gokuls commited on
Commit
bd4f580
·
1 Parent(s): 65b90a3

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48",
3
+ "activation": "relu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.005,
8
+ "cache_dir": null,
9
+ "dim": 768,
10
+ "dropout": 0.005,
11
+ "embedding_size": 128,
12
+ "finetuning_task": "wnli",
13
+ "hidden_dim": 3072,
14
+ "id2label": {
15
+ "0": "not_entailment",
16
+ "1": "entailment"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "entailment": 1,
21
+ "not_entailment": 0
22
+ },
23
+ "max_position_embeddings": 512,
24
+ "model_type": "hybridbert",
25
+ "n_heads": 12,
26
+ "n_layers": 12,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.005,
30
+ "revision": "main",
31
+ "seq_classif_dropout": 0.005,
32
+ "sinusoidal_pos_embds": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.30.2",
35
+ "use_auth_token": null,
36
+ "vocab_size": 30522
37
+ }
logs/events.out.tfevents.1686837097.garda.2601621.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d966851a83c889bb99119911e0df4eeda2822cf598f774c1f9604bac4880b8e3
3
+ size 4626
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe3cd35d387f0e13f4c9a4ccb14f40279516a6bd28b3fb70feec76f868dd3f5
3
+ size 402044133
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2781ff538185d65a375f7893bc2272f9bb97871a72726a39281c0583ac4cd49
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff