Hugging Face's logo

legacy107
/
flan-t5-large-bottleneck-ia3-union-cpgQA

Adapters
PyTorch
TensorBoard
t5
Model card Files Metrics Community
legacy107 commited on
Commit
f0dce44
•
1 Parent(s): 2371f78

Training in progress, step 500

Browse files
Files changed (12) hide show
  1. .gitignore +1 -0
  2. config.json +94 -0
  3. pytorch_model.bin +3 -0
  4. runs/Sep11_01-08-36_be577787e2f7/1694394527.997717/events.out.tfevents.1694394527.be577787e2f7.28.1 +3 -0
  5. runs/Sep11_01-08-36_be577787e2f7/1694394616.0987616/events.out.tfevents.1694394616.be577787e2f7.28.2 +3 -0
  6. runs/Sep11_01-08-36_be577787e2f7/1694394617.2544048/events.out.tfevents.1694394617.be577787e2f7.28.3 +3 -0
  7. runs/Sep11_01-08-36_be577787e2f7/events.out.tfevents.1694394527.be577787e2f7.28.0 +3 -0
  8. special_tokens_map.json +107 -0
  9. spiece.model +3 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +113 -0
  12. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-large",
3
+ "adapters": {
4
+ "adapters": {
5
+ "question_answering_union": "1f8ebc8c4a9631dd"
6
+ },
7
+ "config_map": {
8
+ "1f8ebc8c4a9631dd": {
9
+ "architecture": "union",
10
+ "configs": [
11
+ {
12
+ "alpha": 1,
13
+ "architecture": "lora",
14
+ "attn_matrices": [
15
+ "q",
16
+ "v"
17
+ ],
18
+ "composition_mode": "scale",
19
+ "dropout": 0.0,
20
+ "init_weights": "ia3",
21
+ "intermediate_lora": true,
22
+ "output_lora": false,
23
+ "r": 1,
24
+ "selfattn_lora": true,
25
+ "use_gating": false
26
+ },
27
+ {
28
+ "adapter_residual_before_ln": false,
29
+ "cross_adapter": false,
30
+ "factorized_phm_W": true,
31
+ "factorized_phm_rule": false,
32
+ "hypercomplex_nonlinearity": "glorot-uniform",
33
+ "init_weights": "bert",
34
+ "inv_adapter": null,
35
+ "inv_adapter_reduction_factor": null,
36
+ "is_parallel": false,
37
+ "learn_phm": true,
38
+ "leave_out": [],
39
+ "ln_after": false,
40
+ "ln_before": false,
41
+ "mh_adapter": true,
42
+ "non_linearity": "swish",
43
+ "original_ln_after": true,
44
+ "original_ln_before": false,
45
+ "output_adapter": true,
46
+ "phm_bias": true,
47
+ "phm_c_init": "normal",
48
+ "phm_dim": 4,
49
+ "phm_init_range": 0.0001,
50
+ "phm_layer": false,
51
+ "phm_rank": 1,
52
+ "reduction_factor": 8,
53
+ "residual_before_ln": true,
54
+ "scaling": 1.0,
55
+ "shared_W_phm": false,
56
+ "shared_phm_rule": true,
57
+ "use_gating": false
58
+ }
59
+ ]
60
+ }
61
+ },
62
+ "fusion_config_map": {},
63
+ "fusions": {}
64
+ },
65
+ "architectures": [
66
+ "T5ForConditionalGeneration"
67
+ ],
68
+ "d_ff": 2816,
69
+ "d_kv": 64,
70
+ "d_model": 1024,
71
+ "decoder_start_token_id": 0,
72
+ "dense_act_fn": "gelu_new",
73
+ "dropout_rate": 0.1,
74
+ "eos_token_id": 1,
75
+ "feed_forward_proj": "gated-gelu",
76
+ "initializer_factor": 1.0,
77
+ "is_encoder_decoder": true,
78
+ "is_gated_act": true,
79
+ "layer_norm_epsilon": 1e-06,
80
+ "model_type": "t5",
81
+ "n_positions": 512,
82
+ "num_decoder_layers": 24,
83
+ "num_heads": 16,
84
+ "num_layers": 24,
85
+ "output_past": true,
86
+ "pad_token_id": 0,
87
+ "relative_attention_max_distance": 128,
88
+ "relative_attention_num_buckets": 32,
89
+ "tie_word_embeddings": false,
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.26.1",
92
+ "use_cache": true,
93
+ "vocab_size": 32128
94
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04e642cdb74da44ef05d6f1926cdb7fac27a0dbb0426ef7ff2e68897b23fc03
3
+ size 3235245835
runs/Sep11_01-08-36_be577787e2f7/1694394527.997717/events.out.tfevents.1694394527.be577787e2f7.28.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056beb5af2a516d2d9d223372d8419f8043ba6682af9b4e179fcc547b9132e64
3
+ size 6034
runs/Sep11_01-08-36_be577787e2f7/1694394616.0987616/events.out.tfevents.1694394616.be577787e2f7.28.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f0c03fb4f604893e0795c0d20ba07243500a31bd7b97df42bfe3d921de2515
3
+ size 6034
runs/Sep11_01-08-36_be577787e2f7/1694394617.2544048/events.out.tfevents.1694394617.be577787e2f7.28.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcec9b649e535616dcef4868efb0d3e4f121060a06b60894612d93de349c990
3
+ size 6034
runs/Sep11_01-08-36_be577787e2f7/events.out.tfevents.1694394527.be577787e2f7.28.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41430f73ddf330074cde410fe73177eb8324dba0815370f36b84abe1dd435001
3
+ size 19947
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 512,
107
+ "name_or_path": "google/flan-t5-large",
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-large/snapshots/314bc112b191ec17b625ba81438dc73d6c23659d/special_tokens_map.json",
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c8f275dc4a958d31c54f781ea154b8a780e97a48e79972ca7c95c6b968d60f
3
+ size 3643