Hugging Face's logo

yfqiu-nlp
/
mfact-weighted-loss

Model card Files Community
Yifu Qiu commited on
Commit
601c5eb
•
1 Parent(s): 0fa32f1

mfact-weighted-loss-v1

Browse files
Files changed (15) hide show
  1. .gitattributes +2 -0
  2. mlm/adapter_config.json +41 -0
  3. mlm/head_config.json +15 -0
  4. mlm/pytorch_adapter.bin +3 -0
  5. mlm/pytorch_model_head.bin +3 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +63 -0
  8. summarization/adapter_config.json +41 -0
  9. summarization/head_config.json +15 -0
  10. summarization/pytorch_adapter.bin +3 -0
  11. summarization/pytorch_model_head.bin +3 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +77 -0
  14. trainer_state.json +85 -0
  15. training_args.bin +3 -0
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ mlm filter=lfs diff=lfs merge=lfs -text
36
+ summarization filter=lfs diff=lfs merge=lfs -text
mlm/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": "nice",
10
+ "inv_adapter_reduction_factor": 2,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": false,
17
+ "non_linearity": "relu",
18
+ "original_ln_after": true,
19
+ "original_ln_before": true,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 16,
28
+ "residual_before_ln": true,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "config_id": "9ed5b5a29de19b71",
35
+ "hidden_size": 1024,
36
+ "model_class": "MBartForConditionalGeneration",
37
+ "model_name": "facebook/mbart-large-50",
38
+ "model_type": "mbart",
39
+ "name": "wikitext",
40
+ "version": "3.2.0a0"
41
+ }
mlm/head_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 1024,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1,
7
+ "LABEL_2": 2
8
+ },
9
+ "model_class": "MBartForConditionalGeneration",
10
+ "model_name": "facebook/mbart-large-50",
11
+ "model_type": "mbart",
12
+ "name": null,
13
+ "num_labels": 3,
14
+ "version": "3.2.0a0"
15
+ }
mlm/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d717daeb5c68c48a5a7e57ff2712f3148b119093ba45e98ed10af4c2899519
3
+ size 14830726
mlm/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafff387342a8934a12e1a17887f892eabbca0d22db3ec8e22a675ecd6d8eb54
3
+ size 1025222455
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
summarization/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": null,
10
+ "inv_adapter_reduction_factor": null,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": false,
17
+ "non_linearity": "relu",
18
+ "original_ln_after": true,
19
+ "original_ln_before": true,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 16,
28
+ "residual_before_ln": true,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "config_id": "9076f36a74755ac4",
35
+ "hidden_size": 1024,
36
+ "model_class": "MBartForConditionalGeneration",
37
+ "model_name": "facebook/mbart-large-50",
38
+ "model_type": "mbart",
39
+ "name": "summarization",
40
+ "version": "3.2.0a0"
41
+ }
summarization/head_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 1024,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1,
7
+ "LABEL_2": 2
8
+ },
9
+ "model_class": "MBartForConditionalGeneration",
10
+ "model_name": "facebook/mbart-large-50",
11
+ "model_type": "mbart",
12
+ "name": null,
13
+ "num_labels": 3,
14
+ "version": "3.2.0a0"
15
+ }
summarization/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb316c711cc7bc1807dcf29dc1660c95d7f458f7cbb711b72a4b7d6934f549d0
3
+ size 12723881
summarization/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafff387342a8934a12e1a17887f892eabbca0d22db3ec8e22a675ecd6d8eb54
3
+ size 1025222455
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "__type": "AddedToken",
61
+ "content": "<mask>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "model_max_length": 1024,
68
+ "name_or_path": "facebook/mbart-large-50",
69
+ "pad_token": "<pad>",
70
+ "sep_token": "</s>",
71
+ "sp_model_kwargs": {},
72
+ "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
73
+ "src_lang": null,
74
+ "tgt_lang": null,
75
+ "tokenizer_class": "MBart50Tokenizer",
76
+ "unk_token": "<unk>"
77
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.999955993017558,
5
+ "global_step": 85210,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9.054069295242593e-05,
13
+ "loss": 1.6188,
14
+ "step": 8521
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 8.049172706882305e-05,
19
+ "loss": 1.5369,
20
+ "step": 17042
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 7.044276118522018e-05,
25
+ "loss": 1.5126,
26
+ "step": 25563
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 6.039379530161728e-05,
31
+ "loss": 1.496,
32
+ "step": 34084
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 5.0344829418014404e-05,
37
+ "loss": 1.4796,
38
+ "step": 42605
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 4.029586353441152e-05,
43
+ "loss": 1.4672,
44
+ "step": 51126
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 3.0246897650808646e-05,
49
+ "loss": 1.4581,
50
+ "step": 59647
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 2.0197931767205764e-05,
55
+ "loss": 1.451,
56
+ "step": 68168
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 1.0148965883602883e-05,
61
+ "loss": 1.4451,
62
+ "step": 76689
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 9.999999999999998e-08,
67
+ "loss": 1.4408,
68
+ "step": 85210
69
+ },
70
+ {
71
+ "epoch": 10.0,
72
+ "step": 85210,
73
+ "total_flos": 5.230860312759798e+18,
74
+ "train_loss": 1.4906291372968254,
75
+ "train_runtime": 109697.9633,
76
+ "train_samples_per_second": 24.858,
77
+ "train_steps_per_second": 0.777
78
+ }
79
+ ],
80
+ "max_steps": 85210,
81
+ "num_train_epochs": 10,
82
+ "total_flos": 5.230860312759798e+18,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a17ea62302969f1db7c384ce4f61154bd771bfc299e169c27ef314ed932d40c
3
+ size 3567