Training in progress, step 500
Browse files- config.json +111 -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
config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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": "Abby",
|
13 |
+
"1": "Andy",
|
14 |
+
"2": "Angela",
|
15 |
+
"3": "Billy Merchant",
|
16 |
+
"4": "Captain Jack",
|
17 |
+
"5": "Carol",
|
18 |
+
"6": "Christian",
|
19 |
+
"7": "Craig",
|
20 |
+
"8": "Creed",
|
21 |
+
"9": "Darryl",
|
22 |
+
"10": "David",
|
23 |
+
"11": "Dwight",
|
24 |
+
"12": "Hannah",
|
25 |
+
"13": "Improv Teacher",
|
26 |
+
"14": "Jake",
|
27 |
+
"15": "Jan",
|
28 |
+
"16": "Jim",
|
29 |
+
"17": "Josh",
|
30 |
+
"18": "Karen",
|
31 |
+
"19": "Katy",
|
32 |
+
"20": "Kelly",
|
33 |
+
"21": "Kevin",
|
34 |
+
"22": "Martin",
|
35 |
+
"23": "Mary-Beth",
|
36 |
+
"24": "Melissa",
|
37 |
+
"25": "Meredith",
|
38 |
+
"26": "Michael",
|
39 |
+
"27": "Mr. Brown",
|
40 |
+
"28": "Oscar",
|
41 |
+
"29": "Pam",
|
42 |
+
"30": "Pam's Mom",
|
43 |
+
"31": "Photographer",
|
44 |
+
"32": "Phyllis",
|
45 |
+
"33": "Roy",
|
46 |
+
"34": "Ryan",
|
47 |
+
"35": "Sadiq (IT guy)",
|
48 |
+
"36": "Second Cindy",
|
49 |
+
"37": "Stanley",
|
50 |
+
"38": "Toby",
|
51 |
+
"39": "Todd Packer",
|
52 |
+
"40": "Tony"
|
53 |
+
},
|
54 |
+
"initializer_range": 0.02,
|
55 |
+
"label2id": {
|
56 |
+
"Abby": 0,
|
57 |
+
"Andy": 1,
|
58 |
+
"Angela": 2,
|
59 |
+
"Billy Merchant": 3,
|
60 |
+
"Captain Jack": 4,
|
61 |
+
"Carol": 5,
|
62 |
+
"Christian": 6,
|
63 |
+
"Craig": 7,
|
64 |
+
"Creed": 8,
|
65 |
+
"Darryl": 9,
|
66 |
+
"David": 10,
|
67 |
+
"Dwight": 11,
|
68 |
+
"Hannah": 12,
|
69 |
+
"Improv Teacher": 13,
|
70 |
+
"Jake": 14,
|
71 |
+
"Jan": 15,
|
72 |
+
"Jim": 16,
|
73 |
+
"Josh": 17,
|
74 |
+
"Karen": 18,
|
75 |
+
"Katy": 19,
|
76 |
+
"Kelly": 20,
|
77 |
+
"Kevin": 21,
|
78 |
+
"Martin": 22,
|
79 |
+
"Mary-Beth": 23,
|
80 |
+
"Melissa": 24,
|
81 |
+
"Meredith": 25,
|
82 |
+
"Michael": 26,
|
83 |
+
"Mr. Brown": 27,
|
84 |
+
"Oscar": 28,
|
85 |
+
"Pam": 29,
|
86 |
+
"Pam's Mom": 30,
|
87 |
+
"Photographer": 31,
|
88 |
+
"Phyllis": 32,
|
89 |
+
"Roy": 33,
|
90 |
+
"Ryan": 34,
|
91 |
+
"Sadiq (IT guy)": 35,
|
92 |
+
"Second Cindy": 36,
|
93 |
+
"Stanley": 37,
|
94 |
+
"Toby": 38,
|
95 |
+
"Todd Packer": 39,
|
96 |
+
"Tony": 40
|
97 |
+
},
|
98 |
+
"max_position_embeddings": 512,
|
99 |
+
"model_type": "distilbert",
|
100 |
+
"n_heads": 12,
|
101 |
+
"n_layers": 6,
|
102 |
+
"pad_token_id": 0,
|
103 |
+
"problem_type": "single_label_classification",
|
104 |
+
"qa_dropout": 0.1,
|
105 |
+
"seq_classif_dropout": 0.2,
|
106 |
+
"sinusoidal_pos_embds": false,
|
107 |
+
"tie_weights_": true,
|
108 |
+
"torch_dtype": "float32",
|
109 |
+
"transformers_version": "4.32.1",
|
110 |
+
"vocab_size": 30522
|
111 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea440653154cd1eb02ef5671f79f991c28afa49fe24b1c486ab8d9b4ea79d717
|
3 |
+
size 267974061
|
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": "DistilBertTokenizer",
|
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:d70025b325d65e78076306d014aa5040a0410787084e6050f007b9173b4d86d9
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|