gokuls commited on
Commit
8c6f6cb
1 Parent(s): d0e2d82

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gokuls/bert_12_layer_model_v1",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "wnli",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "not_entailment",
14
+ "1": "entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "entailment": 1,
19
+ "not_entailment": 0
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "hybridbert",
23
+ "n_heads": 12,
24
+ "n_layers": 12,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.26.1",
32
+ "vocab_size": 30522
33
+ }
logs/1677756205.5604436/events.out.tfevents.1677756205.serv-9223.249682.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7436b38bf479b37781b79eedacf0ed44d99728973516103d71b7f32c2c8ece30
3
+ size 5648
logs/events.out.tfevents.1677756205.serv-9223.249682.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9827c87da68938c2ad1d8a747b0d3287c57a98a2c385cd852908caa001cfff93
3
+ size 4319
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab20ff3bc9dd77222db7bfb0dde234bde7b8c2fd0053464bef9d8e50b45f5f4
3
+ size 424356413
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:acdbbd87426631938377d0d9c735d46df5e63fb0b7a85358524875b392830f60
3
+ size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff