Mahmoud8 commited on
Commit
d529efb
1 Parent(s): f66f3e2

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": "uw-madison/yoso-4096",
3
+ "architectures": [
4
+ "YosoForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "conv_window": null,
9
+ "eos_token_id": 2,
10
+ "hash_code_len": 9,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-12,
17
+ "lsh_backward": true,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "yoso",
20
+ "num_attention_heads": 12,
21
+ "num_hash": 64,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "problem_type": "single_label_classification",
26
+ "tokenizer_class": "AlbertTokenizer",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.31.0",
29
+ "type_vocab_size": 1,
30
+ "use_expectation": true,
31
+ "use_fast_hash": true,
32
+ "vocab_size": 50265
33
+ }
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 sha256:65fe41e03fe438f8ab9b891dc292fbe0eccdcf9f969cc6fde997595e43acdad6
3
+ size 509667121
runs/Oct31_07-45-46_3d43c92c4d8b/events.out.tfevents.1698738350.3d43c92c4d8b.31.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92dd73b512f163898ec0e30eb2cb00fc9abeb85b20da82eaf69a2e5c28ef990d
3
+ size 5558
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2165332e380d087e736a27cd03f956f3010c51ce9498d4701152dcd830487fb8
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff