paragsmhatre
commited on
Commit
·
d77376c
1
Parent(s):
41ae7d4
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +76 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../DATA/OUTPUT/",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
+
"generator_size": "0.25",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 256,
|
13 |
+
"id2label": {
|
14 |
+
"0": "rec.sport.baseball",
|
15 |
+
"1": "alt.atheism",
|
16 |
+
"2": "talk.politics.misc",
|
17 |
+
"3": "sci.med",
|
18 |
+
"4": "talk.religion.misc",
|
19 |
+
"5": "comp.sys.ibm.pc.hardware",
|
20 |
+
"6": "sci.electronics",
|
21 |
+
"7": "rec.motorcycles",
|
22 |
+
"8": "comp.graphics",
|
23 |
+
"9": "comp.os.ms-windows.misc",
|
24 |
+
"10": "comp.windows.x",
|
25 |
+
"11": "talk.politics.mideast",
|
26 |
+
"12": "talk.politics.guns",
|
27 |
+
"13": "rec.autos",
|
28 |
+
"14": "comp.sys.mac.hardware",
|
29 |
+
"15": "sci.crypt",
|
30 |
+
"16": "sci.space",
|
31 |
+
"17": "misc.forsale",
|
32 |
+
"18": "soc.religion.christian",
|
33 |
+
"19": "rec.sport.hockey"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 1024,
|
37 |
+
"label2id": {
|
38 |
+
"alt.atheism": 1,
|
39 |
+
"comp.graphics": 8,
|
40 |
+
"comp.os.ms-windows.misc": 9,
|
41 |
+
"comp.sys.ibm.pc.hardware": 5,
|
42 |
+
"comp.sys.mac.hardware": 14,
|
43 |
+
"comp.windows.x": 10,
|
44 |
+
"misc.forsale": 17,
|
45 |
+
"rec.autos": 13,
|
46 |
+
"rec.motorcycles": 7,
|
47 |
+
"rec.sport.baseball": 0,
|
48 |
+
"rec.sport.hockey": 19,
|
49 |
+
"sci.crypt": 15,
|
50 |
+
"sci.electronics": 6,
|
51 |
+
"sci.med": 3,
|
52 |
+
"sci.space": 16,
|
53 |
+
"soc.religion.christian": 18,
|
54 |
+
"talk.politics.guns": 12,
|
55 |
+
"talk.politics.mideast": 11,
|
56 |
+
"talk.politics.misc": 2,
|
57 |
+
"talk.religion.misc": 4
|
58 |
+
},
|
59 |
+
"layer_norm_eps": 1e-12,
|
60 |
+
"max_position_embeddings": 512,
|
61 |
+
"model_type": "electra",
|
62 |
+
"num_attention_heads": 4,
|
63 |
+
"num_hidden_layers": 12,
|
64 |
+
"pad_token_id": 0,
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"problem_type": "single_label_classification",
|
67 |
+
"summary_activation": "gelu",
|
68 |
+
"summary_last_dropout": 0.1,
|
69 |
+
"summary_type": "first",
|
70 |
+
"summary_use_proj": true,
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.25.1",
|
73 |
+
"type_vocab_size": 2,
|
74 |
+
"use_cache": true,
|
75 |
+
"vocab_size": 119547
|
76 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3faf3cdf9fc4ea5f43259cb3ed45a71e512b870c56f996bfc902f9b7b645745
|
3 |
+
size 99867773
|
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_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "../DATA/INPUT/UNZIP_DATASET",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"return_tensors": "pt",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f8a1cd8032cdcccfed41aed970cd22abf525252f6b031662777f78ba5be9b23
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|