zakerytclarke commited on
Commit
4ff0462
·
verified ·
1 Parent(s): 1c1f2ad

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. added_tokens.json +102 -0
  2. checkpoint-11130/added_tokens.json +102 -0
  3. checkpoint-11130/config.json +62 -0
  4. checkpoint-11130/generation_config.json +7 -0
  5. checkpoint-11130/model.safetensors +3 -0
  6. checkpoint-11130/optimizer.pt +3 -0
  7. checkpoint-11130/rng_state.pth +3 -0
  8. checkpoint-11130/scheduler.pt +3 -0
  9. checkpoint-11130/special_tokens_map.json +125 -0
  10. checkpoint-11130/spiece.model +3 -0
  11. checkpoint-11130/tokenizer_config.json +941 -0
  12. checkpoint-11130/trainer_state.json +1545 -0
  13. checkpoint-11130/training_args.bin +3 -0
  14. checkpoint-11395/added_tokens.json +102 -0
  15. checkpoint-11395/config.json +62 -0
  16. checkpoint-11395/generation_config.json +7 -0
  17. checkpoint-11395/model.safetensors +3 -0
  18. checkpoint-11395/optimizer.pt +3 -0
  19. checkpoint-11395/rng_state.pth +3 -0
  20. checkpoint-11395/scheduler.pt +3 -0
  21. checkpoint-11395/special_tokens_map.json +125 -0
  22. checkpoint-11395/spiece.model +3 -0
  23. checkpoint-11395/tokenizer_config.json +941 -0
  24. checkpoint-11395/trainer_state.json +1581 -0
  25. checkpoint-11395/training_args.bin +3 -0
  26. checkpoint-11660/added_tokens.json +102 -0
  27. checkpoint-11660/config.json +62 -0
  28. checkpoint-11660/generation_config.json +7 -0
  29. checkpoint-11660/model.safetensors +3 -0
  30. checkpoint-11660/optimizer.pt +3 -0
  31. checkpoint-11660/rng_state.pth +3 -0
  32. checkpoint-11660/scheduler.pt +3 -0
  33. checkpoint-11660/special_tokens_map.json +125 -0
  34. checkpoint-11660/spiece.model +3 -0
  35. checkpoint-11660/tokenizer_config.json +941 -0
  36. checkpoint-11660/trainer_state.json +1617 -0
  37. checkpoint-11660/training_args.bin +3 -0
  38. checkpoint-11925/added_tokens.json +102 -0
  39. checkpoint-11925/config.json +62 -0
  40. checkpoint-11925/generation_config.json +7 -0
  41. checkpoint-11925/model.safetensors +3 -0
  42. checkpoint-11925/optimizer.pt +3 -0
  43. checkpoint-11925/rng_state.pth +3 -0
  44. checkpoint-11925/scheduler.pt +3 -0
  45. checkpoint-11925/special_tokens_map.json +125 -0
  46. checkpoint-11925/spiece.model +3 -0
  47. checkpoint-11925/tokenizer_config.json +941 -0
  48. checkpoint-11925/trainer_state.json +1653 -0
  49. checkpoint-11925/training_args.bin +3 -0
  50. checkpoint-12190/added_tokens.json +102 -0
added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
checkpoint-11130/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
checkpoint-11130/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
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": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.48.3",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
checkpoint-11130/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": "4.48.3"
7
+ }
checkpoint-11130/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d167fc8935b94437d50550dec0fe523e22dd5f724396583719b9302c1658db
3
+ size 990345064
checkpoint-11130/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8762dacf824ae36e0cecbaec30bc74357a0b90050aba9690e2ac79fbfd749506
3
+ size 1980860410
checkpoint-11130/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48ba5f5287f7ccaf7775383a2d6a4d755536de68246a00a73410122ca794647
3
+ size 14244
checkpoint-11130/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20de03586951c9d1cb5d51e68081d7add5729d0477364cb4c18ead10caada79f
3
+ size 1064
checkpoint-11130/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoint-11130/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-11130/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 512,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
checkpoint-11130/trainer_state.json ADDED
@@ -0,0 +1,1545 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06431461870670319,
3
+ "best_model_checkpoint": "./teapotllm/checkpoint-1855",
4
+ "epoch": 42.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "em_boolean": 0.11764705882352941,
13
+ "em_extraction": 0.06666666666666667,
14
+ "em_qa": 0.0,
15
+ "em_summarization": 0.0,
16
+ "em_unanswerable": 0.0,
17
+ "epoch": 1.0,
18
+ "mean_em": 0.0375,
19
+ "mean_similarity": 0.3622433557640761,
20
+ "mean_word_count_diff": 17.7125,
21
+ "similarity_boolean": 0.18269754047779477,
22
+ "similarity_extraction": 0.2946929598848025,
23
+ "similarity_qa": 0.43210459053516387,
24
+ "similarity_summarization": 0.6143242551220788,
25
+ "similarity_unanswerable": 0.26092069496711096,
26
+ "word_count_diff_boolean": 9.0,
27
+ "word_count_diff_extraction": 7.666666666666667,
28
+ "word_count_diff_qa": 6.933333333333334,
29
+ "word_count_diff_summarization": 53.111111111111114,
30
+ "word_count_diff_unanswerable": 5.933333333333334
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 101.51641082763672,
35
+ "learning_rate": 1.59e-05,
36
+ "loss": 40.3479,
37
+ "step": 265
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 19.639965057373047,
42
+ "eval_runtime": 1.7948,
43
+ "eval_samples_per_second": 44.573,
44
+ "eval_steps_per_second": 5.572,
45
+ "step": 265
46
+ },
47
+ {
48
+ "em_boolean": 0.058823529411764705,
49
+ "em_extraction": 0.0,
50
+ "em_qa": 0.0,
51
+ "em_summarization": 0.0,
52
+ "em_unanswerable": 0.0,
53
+ "epoch": 2.0,
54
+ "mean_em": 0.0125,
55
+ "mean_similarity": 0.37655651543755086,
56
+ "mean_word_count_diff": 17.1625,
57
+ "similarity_boolean": 0.10583376435234267,
58
+ "similarity_extraction": 0.21972424462437629,
59
+ "similarity_qa": 0.5285325924555461,
60
+ "similarity_summarization": 0.6654400361908807,
61
+ "similarity_unanswerable": 0.34157160222530364,
62
+ "word_count_diff_boolean": 10.176470588235293,
63
+ "word_count_diff_extraction": 6.133333333333334,
64
+ "word_count_diff_qa": 5.866666666666666,
65
+ "word_count_diff_summarization": 52.166666666666664,
66
+ "word_count_diff_unanswerable": 5.4
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.2927296459674835,
71
+ "learning_rate": 2.9999590191302685e-05,
72
+ "loss": 1.8688,
73
+ "step": 530
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.08876434713602066,
78
+ "eval_runtime": 1.7881,
79
+ "eval_samples_per_second": 44.74,
80
+ "eval_steps_per_second": 5.593,
81
+ "step": 530
82
+ },
83
+ {
84
+ "em_boolean": 0.29411764705882354,
85
+ "em_extraction": 0.13333333333333333,
86
+ "em_qa": 0.06666666666666667,
87
+ "em_summarization": 0.0,
88
+ "em_unanswerable": 0.0,
89
+ "epoch": 3.0,
90
+ "mean_em": 0.1,
91
+ "mean_similarity": 0.468679612770211,
92
+ "mean_word_count_diff": 16.8875,
93
+ "similarity_boolean": 0.36136592250755606,
94
+ "similarity_extraction": 0.3513699695467949,
95
+ "similarity_qa": 0.5638724292318026,
96
+ "similarity_summarization": 0.661304693048199,
97
+ "similarity_unanswerable": 0.3812685254961252,
98
+ "word_count_diff_boolean": 5.411764705882353,
99
+ "word_count_diff_extraction": 8.066666666666666,
100
+ "word_count_diff_qa": 5.6,
101
+ "word_count_diff_summarization": 53.333333333333336,
102
+ "word_count_diff_unanswerable": 6.266666666666667
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "grad_norm": 0.2717432379722595,
107
+ "learning_rate": 2.9960391039419217e-05,
108
+ "loss": 0.0745,
109
+ "step": 795
110
+ },
111
+ {
112
+ "epoch": 3.0,
113
+ "eval_loss": 0.07186319679021835,
114
+ "eval_runtime": 1.7817,
115
+ "eval_samples_per_second": 44.901,
116
+ "eval_steps_per_second": 5.613,
117
+ "step": 795
118
+ },
119
+ {
120
+ "em_boolean": 0.5294117647058824,
121
+ "em_extraction": 0.0,
122
+ "em_qa": 0.0,
123
+ "em_summarization": 0.0,
124
+ "em_unanswerable": 0.0,
125
+ "epoch": 4.0,
126
+ "mean_em": 0.1125,
127
+ "mean_similarity": 0.5406636619823985,
128
+ "mean_word_count_diff": 16.4,
129
+ "similarity_boolean": 0.5694808649337467,
130
+ "similarity_extraction": 0.2759806969513496,
131
+ "similarity_qa": 0.5888164043426514,
132
+ "similarity_summarization": 0.6777413653002845,
133
+ "similarity_unanswerable": 0.5600411439935367,
134
+ "word_count_diff_boolean": 3.411764705882353,
135
+ "word_count_diff_extraction": 9.133333333333333,
136
+ "word_count_diff_qa": 5.733333333333333,
137
+ "word_count_diff_summarization": 52.611111111111114,
138
+ "word_count_diff_unanswerable": 5.6
139
+ },
140
+ {
141
+ "epoch": 4.0,
142
+ "grad_norm": 0.33120226860046387,
143
+ "learning_rate": 2.985743020616636e-05,
144
+ "loss": 0.0583,
145
+ "step": 1060
146
+ },
147
+ {
148
+ "epoch": 4.0,
149
+ "eval_loss": 0.06767071783542633,
150
+ "eval_runtime": 1.8031,
151
+ "eval_samples_per_second": 44.368,
152
+ "eval_steps_per_second": 5.546,
153
+ "step": 1060
154
+ },
155
+ {
156
+ "em_boolean": 0.35294117647058826,
157
+ "em_extraction": 0.06666666666666667,
158
+ "em_qa": 0.06666666666666667,
159
+ "em_summarization": 0.0,
160
+ "em_unanswerable": 0.0,
161
+ "epoch": 5.0,
162
+ "mean_em": 0.1,
163
+ "mean_similarity": 0.5391882328083739,
164
+ "mean_word_count_diff": 16.5375,
165
+ "similarity_boolean": 0.4291324294446146,
166
+ "similarity_extraction": 0.3934509038925171,
167
+ "similarity_qa": 0.5968125452597935,
168
+ "similarity_summarization": 0.6669783542553583,
169
+ "similarity_unanswerable": 0.5986830140153567,
170
+ "word_count_diff_boolean": 5.9411764705882355,
171
+ "word_count_diff_extraction": 5.866666666666666,
172
+ "word_count_diff_qa": 5.4,
173
+ "word_count_diff_summarization": 53.77777777777778,
174
+ "word_count_diff_unanswerable": 5.666666666666667
175
+ },
176
+ {
177
+ "epoch": 5.0,
178
+ "grad_norm": 0.05014026165008545,
179
+ "learning_rate": 2.969114651402049e-05,
180
+ "loss": 0.0512,
181
+ "step": 1325
182
+ },
183
+ {
184
+ "epoch": 5.0,
185
+ "eval_loss": 0.06544757634401321,
186
+ "eval_runtime": 1.797,
187
+ "eval_samples_per_second": 44.518,
188
+ "eval_steps_per_second": 5.565,
189
+ "step": 1325
190
+ },
191
+ {
192
+ "em_boolean": 0.35294117647058826,
193
+ "em_extraction": 0.13333333333333333,
194
+ "em_qa": 0.0,
195
+ "em_summarization": 0.0,
196
+ "em_unanswerable": 0.0,
197
+ "epoch": 6.0,
198
+ "mean_em": 0.1,
199
+ "mean_similarity": 0.5817075100494549,
200
+ "mean_word_count_diff": 16.1375,
201
+ "similarity_boolean": 0.3759182594059145,
202
+ "similarity_extraction": 0.5534958879152934,
203
+ "similarity_qa": 0.6812621881564458,
204
+ "similarity_summarization": 0.661298368126154,
205
+ "similarity_unanswerable": 0.648083241780599,
206
+ "word_count_diff_boolean": 6.294117647058823,
207
+ "word_count_diff_extraction": 4.466666666666667,
208
+ "word_count_diff_qa": 5.666666666666667,
209
+ "word_count_diff_summarization": 52.55555555555556,
210
+ "word_count_diff_unanswerable": 5.733333333333333
211
+ },
212
+ {
213
+ "epoch": 6.0,
214
+ "grad_norm": 0.37450432777404785,
215
+ "learning_rate": 2.9462248669576738e-05,
216
+ "loss": 0.0466,
217
+ "step": 1590
218
+ },
219
+ {
220
+ "epoch": 6.0,
221
+ "eval_loss": 0.0656035840511322,
222
+ "eval_runtime": 1.8115,
223
+ "eval_samples_per_second": 44.161,
224
+ "eval_steps_per_second": 5.52,
225
+ "step": 1590
226
+ },
227
+ {
228
+ "em_boolean": 0.29411764705882354,
229
+ "em_extraction": 0.06666666666666667,
230
+ "em_qa": 0.06666666666666667,
231
+ "em_summarization": 0.0,
232
+ "em_unanswerable": 0.0,
233
+ "epoch": 7.0,
234
+ "mean_em": 0.0875,
235
+ "mean_similarity": 0.584748298721388,
236
+ "mean_word_count_diff": 16.4875,
237
+ "similarity_boolean": 0.3921016369234113,
238
+ "similarity_extraction": 0.4258095269401868,
239
+ "similarity_qa": 0.8010195712248485,
240
+ "similarity_summarization": 0.7269510593679216,
241
+ "similarity_unanswerable": 0.5751053685943286,
242
+ "word_count_diff_boolean": 6.529411764705882,
243
+ "word_count_diff_extraction": 7.4,
244
+ "word_count_diff_qa": 4.266666666666667,
245
+ "word_count_diff_summarization": 51.5,
246
+ "word_count_diff_unanswerable": 7.066666666666666
247
+ },
248
+ {
249
+ "epoch": 7.0,
250
+ "grad_norm": 0.2656797170639038,
251
+ "learning_rate": 2.9171712243018076e-05,
252
+ "loss": 0.043,
253
+ "step": 1855
254
+ },
255
+ {
256
+ "epoch": 7.0,
257
+ "eval_loss": 0.06431461870670319,
258
+ "eval_runtime": 1.779,
259
+ "eval_samples_per_second": 44.968,
260
+ "eval_steps_per_second": 5.621,
261
+ "step": 1855
262
+ },
263
+ {
264
+ "em_boolean": 0.23529411764705882,
265
+ "em_extraction": 0.3333333333333333,
266
+ "em_qa": 0.13333333333333333,
267
+ "em_summarization": 0.0,
268
+ "em_unanswerable": 0.0,
269
+ "epoch": 8.0,
270
+ "mean_em": 0.1375,
271
+ "mean_similarity": 0.5707565736840479,
272
+ "mean_word_count_diff": 15.9125,
273
+ "similarity_boolean": 0.3595361856962828,
274
+ "similarity_extraction": 0.6590617413322131,
275
+ "similarity_qa": 0.6671084851026535,
276
+ "similarity_summarization": 0.672764014866617,
277
+ "similarity_unanswerable": 0.503073671584328,
278
+ "word_count_diff_boolean": 6.705882352941177,
279
+ "word_count_diff_extraction": 4.133333333333334,
280
+ "word_count_diff_qa": 4.0,
281
+ "word_count_diff_summarization": 51.833333333333336,
282
+ "word_count_diff_unanswerable": 6.933333333333334
283
+ },
284
+ {
285
+ "epoch": 8.0,
286
+ "grad_norm": 0.1501343548297882,
287
+ "learning_rate": 2.882077551020291e-05,
288
+ "loss": 0.0393,
289
+ "step": 2120
290
+ },
291
+ {
292
+ "epoch": 8.0,
293
+ "eval_loss": 0.064610555768013,
294
+ "eval_runtime": 1.7854,
295
+ "eval_samples_per_second": 44.809,
296
+ "eval_steps_per_second": 5.601,
297
+ "step": 2120
298
+ },
299
+ {
300
+ "em_boolean": 0.29411764705882354,
301
+ "em_extraction": 0.13333333333333333,
302
+ "em_qa": 0.0,
303
+ "em_summarization": 0.0,
304
+ "em_unanswerable": 0.0,
305
+ "epoch": 9.0,
306
+ "mean_em": 0.0875,
307
+ "mean_similarity": 0.5716628619702533,
308
+ "mean_word_count_diff": 16.075,
309
+ "similarity_boolean": 0.46071117371320724,
310
+ "similarity_extraction": 0.5175981452067693,
311
+ "similarity_qa": 0.6631501737982035,
312
+ "similarity_summarization": 0.6426751317663325,
313
+ "similarity_unanswerable": 0.5747707898418108,
314
+ "word_count_diff_boolean": 5.235294117647059,
315
+ "word_count_diff_extraction": 7.333333333333333,
316
+ "word_count_diff_qa": 5.6,
317
+ "word_count_diff_summarization": 52.22222222222222,
318
+ "word_count_diff_unanswerable": 4.2
319
+ },
320
+ {
321
+ "epoch": 9.0,
322
+ "grad_norm": 0.23849624395370483,
323
+ "learning_rate": 2.8410934175092426e-05,
324
+ "loss": 0.0363,
325
+ "step": 2385
326
+ },
327
+ {
328
+ "epoch": 9.0,
329
+ "eval_loss": 0.06528123468160629,
330
+ "eval_runtime": 1.7964,
331
+ "eval_samples_per_second": 44.533,
332
+ "eval_steps_per_second": 5.567,
333
+ "step": 2385
334
+ },
335
+ {
336
+ "em_boolean": 0.4117647058823529,
337
+ "em_extraction": 0.13333333333333333,
338
+ "em_qa": 0.06666666666666667,
339
+ "em_summarization": 0.0,
340
+ "em_unanswerable": 0.0,
341
+ "epoch": 10.0,
342
+ "mean_em": 0.125,
343
+ "mean_similarity": 0.5984957347856834,
344
+ "mean_word_count_diff": 16.2375,
345
+ "similarity_boolean": 0.4425226738128592,
346
+ "similarity_extraction": 0.5075533439715704,
347
+ "similarity_qa": 0.6813998910288016,
348
+ "similarity_summarization": 0.6938931312825944,
349
+ "similarity_unanswerable": 0.6688265626629194,
350
+ "word_count_diff_boolean": 5.352941176470588,
351
+ "word_count_diff_extraction": 6.466666666666667,
352
+ "word_count_diff_qa": 6.2,
353
+ "word_count_diff_summarization": 52.166666666666664,
354
+ "word_count_diff_unanswerable": 5.266666666666667
355
+ },
356
+ {
357
+ "epoch": 10.0,
358
+ "grad_norm": 0.2859129309654236,
359
+ "learning_rate": 2.7943934995010845e-05,
360
+ "loss": 0.0338,
361
+ "step": 2650
362
+ },
363
+ {
364
+ "epoch": 10.0,
365
+ "eval_loss": 0.06541204452514648,
366
+ "eval_runtime": 1.7939,
367
+ "eval_samples_per_second": 44.595,
368
+ "eval_steps_per_second": 5.574,
369
+ "step": 2650
370
+ },
371
+ {
372
+ "em_boolean": 0.35294117647058826,
373
+ "em_extraction": 0.2,
374
+ "em_qa": 0.06666666666666667,
375
+ "em_summarization": 0.0,
376
+ "em_unanswerable": 0.0,
377
+ "epoch": 11.0,
378
+ "mean_em": 0.125,
379
+ "mean_similarity": 0.584741565072909,
380
+ "mean_word_count_diff": 15.85,
381
+ "similarity_boolean": 0.41579638640670213,
382
+ "similarity_extraction": 0.575649573157231,
383
+ "similarity_qa": 0.68668532371521,
384
+ "similarity_summarization": 0.7162102411190668,
385
+ "similarity_unanswerable": 0.5255985895792643,
386
+ "word_count_diff_boolean": 5.0,
387
+ "word_count_diff_extraction": 4.333333333333333,
388
+ "word_count_diff_qa": 5.4,
389
+ "word_count_diff_summarization": 51.72222222222222,
390
+ "word_count_diff_unanswerable": 7.066666666666666
391
+ },
392
+ {
393
+ "epoch": 11.0,
394
+ "grad_norm": 0.19708961248397827,
395
+ "learning_rate": 2.7421768335907942e-05,
396
+ "loss": 0.0314,
397
+ "step": 2915
398
+ },
399
+ {
400
+ "epoch": 11.0,
401
+ "eval_loss": 0.06535650044679642,
402
+ "eval_runtime": 1.7968,
403
+ "eval_samples_per_second": 44.525,
404
+ "eval_steps_per_second": 5.566,
405
+ "step": 2915
406
+ },
407
+ {
408
+ "em_boolean": 0.4117647058823529,
409
+ "em_extraction": 0.13333333333333333,
410
+ "em_qa": 0.06666666666666667,
411
+ "em_summarization": 0.0,
412
+ "em_unanswerable": 0.0,
413
+ "epoch": 12.0,
414
+ "mean_em": 0.125,
415
+ "mean_similarity": 0.5985993921523913,
416
+ "mean_word_count_diff": 15.65,
417
+ "similarity_boolean": 0.49136487109696164,
418
+ "similarity_extraction": 0.4834645986557007,
419
+ "similarity_qa": 0.7439890225728353,
420
+ "similarity_summarization": 0.7199151118596395,
421
+ "similarity_unanswerable": 0.5442981487760942,
422
+ "word_count_diff_boolean": 5.294117647058823,
423
+ "word_count_diff_extraction": 6.466666666666667,
424
+ "word_count_diff_qa": 5.0,
425
+ "word_count_diff_summarization": 51.333333333333336,
426
+ "word_count_diff_unanswerable": 4.4
427
+ },
428
+ {
429
+ "epoch": 12.0,
430
+ "grad_norm": 0.32636699080467224,
431
+ "learning_rate": 2.6846659689353532e-05,
432
+ "loss": 0.0291,
433
+ "step": 3180
434
+ },
435
+ {
436
+ "epoch": 12.0,
437
+ "eval_loss": 0.06654994189739227,
438
+ "eval_runtime": 1.7794,
439
+ "eval_samples_per_second": 44.96,
440
+ "eval_steps_per_second": 5.62,
441
+ "step": 3180
442
+ },
443
+ {
444
+ "em_boolean": 0.29411764705882354,
445
+ "em_extraction": 0.2,
446
+ "em_qa": 0.13333333333333333,
447
+ "em_summarization": 0.0,
448
+ "em_unanswerable": 0.0,
449
+ "epoch": 13.0,
450
+ "mean_em": 0.125,
451
+ "mean_similarity": 0.5608657638425939,
452
+ "mean_word_count_diff": 15.4875,
453
+ "similarity_boolean": 0.3726646105265793,
454
+ "similarity_extraction": 0.4880456611514091,
455
+ "similarity_qa": 0.6968116387724876,
456
+ "similarity_summarization": 0.7003769092261791,
457
+ "similarity_unanswerable": 0.5436212575683991,
458
+ "word_count_diff_boolean": 6.470588235294118,
459
+ "word_count_diff_extraction": 4.0,
460
+ "word_count_diff_qa": 4.266666666666667,
461
+ "word_count_diff_summarization": 50.22222222222222,
462
+ "word_count_diff_unanswerable": 6.733333333333333
463
+ },
464
+ {
465
+ "epoch": 13.0,
466
+ "grad_norm": 0.09956305474042892,
467
+ "learning_rate": 2.622106018741882e-05,
468
+ "loss": 0.0268,
469
+ "step": 3445
470
+ },
471
+ {
472
+ "epoch": 13.0,
473
+ "eval_loss": 0.06867102533578873,
474
+ "eval_runtime": 1.7923,
475
+ "eval_samples_per_second": 44.635,
476
+ "eval_steps_per_second": 5.579,
477
+ "step": 3445
478
+ },
479
+ {
480
+ "em_boolean": 0.4117647058823529,
481
+ "em_extraction": 0.13333333333333333,
482
+ "em_qa": 0.06666666666666667,
483
+ "em_summarization": 0.0,
484
+ "em_unanswerable": 0.0,
485
+ "epoch": 14.0,
486
+ "mean_em": 0.125,
487
+ "mean_similarity": 0.6118219185853377,
488
+ "mean_word_count_diff": 15.1,
489
+ "similarity_boolean": 0.5559550164376988,
490
+ "similarity_extraction": 0.4480490814894438,
491
+ "similarity_qa": 0.8226341267426809,
492
+ "similarity_summarization": 0.7094271017445458,
493
+ "similarity_unanswerable": 0.5109721501668294,
494
+ "word_count_diff_boolean": 3.235294117647059,
495
+ "word_count_diff_extraction": 5.333333333333333,
496
+ "word_count_diff_qa": 4.066666666666666,
497
+ "word_count_diff_summarization": 51.333333333333336,
498
+ "word_count_diff_unanswerable": 5.866666666666666
499
+ },
500
+ {
501
+ "epoch": 14.0,
502
+ "grad_norm": 0.2182687222957611,
503
+ "learning_rate": 2.554763615587042e-05,
504
+ "loss": 0.0254,
505
+ "step": 3710
506
+ },
507
+ {
508
+ "epoch": 14.0,
509
+ "eval_loss": 0.06904994696378708,
510
+ "eval_runtime": 1.7971,
511
+ "eval_samples_per_second": 44.517,
512
+ "eval_steps_per_second": 5.565,
513
+ "step": 3710
514
+ },
515
+ {
516
+ "em_boolean": 0.17647058823529413,
517
+ "em_extraction": 0.13333333333333333,
518
+ "em_qa": 0.13333333333333333,
519
+ "em_summarization": 0.0,
520
+ "em_unanswerable": 0.0,
521
+ "epoch": 15.0,
522
+ "mean_em": 0.0875,
523
+ "mean_similarity": 0.5906956384656951,
524
+ "mean_word_count_diff": 15.8,
525
+ "similarity_boolean": 0.30824649366824064,
526
+ "similarity_extraction": 0.5498731901248296,
527
+ "similarity_qa": 0.7911941662430764,
528
+ "similarity_summarization": 0.7216936614778307,
529
+ "similarity_unanswerable": 0.5939309621850649,
530
+ "word_count_diff_boolean": 5.294117647058823,
531
+ "word_count_diff_extraction": 5.533333333333333,
532
+ "word_count_diff_qa": 4.933333333333334,
533
+ "word_count_diff_summarization": 50.833333333333336,
534
+ "word_count_diff_unanswerable": 6.8
535
+ },
536
+ {
537
+ "epoch": 15.0,
538
+ "grad_norm": 0.278495728969574,
539
+ "learning_rate": 2.4829257750201806e-05,
540
+ "loss": 0.0235,
541
+ "step": 3975
542
+ },
543
+ {
544
+ "epoch": 15.0,
545
+ "eval_loss": 0.07152120769023895,
546
+ "eval_runtime": 1.8045,
547
+ "eval_samples_per_second": 44.334,
548
+ "eval_steps_per_second": 5.542,
549
+ "step": 3975
550
+ },
551
+ {
552
+ "em_boolean": 0.35294117647058826,
553
+ "em_extraction": 0.13333333333333333,
554
+ "em_qa": 0.06666666666666667,
555
+ "em_summarization": 0.0,
556
+ "em_unanswerable": 0.0,
557
+ "epoch": 16.0,
558
+ "mean_em": 0.1125,
559
+ "mean_similarity": 0.6044320391491056,
560
+ "mean_word_count_diff": 15.3625,
561
+ "similarity_boolean": 0.4709787254824358,
562
+ "similarity_extraction": 0.48890374253193536,
563
+ "similarity_qa": 0.7086231042941411,
564
+ "similarity_summarization": 0.6860101450648572,
565
+ "similarity_unanswerable": 0.6691226323445638,
566
+ "word_count_diff_boolean": 5.176470588235294,
567
+ "word_count_diff_extraction": 4.133333333333334,
568
+ "word_count_diff_qa": 5.8,
569
+ "word_count_diff_summarization": 51.388888888888886,
570
+ "word_count_diff_unanswerable": 4.466666666666667
571
+ },
572
+ {
573
+ "epoch": 16.0,
574
+ "grad_norm": 0.12528866529464722,
575
+ "learning_rate": 2.4068986722935625e-05,
576
+ "loss": 0.0219,
577
+ "step": 4240
578
+ },
579
+ {
580
+ "epoch": 16.0,
581
+ "eval_loss": 0.07122211903333664,
582
+ "eval_runtime": 1.7912,
583
+ "eval_samples_per_second": 44.663,
584
+ "eval_steps_per_second": 5.583,
585
+ "step": 4240
586
+ },
587
+ {
588
+ "em_boolean": 0.23529411764705882,
589
+ "em_extraction": 0.2,
590
+ "em_qa": 0.06666666666666667,
591
+ "em_summarization": 0.0,
592
+ "em_unanswerable": 0.0,
593
+ "epoch": 17.0,
594
+ "mean_em": 0.1,
595
+ "mean_similarity": 0.5854583959793672,
596
+ "mean_word_count_diff": 16.1125,
597
+ "similarity_boolean": 0.3930098557954325,
598
+ "similarity_extraction": 0.5295473781724771,
599
+ "similarity_qa": 0.7186618636051814,
600
+ "similarity_summarization": 0.6619544287936555,
601
+ "similarity_unanswerable": 0.6344790523250897,
602
+ "word_count_diff_boolean": 5.764705882352941,
603
+ "word_count_diff_extraction": 5.066666666666666,
604
+ "word_count_diff_qa": 6.066666666666666,
605
+ "word_count_diff_summarization": 52.22222222222222,
606
+ "word_count_diff_unanswerable": 5.6
607
+ },
608
+ {
609
+ "epoch": 17.0,
610
+ "grad_norm": 0.18347615003585815,
611
+ "learning_rate": 2.327006337433323e-05,
612
+ "loss": 0.0208,
613
+ "step": 4505
614
+ },
615
+ {
616
+ "epoch": 17.0,
617
+ "eval_loss": 0.07514352351427078,
618
+ "eval_runtime": 1.7952,
619
+ "eval_samples_per_second": 44.563,
620
+ "eval_steps_per_second": 5.57,
621
+ "step": 4505
622
+ },
623
+ {
624
+ "em_boolean": 0.35294117647058826,
625
+ "em_extraction": 0.13333333333333333,
626
+ "em_qa": 0.06666666666666667,
627
+ "em_summarization": 0.0,
628
+ "em_unanswerable": 0.0,
629
+ "epoch": 18.0,
630
+ "mean_em": 0.1125,
631
+ "mean_similarity": 0.6148898253683001,
632
+ "mean_word_count_diff": 15.95,
633
+ "similarity_boolean": 0.45182113108389516,
634
+ "similarity_extraction": 0.5246008743842443,
635
+ "similarity_qa": 0.7161807785431544,
636
+ "similarity_summarization": 0.695978145632479,
637
+ "similarity_unanswerable": 0.6913930257161458,
638
+ "word_count_diff_boolean": 6.705882352941177,
639
+ "word_count_diff_extraction": 5.333333333333333,
640
+ "word_count_diff_qa": 5.133333333333334,
641
+ "word_count_diff_summarization": 51.72222222222222,
642
+ "word_count_diff_unanswerable": 4.933333333333334
643
+ },
644
+ {
645
+ "epoch": 18.0,
646
+ "grad_norm": 0.39281344413757324,
647
+ "learning_rate": 2.2435892742127786e-05,
648
+ "loss": 0.0197,
649
+ "step": 4770
650
+ },
651
+ {
652
+ "epoch": 18.0,
653
+ "eval_loss": 0.07489313185214996,
654
+ "eval_runtime": 1.7966,
655
+ "eval_samples_per_second": 44.528,
656
+ "eval_steps_per_second": 5.566,
657
+ "step": 4770
658
+ },
659
+ {
660
+ "em_boolean": 0.35294117647058826,
661
+ "em_extraction": 0.13333333333333333,
662
+ "em_qa": 0.06666666666666667,
663
+ "em_summarization": 0.0,
664
+ "em_unanswerable": 0.0,
665
+ "epoch": 19.0,
666
+ "mean_em": 0.1125,
667
+ "mean_similarity": 0.6110048872418702,
668
+ "mean_word_count_diff": 15.175,
669
+ "similarity_boolean": 0.4688412766246235,
670
+ "similarity_extraction": 0.5354909280935923,
671
+ "similarity_qa": 0.7334268649419149,
672
+ "similarity_summarization": 0.6523812972009182,
673
+ "similarity_unanswerable": 0.6755639354387919,
674
+ "word_count_diff_boolean": 5.411764705882353,
675
+ "word_count_diff_extraction": 3.6666666666666665,
676
+ "word_count_diff_qa": 5.333333333333333,
677
+ "word_count_diff_summarization": 51.27777777777778,
678
+ "word_count_diff_unanswerable": 4.266666666666667
679
+ },
680
+ {
681
+ "epoch": 19.0,
682
+ "grad_norm": 0.26503777503967285,
683
+ "learning_rate": 2.1570030089140857e-05,
684
+ "loss": 0.0184,
685
+ "step": 5035
686
+ },
687
+ {
688
+ "epoch": 19.0,
689
+ "eval_loss": 0.07855142652988434,
690
+ "eval_runtime": 1.7852,
691
+ "eval_samples_per_second": 44.813,
692
+ "eval_steps_per_second": 5.602,
693
+ "step": 5035
694
+ },
695
+ {
696
+ "em_boolean": 0.058823529411764705,
697
+ "em_extraction": 0.26666666666666666,
698
+ "em_qa": 0.0,
699
+ "em_summarization": 0.0,
700
+ "em_unanswerable": 0.0,
701
+ "epoch": 20.0,
702
+ "mean_em": 0.0625,
703
+ "mean_similarity": 0.5894458804745227,
704
+ "mean_word_count_diff": 15.7625,
705
+ "similarity_boolean": 0.3066763941417722,
706
+ "similarity_extraction": 0.567964817583561,
707
+ "similarity_qa": 0.7356137126684189,
708
+ "similarity_summarization": 0.7311095827155643,
709
+ "similarity_unanswerable": 0.615234752992789,
710
+ "word_count_diff_boolean": 7.0588235294117645,
711
+ "word_count_diff_extraction": 4.133333333333334,
712
+ "word_count_diff_qa": 6.4,
713
+ "word_count_diff_summarization": 50.833333333333336,
714
+ "word_count_diff_unanswerable": 4.533333333333333
715
+ },
716
+ {
717
+ "epoch": 20.0,
718
+ "grad_norm": 0.325967013835907,
719
+ "learning_rate": 2.0676165750634656e-05,
720
+ "loss": 0.0173,
721
+ "step": 5300
722
