b80e17e464bd4a1f2e7b1289286af2fff285a891ac83e3316
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|