gokuls commited on
Commit
2730176
1 Parent(s): add6876

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init",
3
+ "activation": "relu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.05,
8
+ "cache_dir": null,
9
+ "dim": 768,
10
+ "dropout": 0.05,
11
+ "finetuning_task": "qnli",
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "entailment",
15
+ "1": "not_entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "entailment": 0,
20
+ "not_entailment": 1
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "hybridbert",
24
+ "n_heads": 12,
25
+ "n_layers": 12,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "revision": "main",
30
+ "seq_classif_dropout": 0.1,
31
+ "sinusoidal_pos_embds": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.30.2",
34
+ "use_auth_token": null,
35
+ "vocab_size": 30522
36
+ }
logs/events.out.tfevents.1686865234.serv-9225.2647846.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d16dc5c996deecdf3cdc86c27859a76f142d77a2ecf664286de5ece72833d3
3
+ size 4610
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068acd43ab5132888b2a713ade5d6812b46362e99e4fd93b342dfe0cf9fa55d3
3
+ size 476523437
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 sha256:30c0f7b26929a6ff5f4d38ef4764185d7d0779542691ea9718809bf038c9f1c5
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff