Padmaj Srivastav commited on
Commit
b2af1dc
·
1 Parent(s): 0037cce

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "BENGALI",
13
+ "1": "MARATHI",
14
+ "2": "GUJARATI",
15
+ "3": "MALAYALI",
16
+ "4": "PUNJABI",
17
+ "5": "TELUGU",
18
+ "6": "TAMILIAN",
19
+ "7": "ODIYA",
20
+ "8": "KANNADIGA",
21
+ "9": "SINDHI"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "BENGALI": 0,
26
+ "GUJARATI": 2,
27
+ "KANNADIGA": 8,
28
+ "MALAYALI": 3,
29
+ "MARATHI": 1,
30
+ "ODIYA": 7,
31
+ "PUNJABI": 4,
32
+ "SINDHI": 9,
33
+ "TAMILIAN": 6,
34
+ "TELUGU": 5
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "pad_token_id": 0,
41
+ "problem_type": "single_label_classification",
42
+ "qa_dropout": 0.1,
43
+ "seq_classif_dropout": 0.2,
44
+ "sinusoidal_pos_embds": false,
45
+ "tie_weights_": true,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.14.1",
48
+ "vocab_size": 30522
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01f5755269149474c6eceaf0dabb05d2b073f9f24ee9b8a5b7ced2495d2701f
3
+ size 267884657
runs/Feb13_08-37-55_abfrl-cltv-gpu/1676277710.0429344/events.out.tfevents.1676277710.abfrl-cltv-gpu.17172.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2064753ef02eddd0be20101965c3b349f24dec191c6577f2634516009dbddf1
3
+ size 4694
runs/Feb13_08-37-55_abfrl-cltv-gpu/events.out.tfevents.1676277709.abfrl-cltv-gpu.17172.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f64677e6f2542dc84a840ed96ec4c432013580068787c8aed44cf5f55e30839
3
+ size 3735
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae464c1486cc857ca752a9d3eaa88a4bb14de793b7fc957da63c54a47b44de5
3
+ size 2927
vocab.txt ADDED
The diff for this file is too large to render. See raw diff