Shaier commited on
Commit
996e32e
1 Parent(s): 54d989b

Training in progress, epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForMultipleChoice"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "classifier_dropout": null,
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2",
33
+ "3": "LABEL_3"
34
+ },
35
+ "ignore_attention_mask": false,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2,
42
+ "LABEL_3": 3
43
+ },
44
+ "layer_norm_eps": 1e-05,
45
+ "max_position_embeddings": 4098,
46
+ "model_type": "longformer",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 1,
50
+ "position_embedding_type": "absolute",
51
+ "sep_token_id": 2,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.21.3",
54
+ "type_vocab_size": 1,
55
+ "use_cache": true,
56
+ "vocab_size": 50265
57
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcda008fb791cd0fa71d4fe090a517510c5cd04a1d17498c2a3cdbf5389b37b2
3
+ size 594733983
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 4096,
9
+ "name_or_path": "allenai/longformer-base-4096",
10
+ "pad_token": "<pad>",
11
+ "padding": true,
12
+ "sep_token": "</s>",
13
+ "special_tokens_map_file": null,
14
+ "tokenizer_class": "LongformerTokenizer",
15
+ "trim_offsets": true,
16
+ "truncation": true,
17
+ "unk_token": "<unk>"
18
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f8bb3062fb931fc42f58c83a6fe5064cdf7a1c4138621b2e0b60887cfb9558
3
+ size 3311
vocab.json ADDED
The diff for this file is too large to render. See raw diff