Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +36 -0
- logs/1686035023.673918/events.out.tfevents.1686035023.serv-9207.2389173.10 +3 -0
- logs/events.out.tfevents.1686035023.serv-9207.2389173.9 +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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48",
|
3 |
+
"activation": "relu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.05,
|
8 |
+
"cache_dir": null,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.05,
|
11 |
+
"finetuning_task": "qnli",
|
12 |
+
"hidden_dim": 3072,
|
13 |
+
"id2label": {
|
14 |
+
"0": "entailment",
|
15 |
+
"1": "not_entailment"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"entailment": 0,
|
20 |
+
"not_entailment": 1
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "hybridbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 12,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"qa_dropout": 0.1,
|
29 |
+
"revision": "main",
|
30 |
+
"seq_classif_dropout": 0.1,
|
31 |
+
"sinusoidal_pos_embds": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.29.2",
|
34 |
+
"use_auth_token": null,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
logs/1686035023.673918/events.out.tfevents.1686035023.serv-9207.2389173.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e80c823a75cfffe94f51af9fc623803fdd89b6f88510059a639a3c21d9a7ef7c
|
3 |
+
size 5938
|
logs/events.out.tfevents.1686035023.serv-9207.2389173.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e60851307a2b9d6588fa2ebb2fa6c09dbb8d6af3583d0ec65e95feab787474de
|
3 |
+
size 4598
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a804e9fd7af503a285cff8b7792f54864dcd9ae104d3c836ccb266d8b99767ff
|
3 |
+
size 481099229
|
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:a0cf0ec9a96c5190e3a62d91378dd06f72e84cdace46da211c3e2b192d6992da
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|