ireneli1024 commited on
Commit
3842a17
1 Parent(s): bcfdccf

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bigbird-pegasus-large-pubmed",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "BigBirdPegasusForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_type": "block_sparse",
10
+ "block_size": 64,
11
+ "bos_token_id": 2,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 16,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 16,
24
+ "eos_token_id": 1,
25
+ "gradient_checkpointing": false,
26
+ "init_std": 0.02,
27
+ "is_encoder_decoder": true,
28
+ "length_penalty": 0.8,
29
+ "max_length": 256,
30
+ "max_position_embeddings": 4096,
31
+ "model_type": "bigbird_pegasus",
32
+ "num_beams": 5,
33
+ "num_hidden_layers": 16,
34
+ "num_random_blocks": 3,
35
+ "pad_token_id": 0,
36
+ "scale_embedding": true,
37
+ "tokenizer_class": "PegasusTokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.0",
40
+ "use_bias": false,
41
+ "use_cache": true,
42
+ "vocab_size": 96103
43
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 1,
6
+ "length_penalty": 0.8,
7
+ "max_length": 256,
8
+ "num_beams": 5,
9
+ "pad_token_id": 0,
10
+ "transformers_version": "4.28.0"
11
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89891343e4c453398c4ee472bc7e5c013dd5008b05f44e0f604eb94acb969fe9
3
+ size 4615427341
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c005e7290aa8a5ab4dc9f835949a1c1b0bcbcf4f3472b1b0cb9b5e839503b7f8
3
+ size 2308118957
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ec3ad6525d3fc0683b243a3ef44551e9bf629b2b8b4768b78209e132e64c40
3
+ size 15661
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb3a07d02472a0c7263892683f16fb010db062c726c2f5630f74b29bd08c4bc
3
+ size 627
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:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
3
+ size 1915455
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": "[MASK]",
29
+ "mask_token_sent": null,
30
+ "model_max_length": 4096,
31
+ "offset": 0,
32
+ "pad_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<pad>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "sep_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[SEP]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "tokenizer_class": "PegasusTokenizer",
49
+ "unk_token": {
50
+ "__type": "AddedToken",
51
+ "content": "<unk>",
52
+ "lstrip": false,
53
+ "normalized": true,
54
+ "rstrip": false,
55
+ "single_word": false
56
+ }
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.4188034188034186,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 1e-05,
13
+ "loss": 4.4095,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.34,
18
+ "learning_rate": 2e-05,
19
+ "loss": 3.5202,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.51,
24
+ "learning_rate": 1.888888888888889e-05,
25
+ "loss": 3.2715,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.68,
30
+ "learning_rate": 1.7777777777777777e-05,
31
+ "loss": 3.0872,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.85,
36
+ "learning_rate": 1.6666666666666667e-05,
37
+ "loss": 2.9574,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.03,
42
+ "learning_rate": 1.555555555555556e-05,
43
+ "loss": 2.8833,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.2,
48
+ "learning_rate": 1.4444444444444446e-05,
49
+ "loss": 2.8135,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.37,
54
+ "learning_rate": 1.3333333333333333e-05,
55
+ "loss": 2.7587,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.54,
60
+ "learning_rate": 1.2222222222222224e-05,
61
+ "loss": 2.7349,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.71,
66
+ "learning_rate": 1.1111111111111113e-05,
67
+ "loss": 2.7262,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.88,
72
+ "learning_rate": 1e-05,
73
+ "loss": 2.6846,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.05,
78
+ "learning_rate": 8.888888888888888e-06,
79
+ "loss": 2.658,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.22,
84
+ "learning_rate": 7.77777777777778e-06,
85
+ "loss": 2.6489,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.39,
90
+ "learning_rate": 6.666666666666667e-06,
91
+ "loss": 2.6384,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.56,
96
+ "learning_rate": 5.555555555555557e-06,
97
+ "loss": 2.6136,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.74,
102
+ "learning_rate": 4.444444444444444e-06,
103
+ "loss": 2.6143,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.91,
108
+ "learning_rate": 3.3333333333333333e-06,
109
+ "loss": 2.5972,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 3.08,
114
+ "learning_rate": 2.222222222222222e-06,
115
+ "loss": 2.5893,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 3.25,
120
+ "learning_rate": 1.111111111111111e-06,
121
+ "loss": 2.5803,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.42,
126
+ "learning_rate": 0.0,
127
+ "loss": 2.5825,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 10000,
132
+ "num_train_epochs": 4,
133
+ "total_flos": 2.310345220643881e+17,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391a37ee3847000c0327cec93314eaabdd62d37cfa442b44ae7e9a4c0adaf9e7
3
+ size 3771