paragsmhatre
commited on
Commit
•
b406ac4
1
Parent(s):
9418d2e
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +69 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "rec.sport.baseball",
|
13 |
+
"1": "alt.atheism",
|
14 |
+
"2": "talk.politics.misc",
|
15 |
+
"3": "sci.med",
|
16 |
+
"4": "talk.religion.misc",
|
17 |
+
"5": "comp.sys.ibm.pc.hardware",
|
18 |
+
"6": "sci.electronics",
|
19 |
+
"7": "rec.motorcycles",
|
20 |
+
"8": "comp.graphics",
|
21 |
+
"9": "comp.os.ms-windows.misc",
|
22 |
+
"10": "comp.windows.x",
|
23 |
+
"11": "talk.politics.mideast",
|
24 |
+
"12": "talk.politics.guns",
|
25 |
+
"13": "rec.autos",
|
26 |
+
"14": "comp.sys.mac.hardware",
|
27 |
+
"15": "sci.crypt",
|
28 |
+
"16": "sci.space",
|
29 |
+
"17": "misc.forsale",
|
30 |
+
"18": "soc.religion.christian",
|
31 |
+
"19": "rec.sport.hockey"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"label2id": {
|
35 |
+
"alt.atheism": 1,
|
36 |
+
"comp.graphics": 8,
|
37 |
+
"comp.os.ms-windows.misc": 9,
|
38 |
+
"comp.sys.ibm.pc.hardware": 5,
|
39 |
+
"comp.sys.mac.hardware": 14,
|
40 |
+
"comp.windows.x": 10,
|
41 |
+
"misc.forsale": 17,
|
42 |
+
"rec.autos": 13,
|
43 |
+
"rec.motorcycles": 7,
|
44 |
+
"rec.sport.baseball": 0,
|
45 |
+
"rec.sport.hockey": 19,
|
46 |
+
"sci.crypt": 15,
|
47 |
+
"sci.electronics": 6,
|
48 |
+
"sci.med": 3,
|
49 |
+
"sci.space": 16,
|
50 |
+
"soc.religion.christian": 18,
|
51 |
+
"talk.politics.guns": 12,
|
52 |
+
"talk.politics.mideast": 11,
|
53 |
+
"talk.politics.misc": 2,
|
54 |
+
"talk.religion.misc": 4
|
55 |
+
},
|
56 |
+
"max_position_embeddings": 512,
|
57 |
+
"model_type": "distilbert",
|
58 |
+
"n_heads": 12,
|
59 |
+
"n_layers": 6,
|
60 |
+
"pad_token_id": 0,
|
61 |
+
"problem_type": "single_label_classification",
|
62 |
+
"qa_dropout": 0.1,
|
63 |
+
"seq_classif_dropout": 0.2,
|
64 |
+
"sinusoidal_pos_embds": false,
|
65 |
+
"tie_weights_": true,
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.25.1",
|
68 |
+
"vocab_size": 30522
|
69 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a60ec94225cd6da5c0dc3181f666eed9b052792317261ab842a1cdecf65bd80
|
3 |
+
size 267909485
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc2a823291e6cb3932a82912810599d8c0bd99f906ead4ba70ad169b2e380e8
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|