gokuls commited on
Commit
02e9a8d
1 Parent(s): 2abc94f

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_v2",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "rte",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "not_entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "entailment": 0,
19
+ "not_entailment": 1
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/1677989993.380263/events.out.tfevents.1677989993.serv-3317.65033.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388deb72f3c8f2dd5a3e968616a8d317c2eeec3981a8c37e61e7895068fb4bc4
3
+ size 5680
logs/events.out.tfevents.1677989993.serv-3317.65033.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcd8cb202c4fa11e7b33d98e7e96efffe91624d98fa0142d3489059a5b0f937
3
+ size 4359
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbac89ff9bfbddf016bccd8df28dfa0378d4d25d35437c436ba018255693eb6
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 sha256:2d4927a8cebc3d2afba2872531fff0305676e549d7ef1f6a388f38824112ee06
3
+ size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff