gokuls commited on
Commit
162c8bf
1 Parent(s): 0d31109

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gokuls/bert_12_layer_model_v2",
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
+ "initializer_range": 0.02,
12
+ "label2id": {
13
+ "entailment": 0,
14
+ "not_entailment": 1
15
+ },
16
+ "max_position_embeddings": 512,
17
+ "model_type": "hybridbert",
18
+ "n_heads": 12,
19
+ "n_layers": 12,
20
+ "pad_token_id": 0,
21
+ "problem_type": "single_label_classification",
22
+ "qa_dropout": 0.1,
23
+ "seq_classif_dropout": 0.2,
24
+ "sinusoidal_pos_embds": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.26.1",
27
+ "vocab_size": 30522
28
+ }
logs/1677673684.0526414/events.out.tfevents.1677673684.kyoto.1079667.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abf68e651c56d1f9f40430d76eea1a82b1c651d31220b3603f288fc232d96bc
3
+ size 5684
logs/events.out.tfevents.1677673684.kyoto.1079667.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:901cd4da8471cd8dc43998821f85e52babf2065acaacc149db6c1fa052d284b2
3
+ size 4274
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208c0774edde2112bbb007fff5c37b5fe7a2baad0c7b66afd9a7caeeb259731b
3
+ size 419780621
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": "bert-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": "BertTokenizer",
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:c50da10ad3de6f16f0551fd8404bc902611877ce5b0c41d1339ad1ad11bd48d0
3
+ size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff