amottelson
commited on
Commit
•
e18e7be
1
Parent(s):
22c5f8e
Training in progress, epoch 1
Browse files- config.json +17 -20
- pytorch_model.bin +2 -2
- runs/Apr13_19-52-44_2109fa16c98d/1681415657.4126906/events.out.tfevents.1681415657.2109fa16c98d.2911.1 +3 -0
- runs/Apr13_19-52-44_2109fa16c98d/events.out.tfevents.1681415657.2109fa16c98d.2911.0 +3 -0
- special_tokens_map.json +5 -49
- tokenizer.json +0 -0
- tokenizer_config.json +8 -60
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,36 +1,33 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
"0": "no",
|
15 |
"1": "yes"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
-
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
"no": 0,
|
21 |
"yes": 1
|
22 |
},
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"pad_token_id": 1,
|
29 |
-
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.28.0",
|
33 |
-
"
|
34 |
-
"use_cache": true,
|
35 |
-
"vocab_size": 50265
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "coding-gen/binary_text_classification_model",
|
3 |
+
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
|
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "no",
|
13 |
"1": "yes"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
|
|
16 |
"label2id": {
|
17 |
"no": 0,
|
18 |
"yes": 1
|
19 |
},
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "distilbert",
|
22 |
+
"n_heads": 12,
|
23 |
+
"n_layers": 6,
|
24 |
+
"pad_token_id": 0,
|
|
|
|
|
25 |
"problem_type": "single_label_classification",
|
26 |
+
"qa_dropout": 0.1,
|
27 |
+
"seq_classif_dropout": 0.2,
|
28 |
+
"sinusoidal_pos_embds": false,
|
29 |
+
"tie_weights_": true,
|
30 |
"torch_dtype": "float32",
|
31 |
"transformers_version": "4.28.0",
|
32 |
+
"vocab_size": 30522
|
|
|
|
|
33 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0f89edc73d97ba3f65b3175e5b64e1226faadee03a401b20d0be6e9b19bb057
|
3 |
+
size 267855533
|
runs/Apr13_19-52-44_2109fa16c98d/1681415657.4126906/events.out.tfevents.1681415657.2109fa16c98d.2911.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:305b45b48924779a217d255b247eb167cf495feafac59130208fc5fabecf888f
|
3 |
+
size 5879
|
runs/Apr13_19-52-44_2109fa16c98d/events.out.tfevents.1681415657.2109fa16c98d.2911.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ac775536e9bdd6f1b0454acdfcf588a5a9e421c021f5bc6b0f9b8a0b932c690
|
3 |
+
size 4408
|
special_tokens_map.json
CHANGED
@@ -1,51 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "<s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "</s>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "<mask>",
|
25 |
-
"lstrip": true,
|
26 |
-
"normalized": true,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "<pad>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "</s>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
-
"unk_token": {
|
45 |
-
"content": "<unk>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false
|
50 |
-
}
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,65 +1,13 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": {
|
4 |
-
"__type": "AddedToken",
|
5 |
-
"content": "<s>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false
|
10 |
-
},
|
11 |
"clean_up_tokenization_spaces": true,
|
12 |
-
"cls_token":
|
13 |
-
"__type": "AddedToken",
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": true,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
-
},
|
20 |
"do_lower_case": true,
|
21 |
-
"
|
22 |
-
"__type": "AddedToken",
|
23 |
-
"content": "</s>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": true,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false
|
28 |
-
},
|
29 |
-
"errors": "replace",
|
30 |
-
"mask_token": {
|
31 |
-
"__type": "AddedToken",
|
32 |
-
"content": "<mask>",
|
33 |
-
"lstrip": true,
|
34 |
-
"normalized": true,
|
35 |
-
"rstrip": false,
|
36 |
-
"single_word": false
|
37 |
-
},
|
38 |
"model_max_length": 512,
|
39 |
-
"pad_token":
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
"single_word": false
|
46 |
-
},
|
47 |
-
"sep_token": {
|
48 |
-
"__type": "AddedToken",
|
49 |
-
"content": "</s>",
|
50 |
-
"lstrip": false,
|
51 |
-
"normalized": true,
|
52 |
-
"rstrip": false,
|
53 |
-
"single_word": false
|
54 |
-
},
|
55 |
-
"tokenizer_class": "RobertaTokenizer",
|
56 |
-
"trim_offsets": true,
|
57 |
-
"unk_token": {
|
58 |
-
"__type": "AddedToken",
|
59 |
-
"content": "<unk>",
|
60 |
-
"lstrip": false,
|
61 |
-
"normalized": true,
|
62 |
-
"rstrip": false,
|
63 |
-
"single_word": false
|
64 |
-
}
|
65 |
}
|
|
|
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": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3579
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b36492cfb44b561ffe32f7706ea3c8c824ec0db670f9d0498653b23cf3cdf05
|
3 |
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|