+ },
723
+ {
724
+ "epoch": 20.0,
725
+ "eval_loss": 0.07865440845489502,
726
+ "eval_runtime": 1.7895,
727
+ "eval_samples_per_second": 44.705,
728
+ "eval_steps_per_second": 5.588,
729
+ "step": 5300
730
+ },
731
+ {
732
+ "em_boolean": 0.5294117647058824,
733
+ "em_extraction": 0.26666666666666666,
734
+ "em_qa": 0.06666666666666667,
735
+ "em_summarization": 0.0,
736
+ "em_unanswerable": 0.0,
737
+ "epoch": 21.0,
738
+ "mean_em": 0.175,
739
+ "mean_similarity": 0.6464177187765017,
740
+ "mean_word_count_diff": 14.8375,
741
+ "similarity_boolean": 0.6461278642801678,
742
+ "similarity_extraction": 0.6178931772708893,
743
+ "similarity_qa": 0.7566967884699504,
744
+ "similarity_summarization": 0.6613570315142473,
745
+ "similarity_unanswerable": 0.5470645170658827,
746
+ "word_count_diff_boolean": 3.176470588235294,
747
+ "word_count_diff_extraction": 5.4,
748
+ "word_count_diff_qa": 4.6,
749
+ "word_count_diff_summarization": 50.5,
750
+ "word_count_diff_unanswerable": 4.933333333333334
751
+ },
752
+ {
753
+ "epoch": 21.0,
754
+ "grad_norm": 0.18580074608325958,
755
+ "learning_rate": 1.975810940598114e-05,
756
+ "loss": 0.0162,
757
+ "step": 5565
758
+ },
759
+ {
760
+ "epoch": 21.0,
761
+ "eval_loss": 0.08283738046884537,
762
+ "eval_runtime": 1.8062,
763
+ "eval_samples_per_second": 44.292,
764
+ "eval_steps_per_second": 5.537,
765
+ "step": 5565
766
+ },
767
+ {
768
+ "em_boolean": 0.47058823529411764,
769
+ "em_extraction": 0.26666666666666666,
770
+ "em_qa": 0.06666666666666667,
771
+ "em_summarization": 0.0,
772
+ "em_unanswerable": 0.0,
773
+ "epoch": 22.0,
774
+ "mean_em": 0.1625,
775
+ "mean_similarity": 0.6508607531315647,
776
+ "mean_word_count_diff": 15.1875,
777
+ "similarity_boolean": 0.5319088667302447,
778
+ "similarity_extraction": 0.6322630804032088,
779
+ "similarity_qa": 0.7358093798160553,
780
+ "similarity_summarization": 0.6958086478213469,
781
+ "similarity_unanswerable": 0.6653844634691874,
782
+ "word_count_diff_boolean": 5.352941176470588,
783
+ "word_count_diff_extraction": 3.933333333333333,
784
+ "word_count_diff_qa": 5.266666666666667,
785
+ "word_count_diff_summarization": 51.166666666666664,
786
+ "word_count_diff_unanswerable": 4.333333333333333
787
+ },
788
+ {
789
+ "epoch": 22.0,
790
+ "grad_norm": 0.7463592886924744,
791
+ "learning_rate": 1.881977384168254e-05,
792
+ "loss": 0.0158,
793
+ "step": 5830
794
+ },
795
+ {
796
+ "epoch": 22.0,
797
+ "eval_loss": 0.08268458396196365,
798
+ "eval_runtime": 1.7886,
799
+ "eval_samples_per_second": 44.728,
800
+ "eval_steps_per_second": 5.591,
801
+ "step": 5830
802
+ },
803
+ {
804
+ "em_boolean": 0.4117647058823529,
805
+ "em_extraction": 0.2,
806
+ "em_qa": 0.13333333333333333,
807
+ "em_summarization": 0.0,
808
+ "em_unanswerable": 0.0,
809
+ "epoch": 23.0,
810
+ "mean_em": 0.15,
811
+ "mean_similarity": 0.6376353252329864,
812
+ "mean_word_count_diff": 15.5625,
813
+ "similarity_boolean": 0.5682552300722283,
814
+ "similarity_extraction": 0.5148679026712973,
815
+ "similarity_qa": 0.7483514944712321,
816
+ "similarity_summarization": 0.7200961951166391,
817
+ "similarity_unanswerable": 0.629364309211572,
818
+ "word_count_diff_boolean": 3.823529411764706,
819
+ "word_count_diff_extraction": 5.266666666666667,
820
+ "word_count_diff_qa": 4.933333333333334,
821
+ "word_count_diff_summarization": 51.388888888888886,
822
+ "word_count_diff_unanswerable": 6.8
823
+ },
824
+ {
825
+ "epoch": 23.0,
826
+ "grad_norm": 0.30431216955184937,
827
+ "learning_rate": 1.7865158274945846e-05,
828
+ "loss": 0.0149,
829
+ "step": 6095
830
+ },
831
+ {
832
+ "epoch": 23.0,
833
+ "eval_loss": 0.08500902354717255,
834
+ "eval_runtime": 1.8006,
835
+ "eval_samples_per_second": 44.43,
836
+ "eval_steps_per_second": 5.554,
837
+ "step": 6095
838
+ },
839
+ {
840
+ "em_boolean": 0.35294117647058826,
841
+ "em_extraction": 0.2,
842
+ "em_qa": 0.0,
843
+ "em_summarization": 0.0,
844
+ "em_unanswerable": 0.0,
845
+ "epoch": 24.0,
846
+ "mean_em": 0.1125,
847
+ "mean_similarity": 0.6209718830883503,
848
+ "mean_word_count_diff": 15.625,
849
+ "similarity_boolean": 0.4452236132586704,
850
+ "similarity_extraction": 0.5458283141255379,
851
+ "similarity_qa": 0.7422831366459529,
852
+ "similarity_summarization": 0.7023132857349184,
853
+ "similarity_unanswerable": 0.6763758877913157,
854
+ "word_count_diff_boolean": 5.470588235294118,
855
+ "word_count_diff_extraction": 5.6,
856
+ "word_count_diff_qa": 5.533333333333333,
857
+ "word_count_diff_summarization": 51.611111111111114,
858
+ "word_count_diff_unanswerable": 4.066666666666666
859
+ },
860
+ {
861
+ "epoch": 24.0,
862
+ "grad_norm": 0.1550023853778839,
863
+ "learning_rate": 1.6898331308886863e-05,
864
+ "loss": 0.0138,
865
+ "step": 6360
866
+ },
867
+ {
868
+ "epoch": 24.0,
869
+ "eval_loss": 0.08557449281215668,
870
+ "eval_runtime": 1.7865,
871
+ "eval_samples_per_second": 44.78,
872
+ "eval_steps_per_second": 5.598,
873
+ "step": 6360
874
+ },
875
+ {
876
+ "em_boolean": 0.4117647058823529,
877
+ "em_extraction": 0.26666666666666666,
878
+ "em_qa": 0.13333333333333333,
879
+ "em_summarization": 0.0,
880
+ "em_unanswerable": 0.0,
881
+ "epoch": 25.0,
882
+ "mean_em": 0.1625,
883
+ "mean_similarity": 0.6411203743191436,
884
+ "mean_word_count_diff": 15.1875,
885
+ "similarity_boolean": 0.5644924241830321,
886
+ "similarity_extraction": 0.5594843897968531,
887
+ "similarity_qa": 0.7792828718821208,
888
+ "similarity_summarization": 0.6979754573355118,
889
+ "similarity_unanswerable": 0.6032127718130748,
890
+ "word_count_diff_boolean": 3.7058823529411766,
891
+ "word_count_diff_extraction": 4.533333333333333,
892
+ "word_count_diff_qa": 4.933333333333334,
893
+ "word_count_diff_summarization": 51.833333333333336,
894
+ "word_count_diff_unanswerable": 5.133333333333334
895
+ },
896
+ {
897
+ "epoch": 25.0,
898
+ "grad_norm": 0.23536083102226257,
899
+ "learning_rate": 1.5923413592009145e-05,
900
+ "loss": 0.0132,
901
+ "step": 6625
902
+ },
903
+ {
904
+ "epoch": 25.0,
905
+ "eval_loss": 0.0886365994811058,
906
+ "eval_runtime": 1.7918,
907
+ "eval_samples_per_second": 44.648,
908
+ "eval_steps_per_second": 5.581,
909
+ "step": 6625
910
+ },
911
+ {
912
+ "em_boolean": 0.29411764705882354,
913
+ "em_extraction": 0.13333333333333333,
914
+ "em_qa": 0.0,
915
+ "em_summarization": 0.0,
916
+ "em_unanswerable": 0.0,
917
+ "epoch": 26.0,
918
+ "mean_em": 0.0875,
919
+ "mean_similarity": 0.5999299102462828,
920
+ "mean_word_count_diff": 15.6625,
921
+ "similarity_boolean": 0.44055906716076765,
922
+ "similarity_extraction": 0.4907683741301298,
923
+ "similarity_qa": 0.64702517837286,
924
+ "similarity_summarization": 0.7336946874856949,
925
+ "similarity_unanswerable": 0.6820987343788147,
926
+ "word_count_diff_boolean": 5.9411764705882355,
927
+ "word_count_diff_extraction": 5.466666666666667,
928
+ "word_count_diff_qa": 7.066666666666666,
929
+ "word_count_diff_summarization": 50.27777777777778,
930
+ "word_count_diff_unanswerable": 3.933333333333333
931
+ },
932
+ {
933
+ "epoch": 26.0,
934
+ "grad_norm": 0.0521920807659626,
935
+ "learning_rate": 1.4944560255863805e-05,
936
+ "loss": 0.0127,
937
+ "step": 6890
938
+ },
939
+ {
940
+ "epoch": 26.0,
941
+ "eval_loss": 0.09115185588598251,
942
+ "eval_runtime": 1.7871,
943
+ "eval_samples_per_second": 44.764,
944
+ "eval_steps_per_second": 5.596,
945
+ "step": 6890
946
+ },
947
+ {
948
+ "em_boolean": 0.29411764705882354,
949
+ "em_extraction": 0.2,
950
+ "em_qa": 0.06666666666666667,
951
+ "em_summarization": 0.0,
952
+ "em_unanswerable": 0.0,
953
+ "epoch": 27.0,
954
+ "mean_em": 0.1125,
955
+ "mean_similarity": 0.5961971989367157,
956
+ "mean_word_count_diff": 15.9,
957
+ "similarity_boolean": 0.47167208264855776,
958
+ "similarity_extraction": 0.563706802825133,
959
+ "similarity_qa": 0.6419207287331422,
960
+ "similarity_summarization": 0.6927380098236932,
961
+ "similarity_unanswerable": 0.608243557314078,
962
+ "word_count_diff_boolean": 5.0,
963
+ "word_count_diff_extraction": 4.933333333333334,
964
+ "word_count_diff_qa": 6.0,
965
+ "word_count_diff_summarization": 52.0,
966
+ "word_count_diff_unanswerable": 5.8
967
+ },
968
+ {
969
+ "epoch": 27.0,
970
+ "grad_norm": 0.23173846304416656,
971
+ "learning_rate": 1.396594320574144e-05,
972
+ "loss": 0.0121,
973
+ "step": 7155
974
+ },
975
+ {
976
+ "epoch": 27.0,
977
+ "eval_loss": 0.09045173972845078,
978
+ "eval_runtime": 1.7961,
979
+ "eval_samples_per_second": 44.541,
980
+ "eval_steps_per_second": 5.568,
981
+ "step": 7155
982
+ },
983
+ {
984
+ "em_boolean": 0.5294117647058824,
985
+ "em_extraction": 0.13333333333333333,
986
+ "em_qa": 0.06666666666666667,
987
+ "em_summarization": 0.0,
988
+ "em_unanswerable": 0.0,
989
+ "epoch": 28.0,
990
+ "mean_em": 0.15,
991
+ "mean_similarity": 0.6426682359306142,
992
+ "mean_word_count_diff": 15.4625,
993
+ "similarity_boolean": 0.6154902246506775,
994
+ "similarity_extraction": 0.559150509784619,
995
+ "similarity_qa": 0.7585609555244446,
996
+ "similarity_summarization": 0.7132770286666023,
997
+ "similarity_unanswerable": 0.5563644373168548,
998
+ "word_count_diff_boolean": 3.9411764705882355,
999
+ "word_count_diff_extraction": 5.933333333333334,
1000
+ "word_count_diff_qa": 5.4,
1001
+ "word_count_diff_summarization": 51.94444444444444,
1002
+ "word_count_diff_unanswerable": 4.333333333333333
1003
+ },
1004
+ {
1005
+ "epoch": 28.0,
1006
+ "grad_norm": 0.15653730928897858,
1007
+ "learning_rate": 1.2991733339873795e-05,
1008
+ "loss": 0.0114,
1009
+ "step": 7420
1010
+ },
1011
+ {
1012
+ "epoch": 28.0,
1013
+ "eval_loss": 0.09521345049142838,
1014
+ "eval_runtime": 1.7969,
1015
+ "eval_samples_per_second": 44.521,
1016
+ "eval_steps_per_second": 5.565,
1017
+ "step": 7420
1018
+ },
1019
+ {
1020
+ "em_boolean": 0.5882352941176471,
1021
+ "em_extraction": 0.2,
1022
+ "em_qa": 0.0,
1023
+ "em_summarization": 0.0,
1024
+ "em_unanswerable": 0.0,
1025
+ "epoch": 29.0,
1026
+ "mean_em": 0.1625,
1027
+ "mean_similarity": 0.670323112141341,
1028
+ "mean_word_count_diff": 14.8125,
1029
+ "similarity_boolean": 0.6801450522068668,
1030
+ "similarity_extraction": 0.5754425642391046,
1031
+ "similarity_qa": 0.7391265859206517,
1032
+ "similarity_summarization": 0.7395255797439151,
1033
+ "similarity_unanswerable": 0.6022256930669149,
1034
+ "word_count_diff_boolean": 2.588235294117647,
1035
+ "word_count_diff_extraction": 4.0,
1036
+ "word_count_diff_qa": 5.666666666666667,
1037
+ "word_count_diff_summarization": 50.333333333333336,
1038
+ "word_count_diff_unanswerable": 6.0
1039
+ },
1040
+ {
1041
+ "epoch": 29.0,
1042
+ "grad_norm": 0.13572590053081512,
1043
+ "learning_rate": 1.2026082772927574e-05,
1044
+ "loss": 0.0112,
1045
+ "step": 7685
1046
+ },
1047
+ {
1048
+ "epoch": 29.0,
1049
+ "eval_loss": 0.09561847150325775,
1050
+ "eval_runtime": 1.7863,
1051
+ "eval_samples_per_second": 44.786,
1052
+ "eval_steps_per_second": 5.598,
1053
+ "step": 7685
1054
+ },
1055
+ {
1056
+ "em_boolean": 0.47058823529411764,
1057
+ "em_extraction": 0.26666666666666666,
1058
+ "em_qa": 0.06666666666666667,
1059
+ "em_summarization": 0.0,
1060
+ "em_unanswerable": 0.0,
1061
+ "epoch": 30.0,
1062
+ "mean_em": 0.1625,
1063
+ "mean_similarity": 0.6361284551327117,
1064
+ "mean_word_count_diff": 15.1625,
1065
+ "similarity_boolean": 0.5678887126748177,
1066
+ "similarity_extraction": 0.528444591164589,
1067
+ "similarity_qa": 0.7746080329020818,
1068
+ "similarity_summarization": 0.7153815428415934,
1069
+ "similarity_unanswerable": 0.5875674108664195,
1070
+ "word_count_diff_boolean": 3.6470588235294117,
1071
+ "word_count_diff_extraction": 4.2,
1072
+ "word_count_diff_qa": 5.666666666666667,
1073
+ "word_count_diff_summarization": 51.05555555555556,
1074
+ "word_count_diff_unanswerable": 5.6
1075
+ },
1076
+ {
1077
+ "epoch": 30.0,
1078
+ "grad_norm": 0.11106608062982559,
1079
+ "learning_rate": 1.1073107139554395e-05,
1080
+ "loss": 0.0111,
1081
+ "step": 7950
1082
+ },
1083
+ {
1084
+ "epoch": 30.0,
1085
+ "eval_loss": 0.09475980699062347,
1086
+ "eval_runtime": 1.8027,
1087
+ "eval_samples_per_second": 44.379,
1088
+ "eval_steps_per_second": 5.547,
1089
+ "step": 7950
1090
+ },
1091
+ {
1092
+ "em_boolean": 0.47058823529411764,
1093
+ "em_extraction": 0.0,
1094
+ "em_qa": 0.06666666666666667,
1095
+ "em_summarization": 0.0,
1096
+ "em_unanswerable": 0.0,
1097
+ "epoch": 31.0,
1098
+ "mean_em": 0.1125,
1099
+ "mean_similarity": 0.5996635487768799,
1100
+ "mean_word_count_diff": 15.9625,
1101
+ "similarity_boolean": 0.5703230380792829,
1102
+ "similarity_extraction": 0.43614052472015225,
1103
+ "similarity_qa": 0.6746748656034469,
1104
+ "similarity_summarization": 0.6909497512711419,
1105
+ "similarity_unanswerable": 0.6118843918045361,
1106
+ "word_count_diff_boolean": 4.176470588235294,
1107
+ "word_count_diff_extraction": 6.933333333333334,
1108
+ "word_count_diff_qa": 6.466666666666667,
1109
+ "word_count_diff_summarization": 51.888888888888886,
1110
+ "word_count_diff_unanswerable": 4.733333333333333
1111
+ },
1112
+ {
1113
+ "epoch": 31.0,
1114
+ "grad_norm": 0.15586383640766144,
1115
+ "learning_rate": 1.0136868053419842e-05,
1116
+ "loss": 0.0105,
1117
+ "step": 8215
1118
+ },
1119
+ {
1120
+ "epoch": 31.0,
1121
+ "eval_loss": 0.09651915729045868,
1122
+ "eval_runtime": 1.7878,
1123
+ "eval_samples_per_second": 44.749,
1124
+ "eval_steps_per_second": 5.594,
1125
+ "step": 8215
1126
+ },
1127
+ {
1128
+ "em_boolean": 0.35294117647058826,
1129
+ "em_extraction": 0.26666666666666666,
1130
+ "em_qa": 0.0,
1131
+ "em_summarization": 0.0,
1132
+ "em_unanswerable": 0.0,
1133
+ "epoch": 32.0,
1134
+ "mean_em": 0.125,
1135
+ "mean_similarity": 0.6647563714534044,
1136
+ "mean_word_count_diff": 15.3125,
1137
+ "similarity_boolean": 0.4992627663647427,
1138
+ "similarity_extraction": 0.6371853078405062,
1139
+ "similarity_qa": 0.7779242674509684,
1140
+ "similarity_summarization": 0.7545208003785875,
1141
+ "similarity_unanswerable": 0.6590016434590021,
1142
+ "word_count_diff_boolean": 4.352941176470588,
1143
+ "word_count_diff_extraction": 3.6666666666666665,
1144
+ "word_count_diff_qa": 7.133333333333334,
1145
+ "word_count_diff_summarization": 52.22222222222222,
1146
+ "word_count_diff_unanswerable": 3.2666666666666666
1147
+ },
1148
+ {
1149
+ "epoch": 32.0,
1150
+ "grad_norm": 0.15895779430866241,
1151
+ "learning_rate": 9.22135579647165e-06,
1152
+ "loss": 0.0103,
1153
+ "step": 8480
1154
+ },
1155
+ {
1156
+ "epoch": 32.0,
1157
+ "eval_loss": 0.09846033155918121,
1158
+ "eval_runtime": 1.7981,
1159
+ "eval_samples_per_second": 44.492,
1160
+ "eval_steps_per_second": 5.562,
1161
+ "step": 8480
1162
+ },
1163
+ {
1164
+ "em_boolean": 0.35294117647058826,
1165
+ "em_extraction": 0.13333333333333333,
1166
+ "em_qa": 0.0,
1167
+ "em_summarization": 0.0,
1168
+ "em_unanswerable": 0.0,
1169
+ "epoch": 33.0,
1170
+ "mean_em": 0.1,
1171
+ "mean_similarity": 0.6497376295737922,
1172
+ "mean_word_count_diff": 15.2,
1173
+ "similarity_boolean": 0.4850216718281017,
1174
+ "similarity_extraction": 0.6169686233003934,
1175
+ "similarity_qa": 0.7874227881431579,
1176
+ "similarity_summarization": 0.720199970735444,
1177
+ "similarity_unanswerable": 0.6469447533289592,
1178
+ "word_count_diff_boolean": 5.529411764705882,
1179
+ "word_count_diff_extraction": 4.0,
1180
+ "word_count_diff_qa": 5.466666666666667,
1181
+ "word_count_diff_summarization": 50.72222222222222,
1182
+ "word_count_diff_unanswerable": 4.466666666666667
1183
+ },
1184
+ {
1185
+ "epoch": 33.0,
1186
+ "grad_norm": 0.16729232668876648,
1187
+ "learning_rate": 8.330472312226091e-06,
1188
+ "loss": 0.0099,
1189
+ "step": 8745
1190
+ },
1191
+ {
1192
+ "epoch": 33.0,
1193
+ "eval_loss": 0.09990086406469345,
1194
+ "eval_runtime": 1.7757,
1195
+ "eval_samples_per_second": 45.052,
1196
+ "eval_steps_per_second": 5.631,
1197
+ "step": 8745
1198
+ },
1199
+ {
1200
+ "em_boolean": 0.4117647058823529,
1201
+ "em_extraction": 0.2,
1202
+ "em_qa": 0.0,
1203
+ "em_summarization": 0.0,
1204
+ "em_unanswerable": 0.0,
1205
+ "epoch": 34.0,
1206
+ "mean_em": 0.125,
1207
+ "mean_similarity": 0.6532467395067215,
1208
+ "mean_word_count_diff": 15.3375,
1209
+ "similarity_boolean": 0.5624497304944431,
1210
+ "similarity_extraction": 0.6123799696564675,
1211
+ "similarity_qa": 0.7896470129489899,
1212
+ "similarity_summarization": 0.6943622730258439,
1213
+ "similarity_unanswerable": 0.6112778725723426,
1214
+ "word_count_diff_boolean": 4.588235294117647,
1215
+ "word_count_diff_extraction": 5.266666666666667,
1216
+ "word_count_diff_qa": 5.933333333333334,
1217
+ "word_count_diff_summarization": 50.666666666666664,
1218
+ "word_count_diff_unanswerable": 4.6
1219
+ },
1220
+ {
1221
+ "epoch": 34.0,
1222
+ "grad_norm": 0.3746591806411743,
1223
+ "learning_rate": 7.468014575555688e-06,
1224
+ "loss": 0.0096,
1225
+ "step": 9010
1226
+ },
1227
+ {
1228
+ "epoch": 34.0,
1229
+ "eval_loss": 0.10108506679534912,
1230
+ "eval_runtime": 1.7759,
1231
+ "eval_samples_per_second": 45.048,
1232
+ "eval_steps_per_second": 5.631,
1233
+ "step": 9010
1234
+ },
1235
+ {
1236
+ "em_boolean": 0.35294117647058826,
1237
+ "em_extraction": 0.13333333333333333,
1238
+ "em_qa": 0.13333333333333333,
1239
+ "em_summarization": 0.0,
1240
+ "em_unanswerable": 0.0,
1241
+ "epoch": 35.0,
1242
+ "mean_em": 0.125,
1243
+ "mean_similarity": 0.6299693588167429,
1244
+ "mean_word_count_diff": 15.35,
1245
+ "similarity_boolean": 0.5166072974748471,
1246
+ "similarity_extraction": 0.55517836039265,
1247
+ "similarity_qa": 0.7496427396933237,
1248
+ "similarity_summarization": 0.7208915799856186,
1249
+ "similarity_unanswerable": 0.6044573138157526,
1250
+ "word_count_diff_boolean": 4.352941176470588,
1251
+ "word_count_diff_extraction": 5.266666666666667,
1252
+ "word_count_diff_qa": 4.8,
1253
+ "word_count_diff_summarization": 51.388888888888886,
1254
+ "word_count_diff_unanswerable": 5.2
1255
+ },
1256
+ {
1257
+ "epoch": 35.0,
1258
+ "grad_norm": 0.310463547706604,
1259
+ "learning_rate": 6.637658409856717e-06,
1260
+ "loss": 0.0096,
1261
+ "step": 9275
1262
+ },
1263
+ {
1264
+ "epoch": 35.0,
1265
+ "eval_loss": 0.10128389298915863,
1266
+ "eval_runtime": 1.7949,
1267
+ "eval_samples_per_second": 44.571,
1268
+ "eval_steps_per_second": 5.571,
1269
+ "step": 9275
1270
+ },
1271
+ {
1272
+ "em_boolean": 0.5294117647058824,
1273
+ "em_extraction": 0.2,
1274
+ "em_qa": 0.06666666666666667,
1275
+ "em_summarization": 0.0,
1276
+ "em_unanswerable": 0.0,
1277
+ "epoch": 36.0,
1278
+ "mean_em": 0.1625,
1279
+ "mean_similarity": 0.6648560125031509,
1280
+ "mean_word_count_diff": 14.9,
1281
+ "similarity_boolean": 0.6631740967688315,
1282
+ "similarity_extraction": 0.5298445565005143,
1283
+ "similarity_qa": 0.7434355229139328,
1284
+ "similarity_summarization": 0.7201196981800927,
1285
+ "similarity_unanswerable": 0.6568777064482371,
1286
+ "word_count_diff_boolean": 2.2941176470588234,
1287
+ "word_count_diff_extraction": 5.2,
1288
+ "word_count_diff_qa": 5.333333333333333,
1289
+ "word_count_diff_summarization": 52.0,
1290
+ "word_count_diff_unanswerable": 3.933333333333333
1291
+ },
1292
+ {
1293
+ "epoch": 36.0,
1294
+ "grad_norm": 0.23128336668014526,
1295
+ "learning_rate": 5.84294282056834e-06,
1296
+ "loss": 0.0094,
1297
+ "step": 9540
1298
+ },
1299
+ {
1300
+ "epoch": 36.0,
1301
+ "eval_loss": 0.10348665714263916,
1302
+ "eval_runtime": 1.7894,
1303
+ "eval_samples_per_second": 44.707,
1304
+ "eval_steps_per_second": 5.588,
1305
+ "step": 9540
1306
+ },
1307
+ {
1308
+ "em_boolean": 0.47058823529411764,
1309
+ "em_extraction": 0.2,
1310
+ "em_qa": 0.0,
1311
+ "em_summarization": 0.0,
1312
+ "em_unanswerable": 0.0,
1313
+ "epoch": 37.0,
1314
+ "mean_em": 0.1375,
1315
+ "mean_similarity": 0.6319401320070028,
1316
+ "mean_word_count_diff": 15.0875,
1317
+ "similarity_boolean": 0.5821067885879208,
1318
+ "similarity_extraction": 0.5178047935167949,
1319
+ "similarity_qa": 0.769520037372907,
1320
+ "similarity_summarization": 0.6793310083448887,
1321
+ "similarity_unanswerable": 0.6081043027341366,
1322
+ "word_count_diff_boolean": 4.235294117647059,
1323
+ "word_count_diff_extraction": 4.866666666666666,
1324
+ "word_count_diff_qa": 5.0,
1325
+ "word_count_diff_summarization": 50.833333333333336,
1326
+ "word_count_diff_unanswerable": 4.8
1327
+ },
1328
+ {
1329
+ "epoch": 37.0,
1330
+ "grad_norm": 0.10078708827495575,
1331
+ "learning_rate": 5.087254911814361e-06,
1332
+ "loss": 0.0092,
1333
+ "step": 9805
1334
+ },
1335
+ {
1336
+ "epoch": 37.0,
1337
+ "eval_loss": 0.10369674116373062,
1338
+ "eval_runtime": 1.7998,
1339
+ "eval_samples_per_second": 44.45,
1340
+ "eval_steps_per_second": 5.556,
1341
+ "step": 9805
1342
+ },
1343
+ {
1344
+ "em_boolean": 0.4117647058823529,
1345
+ "em_extraction": 0.13333333333333333,
1346
+ "em_qa": 0.0,
1347
+ "em_summarization": 0.0,
1348
+ "em_unanswerable": 0.0,
1349
+ "epoch": 38.0,
1350
+ "mean_em": 0.1125,
1351
+ "mean_similarity": 0.6402258106973022,
1352
+ "mean_word_count_diff": 15.3875,
1353
+ "similarity_boolean": 0.5555457597708001,
1354
+ "similarity_extraction": 0.5125755973160266,
1355
+ "similarity_qa": 0.729976910352707,
1356
+ "similarity_summarization": 0.7154302892999517,
1357
+ "similarity_unanswerable": 0.6838502744833629,
1358
+ "word_count_diff_boolean": 4.352941176470588,
1359
+ "word_count_diff_extraction": 4.466666666666667,
1360
+ "word_count_diff_qa": 6.266666666666667,
1361
+ "word_count_diff_summarization": 51.166666666666664,
1362
+ "word_count_diff_unanswerable": 5.0
1363
+ },
1364
+ {
1365
+ "epoch": 38.0,
1366
+ "grad_norm": 0.14647193253040314,
1367
+ "learning_rate": 4.373815450453467e-06,
1368
+ "loss": 0.0087,
1369
+ "step": 10070
1370
+ },
1371
+ {
1372
+ "epoch": 38.0,
1373
+ "eval_loss": 0.10511450469493866,
1374
+ "eval_runtime": 1.8033,
1375
+ "eval_samples_per_second": 44.364,
1376
+ "eval_steps_per_second": 5.545,
1377
+ "step": 10070
1378
+ },
1379
+ {
1380
+ "em_boolean": 0.29411764705882354,
1381
+ "em_extraction": 0.26666666666666666,
1382
+ "em_qa": 0.13333333333333333,
1383
+ "em_summarization": 0.0,
1384
+ "em_unanswerable": 0.0,
1385
+ "epoch": 39.0,
1386
+ "mean_em": 0.1375,
1387
+ "mean_similarity": 0.5966290417010895,
1388
+ "mean_word_count_diff": 15.375,
1389
+ "similarity_boolean": 0.48111217118361416,
1390
+ "similarity_extraction": 0.5464107090607285,
1391
+ "similarity_qa": 0.7710953007141749,
1392
+ "similarity_summarization": 0.6638153013255861,
1393
+ "similarity_unanswerable": 0.5226767236987749,
1394
+ "word_count_diff_boolean": 4.294117647058823,
1395
+ "word_count_diff_extraction": 5.133333333333334,
1396
+ "word_count_diff_qa": 5.466666666666667,
1397
+ "word_count_diff_summarization": 50.611111111111114,
1398
+ "word_count_diff_unanswerable": 5.8
1399
+ },
1400
+ {
1401
+ "epoch": 39.0,
1402
+ "grad_norm": 0.8468394875526428,
1403
+ "learning_rate": 3.7056651390643413e-06,
1404
+ "loss": 0.0088,
1405
+ "step": 10335
1406
+ },
1407
+ {
1408
+ "epoch": 39.0,
1409
+ "eval_loss": 0.10422440618276596,
1410
+ "eval_runtime": 1.7878,
1411
+ "eval_samples_per_second": 44.747,
1412
+ "eval_steps_per_second": 5.593,
1413
+ "step": 10335
1414
+ },
1415
+ {
1416
+ "em_boolean": 0.47058823529411764,
1417
+ "em_extraction": 0.26666666666666666,
1418
+ "em_qa": 0.13333333333333333,
1419
+ "em_summarization": 0.0,
1420
+ "em_unanswerable": 0.0,
1421
+ "epoch": 40.0,
1422
+ "mean_em": 0.175,
1423
+ "mean_similarity": 0.6348526364192366,
1424
+ "mean_word_count_diff": 15.1875,
1425
+ "similarity_boolean": 0.5687163450262126,
1426
+ "similarity_extraction": 0.62134765163064,
1427
+ "similarity_qa": 0.7562251538038254,
1428
+ "similarity_summarization": 0.6440524767256446,
1429
+ "similarity_unanswerable": 0.5908997590343158,
1430
+ "word_count_diff_boolean": 4.529411764705882,
1431
+ "word_count_diff_extraction": 4.133333333333334,
1432
+ "word_count_diff_qa": 4.866666666666666,
1433
+ "word_count_diff_summarization": 50.666666666666664,
1434
+ "word_count_diff_unanswerable": 6.066666666666666
1435
+ },
1436
+ {
1437
+ "epoch": 40.0,
1438
+ "grad_norm": 0.15559451282024384,
1439
+ "learning_rate": 3.08565165637071e-06,
1440
+ "loss": 0.0088,
1441
+ "step": 10600
1442
+ },
1443
+ {
1444
+ "epoch": 40.0,
1445
+ "eval_loss": 0.1041550487279892,
1446
+ "eval_runtime": 1.7986,
1447
+ "eval_samples_per_second": 44.479,
1448
+ "eval_steps_per_second": 5.56,
1449
+ "step": 10600
1450
+ },
1451
+ {
1452
+ "em_boolean": 0.4117647058823529,
1453
+ "em_extraction": 0.2,
1454
+ "em_qa": 0.0,
1455
+ "em_summarization": 0.0,
1456
+ "em_unanswerable": 0.0,
1457
+ "epoch": 41.0,
1458
+ "mean_em": 0.125,
1459
+ "mean_similarity": 0.6427899678237736,
1460
+ "mean_word_count_diff": 15.15,
1461
+ "similarity_boolean": 0.5819402319543502,
1462
+ "similarity_extraction": 0.5856266627709071,
1463
+ "similarity_qa": 0.7046878506739934,
1464
+ "similarity_summarization": 0.7580131689707438,
1465
+ "similarity_unanswerable": 0.5687505826354027,
1466
+ "word_count_diff_boolean": 3.0,
1467
+ "word_count_diff_extraction": 5.266666666666667,
1468
+ "word_count_diff_qa": 5.466666666666667,
1469
+ "word_count_diff_summarization": 51.44444444444444,
1470
+ "word_count_diff_unanswerable": 4.933333333333334
1471
+ },
1472
+ {
1473
+ "epoch": 41.0,
1474
+ "grad_norm": 0.2692953050136566,
1475
+ "learning_rate": 2.516417520340457e-06,
1476
+ "loss": 0.0085,
1477
+ "step": 10865
1478
+ },
1479
+ {
1480
+ "epoch": 41.0,
1481
+ "eval_loss": 0.1051572784781456,
1482
+ "eval_runtime": 1.7897,
1483
+ "eval_samples_per_second": 44.701,
1484
+ "eval_steps_per_second": 5.588,
1485
+ "step": 10865
1486
+ },
1487
+ {
1488
+ "em_boolean": 0.47058823529411764,
1489
+ "em_extraction": 0.3333333333333333,
1490
+ "em_qa": 0.0,
1491
+ "em_summarization": 0.0,
1492
+ "em_unanswerable": 0.0,
1493
+ "epoch": 42.0,
1494
+ "mean_em": 0.1625,
1495
+ "mean_similarity": 0.6774277022806927,
1496
+ "mean_word_count_diff": 15.4,
1497
+ "similarity_boolean": 0.600595106206396,
1498
+ "similarity_extraction": 0.644695137689511,
1499
+ "similarity_qa": 0.7859726687272389,
1500
+ "similarity_summarization": 0.7171196627120177,
1501
+ "similarity_unanswerable": 0.6410618901252747,
1502
+ "word_count_diff_boolean": 3.8823529411764706,
1503
+ "word_count_diff_extraction": 4.0,
1504
+ "word_count_diff_qa": 6.333333333333333,
1505
+ "word_count_diff_summarization": 53.05555555555556,
1506
+ "word_count_diff_unanswerable": 3.7333333333333334
1507
+ },
1508
+ {
1509
+ "epoch": 42.0,
1510
+ "grad_norm": 0.028788737952709198,
1511
+ "learning_rate": 2.000388825686658e-06,
1512
+ "loss": 0.0084,
1513
+ "step": 11130
1514
+ },
1515
+ {
1516
+ "epoch": 42.0,
1517
+ "eval_loss": 0.10606852918863297,
1518
+ "eval_runtime": 1.7957,
1519
+ "eval_samples_per_second": 44.551,
1520
+ "eval_steps_per_second": 5.569,
1521
+ "step": 11130
1522
+ }
1523
+ ],
1524
+ "logging_steps": 500,
1525
+ "max_steps": 13250,
1526
+ "num_input_tokens_seen": 0,
1527
+ "num_train_epochs": 50,
1528
+ "save_steps": 500,
1529
+ "stateful_callbacks": {
1530
+ "TrainerControl": {
1531
+ "args": {
1532
+ "should_epoch_stop": false,
1533
+ "should_evaluate": false,
1534
+ "should_log": false,
1535
+ "should_save": true,
1536
+ "should_training_stop": false
1537
+ },
1538
+ "attributes": {}
1539
+ }
1540
+ },
1541
+ "total_flos": 3.042787771337933e+16,
1542
+ "train_batch_size": 4,
1543
+ "trial_name": null,
1544
+ "trial_params": null
1545
+ }
checkpoint-11130/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a42f35ca56de4716016f99e4c1ec8c3abc7da2b9d03b422aae399b849522e7a
3
+ size 5304
