Hugging Face's logo

lingchensanwen
/
pred_disfluency_models

Model card Files Community
lingchensanwen commited on
Commit
c40bad3
•
1 Parent(s): c83f67d

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. T5-plain/config.json +61 -0
  2. T5-plain/generation_config.json +7 -0
  3. T5-plain/pytorch_model.bin +3 -0
  4. T5-plain/special_tokens_map.json +107 -0
  5. T5-plain/spiece.model +3 -0
  6. T5-plain/tokenizer_config.json +112 -0
  7. T5-plain/training_args.bin +3 -0
  8. T5-tuned/added_tokens.json +5 -0
  9. T5-tuned/config.json +61 -0
  10. T5-tuned/generation_config.json +7 -0
  11. T5-tuned/pytorch_model.bin +3 -0
  12. T5-tuned/special_tokens_map.json +107 -0
  13. T5-tuned/spiece.model +3 -0
  14. T5-tuned/t5_disfluency/bilingual/added_tokens.json +4 -0
  15. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/config.json +65 -0
  16. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/generation_config.json +7 -0
  17. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/optimizer.pt +3 -0
  18. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/pytorch_model.bin +3 -0
  19. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/rng_state.pth +3 -0
  20. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/scheduler.pt +3 -0
  21. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/trainer_state.json +76 -0
  22. T5-tuned/t5_disfluency/bilingual/checkpoint-1176/training_args.bin +3 -0
  23. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/config.json +65 -0
  24. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/generation_config.json +7 -0
  25. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/optimizer.pt +3 -0
  26. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/pytorch_model.bin +3 -0
  27. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/rng_state.pth +3 -0
  28. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/scheduler.pt +3 -0
  29. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/trainer_state.json +84 -0
  30. T5-tuned/t5_disfluency/bilingual/checkpoint-1372/training_args.bin +3 -0
  31. T5-tuned/t5_disfluency/bilingual/checkpoint-196/config.json +65 -0
  32. T5-tuned/t5_disfluency/bilingual/checkpoint-196/generation_config.json +7 -0
  33. T5-tuned/t5_disfluency/bilingual/checkpoint-196/optimizer.pt +3 -0
  34. T5-tuned/t5_disfluency/bilingual/checkpoint-196/pytorch_model.bin +3 -0
  35. T5-tuned/t5_disfluency/bilingual/checkpoint-196/rng_state.pth +3 -0
  36. T5-tuned/t5_disfluency/bilingual/checkpoint-196/scheduler.pt +3 -0
  37. T5-tuned/t5_disfluency/bilingual/checkpoint-196/trainer_state.json +24 -0
  38. T5-tuned/t5_disfluency/bilingual/checkpoint-196/training_args.bin +3 -0
  39. T5-tuned/t5_disfluency/bilingual/checkpoint-392/config.json +65 -0
  40. T5-tuned/t5_disfluency/bilingual/checkpoint-392/generation_config.json +7 -0
  41. T5-tuned/t5_disfluency/bilingual/checkpoint-392/optimizer.pt +3 -0
  42. T5-tuned/t5_disfluency/bilingual/checkpoint-392/pytorch_model.bin +3 -0
  43. T5-tuned/t5_disfluency/bilingual/checkpoint-392/rng_state.pth +3 -0
  44. T5-tuned/t5_disfluency/bilingual/checkpoint-392/scheduler.pt +3 -0
  45. T5-tuned/t5_disfluency/bilingual/checkpoint-392/trainer_state.json +32 -0
  46. T5-tuned/t5_disfluency/bilingual/checkpoint-392/training_args.bin +3 -0
  47. T5-tuned/t5_disfluency/bilingual/checkpoint-588/config.json +65 -0
  48. T5-tuned/t5_disfluency/bilingual/checkpoint-588/generation_config.json +7 -0
  49. T5-tuned/t5_disfluency/bilingual/checkpoint-588/optimizer.pt +3 -0
  50. T5-tuned/t5_disfluency/bilingual/checkpoint-588/pytorch_model.bin +3 -0
T5-plain/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
T5-plain/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.0"
7
+ }
T5-plain/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4688e0fc62bd3737379705ad6203fb52272ba6cada50b5e84a4234cd59a5e997
3
+ size 990408885
T5-plain/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
+ }
T5-plain/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
T5-plain/tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
T5-plain/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:374c1ba42db87e536606232ba9ae91f10837b8feb687f6c8f68fa5429588da2a
3
+ size 3643
T5-tuned/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "NSDISFL": 32101,
3
+ "SDISFL": 32100,
4
+ "WREP": 32102
5
+ }
T5-tuned/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32103
61
+ }
T5-tuned/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.0"
7
+ }
T5-tuned/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc87f45f35c19cd321f114622e9f5d7083d1eb255b67b040e0964b6eb9a867f
3
+ size 990255285
T5-tuned/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
+ }
T5-tuned/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
T5-tuned/t5_disfluency/bilingual/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 32101,
3
+ "[PAD]": 32100
4
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 32101,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 32101,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": true,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 32100,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "sep_token_id": 2,
30
+ "task_specific_params": {
31
+ "summarization": {
32
+ "early_stopping": true,
33
+ "length_penalty": 2.0,
34
+ "max_length": 200,
35
+ "min_length": 30,
36
+ "no_repeat_ngram_size": 3,
37
+ "num_beams": 4,
38
+ "prefix": "summarize: "
39
+ },
40
+ "translation_en_to_de": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to German: "
45
+ },
46
+ "translation_en_to_fr": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to French: "
51
+ },
52
+ "translation_en_to_ro": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to Romanian: "
57
+ }
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.28.1",
62
+ "unk_token_id": 32101,
63
+ "use_cache": true,
64
+ "vocab_size": 32102
65
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726461a7e97db1ab4cf4311ea0f7491d1057b26901749975629e4a2de64692e1
3
+ size 1980470661
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87999b4a045ab8b85d7f792c33a1387ecd47e3b262d919f9b5735245a6f13eb3
3
+ size 990249141
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96bfda3ef041e120b2955c583df23793e6e55f695344580d3329b28ca722818c
3
+ size 16619
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8843bbe0c122ccf3099feaa2e05b04af85e323cb8235c745a57f41192f16b33
3
+ size 627
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0001887563121272251,
3
+ "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/bilingual/checkpoint-980",
4
+ "epoch": 6.0,
5
+ "global_step": 1176,
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
+ "eval_loss": 0.014369768090546131,
13
+ "eval_runtime": 11.164,
14
+ "eval_samples_per_second": 26.783,
15
+ "eval_steps_per_second": 8.957,
16
+ "step": 196
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_loss": 0.0007745437906123698,
21
+ "eval_runtime": 11.1109,
22
+ "eval_samples_per_second": 26.91,
23
+ "eval_steps_per_second": 9.0,
24
+ "step": 392
25
+ },
26
+ {
27
+ "epoch": 2.55,
28
+ "learning_rate": 3.177842565597668e-05,
29
+ "loss": 2.0974,
30
+ "step": 500
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_loss": 0.00042322053923271596,
35
+ "eval_runtime": 11.0688,
36
+ "eval_samples_per_second": 27.013,
37
+ "eval_steps_per_second": 9.034,
38
+ "step": 588
39
+ },
40
+ {
41
+ "epoch": 4.0,
42
+ "eval_loss": 0.0002689457614906132,
43
+ "eval_runtime": 11.0824,
44
+ "eval_samples_per_second": 26.98,
45
+ "eval_steps_per_second": 9.023,
46
+ "step": 784
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "eval_loss": 0.0001887563121272251,
51
+ "eval_runtime": 11.0527,
52
+ "eval_samples_per_second": 27.052,
53
+ "eval_steps_per_second": 9.048,
54
+ "step": 980
55
+ },
56
+ {
57
+ "epoch": 5.1,
58
+ "learning_rate": 1.3556851311953352e-05,
59
+ "loss": 0.0035,
60
+ "step": 1000
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_loss": 0.00030883244471624494,
65
+ "eval_runtime": 11.217,
66
+ "eval_samples_per_second": 26.656,
67
+ "eval_steps_per_second": 8.915,
68
+ "step": 1176
69
+ }
70
+ ],
71
+ "max_steps": 1372,
72
+ "num_train_epochs": 7,
73
+ "total_flos": 1203695586902016.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1176/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060c60a9321fbecf3b13e95ae819722349dfa177ba07f8f2c86b536dd9051ed6
3
+ size 3643
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 32101,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 32101,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": true,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 32100,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "sep_token_id": 2,
30
+ "task_specific_params": {
31
+ "summarization": {
32
+ "early_stopping": true,
33
+ "length_penalty": 2.0,
34
+ "max_length": 200,
35
+ "min_length": 30,
36
+ "no_repeat_ngram_size": 3,
37
+ "num_beams": 4,
38
+ "prefix": "summarize: "
39
+ },
40
+ "translation_en_to_de": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to German: "
45
+ },
46
+ "translation_en_to_fr": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to French: "
51
+ },
52
+ "translation_en_to_ro": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to Romanian: "
57
+ }
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.28.1",
62
+ "unk_token_id": 32101,
63
+ "use_cache": true,
64
+ "vocab_size": 32102
65
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb505128b90cfd327179f21e02bfc85bfd6a29bc272a693600c263fcb2fbd043
3
+ size 1980470661
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3287f95848e15cff197abb1f37532ce498448a0522b3e57a33858659af339273
3
+ size 990249141
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2a6bd5f53271c8fb1b40c4e303bd3bffab556a822f7a3814580ea5d2840757
3
+ size 16619
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62746a3435667192ca1e878c6a63a417521ddcac6cf3ae60af53f10c8898b47a
3
+ size 627
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0001887563121272251,
3
+ "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/bilingual/checkpoint-980",
4
+ "epoch": 7.0,
5
+ "global_step": 1372,
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
+ "eval_loss": 0.014369768090546131,
13
+ "eval_runtime": 11.164,
14
+ "eval_samples_per_second": 26.783,
15
+ "eval_steps_per_second": 8.957,
16
+ "step": 196
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_loss": 0.0007745437906123698,
21
+ "eval_runtime": 11.1109,
22
+ "eval_samples_per_second": 26.91,
23
+ "eval_steps_per_second": 9.0,
24
+ "step": 392
25
+ },
26
+ {
27
+ "epoch": 2.55,
28
+ "learning_rate": 3.177842565597668e-05,
29
+ "loss": 2.0974,
30
+ "step": 500
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_loss": 0.00042322053923271596,
35
+ "eval_runtime": 11.0688,
36
+ "eval_samples_per_second": 27.013,
37
+ "eval_steps_per_second": 9.034,
38
+ "step": 588
39
+ },
40
+ {
41
+ "epoch": 4.0,
42
+ "eval_loss": 0.0002689457614906132,
43
+ "eval_runtime": 11.0824,
44
+ "eval_samples_per_second": 26.98,
45
+ "eval_steps_per_second": 9.023,
46
+ "step": 784
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "eval_loss": 0.0001887563121272251,
51
+ "eval_runtime": 11.0527,
52
+ "eval_samples_per_second": 27.052,
53
+ "eval_steps_per_second": 9.048,
54
+ "step": 980
55
+ },
56
+ {
57
+ "epoch": 5.1,
58
+ "learning_rate": 1.3556851311953352e-05,
59
+ "loss": 0.0035,
60
+ "step": 1000
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_loss": 0.00030883244471624494,
65
+ "eval_runtime": 11.217,
66
+ "eval_samples_per_second": 26.656,
67
+ "eval_steps_per_second": 8.915,
68
+ "step": 1176
69
+ },
70
+ {
71
+ "epoch": 7.0,
72
+ "eval_loss": 0.0003041265008505434,
73
+ "eval_runtime": 11.3384,
74
+ "eval_samples_per_second": 26.371,
75
+ "eval_steps_per_second": 8.82,
76
+ "step": 1372
77
+ }
78
+ ],
79
+ "max_steps": 1372,
80
+ "num_train_epochs": 7,
81
+ "total_flos": 1404311518052352.0,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-1372/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060c60a9321fbecf3b13e95ae819722349dfa177ba07f8f2c86b536dd9051ed6
3
+ size 3643
T5-tuned/t5_disfluency/bilingual/checkpoint-196/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 32101,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 32101,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": true,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 32100,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "sep_token_id": 2,
30
+ "task_specific_params": {
31
+ "summarization": {
32
+ "early_stopping": true,
33
+ "length_penalty": 2.0,
34
+ "max_length": 200,
35
+ "min_length": 30,
36
+ "no_repeat_ngram_size": 3,
37
+ "num_beams": 4,
38
+ "prefix": "summarize: "
39
+ },
40
+ "translation_en_to_de": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to German: "
45
+ },
46
+ "translation_en_to_fr": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to French: "
51
+ },
52
+ "translation_en_to_ro": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to Romanian: "
57
+ }
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.28.1",
62
+ "unk_token_id": 32101,
63
+ "use_cache": true,
64
+ "vocab_size": 32102
65
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-196/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-196/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402643c4bbbd8a9f4a34e67174142765f6d7684f60179605e094d19563558df0
3
+ size 1980470405
T5-tuned/t5_disfluency/bilingual/checkpoint-196/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0acf5e1995eedf692c83e977cebd3661902aa2b52d9cde3edd61f604d2459ee
3
+ size 990249141
T5-tuned/t5_disfluency/bilingual/checkpoint-196/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b32b849ba5319e3a18c71bfe63e468a70842470ca4db3925875f9515f99e1d
3
+ size 16619
T5-tuned/t5_disfluency/bilingual/checkpoint-196/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d84aa600ffdaab76dcaa4f04c2423422e5bb4db6ea4bafe9676bbd37d5504f
3
+ size 627
T5-tuned/t5_disfluency/bilingual/checkpoint-196/trainer_state.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.014369768090546131,
3
+ "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/bilingual/checkpoint-196",
4
+ "epoch": 1.0,
5
+ "global_step": 196,
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
+ "eval_loss": 0.014369768090546131,
13
+ "eval_runtime": 11.164,
14
+ "eval_samples_per_second": 26.783,
15
+ "eval_steps_per_second": 8.957,
16
+ "step": 196
17
+ }
18
+ ],
19
+ "max_steps": 1372,
20
+ "num_train_epochs": 7,
21
+ "total_flos": 200615931150336.0,
22
+ "trial_name": null,
23
+ "trial_params": null
24
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-196/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060c60a9321fbecf3b13e95ae819722349dfa177ba07f8f2c86b536dd9051ed6
3
+ size 3643
T5-tuned/t5_disfluency/bilingual/checkpoint-392/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 32101,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 32101,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": true,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 32100,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "sep_token_id": 2,
30
+ "task_specific_params": {
31
+ "summarization": {
32
+ "early_stopping": true,
33
+ "length_penalty": 2.0,
34
+ "max_length": 200,
35
+ "min_length": 30,
36
+ "no_repeat_ngram_size": 3,
37
+ "num_beams": 4,
38
+ "prefix": "summarize: "
39
+ },
40
+ "translation_en_to_de": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to German: "
45
+ },
46
+ "translation_en_to_fr": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to French: "
51
+ },
52
+ "translation_en_to_ro": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to Romanian: "
57
+ }
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.28.1",
62
+ "unk_token_id": 32101,
63
+ "use_cache": true,
64
+ "vocab_size": 32102
65
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-392/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-392/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd698c0ea3ef0e3095b63dc699acb92f64cedfe61fede9200fc77b1cab87b97
3
+ size 1980470661
T5-tuned/t5_disfluency/bilingual/checkpoint-392/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d97e27c34d95b30899235e84b2e0992c0d429adb4647d11508f2d306eb8103
3
+ size 990249141
T5-tuned/t5_disfluency/bilingual/checkpoint-392/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8e7ff0ff5dde94ee6fdc0390767abd3ca7d65568cc75651f67c28cac74402
3
+ size 16619
T5-tuned/t5_disfluency/bilingual/checkpoint-392/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb3c83959697bc41a29cd2974ece32077426f6a59e06fa1634d97637d2f6188
3
+ size 627
T5-tuned/t5_disfluency/bilingual/checkpoint-392/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0007745437906123698,
3
+ "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/bilingual/checkpoint-392",
4
+ "epoch": 2.0,
5
+ "global_step": 392,
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
+ "eval_loss": 0.014369768090546131,
13
+ "eval_runtime": 11.164,
14
+ "eval_samples_per_second": 26.783,
15
+ "eval_steps_per_second": 8.957,
16
+ "step": 196
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_loss": 0.0007745437906123698,
21
+ "eval_runtime": 11.1109,
22
+ "eval_samples_per_second": 26.91,
23
+ "eval_steps_per_second": 9.0,
24
+ "step": 392
25
+ }
26
+ ],
27
+ "max_steps": 1372,
28
+ "num_train_epochs": 7,
29
+ "total_flos": 401231862300672.0,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-392/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060c60a9321fbecf3b13e95ae819722349dfa177ba07f8f2c86b536dd9051ed6
3
+ size 3643
T5-tuned/t5_disfluency/bilingual/checkpoint-588/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 32101,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 32101,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": true,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 32100,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "sep_token_id": 2,
30
+ "task_specific_params": {
31
+ "summarization": {
32
+ "early_stopping": true,
33
+ "length_penalty": 2.0,
34
+ "max_length": 200,
35
+ "min_length": 30,
36
+ "no_repeat_ngram_size": 3,
37
+ "num_beams": 4,
38
+ "prefix": "summarize: "
39
+ },
40
+ "translation_en_to_de": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to German: "
45
+ },
46
+ "translation_en_to_fr": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to French: "
51
+ },
52
+ "translation_en_to_ro": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to Romanian: "
57
+ }
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.28.1",
62
+ "unk_token_id": 32101,
63
+ "use_cache": true,
64
+ "vocab_size": 32102
65
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-588/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
T5-tuned/t5_disfluency/bilingual/checkpoint-588/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9b42f52580dd485ff50264d47c7f903a1a09e802fcc79756bc2077d711d717
3
+ size 1980470661
T5-tuned/t5_disfluency/bilingual/checkpoint-588/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c4325ee66fa7b3bf20fd0d15e080b1d0508bae3f965d7d4cb77153838faa89
3
+ size 990249141