Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +27 -0
- pytorch_model.bin +3 -0
- runs/Apr22_06-32-20_78cae390ebc5/1682145214.8971086/events.out.tfevents.1682145214.78cae390ebc5.2480.3 +3 -0
- runs/Apr22_06-32-20_78cae390ebc5/events.out.tfevents.1682145214.78cae390ebc5.2480.2 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DeepPavlov/distilrubert-tiny-cased-conversational",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForQuestionAnswering"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 2,
|
16 |
+
"output_attentions": true,
|
17 |
+
"output_hidden_states": true,
|
18 |
+
"output_past": true,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"qa_dropout": 0.1,
|
21 |
+
"seq_classif_dropout": 0.2,
|
22 |
+
"sinusoidal_pos_embds": false,
|
23 |
+
"tie_weights_": true,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.28.1",
|
26 |
+
"vocab_size": 119547
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ae51c2e2e447a05703124e8410008158c889114136b7e99b8390f1c11d1d87
|
3 |
+
size 425548771
|
runs/Apr22_06-32-20_78cae390ebc5/1682145214.8971086/events.out.tfevents.1682145214.78cae390ebc5.2480.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612174244e1e4c82ba703bf8b4ec0e0bb3ecc6b3762b83d4f27aa67282b39469
|
3 |
+
size 5963
|
runs/Apr22_06-32-20_78cae390ebc5/events.out.tfevents.1682145214.78cae390ebc5.2480.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c362a6b723d3adc326ffe5a9f4efc46467829fc3a4d33d879b8817c23f1030c8
|
3 |
+
size 4023
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "DistilBertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a35b853f47c54f8026c0ed1d3e46f7e92bb5ea9874cf03b7c255129c30e7cb12
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|