checkpoint-11395/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
checkpoint-11395/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
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": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.48.3",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
checkpoint-11395/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": "4.48.3"
7
+ }
checkpoint-11395/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96283bf40e4c3208b97c3189bd4e499f3bb04e0e839e824f2acc07caef4405e
3
+ size 990345064
checkpoint-11395/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18be12586d26be4bcf8817cfdd7e9838ad72522aa507ad339d26061e69812a96
3
+ size 1980860410
checkpoint-11395/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0247ef18e7bbd38329972f31ba121f8e6963830d269f2baa2f30ceacc898def
3
+ size 14244
checkpoint-11395/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27772bcb92f28d52dfb75d2b2ec64e7de842ea7de45639e5011417c2cae7ff7
3
+ size 1064
checkpoint-11395/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoint-11395/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-11395/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 512,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
checkpoint-11395/trainer_state.json ADDED
@@ -0,0 +1,1581 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06431461870670319,
3
+ "best_model_checkpoint": "./teapotllm/checkpoint-1855",
4
+ "epoch": 43.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11395,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "em_boolean": 0.11764705882352941,
13
+ "em_extraction": 0.06666666666666667,
14
+ "em_qa": 0.0,
15
+ "em_summarization": 0.0,
16
+ "em_unanswerable": 0.0,
17
+ "epoch": 1.0,
18
+ "mean_em": 0.0375,
19
+ "mean_similarity": 0.3622433557640761,
20
+ "mean_word_count_diff": 17.7125,
21
+ "similarity_boolean": 0.18269754047779477,
22
+ "similarity_extraction": 0.2946929598848025,
23
+ "similarity_qa": 0.43210459053516387,
24
+ "similarity_summarization": 0.6143242551220788,
25
+ "similarity_unanswerable": 0.26092069496711096,
26
+ "word_count_diff_boolean": 9.0,
27
+ "word_count_diff_extraction": 7.666666666666667,
28
+ "word_count_diff_qa": 6.933333333333334,
29
+ "word_count_diff_summarization": 53.111111111111114,
30
+ "word_count_diff_unanswerable": 5.933333333333334
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 101.51641082763672,
35
+ "learning_rate": 1.59e-05,
36
+ "loss": 40.3479,
37
+ "step": 265
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 19.639965057373047,
42
+ "eval_runtime": 1.7948,
43
+ "eval_samples_per_second": 44.573,
44
+ "eval_steps_per_second": 5.572,
45
+ "step": 265
46
+ },
47
+ {
48
+ "em_boolean": 0.058823529411764705,
49
+ "em_extraction": 0.0,
50
+ "em_qa": 0.0,
51
+ "em_summarization": 0.0,
52
+ "em_unanswerable": 0.0,
53
+ "epoch": 2.0,
54
+ "mean_em": 0.0125,
55
+ "mean_similarity": 0.37655651543755086,
56
+ "mean_word_count_diff": 17.1625,
57
+ "similarity_boolean": 0.10583376435234267,
58
+ "similarity_extraction": 0.21972424462437629,
59
+ "similarity_qa": 0.5285325924555461,
60
+ "similarity_summarization": 0.6654400361908807,
61
+ "similarity_unanswerable": 0.34157160222530364,
62
+ "word_count_diff_boolean": 10.176470588235293,
63
+ "word_count_diff_extraction": 6.133333333333334,
64
+ "word_count_diff_qa": 5.866666666666666,
65
+ "word_count_diff_summarization": 52.166666666666664,
66
+ "word_count_diff_unanswerable": 5.4
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.2927296459674835,
71
+ "learning_rate": 2.9999590191302685e-05,
72
+ "loss": 1.8688,
73
+ "step": 530
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.08876434713602066,
78
+ "eval_runtime": 1.7881,
79
+ "eval_samples_per_second": 44.74,
80
+ "eval_steps_per_second": 5.593,
81
+ "step": 530
82
+ },
83
+ {
84
+ "em_boolean": 0.29411764705882354,
85
+ "em_extraction": 0.13333333333333333,
86
+ "em_qa": 0.06666666666666667,
87
+ "em_summarization": 0.0,
88
+ "em_unanswerable": 0.0,
89
+ "epoch": 3.0,
90
+ "mean_em": 0.1,
91
+ "mean_similarity": 0.468679612770211,
92
+ "mean_word_count_diff": 16.8875,
93
+ "similarity_boolean": 0.36136592250755606,
94
+ "similarity_extraction": 0.3513699695467949,
95
+ "similarity_qa": 0.5638724292318026,
96
+ "similarity_summarization": 0.661304693048199,
97
+ "similarity_unanswerable": 0.3812685254961252,
98
+ "word_count_diff_boolean": 5.411764705882353,
99
+ "word_count_diff_extraction": 8.066666666666666,
100
+ "word_count_diff_qa": 5.6,
101
+ "word_count_diff_summarization": 53.333333333333336,
102
+ "word_count_diff_unanswerable": 6.266666666666667
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "grad_norm": 0.2717432379722595,
107
+ "learning_rate": 2.9960391039419217e-05,
108
+ "loss": 0.0745,
109
+ "step": 795
110
+ },
111
+ {
112
+ "epoch": 3.0,
113
+ "eval_loss": 0.07186319679021835,
114
+ "eval_runtime": 1.7817,
115
+ "eval_samples_per_second": 44.901,
116
+ "eval_steps_per_second": 5.613,
117
+ "step": 795
118
+ },
119
+ {
120
+ "em_boolean": 0.5294117647058824,
121
+ "em_extraction": 0.0,
122
+ "em_qa": 0.0,
123
+ "em_summarization": 0.0,
124
+ "em_unanswerable": 0.0,
125
+ "epoch": 4.0,
126
+ "mean_em": 0.1125,
127
+ "mean_similarity": 0.5406636619823985,
128
+ "mean_word_count_diff": 16.4,
129
+ "similarity_boolean": 0.5694808649337467,
130
+ "similarity_extraction": 0.2759806969513496,
131
+ "similarity_qa": 0.5888164043426514,
132
+ "similarity_summarization": 0.6777413653002845,
133
+ "similarity_unanswerable": 0.5600411439935367,
134
+ "word_count_diff_boolean": 3.411764705882353,
135
+ "word_count_diff_extraction": 9.133333333333333,
136
+ "word_count_diff_qa": 5.733333333333333,
137
+ "word_count_diff_summarization": 52.611111111111114,
138
+ "word_count_diff_unanswerable": 5.6
139
+ },
140
+ {
141
+ "epoch": 4.0,
142
+ "grad_norm": 0.33120226860046387,
143
+ "learning_rate": 2.985743020616636e-05,
144
+ "loss": 0.0583,
145
+ "step": 1060
146
+ },
147
+ {
148
+ "epoch": 4.0,
149
+ "eval_loss": 0.06767071783542633,
150
+ "eval_runtime": 1.8031,
151
+ "eval_samples_per_second": 44.368,
152
+ "eval_steps_per_second": 5.546,
153
+ "step": 1060
154
+ },
155
+ {
156
+ "em_boolean": 0.35294117647058826,
157
+ "em_extraction": 0.06666666666666667,
158
+ "em_qa": 0.06666666666666667,
159
+ "em_summarization": 0.0,
160
+ "em_unanswerable": 0.0,
161
+ "epoch": 5.0,
162
+ "mean_em": 0.1,
163
+ "mean_similarity": 0.5391882328083739,
164
+ "mean_word_count_diff": 16.5375,
165
+ "similarity_boolean": 0.4291324294446146,
166
+ "similarity_extraction": 0.3934509038925171,
167
+ "similarity_qa": 0.5968125452597935,
168
+ "similarity_summarization": 0.6669783542553583,
169
+ "similarity_unanswerable": 0.5986830140153567,
170
+ "word_count_diff_boolean": 5.9411764705882355,
171
+ "word_count_diff_extraction": 5.866666666666666,
172
+ "word_count_diff_qa": 5.4,
173
+ "word_count_diff_summarization": 53.77777777777778,
174
+ "word_count_diff_unanswerable": 5.666666666666667
175
+ },
176
+ {
177
+ "epoch": 5.0,
178
+ "grad_norm": 0.05014026165008545,
179
+ "learning_rate": 2.969114651402049e-05,
180
+ "loss": 0.0512,
181
+ "step": 1325
182
+ },
183
+ {
184
+ "epoch": 5.0,
185
+ "eval_loss": 0.06544757634401321,
186
+ "eval_runtime": 1.797,
187
+ "eval_samples_per_second": 44.518,
188
+ "eval_steps_per_second": 5.565,
189
+ "step": 1325
190
+ },
191
+ {
192
+ "em_boolean": 0.35294117647058826,
193
+ "em_extraction": 0.13333333333333333,
194
+ "em_qa": 0.0,
195
+ "em_summarization": 0.0,
196
+ "em_unanswerable": 0.0,
197
+ "epoch": 6.0,
198
+ "mean_em": 0.1,
199
+ "mean_similarity": 0.5817075100494549,
200
+ "mean_word_count_diff": 16.1375,
201
+ "similarity_boolean": 0.3759182594059145,
202
+ "similarity_extraction": 0.5534958879152934,
203
+ "similarity_qa": 0.6812621881564458,
204
+ "similarity_summarization": 0.661298368126154,
205
+ "similarity_unanswerable": 0.648083241780599,
206
+ "word_count_diff_boolean": 6.294117647058823,
207
+ "word_count_diff_extraction": 4.466666666666667,
208
+ "word_count_diff_qa": 5.666666666666667,
209
+ "word_count_diff_summarization": 52.55555555555556,
210
+ "word_count_diff_unanswerable": 5.733333333333333
211
+ },
212
+ {
213
+ "epoch": 6.0,
214
+ "grad_norm": 0.37450432777404785,
215
+ "learning_rate": 2.9462248669576738e-05,
216
+ "loss": 0.0466,
217
+ "step": 1590
218
+ },
219
+ {
220
+ "epoch": 6.0,
221
+ "eval_loss": 0.0656035840511322,
222
+ "eval_runtime": 1.8115,
223
+ "eval_samples_per_second": 44.161,
224
+ "eval_steps_per_second": 5.52,
225
+ "step": 1590
226
+ },
227
+ {
228
+ "em_boolean": 0.29411764705882354,
229
+ "em_extraction": 0.06666666666666667,
230
+ "em_qa": 0.06666666666666667,
231
+ "em_summarization": 0.0,
232
+ "em_unanswerable": 0.0,
233
+ "epoch": 7.0,
234
+ "mean_em": 0.0875,
235
+ "mean_similarity": 0.584748298721388,
236
+ "mean_word_count_diff": 16.4875,
237
+ "similarity_boolean": 0.3921016369234113,
238
+ "similarity_extraction": 0.4258095269401868,
239
+ "similarity_qa": 0.8010195712248485,
240
+ "similarity_summarization": 0.7269510593679216,
241
+ "similarity_unanswerable": 0.5751053685943286,
242
+ "word_count_diff_boolean": 6.529411764705882,
243
+ "word_count_diff_extraction": 7.4,
244
+ "word_count_diff_qa": 4.266666666666667,
245
+ "word_count_diff_summarization": 51.5,
246
+ "word_count_diff_unanswerable": 7.066666666666666
247
+ },
248
+ {
249
+ "epoch": 7.0,
250
+ "grad_norm": 0.2656797170639038,
251
+ "learning_rate": 2.9171712243018076e-05,
252
+ "loss": 0.043,
253
+ "step": 1855
254
+ },
255
+ {
256
+ "epoch": 7.0,
257
+ "eval_loss": 0.06431461870670319,
258
+ "eval_runtime": 1.779,
259
+ "eval_samples_per_second": 44.968,
260
+ "eval_steps_per_second": 5.621,
261
+ "step": 1855
262
+ },
263
+ {
264
+ "em_boolean": 0.23529411764705882,
265
+ "em_extraction": 0.3333333333333333,
266
+ "em_qa": 0.13333333333333333,
267
+ "em_summarization": 0.0,
268
+ "em_unanswerable": 0.0,
269
+ "epoch": 8.0,
270
+ "mean_em": 0.1375,
271
+ "mean_similarity": 0.5707565736840479,
272
+ "mean_word_count_diff": 15.9125,
273
+ "similarity_boolean": 0.3595361856962828,
274
+ "similarity_extraction": 0.6590617413322131,
275
+ "similarity_qa": 0.6671084851026535,
276
+ "similarity_summarization": 0.672764014866617,
277
+ "similarity_unanswerable": 0.503073671584328,
278
+ "word_count_diff_boolean": 6.705882352941177,
279
+ "word_count_diff_extraction": 4.133333333333334,
280
+ "word_count_diff_qa": 4.0,
281
+ "word_count_diff_summarization": 51.833333333333336,
282
+ "word_count_diff_unanswerable": 6.933333333333334
283
+ },
284
+ {
285
+ "epoch": 8.0,
286
+ "grad_norm": 0.1501343548297882,
287
+ "learning_rate": 2.882077551020291e-05,
288
+ "loss": 0.0393,
289
+ "step": 2120
290
+ },
291
+ {
292
+ "epoch": 8.0,
293
+ "eval_loss": 0.064610555768013,
294
+ "eval_runtime": 1.7854,
295
+ "eval_samples_per_second": 44.809,
296
+ "eval_steps_per_second": 5.601,
297
+ "step": 2120
298
+ },
299
+ {
300
+ "em_boolean": 0.29411764705882354,
301
+ "em_extraction": 0.13333333333333333,
302
+ "em_qa": 0.0,
303
+ "em_summarization": 0.0,
304
+ "em_unanswerable": 0.0,
305
+ "epoch": 9.0,
306
+ "mean_em": 0.0875,
307
+ "mean_similarity": 0.5716628619702533,
308
+ "mean_word_count_diff": 16.075,
309
+ "similarity_boolean": 0.46071117371320724,
310
+ "similarity_extraction": 0.5175981452067693,
311
+ "similarity_qa": 0.6631501737982035,
312
+ "similarity_summarization": 0.6426751317663325,
313
+ "similarity_unanswerable": 0.5747707898418108,
314
+ "word_count_diff_boolean": 5.235294117647059,
315
+ "word_count_diff_extraction": 7.333333333333333,
316
+ "word_count_diff_qa": 5.6,
317
+ "word_count_diff_summarization": 52.22222222222222,
318
+ "word_count_diff_unanswerable": 4.2
319
+ },
320
+ {
321
+ "epoch": 9.0,
322
+ "grad_norm": 0.23849624395370483,
323
+ "learning_rate": 2.8410934175092426e-05,
324
+ "loss": 0.0363,
325
+ "step": 2385
326
+ },
327
+ {
328
+ "epoch": 9.0,
329
+ "eval_loss": 0.06528123468160629,
330
+ "eval_runtime": 1.7964,
331
+ "eval_samples_per_second": 44.533,
332
+ "eval_steps_per_second": 5.567,
333
+ "step": 2385
334
+ },
335
+ {
336
+ "em_boolean": 0.4117647058823529,
337
+ "em_extraction": 0.13333333333333333,
338
+ "em_qa": 0.06666666666666667,
339
+ "em_summarization": 0.0,
340
+ "em_unanswerable": 0.0,
341
+ "epoch": 10.0,
342
+ "mean_em": 0.125,
343
+ "mean_similarity": 0.5984957347856834,
344
+ "mean_word_count_diff": 16.2375,
345
+ "similarity_boolean": 0.4425226738128592,
346
+ "similarity_extraction": 0.5075533439715704,
347
+ "similarity_qa": 0.6813998910288016,
348
+ "similarity_summarization": 0.6938931312825944,
349
+ "similarity_unanswerable": 0.6688265626629194,
350
+ "word_count_diff_boolean": 5.352941176470588,
351
+ "word_count_diff_extraction": 6.466666666666667,
352
+ "word_count_diff_qa": 6.2,
353
+ "word_count_diff_summarization": 52.166666666666664,
354
+ "word_count_diff_unanswerable": 5.266666666666667
355
+ },
356
+ {
357
+ "epoch": 10.0,
358
+ "grad_norm": 0.2859129309654236,
359
+ "learning_rate": 2.7943934995010845e-05,
360
+ "loss": 0.0338,
361
+ "step": 2650
362
+ },
363
+ {
364
+ "epoch": 10.0,
365
+ "eval_loss": 0.06541204452514648,
366
+ "eval_runtime": 1.7939,
367
+ "eval_samples_per_second": 44.595,
368
+ "eval_steps_per_second": 5.574,
369
+ "step": 2650
370
+ },
371
+ {
372
+ "em_boolean": 0.35294117647058826,
373
+ "em_extraction": 0.2,
374
+ "em_qa": 0.06666666666666667,
375
+ "em_summarization": 0.0,
376
+ "em_unanswerable": 0.0,
377
+ "epoch": 11.0,
378
+ "mean_em": 0.125,
379
+ "mean_similarity": 0.584741565072909,
380
+ "mean_word_count_diff": 15.85,
381
+ "similarity_boolean": 0.41579638640670213,
382
+ "similarity_extraction": 0.575649573157231,
383
+ "similarity_qa": 0.68668532371521,
384
+ "similarity_summarization": 0.7162102411190668,
385
+ "similarity_unanswerable": 0.5255985895792643,
386
+ "word_count_diff_boolean": 5.0,
387
+ "word_count_diff_extraction": 4.333333333333333,
388
+ "word_count_diff_qa": 5.4,
389
+ "word_count_diff_summarization": 51.72222222222222,
390
+ "word_count_diff_unanswerable": 7.066666666666666
391
+ },
392
+ {
393
+ "epoch": 11.0,
394
+ "grad_norm": 0.19708961248397827,
395
+ "learning_rate": 2.7421768335907942e-05,
396
+ "loss": 0.0314,
397
+ "step": 2915
398
+ },
399
+ {
400
+ "epoch": 11.0,
401
+ "eval_loss": 0.06535650044679642,
402
+ "eval_runtime": 1.7968,
403
+ "eval_samples_per_second": 44.525,
404
+ "eval_steps_per_second": 5.566,
405
+ "step": 2915
406
+ },
407
+ {
408
+ "em_boolean": 0.4117647058823529,
409
+ "em_extraction": 0.13333333333333333,
410
+ "em_qa": 0.06666666666666667,
411
+ "em_summarization": 0.0,
412
+ "em_unanswerable": 0.0,
413
+ "epoch": 12.0,
414
+ "mean_em": 0.125,
415
+ "mean_similarity": 0.5985993921523913,
416
+ "mean_word_count_diff": 15.65,
417
+ "similarity_boolean": 0.49136487109696164,
418
+ "similarity_extraction": 0.4834645986557007,
419
+ "similarity_qa": 0.7439890225728353,
420
+ "similarity_summarization": 0.7199151118596395,
421
+ "similarity_unanswerable": 0.5442981487760942,
422
+ "word_count_diff_boolean": 5.294117647058823,
423
+ "word_count_diff_extraction": 6.466666666666667,
424
+ "word_count_diff_qa": 5.0,
425
+ "word_count_diff_summarization": 51.333333333333336,
426
+ "word_count_diff_unanswerable": 4.4
427
+ },
428
+ {
429
+ "epoch": 12.0,
430
+ "grad_norm": 0.32636699080467224,
431
+ "learning_rate": 2.6846659689353532e-05,
432
+ "loss": 0.0291,
433
+ "step": 3180
434
+ },
435
+ {
436
+ "epoch": 12.0,
437
+ "eval_loss": 0.06654994189739227,
438
+ "eval_runtime": 1.7794,
439
+ "eval_samples_per_second": 44.96,
440
+ "eval_steps_per_second": 5.62,
441
+ "step": 3180
442
+ },
443
+ {
444
+ "em_boolean": 0.29411764705882354,
445
+ "em_extraction": 0.2,
446
+ "em_qa": 0.13333333333333333,
447
+ "em_summarization": 0.0,
448
+ "em_unanswerable": 0.0,
449
+ "epoch": 13.0,
450
+ "mean_em": 0.125,
451
+ "mean_similarity": 0.5608657638425939,
452
+ "mean_word_count_diff": 15.4875,
453
+ "similarity_boolean": 0.3726646105265793,
454
+ "similarity_extraction": 0.4880456611514091,
455
+ "similarity_qa": 0.6968116387724876,
456
+ "similarity_summarization": 0.7003769092261791,
457
+ "similarity_unanswerable": 0.5436212575683991,
458
+ "word_count_diff_boolean": 6.470588235294118,
459
+ "word_count_diff_extraction": 4.0,
460
+ "word_count_diff_qa": 4.266666666666667,
461
+ "word_count_diff_summarization": 50.22222222222222,
462
+ "word_count_diff_unanswerable": 6.733333333333333
463
+ },
464
+ {
465
+ "epoch": 13.0,
466
+ "grad_norm": 0.09956305474042892,
467
+ "learning_rate": 2.622106018741882e-05,
468
+ "loss": 0.0268,
469
+ "step": 3445
470
+ },
471
+ {
472
+ "epoch": 13.0,
473
+ "eval_loss": 0.06867102533578873,
474
+ "eval_runtime": 1.7923,
475
+ "eval_samples_per_second": 44.635,
476
+ "eval_steps_per_second": 5.579,
477
+ "step": 3445
478
+ },
479
+ {
480
+ "em_boolean": 0.4117647058823529,
481
+ "em_extraction": 0.13333333333333333,
482
+ "em_qa": 0.06666666666666667,
483
+ "em_summarization": 0.0,
484
+ "em_unanswerable": 0.0,
485
+ "epoch": 14.0,
486
+ "mean_em": 0.125,
487
+ "mean_similarity": 0.6118219185853377,
488
+ "mean_word_count_diff": 15.1,
489
+ "similarity_boolean": 0.5559550164376988,
490
+ "similarity_extraction": 0.4480490814894438,
491
+ "similarity_qa": 0.8226341267426809,
492
+ "similarity_summarization": 0.7094271017445458,
493
+ "similarity_unanswerable": 0.5109721501668294,
494
+ "word_count_diff_boolean": 3.235294117647059,
495
+ "word_count_diff_extraction": 5.333333333333333,
496
+ "word_count_diff_qa": 4.066666666666666,
497
+ "word_count_diff_summarization": 51.333333333333336,
498
+ "word_count_diff_unanswerable": 5.866666666666666
499
+ },
500
+ {
501
+ "epoch": 14.0,
502
+ "grad_norm": 0.2182687222957611,
503
+ "learning_rate": 2.554763615587042e-05,
504
+ "loss": 0.0254,
505
+ "step": 3710
506
+ },
507
+ {
508
+ "epoch": 14.0,
509
+ "eval_loss": 0.06904994696378708,
510
+ "eval_runtime": 1.7971,
511
+ "eval_samples_per_second": 44.517,
512
+ "eval_steps_per_second": 5.565,
513
+ "step": 3710
514
+ },
515
+ {
516
+ "em_boolean": 0.17647058823529413,
517
+ "em_extraction": 0.13333333333333333,
518
+ "em_qa": 0.13333333333333333,
519
+ "em_summarization": 0.0,
520
+ "em_unanswerable": 0.0,
521
+ "epoch": 15.0,
522
+ "mean_em": 0.0875,
523
+ "mean_similarity": 0.5906956384656951,
524
+ "mean_word_count_diff": 15.8,
525
+ "similarity_boolean": 0.30824649366824064,
526
+ "similarity_extraction": 0.5498731901248296,
527
+ "similarity_qa": 0.7911941662430764,
528
+ "similarity_summarization": 0.7216936614778307,
529
+ "similarity_unanswerable": 0.5939309621850649,
530
+ "word_count_diff_boolean": 5.294117647058823,
531
+ "word_count_diff_extraction": 5.533333333333333,
532
+ "word_count_diff_qa": 4.933333333333334,
533
+ "word_count_diff_summarization": 50.833333333333336,
534
+ "word_count_diff_unanswerable": 6.8
535
+ },
536
+ {
537
+ "epoch": 15.0,
538
+ "grad_norm": 0.278495728969574,
539
+ "learning_rate": 2.4829257750201806e-05,
540
+ "loss": 0.0235,
541
+ "step": 3975
542
+ },
543
+ {
544
+ "epoch": 15.0,
545
+ "eval_loss": 0.07152120769023895,
546
+ "eval_runtime": 1.8045,
547
+ "eval_samples_per_second": 44.334,
548
+ "eval_steps_per_second": 5.542,
549
+ "step": 3975
550
+ },
551
+ {
552
+ "em_boolean": 0.35294117647058826,
553
+ "em_extraction": 0.13333333333333333,
554
+ "em_qa": 0.06666666666666667,
555
+ "em_summarization": 0.0,
556
+ "em_unanswerable": 0.0,
557
+ "epoch": 16.0,
558
+ "mean_em": 0.1125,
559
+ "mean_similarity": 0.6044320391491056,
560
+ "mean_word_count_diff": 15.3625,
561
+ "similarity_boolean": 0.4709787254824358,
562
+ "similarity_extraction": 0.48890374253193536,
563
+ "similarity_qa": 0.7086231042941411,
564
+ "similarity_summarization": 0.6860101450648572,
565
+ "similarity_unanswerable": 0.6691226323445638,
566
+ "word_count_diff_boolean": 5.176470588235294,
567
+ "word_count_diff_extraction": 4.133333333333334,
568
+ "word_count_diff_qa": 5.8,
569
+ "word_count_diff_summarization": 51.388888888888886,
570
+ "word_count_diff_unanswerable": 4.466666666666667
571
+ },
572
+ {
573
+ "epoch": 16.0,
574
+ "grad_norm": 0.12528866529464722,
575
+ "learning_rate": 2.4068986722935625e-05,
576
+ "loss": 0.0219,
577
+ "step": 4240
578
+ },
579
+ {
580
+ "epoch": 16.0,
581
+ "eval_loss": 0.07122211903333664,
582
+ "eval_runtime": 1.7912,
583
+ "eval_samples_per_second": 44.663,
584
+ "eval_steps_per_second": 5.583,
585
+ "step": 4240
586
+ },
587
+ {
588
+ "em_boolean": 0.23529411764705882,
589
+ "em_extraction": 0.2,
590
+ "em_qa": 0.06666666666666667,
591
+ "em_summarization": 0.0,
592
+ "em_unanswerable": 0.0,
593
+ "epoch": 17.0,
594
+ "mean_em": 0.1,
595
+ "mean_similarity": 0.5854583959793672,
596
+ "mean_word_count_diff": 16.1125,
597
+ "similarity_boolean": 0.3930098557954325,
598
+ "similarity_extraction": 0.5295473781724771,
599
+ "similarity_qa": 0.7186618636051814,
600
+ "similarity_summarization": 0.6619544287936555,
601
+ "similarity_unanswerable": 0.6344790523250897,
602
+ "word_count_diff_boolean": 5.764705882352941,
603
+ "word_count_diff_extraction": 5.066666666666666,
604
+ "word_count_diff_qa": 6.066666666666666,
605
+ "word_count_diff_summarization": 52.22222222222222,
606
+ "word_count_diff_unanswerable": 5.6
607
+ },
608
+ {
609
+ "epoch": 17.0,
610
+ "grad_norm": 0.18347615003585815,
611
+ "learning_rate": 2.327006337433323e-05,
612
+ "loss": 0.0208,
613
+ "step": 4505
614
+ },
615
+ {
616
+ "epoch": 17.0,
617
+ "eval_loss": 0.07514352351427078,
618
+ "eval_runtime": 1.7952,
619
+ "eval_samples_per_second": 44.563,
620
+ "eval_steps_per_second": 5.57,
621
+ "step": 4505
622
+ },
623
+ {
624
+ "em_boolean": 0.35294117647058826,
625
+ "em_extraction": 0.13333333333333333,
626
+ "em_qa": 0.06666666666666667,
627
+ "em_summarization": 0.0,
628
+ "em_unanswerable": 0.0,
629
+ "epoch": 18.0,
630
+ "mean_em": 0.1125,
631
+ "mean_similarity": 0.6148898253683001,
632
+ "mean_word_count_diff": 15.95,
633
+ "similarity_boolean": 0.45182113108389516,
634
+ "similarity_extraction": 0.5246008743842443,
635
+ "similarity_qa": 0.7161807785431544,
636
+ "similarity_summarization": 0.695978145632479,
637
+ "similarity_unanswerable": 0.6913930257161458,
638
+ "word_count_diff_boolean": 6.705882352941177,
639
+ "word_count_diff_extraction": 5.333333333333333,
640
+ "word_count_diff_qa": 5.133333333333334,
641
+ "word_count_diff_summarization": 51.72222222222222,
642
+ "word_count_diff_unanswerable": 4.933333333333334
643
+ },
644
+ {
645
+ "epoch": 18.0,
646
+ "grad_norm": 0.39281344413757324,
647
+ "learning_rate": 2.2435892742127786e-05,
648
+ "loss": 0.0197,
649
+ "step": 4770
650
+ },
651
+ {
652
+ "epoch": 18.0,
653
+ "eval_loss": 0.07489313185214996,
654
+ "eval_runtime": 1.7966,
655
+ "eval_samples_per_second": 44.528,
656
+ "eval_steps_per_second": 5.566,
657
+ "step": 4770
658
+ },
659
+ {
660
+ "em_boolean": 0.35294117647058826,
661
+ "em_extraction": 0.13333333333333333,
662
+ "em_qa": 0.06666666666666667,
663
+ "em_summarization": 0.0,
664
+ "em_unanswerable": 0.0,
665
+ "epoch": 19.0,
666
+ "mean_em": 0.1125,
667
+ "mean_similarity": 0.6110048872418702,
668
+ "mean_word_count_diff": 15.175,
669
+ "similarity_boolean": 0.4688412766246235,
670
+ "similarity_extraction": 0.5354909280935923,
671
+ "similarity_qa": 0.7334268649419149,
672
+ "similarity_summarization": 0.6523812972009182,
673
+ "similarity_unanswerable": 0.6755639354387919,
674
+ "word_count_diff_boolean": 5.411764705882353,
675
+ "word_count_diff_extraction": 3.6666666666666665,
676
+ "word_count_diff_qa": 5.333333333333333,
677
+ "word_count_diff_summarization": 51.27777777777778,
678
+ "word_count_diff_unanswerable": 4.266666666666667
679
+ },
680
+ {
681
+ "epoch": 19.0,
682
+ "grad_norm": 0.26503777503967285,
683
+ "learning_rate": 2.1570030089140857e-05,
684
+ "loss": 0.0184,
685
+ "step": 5035
686
+ },
687
+ {
688
+ "epoch": 19.0,
689
+ "eval_loss": 0.07855142652988434,
690
+ "eval_runtime": 1.7852,
691
+ "eval_samples_per_second": 44.813,
692
+ "eval_steps_per_second": 5.602,
693
+ "step": 5035
694
+ },
695
+ {
696
+ "em_boolean": 0.058823529411764705,
697
+ "em_extraction": 0.26666666666666666,
698
+ "em_qa": 0.0,
699
+ "em_summarization": 0.0,
700
+ "em_unanswerable": 0.0,
701
+ "epoch": 20.0,
702
+ "mean_em": 0.0625,
703
+ "mean_similarity": 0.5894458804745227,
704
+ "mean_word_count_diff": 15.7625,
705
+ "similarity_boolean": 0.3066763941417722,
706
+ "similarity_extraction": 0.567964817583561,
707
+ "similarity_qa": 0.7356137126684189,
708
+ "similarity_summarization": 0.7311095827155643,
709
+ "similarity_unanswerable": 0.615234752992789,
710
+ "word_count_diff_boolean": 7.0588235294117645,
711
+ "word_count_diff_extraction": 4.133333333333334,
712
+ "word_count_diff_qa": 6.4,
713
+ "word_count_diff_summarization": 50.833333333333336,
714
+ "word_count_diff_unanswerable": 4.533333333333333
715
+ },
716
+ {
717
+ "epoch": 20.0,
718
+ "grad_norm": 0.325967013835907,
719
+ "learning_rate": 2.0676165750634656e-05,
720
+ "loss": 0.0173,
721
+ "step": 5300
722
+ },
723
+ {
724
+ "epoch": 20.0,
725
+ "eval_loss": 0.07865440845489502,
726
+ "eval_runtime": 1.7895,
727
+ "eval_samples_per_second": 44.705,
728
+ "eval_steps_per_second": 5.588,
729
+ "step": 5300
730
+ },
731
+ {
732
+ "em_boolean": 0.5294117647058824,
733
+ "em_extraction": 0.26666666666666666,
734
+ "em_qa": 0.06666666666666667,
735
+ "em_summarization": 0.0,
736
+ "em_unanswerable": 0.0,
737
+ "epoch": 21.0,
738
+ "mean_em": 0.175,
739
+ "mean_similarity": 0.6464177187765017,
740
+ "mean_word_count_diff": 14.8375,
741
+ "similarity_boolean": 0.6461278642801678,
742
+ "similarity_extraction": 0.6178931772708893,
743
+ "similarity_qa": 0.7566967884699504,
744
+ "similarity_summarization": 0.6613570315142473,
745
+ "similarity_unanswerable": 0.5470645170658827,
746
+ "word_count_diff_boolean": 3.176470588235294,
747
+ "word_count_diff_extraction": 5.4,
748
+ "word_count_diff_qa": 4.6,
749
+ "word_count_diff_summarization": 50.5,
750
+ "word_count_diff_unanswerable": 4.933333333333334
751
+ },
752
+ {
753
+ "epoch": 21.0,
754
+ "grad_norm": 0.18580074608325958,
755
+ "learning_rate": 1.975810940598114e-05,
756
+ "loss": 0.0162,
757
+ "step": 5565
758
+ },
759
+ {
760
+ "epoch": 21.0,
761
+ "eval_loss": 0.08283738046884537,
762
+ "eval_runtime": 1.8062,
763
+ "eval_samples_per_second": 44.292,
764
+ "eval_steps_per_second": 5.537,
765
+ "step": 5565
766
+ },
767
+ {
768
+ "em_boolean": 0.47058823529411764,
769
+ "em_extraction": 0.26666666666666666,
770
+ "em_qa": 0.06666666666666667,
771
+ "em_summarization": 0.0,
772
+ "em_unanswerable": 0.0,
773
+ "epoch": 22.0,
774
+ "mean_em": 0.1625,
775
+ "mean_similarity": 0.6508607531315647,
776
+ "mean_word_count_diff": 15.1875,
777
+ "similarity_boolean": 0.5319088667302447,
778
+ "similarity_extraction": 0.6322630804032088,
779
+ "similarity_qa": 0.7358093798160553,
780
+ "similarity_summarization": 0.6958086478213469,
781
+ "similarity_unanswerable": 0.6653844634691874,
782
+ "word_count_diff_boolean": 5.352941176470588,
783
+ "word_count_diff_extraction": 3.933333333333333,
784
+ "word_count_diff_qa": 5.266666666666667,
785
+ "word_count_diff_summarization": 51.166666666666664,
786
+ "word_count_diff_unanswerable": 4.333333333333333
787
+ },
788
+ {
789
+ "epoch": 22.0,
790
+ "grad_norm": 0.7463592886924744,
791
+ "learning_rate": 1.881977384168254e-05,
792
+ "loss": 0.0158,
793
+ "step": 5830
794
+ },
795
+ {
796
+ "epoch": 22.0,
797
+ "eval_loss": 0.08268458396196365,
798
+ "eval_runtime": 1.7886,
799
+ "eval_samples_per_second": 44.728,
800
+ "eval_steps_per_second": 5.591,
801
+ "step": 5830
802
+ },
803
+ {
804
+ "em_boolean": 0.4117647058823529,
805
+ "em_extraction": 0.2,
806
+ "em_qa": 0.13333333333333333,
807
+ "em_summarization": 0.0,
808
+ "em_unanswerable": 0.0,
809
+ "epoch": 23.0,
810
+ "mean_em": 0.15,
811
+ "mean_similarity": 0.6376353252329864,
812
+ "mean_word_count_diff": 15.5625,
813
+ "similarity_boolean": 0.5682552300722283,
814
+ "similarity_extraction": 0.5148679026712973,
815
+ "similarity_qa": 0.7483514944712321,
816
+ "similarity_summarization": 0.7200961951166391,
817
+ "similarity_unanswerable": 0.629364309211572,
818
+ "word_count_diff_boolean": 3.823529411764706,
819
+ "word_count_diff_extraction": 5.266666666666667,
820
+ "word_count_diff_qa": 4.933333333333334,
821
+ "word_count_diff_summarization": 51.388888888888886,
822
+ "word_count_diff_unanswerable": 6.8
823
+ },
824
+ {
825
+ "epoch": 23.0,
826
+ "grad_norm": 0.30431216955184937,
827
+ "learning_rate": 1.7865158274945846e-05,
828
+ "loss": 0.0149,
829
+ "step": 6095
830
+ },
831
+ {
832
+ "epoch": 23.0,
833
+ "eval_loss": 0.08500902354717255,
834
+ "eval_runtime": 1.8006,
835
+ "eval_samples_per_second": 44.43,
836
+ "eval_steps_per_second": 5.554,
837
+ "step": 6095
838
+ },
839
+ {
840
+ "em_boolean": 0.35294117647058826,
841
+ "em_extraction": 0.2,
842
+ "em_qa": 0.0,
843
+ "em_summarization": 0.0,
844
+ "em_unanswerable": 0.0,
845
+ "epoch": 24.0,
846
+ "mean_em": 0.1125,
847
+ "mean_similarity": 0.6209718830883503,
848
+ "mean_word_count_diff": 15.625,
849
+ "similarity_boolean": 0.4452236132586704,
850
+ "similarity_extraction": 0.5458283141255379,
851
+ "similarity_qa": 0.7422831366459529,
852
+ "similarity_summarization": 0.7023132857349184,
853
+ "similarity_unanswerable": 0.6763758877913157,
854
+ "word_count_diff_boolean": 5.470588235294118,
855
+ "word_count_diff_extraction": 5.6,
856
+ "word_count_diff_qa": 5.533333333333333,
857
+ "word_count_diff_summarization": 51.611111111111114,
858
+ "word_count_diff_unanswerable": 4.066666666666666
859
+ },
860
+ {
861
+ "epoch": 24.0,
862
+ "grad_norm": 0.1550023853778839,
863
+ "learning_rate": 1.6898331308886863e-05,
864
+ "loss": 0.0138,
865
+ "step": 6360
866
+ },
867
+ {
868
+ "epoch": 24.0,
869
+ "eval_loss": 0.08557449281215668,
870
+ "eval_runtime": 1.7865,
871
+ "eval_samples_per_second": 44.78,
872
+ "eval_steps_per_second": 5.598,
873
+ "step": 6360
874
+ },
875
+ {
876
+ "em_boolean": 0.4117647058823529,
877
+ "em_extraction": 0.26666666666666666,
878
+ "em_qa": 0.13333333333333333,
879
+ "em_summarization": 0.0,
880
+ "em_unanswerable": 0.0,
881
+ "epoch": 25.0,
882
+ "mean_em": 0.1625,
883
+ "mean_similarity": 0.6411203743191436,
884
+ "mean_word_count_diff": 15.1875,
885
+ "similarity_boolean": 0.5644924241830321,
886
+ "similarity_extraction": 0.5594843897968531,
887
+ "similarity_qa": 0.7792828718821208,
888
+ "similarity_summarization": 0.6979754573355118,
889
+ "similarity_unanswerable": 0.6032127718130748,
890
+ "word_count_diff_boolean": 3.7058823529411766,
891
+ "word_count_diff_extraction": 4.533333333333333,
892
+ "word_count_diff_qa": 4.933333333333334,
893
+ "word_count_diff_summarization": 51.833333333333336,
894
+ "word_count_diff_unanswerable": 5.133333333333334
895
+ },
896
+ {
897
+ "epoch": 25.0,
898
+ "grad_norm": 0.23536083102226257,
899
+ "learning_rate": 1.5923413592009145e-05,
900
+ "loss": 0.0132,
901
+ "step": 6625
902
+ },
903
+ {
904
+ "epoch": 25.0,
905
+ "eval_loss": 0.0886365994811058,
906
+ "eval_runtime": 1.7918,
907
+ "eval_samples_per_second": 44.648,
908
+ "eval_steps_per_second": 5.581,
909
+ "step": 6625
910
+ },
911
+ {
912
+ "em_boolean": 0.29411764705882354,
913
+ "em_extraction": 0.13333333333333333,
914
+ "em_qa": 0.0,
915
+ "em_summarization": 0.0,
916
+ "em_unanswerable": 0.0,
917
+ "epoch": 26.0,
918
+ "mean_em": 0.0875,
919
+ "mean_similarity": 0.5999299102462828,
920
+ "mean_word_count_diff": 15.6625,
921
+ "similarity_boolean": 0.44055906716076765,
922
+ "similarity_extraction": 0.4907683741301298,
923
+ "similarity_qa": 0.64702517837286,
924
+ "similarity_summarization": 0.7336946874856949,
925
+ "similarity_unanswerable": 0.6820987343788147,
926
+ "word_count_diff_boolean": 5.9411764705882355,
927
+ "word_count_diff_extraction": 5.466666666666667,
928
+ "word_count_diff_qa": 7.066666666666666,
929
+ "word_count_diff_summarization": 50.27777777777778,
930
+ "word_count_diff_unanswerable": 3.933333333333333
931
+ },
932
+ {
933
+ "epoch": 26.0,
934
+ "grad_norm": 0.0521920807659626,
935
+ "learning_rate": 1.4944560255863805e-05,
936
+ "loss": 0.0127,
937
+ "step": 6890
938
+ },
939
+ {
940
+ "epoch": 26.0,
941
+ "eval_loss": 0.09115185588598251,
942
+ "eval_runtime": 1.7871,
943
+ "eval_samples_per_second": 44.764,
944
+ "eval_steps_per_second": 5.596,
945
+ "step": 6890
946
+ },
947
+ {
948
+ "em_boolean": 0.29411764705882354,
949
+ "em_extraction": 0.2,
950
+ "em_qa": 0.06666666666666667,
951
+ "em_summarization": 0.0,
952
+ "em_unanswerable": 0.0,
953
+ "epoch": 27.0,
954
+ "mean_em": 0.1125,
955
+ "mean_similarity": 0.5961971989367157,
956
+ "mean_word_count_diff": 15.9,
957
+ "similarity_boolean": 0.47167208264855776,
958
+ "similarity_extraction": 0.563706802825133,
959
+ "similarity_qa": 0.6419207287331422,
960
+ "similarity_summarization": 0.6927380098236932,
961
+ "similarity_unanswerable": 0.608243557314078,
962
+ "word_count_diff_boolean": 5.0,
963
+ "word_count_diff_extraction": 4.933333333333334,
964
+ "word_count_diff_qa": 6.0,
965
+ "word_count_diff_summarization": 52.0,
966
+ "word_count_diff_unanswerable": 5.8
967
+ },
968
+ {
969
+ "epoch": 27.0,
970
+ "grad_norm": 0.23173846304416656,
971
+ "learning_rate": 1.396594320574144e-05,
972
+ "loss": 0.0121,
973
+ "step": 7155
974
+ },
975
+ {
976
+ "epoch": 27.0,
977
+ "eval_loss": 0.09045173972845078,
978
+ "eval_runtime": 1.7961,
979
+ "eval_samples_per_second": 44.541,
980
+ "eval_steps_per_second": 5.568,
981
+ "step": 7155
982
+ },
983
+ {
984
+ "em_boolean": 0.5294117647058824,
985
+ "em_extraction": 0.13333333333333333,
986
+ "em_qa": 0.06666666666666667,
987
+ "em_summarization": 0.0,
988
+ "em_unanswerable": 0.0,
989
+ "epoch": 28.0,
990
+ "mean_em": 0.15,
991
+ "mean_similarity": 0.6426682359306142,
992
+ "mean_word_count_diff": 15.4625,
993
+ "similarity_boolean": 0.6154902246506775,
994
+ "similarity_extraction": 0.559150509784619,
995
+ "similarity_qa": 0.7585609555244446,
996
+ "similarity_summarization": 0.7132770286666023,
997
+ "similarity_unanswerable": 0.5563644373168548,
998
+ "word_count_diff_boolean": 3.9411764705882355,
999
+ "word_count_diff_extraction": 5.933333333333334,
1000
+ "word_count_diff_qa": 5.4,
1001
+ "word_count_diff_summarization": 51.94444444444444,
1002
+ "word_count_diff_unanswerable": 4.333333333333333
1003
+ },
1004
+ {
1005
+ "epoch": 28.0,
1006
+ "grad_norm": 0.15653730928897858,
1007
+ "learning_rate": 1.2991733339873795e-05,
1008
+ "loss": 0.0114,
1009
+ "step": 7420
1010
+ },
1011
+ {
1012
+ "epoch": 28.0,
1013
+ "eval_loss": 0.09521345049142838,
1014
+ "eval_runtime": 1.7969,
1015
+ "eval_samples_per_second": 44.521,
1016
+ "eval_steps_per_second": 5.565,
1017
+ "step": 7420
1018
+ },
1019
+ {
1020
+ "em_boolean": 0.5882352941176471,
1021
+ "em_extraction": 0.2,
1022
+ "em_qa": 0.0,
1023
+ "em_summarization": 0.0,
1024
+ "em_unanswerable": 0.0,
1025
+ "epoch": 29.0,
1026
+ "mean_em": 0.1625,
1027
+ "mean_similarity": 0.670323112141341,
1028
+ "mean_word_count_diff": 14.8125,
1029
+ "similarity_boolean": 0.6801450522068668,
1030
+ "similarity_extraction": 0.5754425642391046,
1031
+ "similarity_qa": 0.7391265859206517,
1032
+ "similarity_summarization": 0.7395255797439151,
1033
+ "similarity_unanswerable": 0.6022256930669149,
1034
+ "word_count_diff_boolean": 2.588235294117647,
1035
+ "word_count_diff_extraction": 4.0,
1036
+ "word_count_diff_qa": 5.666666666666667,
1037
+ "word_count_diff_summarization": 50.333333333333336,
1038
+ "word_count_diff_unanswerable": 6.0
1039
+ },
1040
+ {
1041
+ "epoch": 29.0,
1042
+ "grad_norm": 0.13572590053081512,
1043
+ "learning_rate": 1.2026082772927574e-05,
1044
+ "loss": 0.0112,
1045
+ "step": 7685
1046
+ },
1047
+ {
1048
+ "epoch": 29.0,
1049
+ "eval_loss": 0.09561847150325775,
1050
+ "eval_runtime": 1.7863,
1051
+ "eval_samples_per_second": 44.786,
1052
+ "eval_steps_per_second": 5.598,
1053
+ "step": 7685
1054
+ },
1055
+ {
1056
+ "em_boolean": 0.47058823529411764,
1057
+ "em_extraction": 0.26666666666666666,
1058
+ "em_qa": 0.06666666666666667,
1059
+ "em_summarization": 0.0,
1060
+ "em_unanswerable": 0.0,
1061
+ "epoch": 30.0,
1062
+ "mean_em": 0.1625,
1063
+ "mean_similarity": 0.6361284551327117,
1064
+ "mean_word_count_diff": 15.1625,
1065
+ "similarity_boolean": 0.5678887126748177,
1066
+ "similarity_extraction": 0.528444591164589,
1067
+ "similarity_qa": 0.7746080329020818,
1068
+ "similarity_summarization": 0.7153815428415934,
1069
+ "similarity_unanswerable": 0.5875674108664195,
1070
+ "word_count_diff_boolean": 3.6470588235294117,
1071
+ "word_count_diff_extraction": 4.2,
1072
+ "word_count_diff_qa": 5.666666666666667,
1073
+ "word_count_diff_summarization": 51.05555555555556,
1074
+ "word_count_diff_unanswerable": 5.6
1075
+ },
1076
+ {
1077
+ "epoch": 30.0,
1078
+ "grad_norm": 0.11106608062982559,
1079
+ "learning_rate": 1.1073107139554395e-05,
1080
+ "loss": 0.0111,
1081
+ "step": 7950
1082
+ },
1083
+ {
1084
+ "epoch": 30.0,
1085
+ "eval_loss": 0.09475980699062347,
1086
+ "eval_runtime": 1.8027,
1087
+ "eval_samples_per_second": 44.379,
1088
+ "eval_steps_per_second": 5.547,
1089
+ "step": 7950
1090
+ },
1091
+ {
1092
+ "em_boolean": 0.47058823529411764,
1093
+ "em_extraction": 0.0,
1094
+ "em_qa": 0.06666666666666667,
1095
+ "em_summarization": 0.0,
1096
+ "em_unanswerable": 0.0,
1097
+ "epoch": 31.0,
1098
+ "mean_em": 0.1125,
1099
+ "mean_similarity": 0.5996635487768799,
1100
+ "mean_word_count_diff": 15.9625,
1101
+ "similarity_boolean": 0.5703230380792829,
1102
+ "similarity_extraction": 0.43614052472015225,
1103
+ "similarity_qa": 0.6746748656034469,
1104
+ "similarity_summarization": 0.6909497512711419,
1105
+ "similarity_unanswerable": 0.6118843918045361,
1106
+ "word_count_diff_boolean": 4.176470588235294,
1107
+ "word_count_diff_extraction": 6.933333333333334,
1108
+ "word_count_diff_qa": 6.466666666666667,
1109
+ "word_count_diff_summarization": 51.888888888888886,
1110
+ "word_count_diff_unanswerable": 4.733333333333333
1111
+ },
1112
+ {
1113
+ "epoch": 31.0,
1114
+ "grad_norm": 0.15586383640766144,
1115
+ "learning_rate": 1.0136868053419842e-05,
1116
+ "loss": 0.0105,
1117
+ "step": 8215
1118
+ },
1119
+ {
1120
+ "epoch": 31.0,
1121
+ "eval_loss": 0.09651915729045868,
1122
+ "eval_runtime": 1.7878,
1123
+ "eval_samples_per_second": 44.749,
1124
+ "eval_steps_per_second": 5.594,
1125
+ "step": 8215
1126
+ },
1127
+ {
1128
+ "em_boolean": 0.35294117647058826,
1129
+ "em_extraction": 0.26666666666666666,
1130
+ "em_qa": 0.0,
1131
+ "em_summarization": 0.0,
1132
+ "em_unanswerable": 0.0,
1133
+ "epoch": 32.0,
1134
+ "mean_em": 0.125,
1135
+ "mean_similarity": 0.6647563714534044,
1136
+ "mean_word_count_diff": 15.3125,
1137
+ "similarity_boolean": 0.4992627663647427,
1138
+ "similarity_extraction": 0.6371853078405062,
1139
+ "similarity_qa": 0.7779242674509684,
1140
+ "similarity_summarization": 0.7545208003785875,
1141
+ "similarity_unanswerable": 0.6590016434590021,
1142
+ "word_count_diff_boolean": 4.352941176470588,
1143
+ "word_count_diff_extraction": 3.6666666666666665,
1144
+ "word_count_diff_qa": 7.133333333333334,
1145
+ "word_count_diff_summarization": 52.22222222222222,
1146
+ "word_count_diff_unanswerable": 3.2666666666666666
1147
+ },
1148
+ {
1149
+ "epoch": 32.0,
1150
+ "grad_norm": 0.15895779430866241,
1151
+ "learning_rate": 9.22135579647165e-06,
1152
+ "loss": 0.0103,
1153
+ "step": 8480
1154
+ },
1155
+ {
1156
+ "epoch": 32.0,
1157
+ "eval_loss": 0.09846033155918121,
1158
+ "eval_runtime": 1.7981,
1159
+ "eval_samples_per_second": 44.492,
1160
+ "eval_steps_per_second": 5.562,
1161
+ "step": 8480
1162
+ },
1163
+ {
1164
+ "em_boolean": 0.35294117647058826,
1165
+ "em_extraction": 0.13333333333333333,
1166
+ "em_qa": 0.0,
1167
+ "em_summarization": 0.0,
1168
+ "em_unanswerable": 0.0,
1169
+ "epoch": 33.0,
1170
+ "mean_em": 0.1,
1171
+ "mean_similarity": 0.6497376295737922,
1172
+ "mean_word_count_diff": 15.2,
1173
+ "similarity_boolean": 0.4850216718281017,
1174
+ "similarity_extraction": 0.6169686233003934,
1175
+ "similarity_qa": 0.7874227881431579,
1176
+ "similarity_summarization": 0.720199970735444,
1177
+ "similarity_unanswerable": 0.6469447533289592,
1178
+ "word_count_diff_boolean": 5.529411764705882,
1179
+ "word_count_diff_extraction": 4.0,
1180
+ "word_count_diff_qa": 5.466666666666667,
1181
+ "word_count_diff_summarization": 50.72222222222222,
1182
+ "word_count_diff_unanswerable": 4.466666666666667
1183
+ },
1184
+ {
1185
+ "epoch": 33.0,
1186
+ "grad_norm": 0.16729232668876648,
1187
+ "learning_rate": 8.330472312226091e-06,
1188
+ "loss": 0.0099,
1189
+ "step": 8745
1190
+ },
1191
+ {
1192
+ "epoch": 33.0,
1193
+ "eval_loss": 0.09990086406469345,
1194
+ "eval_runtime": 1.7757,
1195
+ "eval_samples_per_second": 45.052,
1196
+ "eval_steps_per_second": 5.631,
1197
+ "step": 8745
1198
+ },
1199
+ {
1200
+ "em_boolean": 0.4117647058823529,
1201
+ "em_extraction": 0.2,
1202
+ "em_qa": 0.0,
1203
+ "em_summarization": 0.0,
1204
+ "em_unanswerable": 0.0,
1205
+ "epoch": 34.0,
1206
+ "mean_em": 0.125,
1207
+ "mean_similarity": 0.6532467395067215,
1208
+ "mean_word_count_diff": 15.3375,
1209
+ "similarity_boolean": 0.5624497304944431,
1210
+ "similarity_extraction": 0.6123799696564675,
1211
+ "similarity_qa": 0.7896470129489899,
1212
+ "similarity_summarization": 0.6943622730258439,
1213
+ "similarity_unanswerable": 0.6112778725723426,
1214
+ "word_count_diff_boolean": 4.588235294117647,
1215
+ "word_count_diff_extraction": 5.266666666666667,
1216
+ "word_count_diff_qa": 5.933333333333334,
1217
+ "word_count_diff_summarization": 50.666666666666664,
1218
+ "word_count_diff_unanswerable": 4.6
1219
+ },
1220
+ {
1221
+ "epoch": 34.0,
1222
+ "grad_norm": 0.3746591806411743,
1223
+ "learning_rate": 7.468014575555688e-06,
1224
+ "loss": 0.0096,
1225
+ "step": 9010
1226
+ },
1227
+ {
1228
+ "epoch": 34.0,
1229
+ "eval_loss": 0.10108506679534912,
1230
+ "eval_runtime": 1.7759,
1231
+ "eval_samples_per_second": 45.048,
1232
+ "eval_steps_per_second": 5.631,
1233
+ "step": 9010
1234
+ },
1235
+ {
1236
+ "em_boolean": 0.35294117647058826,
1237
+ "em_extraction": 0.13333333333333333,
1238
+ "em_qa": 0.13333333333333333,
1239
+ "em_summarization": 0.0,
1240
+ "em_unanswerable": 0.0,
1241
+ "epoch": 35.0,
1242
+ "mean_em": 0.125,
1243
+ "mean_similarity": 0.6299693588167429,
1244
+ "mean_word_count_diff": 15.35,
1245
+ "similarity_boolean": 0.5166072974748471,
1246
+ "similarity_extraction": 0.55517836039265,
1247
+ "similarity_qa": 0.7496427396933237,
1248
+ "similarity_summarization": 0.7208915799856186,
1249
+ "similarity_unanswerable": 0.6044573138157526,
1250
+ "word_count_diff_boolean": 4.352941176470588,
1251
+ "word_count_diff_extraction": 5.266666666666667,
1252
+ "word_count_diff_qa": 4.8,
1253
+ "word_count_diff_summarization": 51.388888888888886,
1254
+ "word_count_diff_unanswerable": 5.2
1255
+ },
1256
+ {
1257
+ "epoch": 35.0,
1258
+ "grad_norm": 0.310463547706604,
1259
+ "learning_rate": 6.637658409856717e-06,
1260
+ "loss": 0.0096,
1261
+ "step": 9275
1262
+ },
1263
+ {
1264
+ "epoch": 35.0,
1265
+ "eval_loss": 0.10128389298915863,
1266
+ "eval_runtime": 1.7949,
1267
+ "eval_samples_per_second": 44.571,
1268
+ "eval_steps_per_second": 5.571,
1269
+ "step": 9275
1270
+ },
1271
+ {
1272
+ "em_boolean": 0.5294117647058824,
1273
+ "em_extraction": 0.2,
1274
+ "em_qa": 0.06666666666666667,
1275
+ "em_summarization": 0.0,
1276
+ "em_unanswerable": 0.0,
1277
+ "epoch": 36.0,
1278
+ "mean_em": 0.1625,
1279
+ "mean_similarity": 0.6648560125031509,
1280
+ "mean_word_count_diff": 14.9,
1281
+ "similarity_boolean": 0.6631740967688315,
1282
+ "similarity_extraction": 0.5298445565005143,
1283
+ "similarity_qa": 0.7434355229139328,
1284
+ "similarity_summarization": 0.7201196981800927,
1285
+ "similarity_unanswerable": 0.6568777064482371,
1286
+ "word_count_diff_boolean": 2.2941176470588234,
1287
+ "word_count_diff_extraction": 5.2,
1288
+ "word_count_diff_qa": 5.333333333333333,
1289
+ "word_count_diff_summarization": 52.0,
1290
+ "word_count_diff_unanswerable": 3.933333333333333
1291
+ },
1292
+ {
1293
+ "epoch": 36.0,
1294
+ "grad_norm": 0.23128336668014526,
1295
+ "learning_rate": 5.84294282056834e-06,
1296
+ "loss": 0.0094,
1297
+ "step": 9540
1298
+ },
1299
+ {
1300
+ "epoch": 36.0,
1301
+ "eval_loss": 0.10348665714263916,
1302
+ "eval_runtime": 1.7894,
1303
+ "eval_samples_per_second": 44.707,
1304
+ "eval_steps_per_second": 5.588,
1305
+ "step": 9540
1306
+ },
1307
+ {
1308
+ "em_boolean": 0.47058823529411764,
1309
+ "em_extraction": 0.2,
1310
+ "em_qa": 0.0,
1311
+ "em_summarization": 0.0,
1312
+ "em_unanswerable": 0.0,
1313
+ "epoch": 37.0,
1314
+ "mean_em": 0.1375,
1315
+ "mean_similarity": 0.6319401320070028,
1316
+ "mean_word_count_diff": 15.0875,
1317
+ "similarity_boolean": 0.5821067885879208,
1318
+ "similarity_extraction": 0.5178047935167949,
1319
+ "similarity_qa": 0.769520037372907,
1320
+ "similarity_summarization": 0.6793310083448887,
1321
+ "similarity_unanswerable": 0.6081043027341366,
1322
+ "word_count_diff_boolean": 4.235294117647059,
1323
+ "word_count_diff_extraction": 4.866666666666666,
1324
+ "word_count_diff_qa": 5.0,
1325
+ "word_count_diff_summarization": 50.833333333333336,
1326
+ "word_count_diff_unanswerable": 4.8
1327
+ },
1328
+ {
1329
+ "epoch": 37.0,
1330
+ "grad_norm": 0.10078708827495575,
1331
+ "learning_rate": 5.087254911814361e-06,
1332
+ "loss": 0.0092,
1333
+ "step": 9805
1334
+ },
1335
+ {
1336
+ "epoch": 37.0,
1337
+ "eval_loss": 0.10369674116373062,
1338
+ "eval_runtime": 1.7998,
1339
+ "eval_samples_per_second": 44.45,
1340
+ "eval_steps_per_second": 5.556,
1341
+ "step": 9805
1342
+ },
1343
+ {
1344
+ "em_boolean": 0.4117647058823529,
1345
+ "em_extraction": 0.13333333333333333,
1346
+ "em_qa": 0.0,
1347
+ "em_summarization": 0.0,
1348
+ "em_unanswerable": 0.0,
1349
+ "epoch": 38.0,
1350
+ "mean_em": 0.1125,
1351
+ "mean_similarity": 0.6402258106973022,
1352
+ "mean_word_count_diff": 15.3875,
1353
+ "similarity_boolean": 0.5555457597708001,
1354
+ "similarity_extraction": 0.5125755973160266,
1355
+ "similarity_qa": 0.729976910352707,
1356
+ "similarity_summarization": 0.7154302892999517,
1357
+ "similarity_unanswerable": 0.6838502744833629,
1358
+ "word_count_diff_boolean": 4.352941176470588,
1359
+ "word_count_diff_extraction": 4.466666666666667,
1360
+ "word_count_diff_qa": 6.266666666666667,
1361
+ "word_count_diff_summarization": 51.166666666666664,
1362
+ "word_count_diff_unanswerable": 5.0
1363
+ },
1364
+ {
1365
+ "epoch": 38.0,
1366
+ "grad_norm": 0.14647193253040314,
1367
+ "learning_rate": 4.373815450453467e-06,
1368
+ "loss": 0.0087,
1369
+ "step": 10070
1370
+ },
1371
+ {
1372
+ "epoch": 38.0,
1373
+ "eval_loss": 0.10511450469493866,
1374
+ "eval_runtime": 1.8033,
1375
+ "eval_samples_per_second": 44.364,
1376
+ "eval_steps_per_second": 5.545,
1377
+ "step": 10070
1378
+ },
1379
+ {
1380
+ "em_boolean": 0.29411764705882354,
1381
+ "em_extraction": 0.26666666666666666,
1382
+ "em_qa": 0.13333333333333333,
1383
+ "em_summarization": 0.0,
1384
+ "em_unanswerable": 0.0,
1385
+ "epoch": 39.0,
1386
+ "mean_em": 0.1375,
1387
+ "mean_similarity": 0.5966290417010895,
1388
+ "mean_word_count_diff": 15.375,
1389
+ "similarity_boolean": 0.48111217118361416,
1390
+ "similarity_extraction": 0.5464107090607285,
1391
+ "similarity_qa": 0.7710953007141749,
1392
+ "similarity_summarization": 0.6638153013255861,
1393
+ "similarity_unanswerable": 0.5226767236987749,
1394
+ "word_count_diff_boolean": 4.294117647058823,
1395
+ "word_count_diff_extraction": 5.133333333333334,
1396
+ "word_count_diff_qa": 5.466666666666667,
1397
+ "word_count_diff_summarization": 50.611111111111114,
1398
+ "word_count_diff_unanswerable": 5.8
1399
+ },
1400
+ {
1401
+ "epoch": 39.0,
1402
+ "grad_norm": 0.8468394875526428,
1403
+ "learning_rate": 3.7056651390643413e-06,
1404
+ "loss": 0.0088,
1405
+ "step": 10335
1406
+ },
1407
+ {
1408
+ "epoch": 39.0,
1409
+ "eval_loss": 0.10422440618276596,
1410
+ "eval_runtime": 1.7878,
1411
+ "eval_samples_per_second": 44.747,
1412
+ "eval_steps_per_second": 5.593,
1413
+ "step": 10335
1414
+ },
1415
+ {
1416
+ "em_boolean": 0.47058823529411764,
1417
+ "em_extraction": 0.26666666666666666,
1418
+ "em_qa": 0.13333333333333333,
1419
+ "em_summarization": 0.0,
1420
+ "em_unanswerable": 0.0,
1421
+ "epoch": 40.0,
1422
+ "mean_em": 0.175,
1423
+ "mean_similarity": 0.6348526364192366,
1424
+ "mean_word_count_diff": 15.1875,
1425
+ "similarity_boolean": 0.5687163450262126,
1426
+ "similarity_extraction": 0.62134765163064,
1427
+ "similarity_qa": 0.7562251538038254,
1428
+ "similarity_summarization": 0.6440524767256446,
1429
+ "similarity_unanswerable": 0.5908997590343158,
1430
+ "word_count_diff_boolean": 4.529411764705882,
1431
+ "word_count_diff_extraction": 4.133333333333334,
1432
+ "word_count_diff_qa": 4.866666666666666,
1433
+ "word_count_diff_summarization": 50.666666666666664,
1434
+ "word_count_diff_unanswerable": 6.066666666666666
1435
+ },
1436
+ {
1437
+ "epoch": 40.0,
1438
+ "grad_norm": 0.15559451282024384,
1439
+ "learning_rate": 3.08565165637071e-06,
1440
+ "loss": 0.0088,
1441
+ "step": 10600
1442
+ },
1443
+ {
1444
+ "epoch": 40.0,
1445
+ "eval_loss": 0.1041550487279892,
1446
+ "eval_runtime": 1.7986,
1447
+ "eval_samples_per_second": 44.479,
1448
+ "eval_steps_per_second": 5.56,
1449
+ "step": 10600
1450
+ },
1451
+ {
1452
+ "em_boolean": 0.4117647058823529,
1453
+ "em_extraction": 0.2,
1454
+ "em_qa": 0.0,
1455
+ "em_summarization": 0.0,
1456
+ "em_unanswerable": 0.0,
1457
+ "epoch": 41.0,
1458
+ "mean_em": 0.125,
1459
+ "mean_similarity": 0.6427899678237736,
1460
+ "mean_word_count_diff": 15.15,
1461
+ "similarity_boolean": 0.5819402319543502,
1462
+ "similarity_extraction": 0.5856266627709071,
1463
+ "similarity_qa": 0.7046878506739934,
1464
+ "similarity_summarization": 0.7580131689707438,
1465
+ "similarity_unanswerable": 0.5687505826354027,
1466
+ "word_count_diff_boolean": 3.0,
1467
+ "word_count_diff_extraction": 5.266666666666667,
1468
+ "word_count_diff_qa": 5.466666666666667,
1469
+ "word_count_diff_summarization": 51.44444444444444,
1470
+ "word_count_diff_unanswerable": 4.933333333333334
1471
+ },
1472
+ {
1473
+ "epoch": 41.0,
1474
+ "grad_norm": 0.2692953050136566,
1475
+ "learning_rate": 2.516417520340457e-06,
1476
+ "loss": 0.0085,
1477
+ "step": 10865
1478
+ },
1479
+ {
1480
+ "epoch": 41.0,
1481
+ "eval_loss": 0.1051572784781456,
1482
+ "eval_runtime": 1.7897,
1483
+ "eval_samples_per_second": 44.701,
1484
+ "eval_steps_per_second": 5.588,
1485
+ "step": 10865
1486
+ },
1487
+ {
1488
+ "em_boolean": 0.47058823529411764,
1489
+ "em_extraction": 0.3333333333333333,
1490
+ "em_qa": 0.0,
1491
+ "em_summarization": 0.0,
1492
+ "em_unanswerable": 0.0,
1493
+ "epoch": 42.0,
1494
+ "mean_em": 0.1625,
1495
+ "mean_similarity": 0.6774277022806927,
1496
+ "mean_word_count_diff": 15.4,
1497
+ "similarity_boolean": 0.600595106206396,
1498
+ "similarity_extraction": 0.644695137689511,
1499
+ "similarity_qa": 0.7859726687272389,
1500
+ "similarity_summarization": 0.7171196627120177,
1501
+ "similarity_unanswerable": 0.6410618901252747,
1502
+ "word_count_diff_boolean": 3.8823529411764706,
1503
+ "word_count_diff_extraction": 4.0,
1504
+ "word_count_diff_qa": 6.333333333333333,
1505
+ "word_count_diff_summarization": 53.05555555555556,
1506
+ "word_count_diff_unanswerable": 3.7333333333333334
1507
+ },
1508
+ {
1509
+ "epoch": 42.0,
1510
+ "grad_norm": 0.028788737952709198,
1511
+ "learning_rate": 2.000388825686658e-06,
1512
+ "loss": 0.0084,
1513
+ "step": 11130
1514
+ },
1515
+ {
1516
+ "epoch": 42.0,
1517
+ "eval_loss": 0.10606852918863297,
1518
+ "eval_runtime": 1.7957,
1519
+ "eval_samples_per_second": 44.551,
1520
+ "eval_steps_per_second": 5.569,
1521
+ "step": 11130
1522
+ },
1523
+ {
1524
+ "em_boolean": 0.4117647058823529,
1525
+ "em_extraction": 0.2,
1526
+ "em_qa": 0.0,
1527
+ "em_summarization": 0.0,
1528
+ "em_unanswerable": 0.0,
1529
+ "epoch": 43.0,
1530
+ "mean_em": 0.125,
1531
+ "mean_similarity": 0.6729973700363189,
1532
+ "mean_word_count_diff": 14.55,
1533
+ "similarity_boolean": 0.6187414353822961,
1534
+ "similarity_extraction": 0.5894727125763893,
1535
+ "similarity_qa": 0.7754949867725373,
1536
+ "similarity_summarization": 0.7333515452014076,
1537
+ "similarity_unanswerable": 0.643089459836483,
1538
+ "word_count_diff_boolean": 2.764705882352941,
1539
+ "word_count_diff_extraction": 2.933333333333333,
1540
+ "word_count_diff_qa": 6.0,
1541
+ "word_count_diff_summarization": 50.166666666666664,
1542
+ "word_count_diff_unanswerable": 5.333333333333333
1543
+ },
1544
+ {
1545
+ "epoch": 43.0,
1546
+ "grad_norm": 0.11988003551959991,
1547
+ "learning_rate": 1.5397649037716471e-06,
1548
+ "loss": 0.0084,
1549
+ "step": 11395
1550
+ },
1551
+ {
1552
+ "epoch": 43.0,
1553
+ "eval_loss": 0.10630540549755096,
1554
+ "eval_runtime": 1.7956,
1555
+ "eval_samples_per_second": 44.554,
1556
+ "eval_steps_per_second": 5.569,
1557
+ "step": 11395
1558
+ }
1559
+ ],
1560
+ "logging_steps": 500,
1561
+ "max_steps": 13250,
1562
+ "num_input_tokens_seen": 0,
1563
+ "num_train_epochs": 50,
1564
+ "save_steps": 500,
1565
+ "stateful_callbacks": {
1566
+ "TrainerControl": {
1567
+ "args": {
1568
+ "should_epoch_stop": false,
1569
+ "should_evaluate": false,
1570
+ "should_log": false,
1571
+ "should_save": true,
1572
+ "should_training_stop": false
1573
+ },
1574
+ "attributes": {}
1575
+ }
1576
+ },
1577
+ "total_flos": 3.115235099226931e+16,
1578
+ "train_batch_size": 4,
1579
+ "trial_name": null,
1580
+ "trial_params": null
1581
+ }
checkpoint-11395/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a42f35ca56de4716016f99e4c1ec8c3abc7da2b9d03b422aae399b849522e7a
3
+ size 5304
checkpoint-11660/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
checkpoint-11660/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
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": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.48.3",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
checkpoint-11660/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": "4.48.3"
7
+ }
checkpoint-11660/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd04bec7cb7169f841083d183d2c5635bed8b08be391b16e34d3f97c503d92c
3
+ size 990345064
checkpoint-11660/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d76ff1b5cbed64cc2c284fc044dcbd07dd9d6d8cf546a0d693f3e11a33aded7
3
+ size 1980860410
checkpoint-11660/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9821cacc143a437b8f777c90ad97be014e155d4af4bf1238fde21d580158bda3
3
+ size 14244
checkpoint-11660/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:236292e1706bd2cd229fa1cb3f17be139f01ee21727e39b9347b03f237cb8e40
3
+ size 1064
checkpoint-11660/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoint-11660/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-11660/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 512,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
checkpoint-11660/trainer_state.json ADDED
@@ -0,0 +1,1617 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06431461870670319,
3
+ "best_model_checkpoint": "./teapotllm/checkpoint-1855",
4
+ "epoch": 44.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11660,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "em_boolean": 0.11764705882352941,
13
+ "em_extraction": 0.06666666666666667,
14
+ "em_qa": 0.0,
15
+ "em_summarization": 0.0,
16
+ "em_unanswerable": 0.0,
17
+ "epoch": 1.0,
18
+ "mean_em": 0.0375,
19
+ "mean_similarity": 0.3622433557640761,
20
+ "mean_word_count_diff": 17.7125,
21
+ "similarity_boolean": 0.18269754047779477,
22
+ "similarity_extraction": 0.2946929598848025,
23
+ "similarity_qa": 0.43210459053516387,
24
+ "similarity_summarization": 0.6143242551220788,
25
+ "similarity_unanswerable": 0.26092069496711096,
26
+ "word_count_diff_boolean": 9.0,
27
+ "word_count_diff_extraction": 7.666666666666667,
28
+ "word_count_diff_qa": 6.933333333333334,
29
+ "word_count_diff_summarization": 53.111111111111114,
30
+ "word_count_diff_unanswerable": 5.933333333333334
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 101.51641082763672,
35
+ "learning_rate": 1.59e-05,
36
+ "loss": 40.3479,
37
+ "step": 265
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 19.639965057373047,
42
+ "eval_runtime": 1.7948,
43
+ "eval_samples_per_second": 44.573,
44
+ "eval_steps_per_second": 5.572,
45
+ "step": 265
46
+ },
47
+ {
48
+ "em_boolean": 0.058823529411764705,
49
+ "em_extraction": 0.0,
50
+ "em_qa": 0.0,
51
+ "em_summarization": 0.0,
52
+ "em_unanswerable": 0.0,
53
+ "epoch": 2.0,
54
+ "mean_em": 0.0125,
55
+ "mean_similarity": 0.37655651543755086,
56
+ "mean_word_count_diff": 17.1625,
57
+ "similarity_boolean": 0.10583376435234267,
58
+ "similarity_extraction": 0.21972424462437629,
59
+ "similarity_qa": 0.5285325924555461,
60
+ "similarity_summarization": 0.6654400361908807,
61
+ "similarity_unanswerable": 0.34157160222530364,
62
+ "word_count_diff_boolean": 10.176470588235293,
63
+ "word_count_diff_extraction": 6.133333333333334,
64
+ "word_count_diff_qa": 5.866666666666666,
65
+ "word_count_diff_summarization": 52.166666666666664,
66
+ "word_count_diff_unanswerable": 5.4
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.2927296459674835,
71
+ "learning_rate": 2.9999590191302685e-05,
72
+ "loss": 1.8688,
73
+ "step": 530
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.08876434713602066,
78
+ "eval_runtime": 1.7881,
79
+ "eval_samples_per_second": 44.74,
80
+ "eval_steps_per_second": 5.593,
81
+ "step": 530
82
+ },
83
+ {
84
+ "em_boolean": 0.29411764705882354,
85
+ "em_extraction": 0.13333333333333333,
86
+ "em_qa": 0.06666666666666667,
87
+ "em_summarization": 0.0,
88
+ "em_unanswerable": 0.0,
89
+ "epoch": 3.0,
90
+ "mean_em": 0.1,
91
+ "mean_similarity": 0.468679612770211,
92
+ "mean_word_count_diff": 16.8875,
93
+ "similarity_boolean": 0.36136592250755606,
94
+ "similarity_extraction": 0.3513699695467949,
95
+ "similarity_qa": 0.5638724292318026,
96
+ "similarity_summarization": 0.661304693048199,
97
+ "similarity_unanswerable": 0.3812685254961252,
98
+ "word_count_diff_boolean": 5.411764705882353,
99
+ "word_count_diff_extraction": 8.066666666666666,
100
+ "word_count_diff_qa": 5.6,
101
+ "word_count_diff_summarization": 53.333333333333336,
102
+ "word_count_diff_unanswerable": 6.266666666666667
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "grad_norm": 0.2717432379722595,
107
+ "learning_rate": 2.9960391039419217e-05,
108
+ "loss": 0.0745,
109
+ "step": 795
110
+ },
111
+ {
112
+ "epoch": 3.0,
113
+ "eval_loss": 0.07186319679021835,
114
+ "eval_runtime": 1.7817,
115
+ "eval_samples_per_second": 44.901,
116
+ "eval_steps_per_second": 5.613,
117
+ "step": 795
118
+ },
119
+ {
120
+ "em_boolean": 0.5294117647058824,
121
+ "em_extraction": 0.0,
122
+ "em_qa": 0.0,
123
+ "em_summarization": 0.0,
124
+ "em_unanswerable": 0.0,
125
+ "epoch": 4.0,
126
+ "mean_em": 0.1125,
127
+ "mean_similarity": 0.5406636619823985,
128
+ "mean_word_count_diff": 16.4,
129
+ "similarity_boolean": 0.5694808649337467,
130
+ "similarity_extraction": 0.2759806969513496,
131
+ "similarity_qa": 0.5888164043426514,
132
+ "similarity_summarization": 0.6777413653002845,
133
+ "similarity_unanswerable": 0.5600411439935367,
134
+ "word_count_diff_boolean": 3.411764705882353,
135
+ "word_count_diff_extraction": 9.133333333333333,
136
+ "word_count_diff_qa": 5.733333333333333,
137
+ "word_count_diff_summarization": 52.611111111111114,
138
+ "word_count_diff_unanswerable": 5.6
139
+ },
140
+ {
141
+ "epoch": 4.0,
142
+ "grad_norm": 0.33120226860046387,
143
+ "learning_rate": 2.985743020616636e-05,
144
+ "loss": 0.0583,
145
+ "step": 1060
146
+ },
147
+ {
148
+ "epoch": 4.0,
149
+ "eval_loss": 0.06767071783542633,
150
+ "eval_runtime": 1.8031,
151
+ "eval_samples_per_second": 44.368,
152
+ "eval_steps_per_second": 5.546,
153
+ "step": 1060
154
+ },
155
+ {
156
+ "em_boolean": 0.35294117647058826,
157
+ "em_extraction": 0.06666666666666667,
158
+ "em_qa": 0.06666666666666667,
159
+ "em_summarization": 0.0,
160
+ "em_unanswerable": 0.0,
161
+ "epoch": 5.0,
162
+ "mean_em": 0.1,
163
+ "mean_similarity": 0.5391882328083739,
164
+ "mean_word_count_diff": 16.5375,
165
+ "similarity_boolean": 0.4291324294446146,
166
+ "similarity_extraction": 0.3934509038925171,
167
+ "similarity_qa": 0.5968125452597935,
168
+ "similarity_summarization": 0.6669783542553583,
169
+ "similarity_unanswerable": 0.5986830140153567,
170
+ "word_count_diff_boolean": 5.9411764705882355,
171
+ "word_count_diff_extraction": 5.866666666666666,
172
+ "word_count_diff_qa": 5.4,
173
+ "word_count_diff_summarization": 53.77777777777778,
174
+ "word_count_diff_unanswerable": 5.666666666666667
175
+ },
176
+ {
177
+ "epoch": 5.0,
178
+ "grad_norm": 0.05014026165008545,
179
+ "learning_rate": 2.969114651402049e-05,
180
+ "loss": 0.0512,
181
+ "step": 1325
182
+ },
183
+ {
184
+ "epoch": 5.0,
185
+ "eval_loss": 0.06544757634401321,
186
+ "eval_runtime": 1.797,
187
+ "eval_samples_per_second": 44.518,
188
+ "eval_steps_per_second": 5.565,
189
+ "step": 1325
190
+ },
191
+ {
192
+ "em_boolean": 0.35294117647058826,
193
+ "em_extraction": 0.13333333333333333,
194
+ "em_qa": 0.0,
195
+ "em_summarization": 0.0,
196
+ "em_unanswerable": 0.0,
197
+ "epoch": 6.0,
198
+ "mean_em": 0.1,
199
+ "mean_similarity": 0.5817075100494549,
200
+ "mean_word_count_diff": 16.1375,
201
+ "similarity_boolean": 0.3759182594059145,
202
+ "similarity_extraction": 0.5534958879152934,
203
+ "similarity_qa": 0.6812621881564458,
204
+ "similarity_summarization": 0.661298368126154,
205
+ "similarity_unanswerable": 0.648083241780599,
206
+ "word_count_diff_boolean": 6.294117647058823,
207
+ "word_count_diff_extraction": 4.466666666666667,
208
+ "word_count_diff_qa": 5.666666666666667,
209
+ "word_count_diff_summarization": 52.55555555555556,
210
+ "word_count_diff_unanswerable": 5.733333333333333
211
+ },
212
+ {
213
+ "epoch": 6.0,
214
+ "grad_norm": 0.37450432777404785,
215
+ "learning_rate": 2.9462248669576738e-05,
216
+ "loss": 0.0466,
217
+ "step": 1590
218
+ },
219
+ {
220
+ "epoch": 6.0,
221
+ "eval_loss": 0.0656035840511322,
222
+ "eval_runtime": 1.8115,
223
+ "eval_samples_per_second": 44.161,
224
+ "eval_steps_per_second": 5.52,
225
+ "step": 1590
226
+ },
227
+ {
228
+ "em_boolean": 0.29411764705882354,
229
+ "em_extraction": 0.06666666666666667,
230
+ "em_qa": 0.06666666666666667,
231
+ "em_summarization": 0.0,
232
+ "em_unanswerable": 0.0,
233
+ "epoch": 7.0,
234
+ "mean_em": 0.0875,
235
+ "mean_similarity": 0.584748298721388,
236
+ "mean_word_count_diff": 16.4875,
237
+ "similarity_boolean": 0.3921016369234113,
238
+ "similarity_extraction": 0.4258095269401868,
239
+ "similarity_qa": 0.8010195712248485,
240
+ "similarity_summarization": 0.7269510593679216,
241
+ "similarity_unanswerable": 0.5751053685943286,
242
+ "word_count_diff_boolean": 6.529411764705882,
243
+ "word_count_diff_extraction": 7.4,
244
+ "word_count_diff_qa": 4.266666666666667,
245
+ "word_count_diff_summarization": 51.5,
246
+ "word_count_diff_unanswerable": 7.066666666666666
247
+ },
248
+ {
249
+ "epoch": 7.0,
250
+ "grad_norm": 0.2656797170639038,
251
+ "learning_rate": 2.9171712243018076e-05,
252
+ "loss": 0.043,
253
+ "step": 1855
254
+ },
255
+ {
256
+ "epoch": 7.0,
257
+ "eval_loss": 0.06431461870670319,
258
+ "eval_runtime": 1.779,
259
+ "eval_samples_per_second": 44.968,
260
+ "eval_steps_per_second": 5.621,
261
+ "step": 1855
262
+ },
263
+ {
264
+ "em_boolean": 0.23529411764705882,
265
+ "em_extraction": 0.3333333333333333,
266
+ "em_qa": 0.13333333333333333,
267
+ "em_summarization": 0.0,
268
+ "em_unanswerable": 0.0,
269
+ "epoch": 8.0,
270
+ "mean_em": 0.1375,
271
+ "mean_similarity": 0.5707565736840479,
272
+ "mean_word_count_diff": 15.9125,
273
+ "similarity_boolean": 0.3595361856962828,
274
+ "similarity_extraction": 0.6590617413322131,
275
+ "similarity_qa": 0.6671084851026535,
276
+ "similarity_summarization": 0.672764014866617,
277
+ "similarity_unanswerable": 0.503073671584328,
278
+ "word_count_diff_boolean": 6.705882352941177,
279
+ "word_count_diff_extraction": 4.133333333333334,
280
+ "word_count_diff_qa": 4.0,
281
+ "word_count_diff_summarization": 51.833333333333336,
282
+ "word_count_diff_unanswerable": 6.933333333333334
283
+ },
284
+ {
285
+ "epoch": 8.0,
286
+ "grad_norm": 0.1501343548297882,
287
+ "learning_rate": 2.882077551020291e-05,
288
+ "loss": 0.0393,
289
+ "step": 2120
290
+ },
291
+ {
292
+ "epoch": 8.0,
293
+ "eval_loss": 0.064610555768013,
294
+ "eval_runtime": 1.7854,
295
+ "eval_samples_per_second": 44.809,
296
+ "eval_steps_per_second": 5.601,
297
+ "step": 2120
298
+ },
299
+ {
300
+ "em_boolean": 0.29411764705882354,
301
+ "em_extraction": 0.13333333333333333,
302
+ "em_qa": 0.0,
303
+ "em_summarization": 0.0,
304
+ "em_unanswerable": 0.0,
305
+ "epoch": 9.0,
306
+ "mean_em": 0.0875,
307
+ "mean_similarity": 0.5716628619702533,
308
+ "mean_word_count_diff": 16.075,
309
+ "similarity_boolean": 0.46071117371320724,
310
+ "similarity_extraction": 0.5175981452067693,
311
+ "similarity_qa": 0.6631501737982035,
312
+ "similarity_summarization": 0.6426751317663325,
313
+ "similarity_unanswerable": 0.5747707898418108,
314
+ "word_count_diff_boolean": 5.235294117647059,
315
+ "word_count_diff_extraction": 7.333333333333333,
316
+ "word_count_diff_qa": 5.6,
317
+ "word_count_diff_summarization": 52.22222222222222,
318
+ "word_count_diff_unanswerable": 4.2
319
+ },
320
+ {
321
+ "epoch": 9.0,
322
+ "grad_norm": 0.23849624395370483,
323
+ "learning_rate": 2.8410934175092426e-05,
324
+ "loss": 0.0363,
325
+ "step": 2385
326
+ },
327
+ {
328
+ "epoch": 9.0,
329
+ "eval_loss": 0.06528123468160629,
330
+ "eval_runtime": 1.7964,
331
+ "eval_samples_per_second": 44.533,
332
+ "eval_steps_per_second": 5.567,
333
+ "step": 2385
334
+ },
335
+ {
336
+ "em_boolean": 0.4117647058823529,
337
+ "em_extraction": 0.13333333333333333,
338
+ "em_qa": 0.06666666666666667,
339
+ "em_summarization": 0.0,
340
+ "em_unanswerable": 0.0,
341
+ "epoch": 10.0,
342
+ "mean_em": 0.125,
343
+ "mean_similarity": 0.5984957347856834,
344
+ "mean_word_count_diff": 16.2375,
345
+ "similarity_boolean": 0.4425226738128592,
346
+ "similarity_extraction": 0.5075533439715704,
347
+ "similarity_qa": 0.6813998910288016,
348
+ "similarity_summarization": 0.6938931312825944,
349
+ "similarity_unanswerable": 0.6688265626629194,
350
+ "word_count_diff_boolean": 5.352941176470588,
351
+ "word_count_diff_extraction": 6.466666666666667,
352
+ "word_count_diff_qa": 6.2,
353
+ "word_count_diff_summarization": 52.166666666666664,
354
+ "word_count_diff_unanswerable": 5.266666666666667
355
+ },
356
+ {
357
+ "epoch": 10.0,
358
+ "grad_norm": 0.2859129309654236,
359
+ "learning_rate": 2.7943934995010845e-05,
360
+ "loss": 0.0338,
361
+ "step": 2650
362
+ },
363
+ {
364
+ "epoch": 10.0,
365
+ "eval_loss": 0.06541204452514648,
366
+ "eval_runtime": 1.7939,
367
+ "eval_samples_per_second": 44.595,
368
+ "eval_steps_per_second": 5.574,
369
+ "step": 2650
370
+ },
371
+ {
372
+ "em_boolean": 0.35294117647058826,
373
+ "em_extraction": 0.2,
374
+ "em_qa": 0.06666666666666667,
375
+ "em_summarization": 0.0,
376
+ "em_unanswerable": 0.0,
377
+ "epoch": 11.0,
378
+ "mean_em": 0.125,
379
+ "mean_similarity": 0.584741565072909,
380
+ "mean_word_count_diff": 15.85,
381
+ "similarity_boolean": 0.41579638640670213,
382
+ "similarity_extraction": 0.575649573157231,
383
+ "similarity_qa": 0.68668532371521,
384
+ "similarity_summarization": 0.7162102411190668,
385
+ "similarity_unanswerable": 0.5255985895792643,
386
+ "word_count_diff_boolean": 5.0,
387
+ "word_count_diff_extraction": 4.333333333333333,
388
+ "word_count_diff_qa": 5.4,
389
+ "word_count_diff_summarization": 51.72222222222222,
390
+ "word_count_diff_unanswerable": 7.066666666666666
391
+ },
392
+ {
393
+ "epoch": 11.0,
394
+ "grad_norm": 0.19708961248397827,
395
+ "learning_rate": 2.7421768335907942e-05,
396
+ "loss": 0.0314,
397
+ "step": 2915
398
+ },
399
+ {
400
+ "epoch": 11.0,
401
+ "eval_loss": 0.06535650044679642,
402
+ "eval_runtime": 1.7968,
403
+ "eval_samples_per_second": 44.525,
404
+ "eval_steps_per_second": 5.566,
405
+ "step": 2915
406
+ },
407
+ {
408
+ "em_boolean": 0.4117647058823529,
409
+ "em_extraction": 0.13333333333333333,
410
+ "em_qa": 0.06666666666666667,
411
+ "em_summarization": 0.0,
412
+ "em_unanswerable": 0.0,
413
+ "epoch": 12.0,
414
+ "mean_em": 0.125,
415
+ "mean_similarity": 0.5985993921523913,
416
+ "mean_word_count_diff": 15.65,
417
+ "similarity_boolean": 0.49136487109696164,
418
+ "similarity_extraction": 0.4834645986557007,
419
+ "similarity_qa": 0.7439890225728353,
420
+ "similarity_summarization": 0.7199151118596395,
421
+ "similarity_unanswerable": 0.5442981487760942,
422
+ "word_count_diff_boolean": 5.294117647058823,
423
+ "word_count_diff_extraction": 6.466666666666667,
424
+ "word_count_diff_qa": 5.0,
425
+ "word_count_diff_summarization": 51.333333333333336,
426
+ "word_count_diff_unanswerable": 4.4
427
+ },
428
+ {
429
+ "epoch": 12.0,
430
+ "grad_norm": 0.32636699080467224,
431
+ "learning_rate": 2.6846659689353532e-05,
432
+ "loss": 0.0291,
433
+ "step": 3180
434
+ },
435
+ {
436
+ "epoch": 12.0,
437
+ "eval_loss": 0.06654994189739227,
438
+ "eval_runtime": 1.7794,
439
+ "eval_samples_per_second": 44.96,
440
+ "eval_steps_per_second": 5.62,
441
+ "step": 3180
442
+ },
443
+ {
444
+ "em_boolean": 0.29411764705882354,
445
+ "em_extraction": 0.2,
446
+ "em_qa": 0.13333333333333333,
447
+ "em_summarization": 0.0,
448
+ "em_unanswerable": 0.0,
449
+ "epoch": 13.0,
450
+ "mean_em": 0.125,
451
+ "mean_similarity": 0.5608657638425939,
452
+ "mean_word_count_diff": 15.4875,
453
+ "similarity_boolean": 0.3726646105265793,
454
+ "similarity_extraction": 0.4880456611514091,
455
+ "similarity_qa": 0.6968116387724876,
456
+ "similarity_summarization": 0.7003769092261791,
457
+ "similarity_unanswerable": 0.5436212575683991,
458
+ "word_count_diff_boolean": 6.470588235294118,
459
+ "word_count_diff_extraction": 4.0,
460
+ "word_count_diff_qa": 4.266666666666667,
461
+ "word_count_diff_summarization": 50.22222222222222,
462
+ "word_count_diff_unanswerable": 6.733333333333333
463
+ },
464
+ {
465
+ "epoch": 13.0,
466
+ "grad_norm": 0.09956305474042892,
467
+ "learning_rate": 2.622106018741882e-05,
468
+ "loss": 0.0268,
469
+ "step": 3445
470
+ },
471
+ {
472
+ "epoch": 13.0,
473
+ "eval_loss": 0.06867102533578873,
474
+ "eval_runtime": 1.7923,
475
+ "eval_samples_per_second": 44.635,
476
+ "eval_steps_per_second": 5.579,
477
+ "step": 3445
478
+ },
479
+ {
480
+ "em_boolean": 0.4117647058823529,
481
+ "em_extraction": 0.13333333333333333,
482
+ "em_qa": 0.06666666666666667,
483
+ "em_summarization": 0.0,
484
+ "em_unanswerable": 0.0,
485
+ "epoch": 14.0,
486
+ "mean_em": 0.125,
487
+ "mean_similarity": 0.6118219185853377,
488
+ "mean_word_count_diff": 15.1,
489
+ "similarity_boolean": 0.5559550164376988,
490
+ "similarity_extraction": 0.4480490814894438,
491
+ "similarity_qa": 0.8226341267426809,
492
+ "similarity_summarization": 0.7094271017445458,
493
+ "similarity_unanswerable": 0.5109721501668294,
494
+ "word_count_diff_boolean": 3.235294117647059,
495
+ "word_count_diff_extraction": 5.333333333333333,
496
+ "word_count_diff_qa": 4.066666666666666,
497
+ "word_count_diff_summarization": 51.333333333333336,
498
+ "word_count_diff_unanswerable": 5.866666666666666
499
+ },
500
+ {
501
+ "epoch": 14.0,
502
+ "grad_norm": 0.2182687222957611,
503
+ "learning_rate": 2.554763615587042e-05,
504
+ "loss": 0.0254,
505
+ "step": 3710
506
+ },
507
+ {
508
+ "epoch": 14.0,
509
+ "eval_loss": 0.06904994696378708,
510
+ "eval_runtime": 1.7971,
511
+ "eval_samples_per_second": 44.517,
512
+ "eval_steps_per_second": 5.565,
513
+ "step": 3710
514
+ },
515
+ {
516
+ "em_boolean": 0.17647058823529413,
517
+ "em_extraction": 0.13333333333333333,
518
+ "em_qa": 0.13333333333333333,
519
+ "em_summarization": 0.0,
520
+ "em_unanswerable": 0.0,
521
+ "epoch": 15.0,
522
+ "mean_em": 0.0875,
523
+ "mean_similarity": 0.5906956384656951,
524
+ "mean_word_count_diff": 15.8,
525
+ "similarity_boolean": 0.30824649366824064,
526
+ "similarity_extraction": 0.5498731901248296,
527
+ "similarity_qa": 0.7911941662430764,
528
+ "similarity_summarization": 0.7216936614778307,
529
+ "similarity_unanswerable": 0.5939309621850649,
530
+ "word_count_diff_boolean": 5.294117647058823,
531
+ "word_count_diff_extraction": 5.533333333333333,
532
+ "word_count_diff_qa": 4.933333333333334,
533
+ "word_count_diff_summarization": 50.833333333333336,
534
+ "word_count_diff_unanswerable": 6.8
535
+ },
536
+ {
537
+ "epoch": 15.0,
538
+ "grad_norm": 0.278495728969574,
539
+ "learning_rate": 2.4829257750201806e-05,
540
+ "loss": 0.0235,
541
+ "step": 3975
542
+ },
543
+ {
544
+ "epoch": 15.0,
545
+ "eval_loss": 0.07152120769023895,
546
+ "eval_runtime": 1.8045,
547
+ "eval_samples_per_second": 44.334,
548
+ "eval_steps_per_second": 5.542,
549
+ "step": 3975
550
+ },
551
+ {
552
+ "em_boolean": 0.35294117647058826,
553
+ "em_extraction": 0.13333333333333333,
554
+ "em_qa": 0.06666666666666667,
555
+ "em_summarization": 0.0,
556
+ "em_unanswerable": 0.0,
557
+ "epoch": 16.0,
558
+ "mean_em": 0.1125,
559
+ "mean_similarity": 0.6044320391491056,
560
+ "mean_word_count_diff": 15.3625,
561
+ "similarity_boolean": 0.4709787254824358,
562
+ "similarity_extraction": 0.48890374253193536,
563
+ "similarity_qa": 0.7086231042941411,
564
+ "similarity_summarization": 0.6860101450648572,
565
+ "similarity_unanswerable": 0.6691226323445638,
566
+ "word_count_diff_boolean": 5.176470588235294,
567
+ "word_count_diff_extraction": 4.133333333333334,
568
+ "word_count_diff_qa": 5.8,
569
+ "word_count_diff_summarization": 51.388888888888886,
570
+ "word_count_diff_unanswerable": 4.466666666666667
571
+ },
572
+ {
573
+ "epoch": 16.0,
574
+ "grad_norm": 0.12528866529464722,
575
+ "learning_rate": 2.4068986722935625e-05,
576
+ "loss": 0.0219,
577
+ "step": 4240
578
+ },
579
+ {
580
+ "epoch": 16.0,
581
+ "eval_loss": 0.07122211903333664,
582
+ "eval_runtime": 1.7912,
583
+ "eval_samples_per_second": 44.663,
584
+ "eval_steps_per_second": 5.583,
585
+ "step": 4240
586
+ },
587
+ {
588
+ "em_boolean": 0.23529411764705882,
589
+ "em_extraction": 0.2,
590
+ "em_qa": 0.06666666666666667,
591
+ "em_summarization": 0.0,
592
+ "em_unanswerable": 0.0,
593
+ "epoch": 17.0,
594
+ "mean_em": 0.1,
595
+ "mean_similarity": 0.5854583959793672,
596
+ "mean_word_count_diff": 16.1125,
597
+ "similarity_boolean": 0.3930098557954325,
598
+ "similarity_extraction": 0.5295473781724771,
599
+ "similarity_qa": 0.7186618636051814,
600
+ "similarity_summarization": 0.6619544287936555,
601
+ "similarity_unanswerable": 0.6344790523250897,
602
+ "word_count_diff_boolean": 5.764705882352941,
603
+ "word_count_diff_extraction": 5.066666666666666,
604
+ "word_count_diff_qa": 6.066666666666666,
605
+ "word_count_diff_summarization": 52.22222222222222,
606
+ "word_count_diff_unanswerable": 5.6
607
+ },
608
+ {
609
+ "epoch": 17.0,
610
+ "grad_norm": 0.18347615003585815,
611
+ "learning_rate": 2.327006337433323e-05,
612
+ "loss": 0.0208,
613
+ "step": 4505
614
+ },
615
+ {
616
+ "epoch": 17.0,
617
+ "eval_loss": 0.07514352351427078,
618
+ "eval_runtime": 1.7952,
619
+ "eval_samples_per_second": 44.563,
620
+ "eval_steps_per_second": 5.57,
621
+ "step": 4505
622
+ },
623
+ {
624
+ "em_boolean": 0.35294117647058826,
625
+ "em_extraction": 0.13333333333333333,
626
+ "em_qa": 0.06666666666666667,
627
+ "em_summarization": 0.0,
628
+ "em_unanswerable": 0.0,
629
+ "epoch": 18.0,
630
+ "mean_em": 0.1125,
631
+ "mean_similarity": 0.6148898253683001,
632
+ "mean_word_count_diff": 15.95,
633
+ "similarity_boolean": 0.45182113108389516,
634
+ "similarity_extraction": 0.5246008743842443,
635
+ "similarity_qa": 0.7161807785431544,
636
+ "similarity_summarization": 0.695978145632479,
637
+ "similarity_unanswerable": 0.6913930257161458,
638
+ "word_count_diff_boolean": 6.705882352941177,
639
+ "word_count_diff_extraction": 5.333333333333333,
640
+ "word_count_diff_qa": 5.133333333333334,
641
+ "word_count_diff_summarization": 51.72222222222222,
642
+ "word_count_diff_unanswerable": 4.933333333333334
643
+ },
644
+ {
645
+ "epoch": 18.0,
646
+ "grad_norm": 0.39281344413757324,
647
+ "learning_rate": 2.2435892742127786e-05,
648
+ "loss": 0.0197,
649
+ "step": 4770
650
+ },
651
+ {
652
+ "epoch": 18.0,
653
+ "eval_loss": 0.07489313185214996,
654
+ "eval_runtime": 1.7966,
655
+ "eval_samples_per_second": 44.528,
656
+ "eval_steps_per_second": 5.566,
657
+ "step": 4770
658
+ },
659
+ {
660
+ "em_boolean": 0.35294117647058826,
661
+ "em_extraction": 0.13333333333333333,
662
+ "em_qa": 0.06666666666666667,
663
+ "em_summarization": 0.0,
664
+ "em_unanswerable": 0.0,
665
+ "epoch": 19.0,
666
+ "mean_em": 0.1125,
667
+ "mean_similarity": 0.6110048872418702,
668
+ "mean_word_count_diff": 15.175,
669
+ "similarity_boolean": 0.4688412766246235,
670
+ "similarity_extraction": 0.5354909280935923,
671
+ "similarity_qa": 0.7334268649419149,
672
+ "similarity_summarization": 0.6523812972009182,
673
+ "similarity_unanswerable": 0.6755639354387919,
674
+ "word_count_diff_boolean": 5.411764705882353,
675
+ "word_count_diff_extraction": 3.6666666666666665,
676
+ "word_count_diff_qa": 5.333333333333333,
677
+ "word_count_diff_summarization": 51.27777777777778,
678
+ "word_count_diff_unanswerable": 4.266666666666667
679
+ },
680
+ {
681
+ "epoch": 19.0,
682
+ "grad_norm": 0.26503777503967285,
683
+ "learning_rate": 2.1570030089140857e-05,
684
+ "loss": 0.0184,
685
+ "step": 5035
686
+ },
687
+ {
688
+ "epoch": 19.0,
689
+ "eval_loss": 0.07855142652988434,
690
+ "eval_runtime": 1.7852,
691
+ "eval_samples_per_second": 44.813,
692
+ "eval_steps_per_second": 5.602,
693
+ "step": 5035
694
+ },
695
+ {
696
+ "em_boolean": 0.058823529411764705,
697
+ "em_extraction": 0.26666666666666666,
698
+ "em_qa": 0.0,
699
+ "em_summarization": 0.0,
700
+ "em_unanswerable": 0.0,
701
+ "epoch": 20.0,
702
+ "mean_em": 0.0625,
703
+ "mean_similarity": 0.5894458804745227,
704
+ "mean_word_count_diff": 15.7625,
705
+ "similarity_boolean": 0.3066763941417722,
706
+ "similarity_extraction": 0.567964817583561,
707
+ "similarity_qa": 0.7356137126684189,
708
+ "similarity_summarization": 0.7311095827155643,
709
+ "similarity_unanswerable": 0.615234752992789,
710
+ "word_count_diff_boolean": 7.0588235294117645,
711
+ "word_count_diff_extraction": 4.133333333333334,
712
+ "word_count_diff_qa": 6.4,
713
+ "word_count_diff_summarization": 50.833333333333336,
714
+ "word_count_diff_unanswerable": 4.533333333333333
715
+ },
716
+ {
717
+ "epoch": 20.0,
718
+ "grad_norm": 0.325967013835907,
719
+ "learning_rate": 2.0676165750634656e-05,
720
+ "loss": 0.0173,
721
+ "step": 5300
722
+ },
723
+ {
724
+ "epoch": 20.0,
725
+ "eval_loss": 0.07865440845489502,
726
+ "eval_runtime": 1.7895,
727
+ "eval_samples_per_second": 44.705,
728
+ "eval_steps_per_second": 5.588,
729
+ "step": 5300
730
+ },
731
+ {
732
+ "em_boolean": 0.5294117647058824,
733
+ "em_extraction": 0.26666666666666666,
734
+ "em_qa": 0.06666666666666667,
735
+ "em_summarization": 0.0,
736
+ "em_unanswerable": 0.0,
737
+ "epoch": 21.0,
738
+ "mean_em": 0.175,
739
+ "mean_similarity": 0.6464177187765017,
740
+ "mean_word_count_diff": 14.8375,
741
+ "similarity_boolean": 0.6461278642801678,
742
+ "similarity_extraction": 0.6178931772708893,
743
+ "similarity_qa": 0.7566967884699504,
744
+ "similarity_summarization": 0.6613570315142473,
745
+ "similarity_unanswerable": 0.5470645170658827,
746
+ "word_count_diff_boolean": 3.176470588235294,
747
+ "word_count_diff_extraction": 5.4,
748
+ "word_count_diff_qa": 4.6,
749
+ "word_count_diff_summarization": 50.5,
750
+ "word_count_diff_unanswerable": 4.933333333333334
751
+ },
752
+ {
753
+ "epoch": 21.0,
754
+ "grad_norm": 0.18580074608325958,
755
+ "learning_rate": 1.975810940598114e-05,
756
+ "loss": 0.0162,
757
+ "step": 5565
758
+ },
759
+ {
760
+ "epoch": 21.0,
761
+ "eval_loss": 0.08283738046884537,
762
+ "eval_runtime": 1.8062,
763
+ "eval_samples_per_second": 44.292,
764
+ "eval_steps_per_second": 5.537,
765
+ "step": 5565
766
+ },
767
+ {
768
+ "em_boolean": 0.47058823529411764,
769
+ "em_extraction": 0.26666666666666666,
770
+ "em_qa": 0.06666666666666667,
771
+ "em_summarization": 0.0,
772
+ "em_unanswerable": 0.0,
773
+ "epoch": 22.0,
774
+ "mean_em": 0.1625,
775
+ "mean_similarity": 0.6508607531315647,
776
+ "mean_word_count_diff": 15.1875,
777
+ "similarity_boolean": 0.5319088667302447,
778
+ "similarity_extraction": 0.6322630804032088,
779
+ "similarity_qa": 0.7358093798160553,
780
+ "similarity_summarization": 0.6958086478213469,
781
+ "similarity_unanswerable": 0.6653844634691874,
782
+ "word_count_diff_boolean": 5.352941176470588,
783
+ "word_count_diff_extraction": 3.933333333333333,
784
+ "word_count_diff_qa": 5.266666666666667,
785
+ "word_count_diff_summarization": 51.166666666666664,
786
+ "word_count_diff_unanswerable": 4.333333333333333
787
+ },
788
+ {
789
+ "epoch": 22.0,
790
+ "grad_norm": 0.7463592886924744,
791
+ "learning_rate": 1.881977384168254e-05,
792
+ "loss": 0.0158,
793
+ "step": 5830
794
+ },
795
+ {
796
+ "epoch": 22.0,
797
+ "eval_loss": 0.08268458396196365,
798
+ "eval_runtime": 1.7886,
799
+ "eval_samples_per_second": 44.728,
800
+ "eval_steps_per_second": 5.591,
801
+ "step": 5830
802
+ },
803
+ {
804
+ "em_boolean": 0.4117647058823529,
805
+ "em_extraction": 0.2,
806
+ "em_qa": 0.13333333333333333,
807
+ "em_summarization": 0.0,
808
+ "em_unanswerable": 0.0,
809
+ "epoch": 23.0,
810
+ "mean_em": 0.15,
811
+ "mean_similarity": 0.6376353252329864,
812
+ "mean_word_count_diff": 15.5625,
813
+ "similarity_boolean": 0.5682552300722283,
814
+ "similarity_extraction": 0.5148679026712973,
815
+ "similarity_qa": 0.7483514944712321,
816
+ "similarity_summarization": 0.7200961951166391,
817
+ "similarity_unanswerable": 0.629364309211572,
818
+ "word_count_diff_boolean": 3.823529411764706,
819
+ "word_count_diff_extraction": 5.266666666666667,
820
+ "word_count_diff_qa": 4.933333333333334,
821
+ "word_count_diff_summarization": 51.388888888888886,
822
+ "word_count_diff_unanswerable": 6.8
823
+ },
824
+ {
825
+ "epoch": 23.0,
826
+ "grad_norm": 0.30431216955184937,
827
+ "learning_rate": 1.7865158274945846e-05,
828
+ "loss": 0.0149,
829
+ "step": 6095
830
+ },
831
+ {
832
+ "epoch": 23.0,
833
+ "eval_loss": 0.08500902354717255,
834
+ "eval_runtime": 1.8006,
835
+ "eval_samples_per_second": 44.43,
836
+ "eval_steps_per_second": 5.554,
837
+ "step": 6095
838
+ },
839
+ {
840
+ "em_boolean": 0.35294117647058826,
841
+ "em_extraction": 0.2,
842
+ "em_qa": 0.0,
843
+ "em_summarization": 0.0,
844
+ "em_unanswerable": 0.0,
845
+ "epoch": 24.0,
846
+ "mean_em": 0.1125,
847
+ "mean_similarity": 0.6209718830883503,
848
+ "mean_word_count_diff": 15.625,
849
+ "similarity_boolean": 0.4452236132586704,
850
+ "similarity_extraction": 0.5458283141255379,
851
+ "similarity_qa": 0.7422831366459529,
852
+ "similarity_summarization": 0.7023132857349184,
853
+ "similarity_unanswerable": 0.6763758877913157,
854
+ "word_count_diff_boolean": 5.470588235294118,
855
+ "word_count_diff_extraction": 5.6,
856
+ "word_count_diff_qa": 5.533333333333333,
857
+ "word_count_diff_summarization": 51.611111111111114,
858
+ "word_count_diff_unanswerable": 4.066666666666666
859
+ },
860
+ {
861
+ "epoch": 24.0,
862
+ "grad_norm": 0.1550023853778839,
863
+ "learning_rate": 1.6898331308886863e-05,
864
+ "loss": 0.0138,
865
+ "step": 6360
866
+ },
867
+ {
868
+ "epoch": 24.0,
869
+ "eval_loss": 0.08557449281215668,
870
+ "eval_runtime": 1.7865,
871
+ "eval_samples_per_second": 44.78,
872
+ "eval_steps_per_second": 5.598,
873
+ "step": 6360
874
+ },
875
+ {
876
+ "em_boolean": 0.4117647058823529,
877
+ "em_extraction": 0.26666666666666666,
878
+ "em_qa": 0.13333333333333333,
879
+ "em_summarization": 0.0,
880
+ "em_unanswerable": 0.0,
881
+ "epoch": 25.0,
882
+ "mean_em": 0.1625,
883
+ "mean_similarity": 0.6411203743191436,
884
+ "mean_word_count_diff": 15.1875,
885
+ "similarity_boolean": 0.5644924241830321,
886
+ "similarity_extraction": 0.5594843897968531,
887
+ "similarity_qa": 0.7792828718821208,
888
+ "similarity_summarization": 0.6979754573355118,
889
+ "similarity_unanswerable": 0.6032127718130748,
890
+ "word_count_diff_boolean": 3.7058823529411766,
891
+ "word_count_diff_extraction": 4.533333333333333,
892
+ "word_count_diff_qa": 4.933333333333334,
893
+ "word_count_diff_summarization": 51.833333333333336,
894
+ "word_count_diff_unanswerable": 5.133333333333334
895
+ },
896
+ {
897
+ "epoch": 25.0,
898
+ "grad_norm": 0.23536083102226257,
899
+ "learning_rate": 1.5923413592009145e-05,
900
+ "loss": 0.0132,
901
+ "step": 6625
902
+ },
903
+ {
904
+ "epoch": 25.0,
905
+ "eval_loss": 0.0886365994811058,
906
+ "eval_runtime": 1.7918,
907
+ "eval_samples_per_second": 44.648,
908
+ "eval_steps_per_second": 5.581,
909
+ "step": 6625
910
+ },
911
+ {
912
+ "em_boolean": 0.29411764705882354,
913
+ "em_extraction": 0.13333333333333333,
914
+ "em_qa": 0.0,
915
+ "em_summarization": 0.0,
916
+ "em_unanswerable": 0.0,
917
+ "epoch": 26.0,
918
+ "mean_em": 0.0875,
919
+ "mean_similarity": 0.5999299102462828,
920
+ "mean_word_count_diff": 15.6625,
921
+ "similarity_boolean": 0.44055906716076765,
922
+ "similarity_extraction": 0.4907683741301298,
923
+ "similarity_qa": 0.64702517837286,
924
+ "similarity_summarization": 0.7336946874856949,
925
+ "similarity_unanswerable": 0.6820987343788147,
926
+ "word_count_diff_boolean": 5.9411764705882355,
927
+ "word_count_diff_extraction": 5.466666666666667,
928
+ "word_count_diff_qa": 7.066666666666666,
929
+ "word_count_diff_summarization": 50.27777777777778,
930
+ "word_count_diff_unanswerable": 3.933333333333333
931
+ },
932
+ {
933
+ "epoch": 26.0,
934
+ "grad_norm": 0.0521920807659626,
935
+ "learning_rate": 1.4944560255863805e-05,
936
+ "loss": 0.0127,
937
+ "step": 6890
938
+ },
939
+ {
940
+ "epoch": 26.0,
941
+ "eval_loss": 0.09115185588598251,
942
+ "eval_runtime": 1.7871,
943
+ "eval_samples_per_second": 44.764,
944
+ "eval_steps_per_second": 5.596,
945
+ "step": 6890
946
+ },
947
+ {
948
+ "em_boolean": 0.29411764705882354,
949
+ "em_extraction": 0.2,
950
+ "em_qa": 0.06666666666666667,
951
+ "em_summarization": 0.0,
952
+ "em_unanswerable": 0.0,
953
+ "epoch": 27.0,
954
+ "mean_em": 0.1125,
955
+ "mean_similarity": 0.5961971989367157,
956
+ "mean_word_count_diff": 15.9,
957
+ "similarity_boolean": 0.47167208264855776,
958
+ "similarity_extraction": 0.563706802825133,
959
+ "similarity_qa": 0.6419207287331422,
960
+ "similarity_summarization": 0.6927380098236932,
961
+ "similarity_unanswerable": 0.608243557314078,
962
+ "word_count_diff_boolean": 5.0,
963
+ "word_count_diff_extraction": 4.933333333333334,
964
+ "word_count_diff_qa": 6.0,
965
+ "word_count_diff_summarization": 52.0,
966
+ "word_count_diff_unanswerable": 5.8
967
+ },
968
+ {
969
+ "epoch": 27.0,
970
+ "grad_norm": 0.23173846304416656,
971
+ "learning_rate": 1.396594320574144e-05,
972
+ "loss": 0.0121,
973
+ "step": 7155
974
+ },
975
+ {
976
+ "epoch": 27.0,
977
+ "eval_loss": 0.09045173972845078,
978
+ "eval_runtime": 1.7961,
979
+ "eval_samples_per_second": 44.541,
980
+ "eval_steps_per_second": 5.568,
981
+ "step": 7155
982
+ },
983
+ {
984
+ "em_boolean": 0.5294117647058824,
985
+ "em_extraction": 0.13333333333333333,
986
+ "em_qa": 0.06666666666666667,
987
+ "em_summarization": 0.0,
988
+ "em_unanswerable": 0.0,
989
+ "epoch": 28.0,
990
+ "mean_em": 0.15,
991
+ "mean_similarity": 0.6426682359306142,
992
+ "mean_word_count_diff": 15.4625,
993
+ "similarity_boolean": 0.6154902246506775,
994
+ "similarity_extraction": 0.559150509784619,
995
+ "similarity_qa": 0.7585609555244446,
996
+ "similarity_summarization": 0.7132770286666023,
997
+ "similarity_unanswerable": 0.5563644373168548,
998
+ "word_count_diff_boolean": 3.9411764705882355,
999
+ "word_count_diff_extraction": 5.933333333333334,
1000
+ "word_count_diff_qa": 5.4,
1001
+ "word_count_diff_summarization": 51.94444444444444,
1002
+ "word_count_diff_unanswerable": 4.333333333333333
1003
+ },
1004
+ {
1005
+ "epoch": 28.0,
1006
+ "grad_norm": 0.15653730928897858,
1007
+ "learning_rate": 1.2991733339873795e-05,
1008
+ "loss": 0.0114,
1009
+ "step": 7420
1010
+ },
1011
+ {
1012
+ "epoch": 28.0,
1013
+ "eval_loss": 0.09521345049142838,
1014
+ "eval_runtime": 1.7969,
1015
+ "eval_samples_per_second": 44.521,
1016
+ "eval_steps_per_second": 5.565,
1017
+ "step": 7420
1018
+ },
1019
+ {
1020
+ "em_boolean": 0.5882352941176471,
1021
+ "em_extraction": 0.2,
1022
+ "em_qa": 0.0,
1023
+ "em_summarization": 0.0,
1024
+ "em_unanswerable": 0.0,
1025
+ "epoch": 29.0,
1026
+ "mean_em": 0.1625,
1027
+ "mean_similarity": 0.670323112141341,
1028
+ "mean_word_count_diff": 14.8125,
1029
+ "similarity_boolean": 0.6801450522068668,
1030
+ "similarity_extraction": 0.5754425642391046,
1031
+ "similarity_qa": 0.7391265859206517,
1032
+ "similarity_summarization": 0.7395255797439151,
1033
+ "similarity_unanswerable": 0.6022256930669149,
1034
+ "word_count_diff_boolean": 2.588235294117647,
1035
+ "word_count_diff_extraction": 4.0,
1036
+ "word_count_diff_qa": 5.666666666666667,
1037
+ "word_count_diff_summarization": 50.333333333333336,
1038
+ "word_count_diff_unanswerable": 6.0
1039
+ },
1040
+ {
1041
+ "epoch": 29.0,
1042
+ "grad_norm": 0.13572590053081512,
1043
+ "learning_rate": 1.2026082772927574e-05,
1044
+ "loss": 0.0112,
1045
+ "step": 7685
1046
+ },
1047
+ {
1048
+ "epoch": 29.0,
1049
+ "eval_loss": 0.09561847150325775,
1050
+ "eval_runtime": 1.7863,
1051
+ "eval_samples_per_second": 44.786,
1052
+ "eval_steps_per_second": 5.598,
1053
+ "step": 7685
1054
+ },
1055
+ {
1056
+ "em_boolean": 0.47058823529411764,
1057
+ "em_extraction": 0.26666666666666666,
1058
+ "em_qa": 0.06666666666666667,
1059
+ "em_summarization": 0.0,
1060
+ "em_unanswerable": 0.0,
1061
+ "epoch": 30.0,
1062
+ "mean_em": 0.1625,
1063
+ "mean_similarity": 0.6361284551327117,
1064
+ "mean_word_count_diff": 15.1625,
1065
+ "similarity_boolean": 0.5678887126748177,
1066
+ "similarity_extraction": 0.528444591164589,
1067
+ "similarity_qa": 0.7746080329020818,
1068
+ "similarity_summarization": 0.7153815428415934,
1069
+ "similarity_unanswerable": 0.5875674108664195,
1070
+ "word_count_diff_boolean": 3.6470588235294117,
1071
+ "word_count_diff_extraction": 4.2,
1072
+ "word_count_diff_qa": 5.666666666666667,
1073
+ "word_count_diff_summarization": 51.05555555555556,
1074
+ "word_count_diff_unanswerable": 5.6
1075
+ },
1076
+ {
1077
+ "epoch": 30.0,
1078
+ "grad_norm": 0.11106608062982559,
1079
+ "learning_rate": 1.1073107139554395e-05,
1080
+ "loss": 0.0111,
1081
+ "step": 7950
1082
+ },
1083
+ {
1084
+ "epoch": 30.0,
1085
+ "eval_loss": 0.09475980699062347,
1086
+ "eval_runtime": 1.8027,
1087
+ "eval_samples_per_second": 44.379,
1088
+ "eval_steps_per_second": 5.547,
1089
+ "step": 7950
1090
+ },
1091
+ {
1092
+ "em_boolean": 0.47058823529411764,
1093
+ "em_extraction": 0.0,
1094
+ "em_qa": 0.06666666666666667,
1095
+ "em_summarization": 0.0,
1096
+ "em_unanswerable": 0.0,
1097
+ "epoch": 31.0,
1098
+ "mean_em": 0.1125,
1099
+ "mean_similarity": 0.5996635487768799,
1100
+ "mean_word_count_diff": 15.9625,
1101
+ "similarity_boolean": 0.5703230380792829,
1102
+ "similarity_extraction": 0.43614052472015225,
1103
+ "similarity_qa": 0.6746748656034469,
1104
+ "similarity_summarization": 0.6909497512711419,
1105
+ "similarity_unanswerable": 0.6118843918045361,
1106
+ "word_count_diff_boolean": 4.176470588235294,
1107
+ "word_count_diff_extraction": 6.933333333333334,
1108
+ "word_count_diff_qa": 6.466666666666667,
1109
+ "word_count_diff_summarization": 51.888888888888886,
1110
+ "word_count_diff_unanswerable": 4.733333333333333
1111
+ },
1112
+ {
1113
+ "epoch": 31.0,
1114
+ "grad_norm": 0.15586383640766144,
1115
+ "learning_rate": 1.0136868053419842e-05,
1116
+ "loss": 0.0105,
1117
+ "step": 8215
1118
+ },
1119
+ {
1120
+ "epoch": 31.0,
1121
+ "eval_loss": 0.09651915729045868,
1122
+ "eval_runtime": 1.7878,
1123
+ "eval_samples_per_second": 44.749,
1124
+ "eval_steps_per_second": 5.594,
1125
+ "step": 8215
1126
+ },
1127
+ {
1128
+ "em_boolean": 0.35294117647058826,
1129
+ "em_extraction": 0.26666666666666666,
1130
+ "em_qa": 0.0,
1131
+ "em_summarization": 0.0,
1132
+ "em_unanswerable": 0.0,
1133
+ "epoch": 32.0,
1134
+ "mean_em": 0.125,
1135
+ "mean_similarity": 0.6647563714534044,
1136
+ "mean_word_count_diff": 15.3125,
1137
+ "similarity_boolean": 0.4992627663647427,
1138
+ "similarity_extraction": 0.6371853078405062,
1139
+ "similarity_qa": 0.7779242674509684,
1140
+ "similarity_summarization": 0.7545208003785875,
1141
+ "similarity_unanswerable": 0.6590016434590021,
1142
+ "word_count_diff_boolean": 4.352941176470588,
1143
+ "word_count_diff_extraction": 3.6666666666666665,
1144
+ "word_count_diff_qa": 7.133333333333334,
1145
+ "word_count_diff_summarization": 52.22222222222222,
1146
+ "word_count_diff_unanswerable": 3.2666666666666666
1147
+ },
1148
+ {
1149
+ "epoch": 32.0,
1150
+ "grad_norm": 0.15895779430866241,
1151
+ "learning_rate": 9.22135579647165e-06,
1152
+ "loss": 0.0103,
1153
+ "step": 8480
1154
+ },
1155
+ {
1156
+ "epoch": 32.0,
1157
+ "eval_loss": 0.09846033155918121,
1158
+ "eval_runtime": 1.7981,
1159
+ "eval_samples_per_second": 44.492,
1160
+ "eval_steps_per_second": 5.562,
1161
+ "step": 8480
1162
+ },
1163
+ {
1164
+ "em_boolean": 0.35294117647058826,
1165
+ "em_extraction": 0.13333333333333333,
1166
+ "em_qa": 0.0,
1167
+ "em_summarization": 0.0,
1168
+ "em_unanswerable": 0.0,
1169
+ "epoch": 33.0,
1170
+ "mean_em": 0.1,
1171
+ "mean_similarity": 0.6497376295737922,
1172
+ "mean_word_count_diff": 15.2,
1173
+ "similarity_boolean": 0.4850216718281017,
1174
+ "similarity_extraction": 0.6169686233003934,
1175
+ "similarity_qa": 0.7874227881431579,
1176
+ "similarity_summarization": 0.720199970735444,
1177
+ "similarity_unanswerable": 0.6469447533289592,
1178
+ "word_count_diff_boolean": 5.529411764705882,
1179
+ "word_count_diff_extraction": 4.0,
1180
+ "word_count_diff_qa": 5.466666666666667,
1181
+ "word_count_diff_summarization": 50.72222222222222,
1182
+ "word_count_diff_unanswerable": 4.466666666666667
1183
+ },
1184
+ {
1185
+ "epoch": 33.0,
1186
+ "grad_norm": 0.16729232668876648,
1187
+ "learning_rate": 8.330472312226091e-06,
1188
+ "loss": 0.0099,
1189
+ "step": 8745
1190
+ },
1191
+ {
1192
+ "epoch": 33.0,
1193
+ "eval_loss": 0.09990086406469345,
1194
+ "eval_runtime": 1.7757,
1195
+ "eval_samples_per_second": 45.052,
1196
+ "eval_steps_per_second": 5.631,
1197
+ "step": 8745
1198
+ },
1199
+ {
1200
+ "em_boolean": 0.4117647058823529,
1201
+ "em_extraction": 0.2,
1202
+ "em_qa": 0.0,
1203
+ "em_summarization": 0.0,
1204
+ "em_unanswerable": 0.0,
1205
+ "epoch": 34.0,
1206
+ "mean_em": 0.125,
1207
+ "mean_similarity": 0.6532467395067215,
1208
+ "mean_word_count_diff": 15.3375,
1209
+ "similarity_boolean": 0.5624497304944431,
1210
+ "similarity_extraction": 0.6123799696564675,
1211
+ "similarity_qa": 0.7896470129489899,
1212
+ "similarity_summarization": 0.6943622730258439,
1213
+ "similarity_unanswerable": 0.6112778725723426,
1214
+ "word_count_diff_boolean": 4.588235294117647,
1215
+ "word_count_diff_extraction": 5.266666666666667,
1216
+ "word_count_diff_qa": 5.933333333333334,
1217
+ "word_count_diff_summarization": 50.666666666666664,
1218
+ "word_count_diff_unanswerable": 4.6
1219
+ },
1220
+ {
1221
+ "epoch": 34.0,
1222
+ "grad_norm": 0.3746591806411743,
1223
+ "learning_rate": 7.468014575555688e-06,
1224
+ "loss": 0.0096,
1225
+ "step": 9010
1226
+ },
1227
+ {
1228
+ "epoch": 34.0,
1229
+ "eval_loss": 0.10108506679534912,
1230
+ "eval_runtime": 1.7759,
1231
+ "eval_samples_per_second": 45.048,
1232
+ "eval_steps_per_second": 5.631,
1233
+ "step": 9010
1234
+ },
1235
+ {
1236
+ "em_boolean": 0.35294117647058826,
1237
+ "em_extraction": 0.13333333333333333,
1238
+ "em_qa": 0.13333333333333333,
1239
+ "em_summarization": 0.0,
1240
+ "em_unanswerable": 0.0,
1241
+ "epoch": 35.0,
1242
+ "mean_em": 0.125,
1243
+ "mean_similarity": 0.6299693588167429,
1244
+ "mean_word_count_diff": 15.35,
1245
+ "similarity_boolean": 0.5166072974748471,
1246
+ "similarity_extraction": 0.55517836039265,
1247
+ "similarity_qa": 0.7496427396933237,
1248
+ "similarity_summarization": 0.7208915799856186,
1249
+ "similarity_unanswerable": 0.6044573138157526,
1250
+ "word_count_diff_boolean": 4.352941176470588,
1251
+ "word_count_diff_extraction": 5.266666666666667,
1252
+ "word_count_diff_qa": 4.8,
1253
+ "word_count_diff_summarization": 51.388888888888886,
1254
+ "word_count_diff_unanswerable": 5.2
1255
+ },
1256
+ {
1257
+ "epoch": 35.0,
1258
+ "grad_norm": 0.310463547706604,
1259
+ "learning_rate": 6.637658409856717e-06,
1260
+ "loss": 0.0096,
1261
+ "step": 9275
1262
+ },
1263
+ {
1264
+ "epoch": 35.0,
1265
+ "eval_loss": 0.10128389298915863,
1266
+ "eval_runtime": 1.7949,
1267
+ "eval_samples_per_second": 44.571,
1268
+ "eval_steps_per_second": 5.571,
1269
+ "step": 9275
1270
+ },
1271
+ {
1272
+ "em_boolean": 0.5294117647058824,
1273
+ "em_extraction": 0.2,
1274
+ "em_qa": 0.06666666666666667,
1275
+ "em_summarization": 0.0,
1276
+ "em_unanswerable": 0.0,
1277
+ "epoch": 36.0,
1278
+ "mean_em": 0.1625,
1279
+ "mean_similarity": 0.6648560125031509,
1280
+ "mean_word_count_diff": 14.9,
1281
+ "similarity_boolean": 0.6631740967688315,
1282
+ "similarity_extraction": 0.5298445565005143,
1283
+ "similarity_qa": 0.7434355229139328,
1284
+ "similarity_summarization": 0.7201196981800927,
1285
+ "similarity_unanswerable": 0.6568777064482371,
1286
+ "word_count_diff_boolean": 2.2941176470588234,
1287
+ "word_count_diff_extraction": 5.2,
1288
+ "word_count_diff_qa": 5.333333333333333,
1289
+ "word_count_diff_summarization": 52.0,
1290
+ "word_count_diff_unanswerable": 3.933333333333333
1291
+ },
1292
+ {
1293
+ "epoch": 36.0,
1294
+ "grad_norm": 0.23128336668014526,
1295
+ "learning_rate": 5.84294282056834e-06,
1296
+ "loss": 0.0094,
1297
+ "step": 9540
1298
+ },
1299
+ {
1300
+ "epoch": 36.0,
1301
+ "eval_loss": 0.10348665714263916,
1302
+ "eval_runtime": 1.7894,
1303
+ "eval_samples_per_second": 44.707,
1304
+ "eval_steps_per_second": 5.588,
1305
+ "step": 9540
1306
+ },
1307
+ {
1308
+ "em_boolean": 0.47058823529411764,
1309
+ "em_extraction": 0.2,
1310
+ "em_qa": 0.0,
1311
+ "em_summarization": 0.0,
1312
+ "em_unanswerable": 0.0,
1313
+ "epoch": 37.0,
1314
+ "mean_em": 0.1375,
1315
+ "mean_similarity": 0.6319401320070028,
1316
+ "mean_word_count_diff": 15.0875,
1317
+ "similarity_boolean": 0.5821067885879208,
1318
+ "similarity_extraction": 0.5178047935167949,
1319
+ "similarity_qa": 0.769520037372907,
1320
+ "similarity_summarization": 0.6793310083448887,
1321
+ "similarity_unanswerable": 0.6081043027341366,
1322
+ "word_count_diff_boolean": 4.235294117647059,
1323
+ "word_count_diff_extraction": 4.866666666666666,
1324
+ "word_count_diff_qa": 5.0,
1325
+ "word_count_diff_summarization": 50.833333333333336,
1326
+ "word_count_diff_unanswerable": 4.8
1327
+ },
1328
+ {
1329
+ "epoch": 37.0,
1330
+ "grad_norm": 0.10078708827495575,
1331
+ "learning_rate": 5.087254911814361e-06,
1332
+ "loss": 0.0092,
1333
+ "step": 9805
1334
+ },
1335
+ {
1336
+ "epoch": 37.0,
1337
+ "eval_loss": 0.10369674116373062,
1338
+ "eval_runtime": 1.7998,
1339
+ "eval_samples_per_second": 44.45,
1340
+ "eval_steps_per_second": 5.556,
1341
+ "step": 9805
1342
+ },
1343
+ {
1344
+ "em_boolean": 0.4117647058823529,
1345
+ "em_extraction": 0.13333333333333333,
1346
+ "em_qa": 0.0,
1347
+ "em_summarization": 0.0,
1348
+ "em_unanswerable": 0.0,
1349
+ "epoch": 38.0,
1350
+ "mean_em": 0.1125,
1351
+ "mean_similarity": 0.6402258106973022,
1352
+ "mean_word_count_diff": 15.3875,
1353
+ "similarity_boolean": 0.5555457597708001,
1354
+ "similarity_extraction": 0.5125755973160266,
1355
+ "similarity_qa": 0.729976910352707,
1356
+ "similarity_summarization": 0.7154302892999517,
1357
+ "similarity_unanswerable": 0.6838502744833629,
1358
+ "word_count_diff_boolean": 4.352941176470588,
1359
+ "word_count_diff_extraction": 4.466666666666667,
1360
+ "word_count_diff_qa": 6.266666666666667,
1361
+ "word_count_diff_summarization": 51.166666666666664,
1362
+ "word_count_diff_unanswerable": 5.0
1363
+ },
1364
+ {
1365
+ "epoch": 38.0,
1366
+ "grad_norm": 0.14647193253040314,
1367
+ "learning_rate": 4.373815450453467e-06,
1368
+ "loss": 0.0087,
1369
+ "step": 10070
1370
+ },
1371
+ {
1372
+ "epoch": 38.0,
1373
+ "eval_loss": 0.10511450469493866,
1374
+ "eval_runtime": 1.8033,
1375
+ "eval_samples_per_second": 44.364,
1376
+ "eval_steps_per_second": 5.545,
1377
+ "step": 10070
1378
+ },
1379
+ {
1380
+ "em_boolean": 0.29411764705882354,
1381
+ "em_extraction": 0.26666666666666666,
1382
+ "em_qa": 0.13333333333333333,
1383
+ "em_summarization": 0.0,
1384
+ "em_unanswerable": 0.0,
1385
+ "epoch": 39.0,
1386
+ "mean_em": 0.1375,
1387
+ "mean_similarity": 0.5966290417010895,
1388
+ "mean_word_count_diff": 15.375,
1389
+ "similarity_boolean": 0.48111217118361416,
1390
+ "similarity_extraction": 0.5464107090607285,
1391
+ "similarity_qa": 0.7710953007141749,
1392
+ "similarity_summarization": 0.6638153013255861,
1393
+ "similarity_unanswerable": 0.5226767236987749,
1394
+ "word_count_diff_boolean": 4.294117647058823,
1395
+ "word_count_diff_extraction": 5.133333333333334,
1396
+ "word_count_diff_qa": 5.466666666666667,
1397
+ "word_count_diff_summarization": 50.611111111111114,
1398
+ "word_count_diff_unanswerable": 5.8
1399
+ },
1400
+ {
1401
+ "epoch": 39.0,
1402
+ "grad_norm": 0.8468394875526428,
1403
+ "learning_rate": 3.7056651390643413e-06,
1404
+ "loss": 0.0088,
1405
+ "step": 10335
1406
+ },
1407
+ {
1408
+ "epoch": 39.0,
1409
+ "eval_loss": 0.10422440618276596,
1410
+ "eval_runtime": 1.7878,
1411
+ "eval_samples_per_second": 44.747,
1412
+ "eval_steps_per_second": 5.593,
1413
+ "step": 10335
1414
+ },
1415
+ {
1416
+ "em_boolean": 0.47058823529411764,
1417
+ "em_extraction": 0.26666666666666666,
1418
+ "em_qa": 0.13333333333333333,
1419
+ "em_summarization": 0.0,
1420
+ "em_unanswerable": 0.0,
1421
+ "epoch": 40.0,
1422
+ "mean_em": 0.175,
1423
+ "mean_similarity": 0.6348526364192366,
1424
+ "mean_word_count_diff": 15.1875,
1425
+ "similarity_boolean": 0.5687163450262126,
1426
+ "similarity_extraction": 0.62134765163064,
1427
+ "similarity_qa": 0.7562251538038254,
1428
+ "similarity_summarization": 0.6440524767256446,
1429
+ "similarity_unanswerable": 0.5908997590343158,
1430
+ "word_count_diff_boolean": 4.529411764705882,
1431
+ "word_count_diff_extraction": 4.133333333333334,
1432
+ "word_count_diff_qa": 4.866666666666666,
1433
+ "word_count_diff_summarization": 50.666666666666664,
1434
+ "word_count_diff_unanswerable": 6.066666666666666
1435
+ },
1436
+ {
1437
+ "epoch": 40.0,
1438
+ "grad_norm": 0.15559451282024384,
1439
+ "learning_rate": 3.08565165637071e-06,
1440
+ "loss": 0.0088,
1441
+ "step": 10600
1442
+ },
1443
+ {
1444
+ "epoch": 40.0,
1445
+ "eval_loss": 0.1041550487279892,
1446
+ "eval_runtime": 1.7986,
1447
+ "eval_samples_per_second": 44.479,
1448
+ "eval_steps_per_second": 5.56,
1449
+ "step": 10600
1450
+ },
1451
+ {
1452
+ "em_boolean": 0.4117647058823529,
1453
+ "em_extraction": 0.2,
1454
+ "em_qa": 0.0,
1455
+ "em_summarization": 0.0,
1456
+ "em_unanswerable": 0.0,
1457
+ "epoch": 41.0,
1458
+ "mean_em": 0.125,
1459
+ "mean_similarity": 0.6427899678237736,
1460
+ "mean_word_count_diff": 15.15,
1461
+ "similarity_boolean": 0.5819402319543502,
1462
+ "similarity_extraction": 0.5856266627709071,
1463
+ "similarity_qa": 0.7046878506739934,
1464
+ "similarity_summarization": 0.7580131689707438,
1465
+ "similarity_unanswerable": 0.5687505826354027,
1466
+ "word_count_diff_boolean": 3.0,
1467
+ "word_count_diff_extraction": 5.266666666666667,
1468
+ "word_count_diff_qa": 5.466666666666667,
1469
+ "word_count_diff_summarization": 51.44444444444444,
1470
+ "word_count_diff_unanswerable": 4.933333333333334
1471
+ },
1472
+ {
1473
+ "epoch": 41.0,
1474
+ "grad_norm": 0.2692953050136566,
1475
+ "learning_rate": 2.516417520340457e-06,
1476
+ "loss": 0.0085,
1477
+ "step": 10865
1478
+ },
1479
+ {
1480
+ "epoch": 41.0,
1481
+ "eval_loss": 0.1051572784781456,
1482
+ "eval_runtime": 1.7897,
1483
+ "eval_samples_per_second": 44.701,
1484
+ "eval_steps_per_second": 5.588,
1485
+ "step": 10865
1486
+ },
1487
+ {
1488
+ "em_boolean": 0.47058823529411764,
1489
+ "em_extraction": 0.3333333333333333,
1490
+ "em_qa": 0.0,
1491
+ "em_summarization": 0.0,
1492
+ "em_unanswerable": 0.0,
1493
+ "epoch": 42.0,
1494
+ "mean_em": 0.1625,
1495
+ "mean_similarity": 0.6774277022806927,
1496
+ "mean_word_count_diff": 15.4,
1497
+ "similarity_boolean": 0.600595106206396,
1498
+ "similarity_extraction": 0.644695137689511,
1499
+ "similarity_qa": 0.7859726687272389,
1500
+ "similarity_summarization": 0.7171196627120177,
1501
+ "similarity_unanswerable": 0.6410618901252747,
1502
+ "word_count_diff_boolean": 3.8823529411764706,
1503
+ "word_count_diff_extraction": 4.0,
1504
+ "word_count_diff_qa": 6.333333333333333,
1505
+ "word_count_diff_summarization": 53.05555555555556,
1506
+ "word_count_diff_unanswerable": 3.7333333333333334
1507
+ },
1508
+ {
1509
+ "epoch": 42.0,
1510
+ "grad_norm": 0.028788737952709198,
1511
+ "learning_rate": 2.000388825686658e-06,
1512
+ "loss": 0.0084,
1513
+ "step": 11130
1514
+ },
1515
+ {
1516
+ "epoch": 42.0,
1517
+ "eval_loss": 0.10606852918863297,
1518
+ "eval_runtime": 1.7957,
1519
+ "eval_samples_per_second": 44.551,
1520
+ "eval_steps_per_second": 5.569,
1521
+ "step": 11130
1522
+ },
1523
+ {
1524
+ "em_boolean": 0.4117647058823529,
1525
+ "em_extraction": 0.2,
1526
+ "em_qa": 0.0,
1527
+ "em_summarization": 0.0,
1528
+ "em_unanswerable": 0.0,
1529
+ "epoch": 43.0,
1530
+ "mean_em": 0.125,
1531
+ "mean_similarity": 0.6729973700363189,
1532
+ "mean_word_count_diff": 14.55,
1533
+ "similarity_boolean": 0.6187414353822961,
1534
+ "similarity_extraction": 0.5894727125763893,
1535
+ "similarity_qa": 0.7754949867725373,
1536
+ "similarity_summarization": 0.7333515452014076,
1537
+ "similarity_unanswerable": 0.643089459836483,
1538
+ "word_count_diff_boolean": 2.764705882352941,
1539
+ "word_count_diff_extraction": 2.933333333333333,
1540
+ "word_count_diff_qa": 6.0,
1541
+ "word_count_diff_summarization": 50.166666666666664,
1542
+ "word_count_diff_unanswerable": 5.333333333333333
1543
+ },
1544
+ {
1545
+ "epoch": 43.0,
1546
+ "grad_norm": 0.11988003551959991,
1547
+ "learning_rate": 1.5397649037716471e-06,
1548
+ "loss": 0.0084,
1549
+ "step": 11395
1550
+ },
1551
+ {
1552
+ "epoch": 43.0,
1553
+ "eval_loss": 0.10630540549755096,
1554
+ "eval_runtime": 1.7956,
1555
+ "eval_samples_per_second": 44.554,
1556
+ "eval_steps_per_second": 5.569,
1557
+ "step": 11395
1558
+ },
1559
+ {
1560
+ "em_boolean": 0.4117647058823529,
1561
+ "em_extraction": 0.13333333333333333,
1562
+ "em_qa": 0.0,
1563
+ "em_summarization": 0.0,
1564
+ "em_unanswerable": 0.0,
1565
+ "epoch": 44.0,
1566
+ "mean_em": 0.1125,
1567
+ "mean_similarity": 0.6471819347003475,
1568
+ "mean_word_count_diff": 14.9,
1569
+ "similarity_boolean": 0.5824065589729477,
1570
+ "similarity_extraction": 0.5456480238586664,
1571
+ "similarity_qa": 0.7224714895089467,
1572
+ "similarity_summarization": 0.7356228894657559,
1573
+ "similarity_unanswerable": 0.6407092375059923,
1574
+ "word_count_diff_boolean": 4.0,
1575
+ "word_count_diff_extraction": 3.8666666666666667,
1576
+ "word_count_diff_qa": 5.466666666666667,
1577
+ "word_count_diff_summarization": 50.388888888888886,
1578
+ "word_count_diff_unanswerable": 5.133333333333334
1579
+ },
1580
+ {
1581
+ "epoch": 44.0,
1582
+ "grad_norm": 0.08798056095838547,
1583
+ "learning_rate": 1.1365089489840635e-06,
1584
+ "loss": 0.0083,
1585
+ "step": 11660
1586
+ },
1587
+ {
1588
+ "epoch": 44.0,
1589
+ "eval_loss": 0.10651306062936783,
1590
+ "eval_runtime": 1.8039,
1591
+ "eval_samples_per_second": 44.348,
1592
+ "eval_steps_per_second": 5.543,
1593
+ "step": 11660
1594
+ }
1595
+ ],
1596
+ "logging_steps": 500,
1597
+ "max_steps": 13250,
1598
+ "num_input_tokens_seen": 0,
1599
+ "num_train_epochs": 50,
1600
+ "save_steps": 500,
1601
+ "stateful_callbacks": {
1602
+ "TrainerControl": {
1603
+ "args": {
1604
+ "should_epoch_stop": false,
1605
+ "should_evaluate": false,
1606
+ "should_log": false,
1607
+ "should_save": true,
1608
+ "should_training_stop": false
1609
+ },
1610
+ "attributes": {}
1611
+ }
1612
+ },
1613
+ "total_flos": 3.1876824271159296e+16,
1614
+ "train_batch_size": 4,
1615
+ "trial_name": null,
1616
+ "trial_params": null
1617
+ }
checkpoint-11660/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a42f35ca56de4716016f99e4c1ec8c3abc7da2b9d03b422aae399b849522e7a
3
+ size 5304
checkpoint-11925/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
checkpoint-11925/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
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": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.48.3",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
checkpoint-11925/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": "4.48.3"
7
+ }
checkpoint-11925/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c47edf9b6f25037e39aef8be9ac3dd11caf2c61a4f86130622a3eb789abc8f
3
+ size 990345064
checkpoint-11925/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9b5900bae91c27c6f9d5ae35611438fec2bdccb2074c07fb1a5c345e166862
3
+ size 1980860410
checkpoint-11925/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b667c934b62681cda2a566e073e2f99ea76f7a4f6fd5bc905f881552457de3
3
+ size 14244
checkpoint-11925/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed6d1b25fc59be4590d64d8f27e97d710dbf77849f7cd9b1c35f9e868741d51
3
+ size 1064
checkpoint-11925/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoint-11925/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-11925/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 512,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
checkpoint-11925/trainer_state.json ADDED
@@ -0,0 +1,1653 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06431461870670319,
3
+ "best_model_checkpoint": "./teapotllm/checkpoint-1855",
4
+ "epoch": 45.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11925,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "em_boolean": 0.11764705882352941,
13
+ "em_extraction": 0.06666666666666667,
14
+ "em_qa": 0.0,
15
+ "em_summarization": 0.0,
16
+ "em_unanswerable": 0.0,
17
+ "epoch": 1.0,
18
+ "mean_em": 0.0375,
19
+ "mean_similarity": 0.3622433557640761,
20
+ "mean_word_count_diff": 17.7125,
21
+ "similarity_boolean": 0.18269754047779477,
22
+ "similarity_extraction": 0.2946929598848025,
23
+ "similarity_qa": 0.43210459053516387,
24
+ "similarity_summarization": 0.6143242551220788,
25
+ "similarity_unanswerable": 0.26092069496711096,
26
+ "word_count_diff_boolean": 9.0,
27
+ "word_count_diff_extraction": 7.666666666666667,
28
+ "word_count_diff_qa": 6.933333333333334,
29
+ "word_count_diff_summarization": 53.111111111111114,
30
+ "word_count_diff_unanswerable": 5.933333333333334
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 101.51641082763672,
35
+ "learning_rate": 1.59e-05,
36
+ "loss": 40.3479,
37
+ "step": 265
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 19.639965057373047,
42
+ "eval_runtime": 1.7948,
43
+ "eval_samples_per_second": 44.573,
44
+ "eval_steps_per_second": 5.572,
45
+ "step": 265
46
+ },
47
+ {
48
+ "em_boolean": 0.058823529411764705,
49
+ "em_extraction": 0.0,
50
+ "em_qa": 0.0,
51
+ "em_summarization": 0.0,
52
+ "em_unanswerable": 0.0,
53
+ "epoch": 2.0,
54
+ "mean_em": 0.0125,
55
+ "mean_similarity": 0.37655651543755086,
56
+ "mean_word_count_diff": 17.1625,
57
+ "similarity_boolean": 0.10583376435234267,
58
+ "similarity_extraction": 0.21972424462437629,
59
+ "similarity_qa": 0.5285325924555461,
60
+ "similarity_summarization": 0.6654400361908807,
61
+ "similarity_unanswerable": 0.34157160222530364,
62
+ "word_count_diff_boolean": 10.176470588235293,
63
+ "word_count_diff_extraction": 6.133333333333334,
64
+ "word_count_diff_qa": 5.866666666666666,
65
+ "word_count_diff_summarization": 52.166666666666664,
66
+ "word_count_diff_unanswerable": 5.4
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.2927296459674835,
71
+ "learning_rate": 2.9999590191302685e-05,
72
+ "loss": 1.8688,
73
+ "step": 530
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.08876434713602066,
78
+ "eval_runtime": 1.7881,
79
+ "eval_samples_per_second": 44.74,
80
+ "eval_steps_per_second": 5.593,
81
+ "step": 530
82
+ },
83
+ {
84
+ "em_boolean": 0.29411764705882354,
85
+ "em_extraction": 0.13333333333333333,
86
+ "em_qa": 0.06666666666666667,
87
+ "em_summarization": 0.0,
88
+ "em_unanswerable": 0.0,
89
+ "epoch": 3.0,
90
+ "mean_em": 0.1,
91
+ "mean_similarity": 0.468679612770211,
92
+ "mean_word_count_diff": 16.8875,
93
+ "similarity_boolean": 0.36136592250755606,
94
+ "similarity_extraction": 0.3513699695467949,
95
+ "similarity_qa": 0.5638724292318026,
96
+ "similarity_summarization": 0.661304693048199,
97
+ "similarity_unanswerable": 0.3812685254961252,
98
+ "word_count_diff_boolean": 5.411764705882353,
99
+ "word_count_diff_extraction": 8.066666666666666,
100
+ "word_count_diff_qa": 5.6,
101
+ "word_count_diff_summarization": 53.333333333333336,
102
+ "word_count_diff_unanswerable": 6.266666666666667
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "grad_norm": 0.2717432379722595,
107
+ "learning_rate": 2.9960391039419217e-05,
108
+ "loss": 0.0745,
109
+ "step": 795
110
+ },
111
+ {
112
+ "epoch": 3.0,
113
+ "eval_loss": 0.07186319679021835,
114
+ "eval_runtime": 1.7817,
115
+ "eval_samples_per_second": 44.901,
116
+ "eval_steps_per_second": 5.613,
117
+ "step": 795
118
+ },
119
+ {
120
+ "em_boolean": 0.5294117647058824,
121
+ "em_extraction": 0.0,
122
+ "em_qa": 0.0,
123
+ "em_summarization": 0.0,
124
+ "em_unanswerable": 0.0,
125
+ "epoch": 4.0,
126
+ "mean_em": 0.1125,
127
+ "mean_similarity": 0.5406636619823985,
128
+ "mean_word_count_diff": 16.4,
129
+ "similarity_boolean": 0.5694808649337467,
130
+ "similarity_extraction": 0.2759806969513496,
131
+ "similarity_qa": 0.5888164043426514,
132
+ "similarity_summarization": 0.6777413653002845,
133
+ "similarity_unanswerable": 0.5600411439935367,
134
+ "word_count_diff_boolean": 3.411764705882353,
135
+ "word_count_diff_extraction": 9.133333333333333,
136
+ "word_count_diff_qa": 5.733333333333333,
137
+ "word_count_diff_summarization": 52.611111111111114,
138
+ "word_count_diff_unanswerable": 5.6
139
+ },
140
+ {
141
+ "epoch": 4.0,
142
+ "grad_norm": 0.33120226860046387,
143
+ "learning_rate": 2.985743020616636e-05,
144
+ "loss": 0.0583,
145
+ "step": 1060
146
+ },
147
+ {
148
+ "epoch": 4.0,
149
+ "eval_loss": 0.06767071783542633,
150
+ "eval_runtime": 1.8031,
151
+ "eval_samples_per_second": 44.368,
152
+ "eval_steps_per_second": 5.546,
153
+ "step": 1060
154
+ },
155
+ {
156
+ "em_boolean": 0.35294117647058826,
157
+ "em_extraction": 0.06666666666666667,
158
+ "em_qa": 0.06666666666666667,
159
+ "em_summarization": 0.0,
160
+ "em_unanswerable": 0.0,
161
+ "epoch": 5.0,
162
+ "mean_em": 0.1,
163
+ "mean_similarity": 0.5391882328083739,
164
+ "mean_word_count_diff": 16.5375,
165
+ "similarity_boolean": 0.4291324294446146,
166
+ "similarity_extraction": 0.3934509038925171,
167
+ "similarity_qa": 0.5968125452597935,
168
+ "similarity_summarization": 0.6669783542553583,
169
+ "similarity_unanswerable": 0.5986830140153567,
170
+ "word_count_diff_boolean": 5.9411764705882355,
171
+ "word_count_diff_extraction": 5.866666666666666,
172
+ "word_count_diff_qa": 5.4,
173
+ "word_count_diff_summarization": 53.77777777777778,
174
+ "word_count_diff_unanswerable": 5.666666666666667
175
+ },
176
+ {
177
+ "epoch": 5.0,
178
+ "grad_norm": 0.05014026165008545,
179
+ "learning_rate": 2.969114651402049e-05,
180
+ "loss": 0.0512,
181
+ "step": 1325
182
+ },
183
+ {
184
+ "epoch": 5.0,
185
+ "eval_loss": 0.06544757634401321,
186
+ "eval_runtime": 1.797,
187
+ "eval_samples_per_second": 44.518,
188
+ "eval_steps_per_second": 5.565,
189
+ "step": 1325
190
+ },
191
+ {
192
+ "em_boolean": 0.35294117647058826,
193
+ "em_extraction": 0.13333333333333333,
194
+ "em_qa": 0.0,
195
+ "em_summarization": 0.0,
196
+ "em_unanswerable": 0.0,
197
+ "epoch": 6.0,
198
+ "mean_em": 0.1,
199
+ "mean_similarity": 0.5817075100494549,
200
+ "mean_word_count_diff": 16.1375,
201
+ "similarity_boolean": 0.3759182594059145,
202
+ "similarity_extraction": 0.5534958879152934,
203
+ "similarity_qa": 0.6812621881564458,
204
+ "similarity_summarization": 0.661298368126154,
205
+ "similarity_unanswerable": 0.648083241780599,
206
+ "word_count_diff_boolean": 6.294117647058823,
207
+ "word_count_diff_extraction": 4.466666666666667,
208
+ "word_count_diff_qa": 5.666666666666667,
209
+ "word_count_diff_summarization": 52.55555555555556,
210
+ "word_count_diff_unanswerable": 5.733333333333333
211
+ },
212
+ {
213
+ "epoch": 6.0,
214
+ "grad_norm": 0.37450432777404785,
215
+ "learning_rate": 2.9462248669576738e-05,
216
+ "loss": 0.0466,
217
+ "step": 1590
218
+ },
219
+ {
220
+ "epoch": 6.0,
221
+ "eval_loss": 0.0656035840511322,
222
+ "eval_runtime": 1.8115,
223
+ "eval_samples_per_second": 44.161,
224
+ "eval_steps_per_second": 5.52,
225
+ "step": 1590
226
+ },
227
+ {
228
+ "em_boolean": 0.29411764705882354,
229
+ "em_extraction": 0.06666666666666667,
230
+ "em_qa": 0.06666666666666667,
231
+ "em_summarization": 0.0,
232
+ "em_unanswerable": 0.0,
233
+ "epoch": 7.0,
234
+ "mean_em": 0.0875,
235
+ "mean_similarity": 0.584748298721388,
236
+ "mean_word_count_diff": 16.4875,
237
+ "similarity_boolean": 0.3921016369234113,
238
+ "similarity_extraction": 0.4258095269401868,
239
+ "similarity_qa": 0.8010195712248485,
240
+ "similarity_summarization": 0.7269510593679216,
241
+ "similarity_unanswerable": 0.5751053685943286,
242
+ "word_count_diff_boolean": 6.529411764705882,
243
+ "word_count_diff_extraction": 7.4,
244
+ "word_count_diff_qa": 4.266666666666667,
245
+ "word_count_diff_summarization": 51.5,
246
+ "word_count_diff_unanswerable": 7.066666666666666
247
+ },
248
+ {
249
+ "epoch": 7.0,
250
+ "grad_norm": 0.2656797170639038,
251
+ "learning_rate": 2.9171712243018076e-05,
252
+ "loss": 0.043,
253
+ "step": 1855
254
+ },
255
+ {
256
+ "epoch": 7.0,
257
+ "eval_loss": 0.06431461870670319,
258
+ "eval_runtime": 1.779,
259
+ "eval_samples_per_second": 44.968,
260
+ "eval_steps_per_second": 5.621,
261
+ "step": 1855
262
+ },
263
+ {
264
+ "em_boolean": 0.23529411764705882,
265
+ "em_extraction": 0.3333333333333333,
266
+ "em_qa": 0.13333333333333333,
267
+ "em_summarization": 0.0,
268
+ "em_unanswerable": 0.0,
269
+ "epoch": 8.0,
270
+ "mean_em": 0.1375,
271
+ "mean_similarity": 0.5707565736840479,
272
+ "mean_word_count_diff": 15.9125,
273
+ "similarity_boolean": 0.3595361856962828,
274
+ "similarity_extraction": 0.6590617413322131,
275
+ "similarity_qa": 0.6671084851026535,
276
+ "similarity_summarization": 0.672764014866617,
277
+ "similarity_unanswerable": 0.503073671584328,
278
+ "word_count_diff_boolean": 6.705882352941177,
279
+ "word_count_diff_extraction": 4.133333333333334,
280
+ "word_count_diff_qa": 4.0,
281
+ "word_count_diff_summarization": 51.833333333333336,
282
+ "word_count_diff_unanswerable": 6.933333333333334
283
+ },
284
+ {
285
+ "epoch": 8.0,
286
+ "grad_norm": 0.1501343548297882,
287
+ "learning_rate": 2.882077551020291e-05,
288
+ "loss": 0.0393,
289
+ "step": 2120
290
+ },
291
+ {
292
+ "epoch": 8.0,
293
+ "eval_loss": 0.064610555768013,
294
+ "eval_runtime": 1.7854,
295
+ "eval_samples_per_second": 44.809,
296
+ "eval_steps_per_second": 5.601,
297
+ "step": 2120
298
+ },
299
+ {
300
+ "em_boolean": 0.29411764705882354,
301
+ "em_extraction": 0.13333333333333333,
302
+ "em_qa": 0.0,
303
+ "em_summarization": 0.0,
304
+ "em_unanswerable": 0.0,
305
+ "epoch": 9.0,
306
+ "mean_em": 0.0875,
307
+ "mean_similarity": 0.5716628619702533,
308
+ "mean_word_count_diff": 16.075,
309
+ "similarity_boolean": 0.46071117371320724,
310
+ "similarity_extraction": 0.5175981452067693,
311
+ "similarity_qa": 0.6631501737982035,
312
+ "similarity_summarization": 0.6426751317663325,
313
+ "similarity_unanswerable": 0.5747707898418108,
314
+ "word_count_diff_boolean": 5.235294117647059,
315
+ "word_count_diff_extraction": 7.333333333333333,
316
+ "word_count_diff_qa": 5.6,
317
+ "word_count_diff_summarization": 52.22222222222222,
318
+ "word_count_diff_unanswerable": 4.2
319
+ },
320
+ {
321
+ "epoch": 9.0,
322
+ "grad_norm": 0.23849624395370483,
323
+ "learning_rate": 2.8410934175092426e-05,
324
+ "loss": 0.0363,
325
+ "step": 2385
326
+ },
327
+ {
328
+ "epoch": 9.0,
329
+ "eval_loss": 0.06528123468160629,
330
+ "eval_runtime": 1.7964,
331
+ "eval_samples_per_second": 44.533,
332
+ "eval_steps_per_second": 5.567,
333
+ "step": 2385
334
+ },
335
+ {
336
+ "em_boolean": 0.4117647058823529,
337
+ "em_extraction": 0.13333333333333333,
338
+ "em_qa": 0.06666666666666667,
339
+ "em_summarization": 0.0,
340
+ "em_unanswerable": 0.0,
341
+ "epoch": 10.0,
342
+ "mean_em": 0.125,
343
+ "mean_similarity": 0.5984957347856834,
344
+ "mean_word_count_diff": 16.2375,
345
+ "similarity_boolean": 0.4425226738128592,
346
+ "similarity_extraction": 0.5075533439715704,
347
+ "similarity_qa": 0.6813998910288016,
348
+ "similarity_summarization": 0.6938931312825944,
349
+ "similarity_unanswerable": 0.6688265626629194,
350
+ "word_count_diff_boolean": 5.352941176470588,
351
+ "word_count_diff_extraction": 6.466666666666667,
352
+ "word_count_diff_qa": 6.2,
353
+ "word_count_diff_summarization": 52.166666666666664,
354
+ "word_count_diff_unanswerable": 5.266666666666667
355
+ },
356
+ {
357
+ "epoch": 10.0,
358
+ "grad_norm": 0.2859129309654236,
359
+ "learning_rate": 2.7943934995010845e-05,
360
+ "loss": 0.0338,
361
+ "step": 2650
362
+ },
363
+ {
364
+ "epoch": 10.0,
365
+ "eval_loss": 0.06541204452514648,
366
+ "eval_runtime": 1.7939,
367
+ "eval_samples_per_second": 44.595,
368
+ "eval_steps_per_second": 5.574,
369
+ "step": 2650
370
+ },
371
+ {
372
+ "em_boolean": 0.35294117647058826,
373
+ "em_extraction": 0.2,
374
+ "em_qa": 0.06666666666666667,
375
+ "em_summarization": 0.0,
376
+ "em_unanswerable": 0.0,
377
+ "epoch": 11.0,
378
+ "mean_em": 0.125,
379
+ "mean_similarity": 0.584741565072909,
380
+ "mean_word_count_diff": 15.85,
381
+ "similarity_boolean": 0.41579638640670213,
382
+ "similarity_extraction": 0.575649573157231,
383
+ "similarity_qa": 0.68668532371521,
384
+ "similarity_summarization": 0.7162102411190668,
385
+ "similarity_unanswerable": 0.5255985895792643,
386
+ "word_count_diff_boolean": 5.0,
387
+ "word_count_diff_extraction": 4.333333333333333,
388
+ "word_count_diff_qa": 5.4,
389
+ "word_count_diff_summarization": 51.72222222222222,
390
+ "word_count_diff_unanswerable": 7.066666666666666
391
+ },
392
+ {
393
+ "epoch": 11.0,
394
+ "grad_norm": 0.19708961248397827,
395
+ "learning_rate": 2.7421768335907942e-05,
396
+ "loss": 0.0314,
397
+ "step": 2915
398
+ },
399
+ {
400
+ "epoch": 11.0,
401
+ "eval_loss": 0.06535650044679642,
402
+ "eval_runtime": 1.7968,
403
+ "eval_samples_per_second": 44.525,
404
+ "eval_steps_per_second": 5.566,
405
+ "step": 2915
406
+ },
407
+ {
408
+ "em_boolean": 0.4117647058823529,
409
+ "em_extraction": 0.13333333333333333,
410
+ "em_qa": 0.06666666666666667,
411
+ "em_summarization": 0.0,
412
+ "em_unanswerable": 0.0,
413
+ "epoch": 12.0,
414
+ "mean_em": 0.125,
415
+ "mean_similarity": 0.5985993921523913,
416
+ "mean_word_count_diff": 15.65,
417
+ "similarity_boolean": 0.49136487109696164,
418
+ "similarity_extraction": 0.4834645986557007,
419
+ "similarity_qa": 0.7439890225728353,
420
+ "similarity_summarization": 0.7199151118596395,
421
+ "similarity_unanswerable": 0.5442981487760942,
422
+ "word_count_diff_boolean": 5.294117647058823,
423
+ "word_count_diff_extraction": 6.466666666666667,
424
+ "word_count_diff_qa": 5.0,
425
+ "word_count_diff_summarization": 51.333333333333336,
426
+ "word_count_diff_unanswerable": 4.4
427
+ },
428
+ {
429
+ "epoch": 12.0,
430
+ "grad_norm": 0.32636699080467224,
431
+ "learning_rate": 2.6846659689353532e-05,
432
+ "loss": 0.0291,
433
+ "step": 3180
434
+ },
435
+ {
436
+ "epoch": 12.0,
437
+ "eval_loss": 0.06654994189739227,
438
+ "eval_runtime": 1.7794,
439
+ "eval_samples_per_second": 44.96,
440
+ "eval_steps_per_second": 5.62,
441
+ "step": 3180
442
+ },
443
+ {
444
+ "em_boolean": 0.29411764705882354,
445
+ "em_extraction": 0.2,
446
+ "em_qa": 0.13333333333333333,
447
+ "em_summarization": 0.0,
448
+ "em_unanswerable": 0.0,
449
+ "epoch": 13.0,
450
+ "mean_em": 0.125,
451
+ "mean_similarity": 0.5608657638425939,
452
+ "mean_word_count_diff": 15.4875,
453
+ "similarity_boolean": 0.3726646105265793,
454
+ "similarity_extraction": 0.4880456611514091,
455
+ "similarity_qa": 0.6968116387724876,
456
+ "similarity_summarization": 0.7003769092261791,
457
+ "similarity_unanswerable": 0.5436212575683991,
458
+ "word_count_diff_boolean": 6.470588235294118,
459
+ "word_count_diff_extraction": 4.0,
460
+ "word_count_diff_qa": 4.266666666666667,
461
+ "word_count_diff_summarization": 50.22222222222222,
462
+ "word_count_diff_unanswerable": 6.733333333333333
463
+ },
464
+ {
465
+ "epoch": 13.0,
466
+ "grad_norm": 0.09956305474042892,
467
+ "learning_rate": 2.622106018741882e-05,
468
+ "loss": 0.0268,
469
+ "step": 3445
470
+ },
471
+ {
472
+ "epoch": 13.0,
473
+ "eval_loss": 0.06867102533578873,
474
+ "eval_runtime": 1.7923,
475
+ "eval_samples_per_second": 44.635,
476
+ "eval_steps_per_second": 5.579,
477
+ "step": 3445
478
+ },
479
+ {
480
+ "em_boolean": 0.4117647058823529,
481
+ "em_extraction": 0.13333333333333333,
482
+ "em_qa": 0.06666666666666667,
483
+ "em_summarization": 0.0,
484
+ "em_unanswerable": 0.0,
485
+ "epoch": 14.0,
486
+ "mean_em": 0.125,
487
+ "mean_similarity": 0.6118219185853377,
488
+ "mean_word_count_diff": 15.1,
489
+ "similarity_boolean": 0.5559550164376988,
490
+ "similarity_extraction": 0.4480490814894438,
491
+ "similarity_qa": 0.8226341267426809,
492
+ "similarity_summarization": 0.7094271017445458,
493
+ "similarity_unanswerable": 0.5109721501668294,
494
+ "word_count_diff_boolean": 3.235294117647059,
495
+ "word_count_diff_extraction": 5.333333333333333,
496
+ "word_count_diff_qa": 4.066666666666666,
497
+ "word_count_diff_summarization": 51.333333333333336,
498
+ "word_count_diff_unanswerable": 5.866666666666666
499
+ },
500
+ {
501
+ "epoch": 14.0,
502
+ "grad_norm": 0.2182687222957611,
503
+ "learning_rate": 2.554763615587042e-05,
504
+ "loss": 0.0254,
505
+ "step": 3710
506
+ },
507
+ {
508
+ "epoch": 14.0,
509
+ "eval_loss": 0.06904994696378708,
510
+ "eval_runtime": 1.7971,
511
+ "eval_samples_per_second": 44.517,
512
+ "eval_steps_per_second": 5.565,
513
+ "step": 3710
514
+ },
515
+ {
516
+ "em_boolean": 0.17647058823529413,
517
+ "em_extraction": 0.13333333333333333,
518
+ "em_qa": 0.13333333333333333,
519
+ "em_summarization": 0.0,
520
+ "em_unanswerable": 0.0,
521
+ "epoch": 15.0,
522
+ "mean_em": 0.0875,
523
+ "mean_similarity": 0.5906956384656951,
524
+ "mean_word_count_diff": 15.8,
525
+ "similarity_boolean": 0.30824649366824064,
526
+ "similarity_extraction": 0.5498731901248296,
527
+ "similarity_qa": 0.7911941662430764,
528
+ "similarity_summarization": 0.7216936614778307,
529
+ "similarity_unanswerable": 0.5939309621850649,
530
+ "word_count_diff_boolean": 5.294117647058823,
531
+ "word_count_diff_extraction": 5.533333333333333,
532
+ "word_count_diff_qa": 4.933333333333334,
533
+ "word_count_diff_summarization": 50.833333333333336,
534
+ "word_count_diff_unanswerable": 6.8
535
+ },
536
+ {
537
+ "epoch": 15.0,
538
+ "grad_norm": 0.278495728969574,
539
+ "learning_rate": 2.4829257750201806e-05,
540
+ "loss": 0.0235,
541
+ "step": 3975
542
+ },
543
+ {
544
+ "epoch": 15.0,
545
+ "eval_loss": 0.07152120769023895,
546
+ "eval_runtime": 1.8045,
547
+ "eval_samples_per_second": 44.334,
548
+ "eval_steps_per_second": 5.542,
549
+ "step": 3975
550
+ },
551
+ {
552
+ "em_boolean": 0.35294117647058826,
553
+ "em_extraction": 0.13333333333333333,
554
+ "em_qa": 0.06666666666666667,
555
+ "em_summarization": 0.0,
556
+ "em_unanswerable": 0.0,
557
+ "epoch": 16.0,
558
+ "mean_em": 0.1125,
559
+ "mean_similarity": 0.6044320391491056,
560
+ "mean_word_count_diff": 15.3625,
561
+ "similarity_boolean": 0.4709787254824358,
562
+ "similarity_extraction": 0.48890374253193536,
563
+ "similarity_qa": 0.7086231042941411,
564
+ "similarity_summarization": 0.6860101450648572,
565
+ "similarity_unanswerable": 0.6691226323445638,
566
+ "word_count_diff_boolean": 5.176470588235294,
567
+ "word_count_diff_extraction": 4.133333333333334,
568
+ "word_count_diff_qa": 5.8,
569
+ "word_count_diff_summarization": 51.388888888888886,
570
+ "word_count_diff_unanswerable": 4.466666666666667
571
+ },
572
+ {
573
+ "epoch": 16.0,
574
+ "grad_norm": 0.12528866529464722,
575
+ "learning_rate": 2.4068986722935625e-05,
576
+ "loss": 0.0219,
577
+ "step": 4240
578
+ },
579
+ {
580
+ "epoch": 16.0,
581
+ "eval_loss": 0.07122211903333664,
582
+ "eval_runtime": 1.7912,
583
+ "eval_samples_per_second": 44.663,
584
+ "eval_steps_per_second": 5.583,
585
+ "step": 4240
586
+ },
587
+ {
588
+ "em_boolean": 0.23529411764705882,
589
+ "em_extraction": 0.2,
590
+ "em_qa": 0.06666666666666667,
591
+ "em_summarization": 0.0,
592
+ "em_unanswerable": 0.0,
593
+ "epoch": 17.0,
594
+ "mean_em": 0.1,
595
+ "mean_similarity": 0.5854583959793672,
596
+ "mean_word_count_diff": 16.1125,
597
+ "similarity_boolean": 0.3930098557954325,
598
+ "similarity_extraction": 0.5295473781724771,
599
+ "similarity_qa": 0.7186618636051814,
600
+ "similarity_summarization": 0.6619544287936555,
601
+ "similarity_unanswerable": 0.6344790523250897,
602
+ "word_count_diff_boolean": 5.764705882352941,
603
+ "word_count_diff_extraction": 5.066666666666666,
604
+ "word_count_diff_qa": 6.066666666666666,
605
+ "word_count_diff_summarization": 52.22222222222222,
606
+ "word_count_diff_unanswerable": 5.6
607
+ },
608
+ {
609
+ "epoch": 17.0,
610
+ "grad_norm": 0.18347615003585815,
611
+ "learning_rate": 2.327006337433323e-05,
612
+ "loss": 0.0208,
613
+ "step": 4505
614
+ },
615
+ {
616
+ "epoch": 17.0,
617
+ "eval_loss": 0.07514352351427078,
618
+ "eval_runtime": 1.7952,
619
+ "eval_samples_per_second": 44.563,
620
+ "eval_steps_per_second": 5.57,
621
+ "step": 4505
622
+ },
623
+ {
624
+ "em_boolean": 0.35294117647058826,
625
+ "em_extraction": 0.13333333333333333,
626
+ "em_qa": 0.06666666666666667,
627
+ "em_summarization": 0.0,
628
+ "em_unanswerable": 0.0,
629
+ "epoch": 18.0,
630
+ "mean_em": 0.1125,
631
+ "mean_similarity": 0.6148898253683001,
632
+ "mean_word_count_diff": 15.95,
633
+ "similarity_boolean": 0.45182113108389516,
634
+ "similarity_extraction": 0.5246008743842443,
635
+ "similarity_qa": 0.7161807785431544,
636
+ "similarity_summarization": 0.695978145632479,
637
+ "similarity_unanswerable": 0.6913930257161458,
638
+ "word_count_diff_boolean": 6.705882352941177,
639
+ "word_count_diff_extraction": 5.333333333333333,
640
+ "word_count_diff_qa": 5.133333333333334,
641
+ "word_count_diff_summarization": 51.72222222222222,
642
+ "word_count_diff_unanswerable": 4.933333333333334
643
+ },
644
+ {
645
+ "epoch": 18.0,
646
+ "grad_norm": 0.39281344413757324,
647
+ "learning_rate": 2.2435892742127786e-05,
648
+ "loss": 0.0197,
649
+ "step": 4770
650
+ },
651
+ {
652
+ "epoch": 18.0,
653
+ "eval_loss": 0.07489313185214996,
654
+ "eval_runtime": 1.7966,
655
+ "eval_samples_per_second": 44.528,
656
+ "eval_steps_per_second": 5.566,
657
+ "step": 4770
658
+ },
659
+ {
660
+ "em_boolean": 0.35294117647058826,
661
+ "em_extraction": 0.13333333333333333,
662
+ "em_qa": 0.06666666666666667,
663
+ "em_summarization": 0.0,
664
+ "em_unanswerable": 0.0,
665
+ "epoch": 19.0,
666
+ "mean_em": 0.1125,
667
+ "mean_similarity": 0.6110048872418702,
668
+ "mean_word_count_diff": 15.175,
669
+ "similarity_boolean": 0.4688412766246235,
670
+ "similarity_extraction": 0.5354909280935923,
671
+ "similarity_qa": 0.7334268649419149,
672
+ "similarity_summarization": 0.6523812972009182,
673
+ "similarity_unanswerable": 0.6755639354387919,
674
+ "word_count_diff_boolean": 5.411764705882353,
675
+ "word_count_diff_extraction": 3.6666666666666665,
676
+ "word_count_diff_qa": 5.333333333333333,
677
+ "word_count_diff_summarization": 51.27777777777778,
678
+ "word_count_diff_unanswerable": 4.266666666666667
679
+ },
680
+ {
681
+ "epoch": 19.0,
682
+ "grad_norm": 0.26503777503967285,
683
+ "learning_rate": 2.1570030089140857e-05,
684
+ "loss": 0.0184,
685
+ "step": 5035
686
+ },
687
+ {
688
+ "epoch": 19.0,
689
+ "eval_loss": 0.07855142652988434,
690
+ "eval_runtime": 1.7852,
691
+ "eval_samples_per_second": 44.813,
692
+ "eval_steps_per_second": 5.602,
693
+ "step": 5035
694
+ },
695
+ {
696
+ "em_boolean": 0.058823529411764705,
697
+ "em_extraction": 0.26666666666666666,
698
+ "em_qa": 0.0,
699
+ "em_summarization": 0.0,
700
+ "em_unanswerable": 0.0,
701
+ "epoch": 20.0,
702
+ "mean_em": 0.0625,
703
+ "mean_similarity": 0.5894458804745227,
704
+ "mean_word_count_diff": 15.7625,
705
+ "similarity_boolean": 0.3066763941417722,
706
+ "similarity_extraction": 0.567964817583561,
707
+ "similarity_qa": 0.7356137126684189,
708
+ "similarity_summarization": 0.7311095827155643,
709
+ "similarity_unanswerable": 0.615234752992789,
710
+ "word_count_diff_boolean": 7.0588235294117645,
711
+ "word_count_diff_extraction": 4.133333333333334,
712
+ "word_count_diff_qa": 6.4,
713
+ "word_count_diff_summarization": 50.833333333333336,
714
+ "word_count_diff_unanswerable": 4.533333333333333
715
+ },
716
+ {
717
+ "epoch": 20.0,
718
+ "grad_norm": 0.325967013835907,
719
+ "learning_rate": 2.0676165750634656e-05,
720
+ "loss": 0.0173,
721
+ "step": 5300
722
+ },
723
+ {
724
+ "epoch": 20.0,
725
+ "eval_loss": 0.07865440845489502,
726
+ "eval_runtime": 1.7895,
727
+ "eval_samples_per_second": 44.705,
728
+ "eval_steps_per_second": 5.588,
729
+ "step": 5300
730
+ },
731
+ {
732
+ "em_boolean": 0.5294117647058824,
733
+ "em_extraction": 0.26666666666666666,
734
+ "em_qa": 0.06666666666666667,
735
+ "em_summarization": 0.0,
736
+ "em_unanswerable": 0.0,
737
+ "epoch": 21.0,
738
+ "mean_em": 0.175,
739
+ "mean_similarity": 0.6464177187765017,
740
+ "mean_word_count_diff": 14.8375,
741
+ "similarity_boolean": 0.6461278642801678,
742
+ "similarity_extraction": 0.6178931772708893,
743
+ "similarity_qa": 0.7566967884699504,
744
+ "similarity_summarization": 0.6613570315142473,
745
+ "similarity_unanswerable": 0.5470645170658827,
746
+ "word_count_diff_boolean": 3.176470588235294,
747
+ "word_count_diff_extraction": 5.4,
748
+ "word_count_diff_qa": 4.6,
749
+ "word_count_diff_summarization": 50.5,
750
+ "word_count_diff_unanswerable": 4.933333333333334
751
+ },
752
+ {
753
+ "epoch": 21.0,
754
+ "grad_norm": 0.18580074608325958,
755
+ "learning_rate": 1.975810940598114e-05,
756
+ "loss": 0.0162,
757
+ "step": 5565
758
+ },
759
+ {
760
+ "epoch": 21.0,
761
+ "eval_loss": 0.08283738046884537,
762
+ "eval_runtime": 1.8062,
763
+ "eval_samples_per_second": 44.292,
764
+ "eval_steps_per_second": 5.537,
765
+ "step": 5565
766
+ },
767
+ {
768
+ "em_boolean": 0.47058823529411764,
769
+ "em_extraction": 0.26666666666666666,
770
+ "em_qa": 0.06666666666666667,
771
+ "em_summarization": 0.0,
772
+ "em_unanswerable": 0.0,
773
+ "epoch": 22.0,
774
+ "mean_em": 0.1625,
775
+ "mean_similarity": 0.6508607531315647,
776
+ "mean_word_count_diff": 15.1875,
777
+ "similarity_boolean": 0.5319088667302447,
778
+ "similarity_extraction": 0.6322630804032088,
779
+ "similarity_qa": 0.7358093798160553,
780
+ "similarity_summarization": 0.6958086478213469,
781
+ "similarity_unanswerable": 0.6653844634691874,
782
+ "word_count_diff_boolean": 5.352941176470588,
783
+ "word_count_diff_extraction": 3.933333333333333,
784
+ "word_count_diff_qa": 5.266666666666667,
785
+ "word_count_diff_summarization": 51.166666666666664,
786
+ "word_count_diff_unanswerable": 4.333333333333333
787
+ },
788
+ {
789
+ "epoch": 22.0,
790
+ "grad_norm": 0.7463592886924744,
791
+ "learning_rate": 1.881977384168254e-05,
792
+ "loss": 0.0158,
793
+ "step": 5830
794
+ },
795
+ {
796
+ "epoch": 22.0,
797
+ "eval_loss": 0.08268458396196365,
798
+ "eval_runtime": 1.7886,
799
+ "eval_samples_per_second": 44.728,
800
+ "eval_steps_per_second": 5.591,
801
+ "step": 5830
802
+ },
803
+ {
804
+ "em_boolean": 0.4117647058823529,
805
+ "em_extraction": 0.2,
806
+ "em_qa": 0.13333333333333333,
807
+ "em_summarization": 0.0,
808
+ "em_unanswerable": 0.0,
809
+ "epoch": 23.0,
810
+ "mean_em": 0.15,
811
+ "mean_similarity": 0.6376353252329864,
812
+ "mean_word_count_diff": 15.5625,
813
+ "similarity_boolean": 0.5682552300722283,
814
+ "similarity_extraction": 0.5148679026712973,
815
+ "similarity_qa": 0.7483514944712321,
816
+ "similarity_summarization": 0.7200961951166391,
817
+ "similarity_unanswerable": 0.629364309211572,
818
+ "word_count_diff_boolean": 3.823529411764706,
819
+ "word_count_diff_extraction": 5.266666666666667,
820
+ "word_count_diff_qa": 4.933333333333334,
821
+ "word_count_diff_summarization": 51.388888888888886,
822
+ "word_count_diff_unanswerable": 6.8
823
+ },
824
+ {
825
+ "epoch": 23.0,
826
+ "grad_norm": 0.30431216955184937,
827
+ "learning_rate": 1.7865158274945846e-05,
828
+ "loss": 0.0149,
829
+ "step": 6095
830
+ },
831
+ {
832
+ "epoch": 23.0,
833
+ "eval_loss": 0.08500902354717255,
834
+ "eval_runtime": 1.8006,
835
+ "eval_samples_per_second": 44.43,
836
+ "eval_steps_per_second": 5.554,
837
+ "step": 6095
838
+ },
839
+ {
840
+ "em_boolean": 0.35294117647058826,
841
+ "em_extraction": 0.2,
842
+ "em_qa": 0.0,
843
+ "em_summarization": 0.0,
844
+ "em_unanswerable": 0.0,
845
+ "epoch": 24.0,
846
+ "mean_em": 0.1125,
847
+ "mean_similarity": 0.6209718830883503,
848
+ "mean_word_count_diff": 15.625,
849
+ "similarity_boolean": 0.4452236132586704,
850
+ "similarity_extraction": 0.5458283141255379,
851
+ "similarity_qa": 0.7422831366459529,
852
+ "similarity_summarization": 0.7023132857349184,
853
+ "similarity_unanswerable": 0.6763758877913157,
854
+ "word_count_diff_boolean": 5.470588235294118,
855
+ "word_count_diff_extraction": 5.6,
856
+ "word_count_diff_qa": 5.533333333333333,
857
+ "word_count_diff_summarization": 51.611111111111114,
858
+ "word_count_diff_unanswerable": 4.066666666666666
859
+ },
860
+ {
861
+ "epoch": 24.0,
862
+ "grad_norm": 0.1550023853778839,
863
+ "learning_rate": 1.6898331308886863e-05,
864
+ "loss": 0.0138,
865
+ "step": 6360
866
+ },
867
+ {
868
+ "epoch": 24.0,
869
+ "eval_loss": 0.08557449281215668,
870
+ "eval_runtime": 1.7865,
871
+ "eval_samples_per_second": 44.78,
872
+ "eval_steps_per_second": 5.598,
873
+ "step": 6360
874
+ },
875
+ {
876
+ "em_boolean": 0.4117647058823529,
877
+ "em_extraction": 0.26666666666666666,
878
+ "em_qa": 0.13333333333333333,
879
+ "em_summarization": 0.0,
880
+ "em_unanswerable": 0.0,
881
+ "epoch": 25.0,
882
+ "mean_em": 0.1625,
883
+ "mean_similarity": 0.6411203743191436,
884
+ "mean_word_count_diff": 15.1875,
885
+ "similarity_boolean": 0.5644924241830321,
886
+ "similarity_extraction": 0.5594843897968531,
887
+ "similarity_qa": 0.7792828718821208,
888
+ "similarity_summarization": 0.6979754573355118,
889
+ "similarity_unanswerable": 0.6032127718130748,
890
+ "word_count_diff_boolean": 3.7058823529411766,
891
+ "word_count_diff_extraction": 4.533333333333333,
892
+ "word_count_diff_qa": 4.933333333333334,
893
+ "word_count_diff_summarization": 51.833333333333336,
894
+ "word_count_diff_unanswerable": 5.133333333333334
895
+ },
896
+ {
897
+ "epoch": 25.0,
898
+ "grad_norm": 0.23536083102226257,
899
+ "learning_rate": 1.5923413592009145e-05,
900
+ "loss": 0.0132,
901
+ "step": 6625
902
+ },
903
+ {
904
+ "epoch": 25.0,
905
+ "eval_loss": 0.0886365994811058,
906
+ "eval_runtime": 1.7918,
907
+ "eval_samples_per_second": 44.648,
908
+ "eval_steps_per_second": 5.581,
909
+ "step": 6625
910
+ },
911
+ {
912
+ "em_boolean": 0.29411764705882354,
913
+ "em_extraction": 0.13333333333333333,
914
+ "em_qa": 0.0,
915
+ "em_summarization": 0.0,
916
+ "em_unanswerable": 0.0,
917
+ "epoch": 26.0,
918
+ "mean_em": 0.0875,
919
+ "mean_similarity": 0.5999299102462828,
920
+ "mean_word_count_diff": 15.6625,
921
+ "similarity_boolean": 0.44055906716076765,
922
+ "similarity_extraction": 0.4907683741301298,
923
+ "similarity_qa": 0.64702517837286,
924
+ "similarity_summarization": 0.7336946874856949,
925
+ "similarity_unanswerable": 0.6820987343788147,
926
+ "word_count_diff_boolean": 5.9411764705882355,
927
+ "word_count_diff_extraction": 5.466666666666667,
928
+ "word_count_diff_qa": 7.066666666666666,
929
+ "word_count_diff_summarization": 50.27777777777778,
930
+ "word_count_diff_unanswerable": 3.933333333333333
931
+ },
932
+ {
933
+ "epoch": 26.0,
934
+ "grad_norm": 0.0521920807659626,
935
+ "learning_rate": 1.4944560255863805e-05,
936
+ "loss": 0.0127,
937
+ "step": 6890
938
+ },
939
+ {
940
+ "epoch": 26.0,
941
+ "eval_loss": 0.09115185588598251,
942
+ "eval_runtime": 1.7871,
943
+ "eval_samples_per_second": 44.764,
944
+ "eval_steps_per_second": 5.596,
945
+ "step": 6890
946
+ },
947
+ {
948
+ "em_boolean": 0.29411764705882354,
949
+ "em_extraction": 0.2,
950
+ "em_qa": 0.06666666666666667,
951
+ "em_summarization": 0.0,
952
+ "em_unanswerable": 0.0,
953
+ "epoch": 27.0,
954
+ "mean_em": 0.1125,
955
+ "mean_similarity": 0.5961971989367157,
956
+ "mean_word_count_diff": 15.9,
957
+ "similarity_boolean": 0.47167208264855776,
958
+ "similarity_extraction": 0.563706802825133,
959
+ "similarity_qa": 0.6419207287331422,
960
+ "similarity_summarization": 0.6927380098236932,
961
+ "similarity_unanswerable": 0.608243557314078,
962
+ "word_count_diff_boolean": 5.0,
963
+ "word_count_diff_extraction": 4.933333333333334,
964
+ "word_count_diff_qa": 6.0,
965
+ "word_count_diff_summarization": 52.0,
966
+ "word_count_diff_unanswerable": 5.8
967
+ },
968
+ {
969
+ "epoch": 27.0,
970
+ "grad_norm": 0.23173846304416656,
971
+ "learning_rate": 1.396594320574144e-05,
972
+ "loss": 0.0121,
973
+ "step": 7155
974
+ },
975
+ {
976
+ "epoch": 27.0,
977
+ "eval_loss": 0.09045173972845078,
978
+ "eval_runtime": 1.7961,
979
+ "eval_samples_per_second": 44.541,
980
+ "eval_steps_per_second": 5.568,
981
+ "step": 7155
982
+ },
983
+ {
984
+ "em_boolean": 0.5294117647058824,
985
+ "em_extraction": 0.13333333333333333,
986
+ "em_qa": 0.06666666666666667,
987
+ "em_summarization": 0.0,
988
+ "em_unanswerable": 0.0,
989
+ "epoch": 28.0,
990
+ "mean_em": 0.15,
991
+ "mean_similarity": 0.6426682359306142,
992
+ "mean_word_count_diff": 15.4625,
993
+ "similarity_boolean": 0.6154902246506775,
994
+ "similarity_extraction": 0.559150509784619,
995
+ "similarity_qa": 0.7585609555244446,
996
+ "similarity_summarization": 0.7132770286666023,
997
+ "similarity_unanswerable": 0.5563644373168548,
998
+ "word_count_diff_boolean": 3.9411764705882355,
999
+ "word_count_diff_extraction": 5.933333333333334,
1000
+ "word_count_diff_qa": 5.4,
1001
+ "word_count_diff_summarization": 51.94444444444444,
1002
+ "word_count_diff_unanswerable": 4.333333333333333
1003
+ },
1004
+ {
1005
+ "epoch": 28.0,
1006
+ "grad_norm": 0.15653730928897858,
1007
+ "learning_rate": 1.2991733339873795e-05,
1008
+ "loss": 0.0114,
1009
+ "step": 7420
1010
+ },
1011
+ {
1012
+ "epoch": 28.0,
1013
+ "eval_loss": 0.09521345049142838,
1014
+ "eval_runtime": 1.7969,
1015
+ "eval_samples_per_second": 44.521,
1016
+ "eval_steps_per_second": 5.565,
1017
+ "step": 7420
1018
+ },
1019
+ {
1020
+ "em_boolean": 0.5882352941176471,
1021
+ "em_extraction": 0.2,
1022
+ "em_qa": 0.0,
1023
+ "em_summarization": 0.0,
1024
+ "em_unanswerable": 0.0,
1025
+ "epoch": 29.0,
1026
+ "mean_em": 0.1625,
1027
+ "mean_similarity": 0.670323112141341,
1028
+ "mean_word_count_diff": 14.8125,
1029
+ "similarity_boolean": 0.6801450522068668,
1030
+ "similarity_extraction": 0.5754425642391046,
1031
+ "similarity_qa": 0.7391265859206517,
1032
+ "similarity_summarization": 0.7395255797439151,
1033
+ "similarity_unanswerable": 0.6022256930669149,
1034
+ "word_count_diff_boolean": 2.588235294117647,
1035
+ "word_count_diff_extraction": 4.0,
1036
+ "word_count_diff_qa": 5.666666666666667,
1037
+ "word_count_diff_summarization": 50.333333333333336,
1038
+ "word_count_diff_unanswerable": 6.0
1039
+ },
1040
+ {
1041
+ "epoch": 29.0,
1042
+ "grad_norm": 0.13572590053081512,
1043
+ "learning_rate": 1.2026082772927574e-05,
1044
+ "loss": 0.0112,
1045
+ "step": 7685
1046
+ },
1047
+ {
1048
+ "epoch": 29.0,
1049
+ "eval_loss": 0.09561847150325775,
1050
+ "eval_runtime": 1.7863,
1051
+ "eval_samples_per_second": 44.786,
1052
+ "eval_steps_per_second": 5.598,
1053
+ "step": 7685
1054
+ },
1055
+ {
1056
+ "em_boolean": 0.47058823529411764,
1057
+ "em_extraction": 0.26666666666666666,
1058
+ "em_qa": 0.06666666666666667,
1059
+ "em_summarization": 0.0,
1060
+ "em_unanswerable": 0.0,
1061
+ "epoch": 30.0,
1062
+ "mean_em": 0.1625,
1063
+ "mean_similarity": 0.6361284551327117,
1064
+ "mean_word_count_diff": 15.1625,
1065
+ "similarity_boolean": 0.5678887126748177,
1066
+ "similarity_extraction": 0.528444591164589,
1067
+ "similarity_qa": 0.7746080329020818,
1068
+ "similarity_summarization": 0.7153815428415934,
1069
+ "similarity_unanswerable": 0.5875674108664195,
1070
+ "word_count_diff_boolean": 3.6470588235294117,
1071
+ "word_count_diff_extraction": 4.2,
1072
+ "word_count_diff_qa": 5.666666666666667,
1073
+ "word_count_diff_summarization": 51.05555555555556,
1074
+ "word_count_diff_unanswerable": 5.6
1075
+ },
1076
+ {
1077
+ "epoch": 30.0,
1078
+ "grad_norm": 0.11106608062982559,
1079
+ "learning_rate": 1.1073107139554395e-05,
1080
+ "loss": 0.0111,
1081
+ "step": 7950
1082
+ },
1083
+ {
1084
+ "epoch": 30.0,
1085
+ "eval_loss": 0.09475980699062347,
1086
+ "eval_runtime": 1.8027,
1087
+ "eval_samples_per_second": 44.379,
1088
+ "eval_steps_per_second": 5.547,
1089
+ "step": 7950
1090
+ },
1091
+ {
1092
+ "em_boolean": 0.47058823529411764,
1093
+ "em_extraction": 0.0,
1094
+ "em_qa": 0.06666666666666667,
1095
+ "em_summarization": 0.0,
1096
+ "em_unanswerable": 0.0,
1097
+ "epoch": 31.0,
1098
+ "mean_em": 0.1125,
1099
+ "mean_similarity": 0.5996635487768799,
1100
+ "mean_word_count_diff": 15.9625,
1101
+ "similarity_boolean": 0.5703230380792829,
1102
+ "similarity_extraction": 0.43614052472015225,
1103
+ "similarity_qa": 0.6746748656034469,
1104
+ "similarity_summarization": 0.6909497512711419,
1105
+ "similarity_unanswerable": 0.6118843918045361,
1106
+ "word_count_diff_boolean": 4.176470588235294,
1107
+ "word_count_diff_extraction": 6.933333333333334,
1108
+ "word_count_diff_qa": 6.466666666666667,
1109
+ "word_count_diff_summarization": 51.888888888888886,
1110
+ "word_count_diff_unanswerable": 4.733333333333333
1111
+ },
1112
+ {
1113
+ "epoch": 31.0,
1114
+ "grad_norm": 0.15586383640766144,
1115
+ "learning_rate": 1.0136868053419842e-05,
1116
+ "loss": 0.0105,
1117
+ "step": 8215
1118
+ },
1119
+ {
1120
+ "epoch": 31.0,
1121
+ "eval_loss": 0.09651915729045868,
1122
+ "eval_runtime": 1.7878,
1123
+ "eval_samples_per_second": 44.749,
1124
+ "eval_steps_per_second": 5.594,
1125
+ "step": 8215
1126
+ },
1127
+ {
1128
+ "em_boolean": 0.35294117647058826,
1129
+ "em_extraction": 0.26666666666666666,
1130
+ "em_qa": 0.0,
1131
+ "em_summarization": 0.0,
1132
+ "em_unanswerable": 0.0,
1133
+ "epoch": 32.0,
1134
+ "mean_em": 0.125,
1135
+ "mean_similarity": 0.6647563714534044,
1136
+ "mean_word_count_diff": 15.3125,
1137
+ "similarity_boolean": 0.4992627663647427,
1138
+ "similarity_extraction": 0.6371853078405062,
1139
+ "similarity_qa": 0.7779242674509684,
1140
+ "similarity_summarization": 0.7545208003785875,
1141
+ "similarity_unanswerable": 0.6590016434590021,
1142
+ "word_count_diff_boolean": 4.352941176470588,
1143
+ "word_count_diff_extraction": 3.6666666666666665,
1144
+ "word_count_diff_qa": 7.133333333333334,
1145
+ "word_count_diff_summarization": 52.22222222222222,
1146
+ "word_count_diff_unanswerable": 3.2666666666666666
1147
+ },
1148
+ {
1149
+ "epoch": 32.0,
1150
+ "grad_norm": 0.15895779430866241,
1151
+ "learning_rate": 9.22135579647165e-06,
1152
+ "loss": 0.0103,
1153
+ "step": 8480
1154
+ },
1155
+ {
1156
+ "epoch": 32.0,
1157
+ "eval_loss": 0.09846033155918121,
1158
+ "eval_runtime": 1.7981,
1159
+ "eval_samples_per_second": 44.492,
1160
+ "eval_steps_per_second": 5.562,
1161
+ "step": 8480
1162
+ },
1163
+ {
1164
+ "em_boolean": 0.35294117647058826,
1165
+ "em_extraction": 0.13333333333333333,
1166
+ "em_qa": 0.0,
1167
+ "em_summarization": 0.0,
1168
+ "em_unanswerable": 0.0,
1169
+ "epoch": 33.0,
1170
+ "mean_em": 0.1,
1171
+ "mean_similarity": 0.6497376295737922,
1172
+ "mean_word_count_diff": 15.2,
1173
+ "similarity_boolean": 0.4850216718281017,
1174
+ "similarity_extraction": 0.6169686233003934,
1175
+ "similarity_qa": 0.7874227881431579,
1176
+ "similarity_summarization": 0.720199970735444,
1177
+ "similarity_unanswerable": 0.6469447533289592,
1178
+ "word_count_diff_boolean": 5.529411764705882,
1179
+ "word_count_diff_extraction": 4.0,
1180
+ "word_count_diff_qa": 5.466666666666667,
1181
+ "word_count_diff_summarization": 50.72222222222222,
1182
+ "word_count_diff_unanswerable": 4.466666666666667
1183
+ },
1184
+ {
1185
+ "epoch": 33.0,
1186
+ "grad_norm": 0.16729232668876648,
1187
+ "learning_rate": 8.330472312226091e-06,
1188
+ "loss": 0.0099,
1189
+ "step": 8745
1190
+ },
1191
+ {
1192
+ "epoch": 33.0,
1193
+ "eval_loss": 0.09990086406469345,
1194
+ "eval_runtime": 1.7757,
1195
+ "eval_samples_per_second": 45.052,
1196
+ "eval_steps_per_second": 5.631,
1197
+ "step": 8745
1198
+ },
1199
+ {
1200
+ "em_boolean": 0.4117647058823529,
1201
+ "em_extraction": 0.2,
1202
+ "em_qa": 0.0,
1203
+ "em_summarization": 0.0,
1204
+ "em_unanswerable": 0.0,
1205
+ "epoch": 34.0,
1206
+ "mean_em": 0.125,
1207
+ "mean_similarity": 0.6532467395067215,
1208
+ "mean_word_count_diff": 15.3375,
1209
+ "similarity_boolean": 0.5624497304944431,
1210
+ "similarity_extraction": 0.6123799696564675,
1211
+ "similarity_qa": 0.7896470129489899,
1212
+ "similarity_summarization": 0.6943622730258439,
1213
+ "similarity_unanswerable": 0.6112778725723426,
1214
+ "word_count_diff_boolean": 4.588235294117647,
1215
+ "word_count_diff_extraction": 5.266666666666667,
1216
+ "word_count_diff_qa": 5.933333333333334,
1217
+ "word_count_diff_summarization": 50.666666666666664,
1218
+ "word_count_diff_unanswerable": 4.6
1219
+ },
1220
+ {
1221
+ "epoch": 34.0,
1222
+ "grad_norm": 0.3746591806411743,
1223
+ "learning_rate": 7.468014575555688e-06,
1224
+ "loss": 0.0096,
1225
+ "step": 9010
1226
+ },
1227
+ {
1228
+ "epoch": 34.0,
1229
+ "eval_loss": 0.10108506679534912,
1230
+ "eval_runtime": 1.7759,
1231
+ "eval_samples_per_second": 45.048,
1232
+ "eval_steps_per_second": 5.631,
1233
+ "step": 9010
1234
+ },
1235
+ {
1236
+ "em_boolean": 0.35294117647058826,
1237
+ "em_extraction": 0.13333333333333333,
1238
+ "em_qa": 0.13333333333333333,
1239
+ "em_summarization": 0.0,
1240
+ "em_unanswerable": 0.0,
1241
+ "epoch": 35.0,
1242
+ "mean_em": 0.125,
1243
+ "mean_similarity": 0.6299693588167429,
1244
+ "mean_word_count_diff": 15.35,
1245
+ "similarity_boolean": 0.5166072974748471,
1246
+ "similarity_extraction": 0.55517836039265,
1247
+ "similarity_qa": 0.7496427396933237,
1248
+ "similarity_summarization": 0.7208915799856186,
1249
+ "similarity_unanswerable": 0.6044573138157526,
1250
+ "word_count_diff_boolean": 4.352941176470588,
1251
+ "word_count_diff_extraction": 5.266666666666667,
1252
+ "word_count_diff_qa": 4.8,
1253
+ "word_count_diff_summarization": 51.388888888888886,
1254
+ "word_count_diff_unanswerable": 5.2
1255
+ },
1256
+ {
1257
+ "epoch": 35.0,
1258
+ "grad_norm": 0.310463547706604,
1259
+ "learning_rate": 6.637658409856717e-06,
1260
+ "loss": 0.0096,
1261
+ "step": 9275
1262
+ },
1263
+ {
1264
+ "epoch": 35.0,
1265
+ "eval_loss": 0.10128389298915863,
1266
+ "eval_runtime": 1.7949,
1267
+ "eval_samples_per_second": 44.571,
1268
+ "eval_steps_per_second": 5.571,
1269
+ "step": 9275
1270
+ },
1271
+ {
1272
+ "em_boolean": 0.5294117647058824,
1273
+ "em_extraction": 0.2,
1274
+ "em_qa": 0.06666666666666667,
1275
+ "em_summarization": 0.0,
1276
+ "em_unanswerable": 0.0,
1277
+ "epoch": 36.0,
1278
+ "mean_em": 0.1625,
1279
+ "mean_similarity": 0.6648560125031509,
1280
+ "mean_word_count_diff": 14.9,
1281
+ "similarity_boolean": 0.6631740967688315,
1282
+ "similarity_extraction": 0.5298445565005143,
1283
+ "similarity_qa": 0.7434355229139328,
1284
+ "similarity_summarization": 0.7201196981800927,
1285
+ "similarity_unanswerable": 0.6568777064482371,
1286
+ "word_count_diff_boolean": 2.2941176470588234,
1287
+ "word_count_diff_extraction": 5.2,
1288
+ "word_count_diff_qa": 5.333333333333333,
1289
+ "word_count_diff_summarization": 52.0,
1290
+ "word_count_diff_unanswerable": 3.933333333333333
1291
+ },
1292
+ {
1293
+ "epoch": 36.0,
1294
+ "grad_norm": 0.23128336668014526,
1295
+ "learning_rate": 5.84294282056834e-06,
1296
+ "loss": 0.0094,
1297
+ "step": 9540
1298
+ },
1299
+ {
1300
+ "epoch": 36.0,
1301
+ "eval_loss": 0.10348665714263916,
1302
+ "eval_runtime": 1.7894,
1303
+ "eval_samples_per_second": 44.707,
1304
+ "eval_steps_per_second": 5.588,
1305
+ "step": 9540
1306
+ },
1307
+ {
1308
+ "em_boolean": 0.47058823529411764,
1309
+ "em_extraction": 0.2,
1310
+ "em_qa": 0.0,
1311
+ "em_summarization": 0.0,
1312
+ "em_unanswerable": 0.0,
1313
+ "epoch": 37.0,
1314
+ "mean_em": 0.1375,
1315
+ "mean_similarity": 0.6319401320070028,
1316
+ "mean_word_count_diff": 15.0875,
1317
+ "similarity_boolean": 0.5821067885879208,
1318
+ "similarity_extraction": 0.5178047935167949,
1319
+ "similarity_qa": 0.769520037372907,
1320
+ "similarity_summarization": 0.6793310083448887,
1321
+ "similarity_unanswerable": 0.6081043027341366,
1322
+ "word_count_diff_boolean": 4.235294117647059,
1323
+ "word_count_diff_extraction": 4.866666666666666,
1324
+ "word_count_diff_qa": 5.0,
1325
+ "word_count_diff_summarization": 50.833333333333336,
1326
+ "word_count_diff_unanswerable": 4.8
1327
+ },
1328
+ {
1329
+ "epoch": 37.0,
1330
+ "grad_norm": 0.10078708827495575,
1331
+ "learning_rate": 5.087254911814361e-06,
1332
+ "loss": 0.0092,
1333
+ "step": 9805
1334
+ },
1335
+ {
1336
+ "epoch": 37.0,
1337
+ "eval_loss": 0.10369674116373062,
1338
+ "eval_runtime": 1.7998,
1339
+ "eval_samples_per_second": 44.45,
1340
+ "eval_steps_per_second": 5.556,
1341
+ "step": 9805
1342
+ },
1343
+ {
1344
+ "em_boolean": 0.4117647058823529,
1345
+ "em_extraction": 0.13333333333333333,
1346
+ "em_qa": 0.0,
1347
+ "em_summarization": 0.0,
1348
+ "em_unanswerable": 0.0,
1349
+ "epoch": 38.0,
1350
+ "mean_em": 0.1125,
1351
+ "mean_similarity": 0.6402258106973022,
1352
+ "mean_word_count_diff": 15.3875,
1353
+ "similarity_boolean": 0.5555457597708001,
1354
+ "similarity_extraction": 0.5125755973160266,
1355
+ "similarity_qa": 0.729976910352707,
1356
+ "similarity_summarization": 0.7154302892999517,
1357
+ "similarity_unanswerable": 0.6838502744833629,
1358
+ "word_count_diff_boolean": 4.352941176470588,
1359
+ "word_count_diff_extraction": 4.466666666666667,
1360
+ "word_count_diff_qa": 6.266666666666667,
1361
+ "word_count_diff_summarization": 51.166666666666664,
1362
+ "word_count_diff_unanswerable": 5.0
1363
+ },
1364
+ {
1365
+ "epoch": 38.0,
1366
+ "grad_norm": 0.14647193253040314,
1367
+ "learning_rate": 4.373815450453467e-06,
1368
+ "loss": 0.0087,
1369
+ "step": 10070
1370
+ },
1371
+ {
1372
+ "epoch": 38.0,
1373
+ "eval_loss": 0.10511450469493866,
1374
+ "eval_runtime": 1.8033,
1375
+ "eval_samples_per_second": 44.364,
1376
+ "eval_steps_per_second": 5.545,
1377
+ "step": 10070
1378
+ },
1379
+ {
1380
+ "em_boolean": 0.29411764705882354,
1381
+ "em_extraction": 0.26666666666666666,
1382
+ "em_qa": 0.13333333333333333,
1383
+ "em_summarization": 0.0,
1384
+ "em_unanswerable": 0.0,
1385
+ "epoch": 39.0,
1386
+ "mean_em": 0.1375,
1387
+ "mean_similarity": 0.5966290417010895,
1388
+ "mean_word_count_diff": 15.375,
1389
+ "similarity_boolean": 0.48111217118361416,
1390
+ "similarity_extraction": 0.5464107090607285,
1391
+ "similarity_qa": 0.7710953007141749,
1392
+ "similarity_summarization": 0.6638153013255861,
1393
+ "similarity_unanswerable": 0.5226767236987749,
1394
+ "word_count_diff_boolean": 4.294117647058823,
1395
+ "word_count_diff_extraction": 5.133333333333334,
1396
+ "word_count_diff_qa": 5.466666666666667,
1397
+ "word_count_diff_summarization": 50.611111111111114,
1398
+ "word_count_diff_unanswerable": 5.8
1399
+ },
1400
+ {
1401
+ "epoch": 39.0,
1402
+ "grad_norm": 0.8468394875526428,
1403
+ "learning_rate": 3.7056651390643413e-06,
1404
+ "loss": 0.0088,
1405
+ "step": 10335
1406
+ },
1407
+ {
1408
+ "epoch": 39.0,
1409
+ "eval_loss": 0.10422440618276596,
1410
+ "eval_runtime": 1.7878,
1411
+ "eval_samples_per_second": 44.747,
1412
+ "eval_steps_per_second": 5.593,
1413
+ "step": 10335
1414
+ },
1415
+ {
1416
+ "em_boolean": 0.47058823529411764,
1417
+ "em_extraction": 0.26666666666666666,
1418
+ "em_qa": 0.13333333333333333,
1419
+ "em_summarization": 0.0,
1420
+ "em_unanswerable": 0.0,
1421
+ "epoch": 40.0,
1422
+ "mean_em": 0.175,
1423
+ "mean_similarity": 0.6348526364192366,
1424
+ "mean_word_count_diff": 15.1875,
1425
+ "similarity_boolean": 0.5687163450262126,
1426
+ "similarity_extraction": 0.62134765163064,
1427
+ "similarity_qa": 0.7562251538038254,
1428
+ "similarity_summarization": 0.6440524767256446,
1429
+ "similarity_unanswerable": 0.5908997590343158,
1430
+ "word_count_diff_boolean": 4.529411764705882,
1431
+ "word_count_diff_extraction": 4.133333333333334,
1432
+ "word_count_diff_qa": 4.866666666666666,
1433
+ "word_count_diff_summarization": 50.666666666666664,
1434
+ "word_count_diff_unanswerable": 6.066666666666666
1435
+ },
1436
+ {
1437
+ "epoch": 40.0,
1438
+ "grad_norm": 0.15559451282024384,
1439
+ "learning_rate": 3.08565165637071e-06,
1440
+ "loss": 0.0088,
1441
+ "step": 10600
1442
+ },
1443
+ {
1444
+ "epoch": 40.0,
1445
+ "eval_loss": 0.1041550487279892,
1446
+ "eval_runtime": 1.7986,
1447
+ "eval_samples_per_second": 44.479,
1448
+ "eval_steps_per_second": 5.56,
1449
+ "step": 10600
1450
+ },
1451
+ {
1452
+ "em_boolean": 0.4117647058823529,
1453
+ "em_extraction": 0.2,
1454
+ "em_qa": 0.0,
1455
+ "em_summarization": 0.0,
1456
+ "em_unanswerable": 0.0,
1457
+ "epoch": 41.0,
1458
+ "mean_em": 0.125,
1459
+ "mean_similarity": 0.6427899678237736,
1460
+ "mean_word_count_diff": 15.15,
1461
+ "similarity_boolean": 0.5819402319543502,
1462
+ "similarity_extraction": 0.5856266627709071,
1463
+ "similarity_qa": 0.7046878506739934,
1464
+ "similarity_summarization": 0.7580131689707438,
1465
+ "similarity_unanswerable": 0.5687505826354027,
1466
+ "word_count_diff_boolean": 3.0,
1467
+ "word_count_diff_extraction": 5.266666666666667,
1468
+ "word_count_diff_qa": 5.466666666666667,
1469
+ "word_count_diff_summarization": 51.44444444444444,
1470
+ "word_count_diff_unanswerable": 4.933333333333334
1471
+ },
1472
+ {
1473
+ "epoch": 41.0,
1474
+ "grad_norm": 0.2692953050136566,
1475
+ "learning_rate": 2.516417520340457e-06,
1476
+ "loss": 0.0085,
1477
+ "step": 10865
1478
+ },
1479
+ {
1480
+ "epoch": 41.0,
1481
+ "eval_loss": 0.1051572784781456,
1482
+ "eval_runtime": 1.7897,
1483
+ "eval_samples_per_second": 44.701,
1484
+ "eval_steps_per_second": 5.588,
1485
+ "step": 10865
1486
+ },
1487
+ {
1488
+ "em_boolean": 0.47058823529411764,
1489
+ "em_extraction": 0.3333333333333333,
1490
+ "em_qa": 0.0,
1491
+ "em_summarization": 0.0,
1492
+ "em_unanswerable": 0.0,
1493
+ "epoch": 42.0,
1494
+ "mean_em": 0.1625,
1495
+ "mean_similarity": 0.6774277022806927,
1496
+ "mean_word_count_diff": 15.4,
1497
+ "similarity_boolean": 0.600595106206396,
1498
+ "similarity_extraction": 0.644695137689511,
1499
+ "similarity_qa": 0.7859726687272389,
1500
+ "similarity_summarization": 0.7171196627120177,
1501
+ "similarity_unanswerable": 0.6410618901252747,
1502
+ "word_count_diff_boolean": 3.8823529411764706,
1503
+ "word_count_diff_extraction": 4.0,
1504
+ "word_count_diff_qa": 6.333333333333333,
1505
+ "word_count_diff_summarization": 53.05555555555556,
1506
+ "word_count_diff_unanswerable": 3.7333333333333334
1507
+ },
1508
+ {
1509
+ "epoch": 42.0,
1510
+ "grad_norm": 0.028788737952709198,
1511
+ "learning_rate": 2.000388825686658e-06,
1512
+ "loss": 0.0084,
1513
+ "step": 11130
1514
+ },
1515
+ {
1516
+ "epoch": 42.0,
1517
+ "eval_loss": 0.10606852918863297,
1518
+ "eval_runtime": 1.7957,
1519
+ "eval_samples_per_second": 44.551,
1520
+ "eval_steps_per_second": 5.569,
1521
+ "step": 11130
1522
+ },
1523
+ {
1524
+ "em_boolean": 0.4117647058823529,
1525
+ "em_extraction": 0.2,
1526
+ "em_qa": 0.0,
1527
+ "em_summarization": 0.0,
1528
+ "em_unanswerable": 0.0,
1529
+ "epoch": 43.0,
1530
+ "mean_em": 0.125,
1531
+ "mean_similarity": 0.6729973700363189,
1532
+ "mean_word_count_diff": 14.55,
1533
+ "similarity_boolean": 0.6187414353822961,
1534
+ "similarity_extraction": 0.5894727125763893,
1535
+ "similarity_qa": 0.7754949867725373,
1536
+ "similarity_summarization": 0.7333515452014076,
1537
+ "similarity_unanswerable": 0.643089459836483,
1538
+ "word_count_diff_boolean": 2.764705882352941,
1539
+ "word_count_diff_extraction": 2.933333333333333,
1540
+ "word_count_diff_qa": 6.0,
1541
+ "word_count_diff_summarization": 50.166666666666664,
1542
+ "word_count_diff_unanswerable": 5.333333333333333
1543
+ },
1544
+ {
1545
+ "epoch": 43.0,
1546
+ "grad_norm": 0.11988003551959991,
1547
+ "learning_rate": 1.5397649037716471e-06,
1548
+ "loss": 0.0084,
1549
+ "step": 11395
1550
+ },
1551
+ {
1552
+ "epoch": 43.0,
1553
+ "eval_loss": 0.10630540549755096,
1554
+ "eval_runtime": 1.7956,
1555
+ "eval_samples_per_second": 44.554,
1556
+ "eval_steps_per_second": 5.569,
1557
+ "step": 11395
1558
+ },
1559
+ {
1560
+ "em_boolean": 0.4117647058823529,
1561
+ "em_extraction": 0.13333333333333333,
1562
+ "em_qa": 0.0,
1563
+ "em_summarization": 0.0,
1564
+ "em_unanswerable": 0.0,
1565
+ "epoch": 44.0,
1566
+ "mean_em": 0.1125,
1567
+ "mean_similarity": 0.6471819347003475,
1568
+ "mean_word_count_diff": 14.9,
1569
+ "similarity_boolean": 0.5824065589729477,
1570
+ "similarity_extraction": 0.5456480238586664,
1571
+ "similarity_qa": 0.7224714895089467,
1572
+ "similarity_summarization": 0.7356228894657559,
1573
+ "similarity_unanswerable": 0.6407092375059923,
1574
+ "word_count_diff_boolean": 4.0,
1575
+ "word_count_diff_extraction": 3.8666666666666667,
1576
+ "word_count_diff_qa": 5.466666666666667,
1577
+ "word_count_diff_summarization": 50.388888888888886,
1578
+ "word_count_diff_unanswerable": 5.133333333333334
1579
+ },
1580
+ {
1581
+ "epoch": 44.0,
1582
+ "grad_norm": 0.08798056095838547,
1583
+ "learning_rate": 1.1365089489840635e-06,
1584
+ "loss": 0.0083,
1585
+ "step": 11660
1586
+ },
1587
+ {
1588
+ "epoch": 44.0,
1589
+ "eval_loss": 0.10651306062936783,
1590
+ "eval_runtime": 1.8039,
1591
+ "eval_samples_per_second": 44.348,
1592
+ "eval_steps_per_second": 5.543,
1593
+ "step": 11660
1594
+ },
1595
+ {
1596
+ "em_boolean": 0.35294117647058826,
1597
+ "em_extraction": 0.26666666666666666,
1598
+ "em_qa": 0.06666666666666667,
1599
+ "em_summarization": 0.0,
1600
+ "em_unanswerable": 0.0,
1601
+ "epoch": 45.0,
1602
+ "mean_em": 0.1375,
1603
+ "mean_similarity": 0.6303860172163696,
1604
+ "mean_word_count_diff": 15.5,
1605
+ "similarity_boolean": 0.4271486557143576,
1606
+ "similarity_extraction": 0.642005218565464,
1607
+ "similarity_qa": 0.8015492022037506,
1608
+ "similarity_summarization": 0.7182055397166146,
1609
+ "similarity_unanswerable": 0.5725558802485466,
1610
+ "word_count_diff_boolean": 5.764705882352941,
1611
+ "word_count_diff_extraction": 4.533333333333333,
1612
+ "word_count_diff_qa": 4.733333333333333,
1613
+ "word_count_diff_summarization": 50.833333333333336,
1614
+ "word_count_diff_unanswerable": 5.866666666666666
1615
+ },
1616
+ {
1617
+ "epoch": 45.0,
1618
+ "grad_norm": 0.17910261452198029,
1619
+ "learning_rate": 7.923396515393966e-07,
1620
+ "loss": 0.0087,
1621
+ "step": 11925
1622
+ },
1623
+ {
1624
+ "epoch": 45.0,
1625
+ "eval_loss": 0.10618974268436432,
1626
+ "eval_runtime": 1.8032,
1627
+ "eval_samples_per_second": 44.365,
1628
+ "eval_steps_per_second": 5.546,
1629
+ "step": 11925
1630
+ }
1631
+ ],
1632
+ "logging_steps": 500,
1633
+ "max_steps": 13250,
1634
+ "num_input_tokens_seen": 0,
1635
+ "num_train_epochs": 50,
1636
+ "save_steps": 500,
1637
+ "stateful_callbacks": {
1638
+ "TrainerControl": {
1639
+ "args": {
1640
+ "should_epoch_stop": false,
1641
+ "should_evaluate": false,
1642
+ "should_log": false,
1643
+ "should_save": true,
1644
+ "should_training_stop": false
1645
+ },
1646
+ "attributes": {}
1647
+ }
1648
+ },
1649
+ "total_flos": 3.260129755004928e+16,
1650
+ "train_batch_size": 4,
1651
+ "trial_name": null,
1652
+ "trial_params": null
1653
+ }
checkpoint-11925/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a42f35ca56de4716016f99e4c1ec8c3abc7da2b9d03b422aae399b849522e7a
3
+ size 5304
checkpoint-12190/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }