Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +34 -0
- logs/1686057825.9524233/events.out.tfevents.1686057825.serv-9207.2389173.19 +3 -0
- logs/events.out.tfevents.1686057825.serv-9207.2389173.18 +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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "stsb",
|
12 |
+
"hidden_dim": 3072,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "hybridbert",
|
22 |
+
"n_heads": 12,
|
23 |
+
"n_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"problem_type": "regression",
|
26 |
+
"qa_dropout": 0.1,
|
27 |
+
"revision": "main",
|
28 |
+
"seq_classif_dropout": 0.1,
|
29 |
+
"sinusoidal_pos_embds": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.29.2",
|
32 |
+
"use_auth_token": null,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
logs/1686057825.9524233/events.out.tfevents.1686057825.serv-9207.2389173.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52c4211b84950c72d646c1c2d9147b8cb3e919e0c6fc9662346914a6dd1ecbd6
|
3 |
+
size 5938
|
logs/events.out.tfevents.1686057825.serv-9207.2389173.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9a26c3e53e8e8ad9d71d304b681458802e8ebd41388e99946adb11c74da6395
|
3 |
+
size 4639
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd0c844bdd3d159cbf1d928334931285aee4eb6775c65aa1b817ef5ab040b471
|
3 |
+
size 481096157
|
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 sha256:51dc92eb348a650d8bf9bb413f3b77f39d362c840f6c1e5b513eeb2218db9f62
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|