gokuls commited on
Commit
38f8429
1 Parent(s): a658412

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gokuls/bert_12_layer_model_v2_complete_training_new_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": "mnli",
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "entailment",
15
+ "1": "neutral",
16
+ "2": "contradiction"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "contradiction": 2,
21
+ "entailment": 0,
22
+ "neutral": 1
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "hybridbert",
26
+ "n_heads": 12,
27
+ "n_layers": 12,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "revision": "main",
32
+ "seq_classif_dropout": 0.1,
33
+ "sinusoidal_pos_embds": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.29.2",
36
+ "use_auth_token": null,
37
+ "vocab_size": 30522
38
+ }
logs/1686061800.1498263/events.out.tfevents.1686061800.serv-3317.3380349.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3a0a800acdc780117be3bb22e968319d9949d179a9c1bd05cced55c51548dd
3
+ size 5930
logs/events.out.tfevents.1686061800.serv-3317.3380349.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc71861795b69705b0816652ca01091f4e6cd7877a997546775eef8e72f78fb3
3
+ size 4623
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4018e9ef7af85567e591f8e62fce10d8482be33e390db681b79b1deb6cea6c9d
3
+ size 476526509
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 sha256:87425901f4da3b891b6945e6f85eb93c6e2b9f4c24eb9ca938981cd4fdc65c04
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff