daze-unlv commited on
Commit
0519d91
1 Parent(s): 27a4f5a

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bigbird-roberta-base",
3
+ "architectures": [
4
+ "BigBirdForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_type": "block_sparse",
8
+ "block_size": 64,
9
+ "bos_token_id": 1,
10
+ "classifier_dropout": null,
11
+ "eos_token_id": 2,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 4096,
20
+ "model_type": "big_bird",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "num_random_blocks": 3,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "rescale_embeddings": false,
27
+ "sep_token_id": 66,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.39.0.dev0",
30
+ "type_vocab_size": 2,
31
+ "use_bias": true,
32
+ "use_cache": true,
33
+ "vocab_size": 50358
34
+ }
log.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {'loss': 1.3895, 'grad_norm': 0.917380154132843, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
2
+ {'loss': 1.3891, 'grad_norm': 0.43125149607658386, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
3
+ {'loss': 1.3883, 'grad_norm': 0.3787681758403778, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
4
+ {'loss': 1.3882, 'grad_norm': 0.400529682636261, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
5
+ {'loss': 1.3882, 'grad_norm': 0.31423699855804443, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6dd30730271cbe2f23639c21037488adc6543b449ab34cfb787d692f499fef
3
+ size 509901812
runs/Mar12_12-22-43_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710271366.cehsc-app-001.ad.unlv.edu.2392965.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfe7fdc822eba85392d786f6d5273d10ad59d72ac5517990712396a6d768c95
3
+ size 6227
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
3
+ size 845731
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "65": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "66": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "67": {
44
+ "content": "[MASK]",
45
+ "lstrip": true,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "100": {
52
+ "content": "<unk>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "</s>",
61
+ "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "eos_token": "<s>",
64
+ "mask_token": "[MASK]",
65
+ "model_max_length": 4096,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "[SEP]",
68
+ "sp_model_kwargs": {},
69
+ "tokenizer_class": "BigBirdTokenizer",
70
+ "unk_token": "<unk>"
71
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021a2495c5716891a8af3d9ecc817ea9268829bd81c466b63664adcd87120223
3
+ size 4920