zakerytclarke commited on
Commit
78398a7
·
verified ·
1 Parent(s): 43b8ed2

Upload folder using huggingface_hub

Browse files
checkpoint-372/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-372/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./teapotllmbase",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
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": 24,
22
+ "num_heads": 16,
23
+ "num_layers": 24,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.48.3",
31
+ "use_cache": true,
32
+ "vocab_size": 32128
33
+ }
checkpoint-372/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-372/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8904274c493ef5fb3e915279d1af7acb4f5b5057741047082c13c8f3f91fc48
3
+ size 3132668808
checkpoint-372/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7beb430b294846ff8862f8e7d1f3a37dd6d398f5366f01b3675adca9a057204
3
+ size 6265677800
checkpoint-372/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8936c1c0a4780108e3680063c2f8c2363777cb0157fdb8695369c4122566378f
3
+ size 14244
checkpoint-372/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56696064bd01df514fccf747b767a773ba1a83d59498e2420ec06e0eff0f7296
3
+ size 1064
checkpoint-372/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-372/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-372/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-372/trainer_state.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.02781366929411888,
3
+ "best_model_checkpoint": "./teapotllm/checkpoint-372",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 372,
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": 0.4,
13
+ "em_extraction": 0.5,
14
+ "em_qa": 0.0,
15
+ "em_summarization": 0.0,
16
+ "em_unanswerable": 0.0,
17
+ "epoch": 1.0,
18
+ "mean_em": 0.13636363636363635,
19
+ "mean_similarity": 0.7151702378848286,
20
+ "mean_word_count_diff": 4.0606060606060606,
21
+ "similarity_boolean": 0.6859854146838188,
22
+ "similarity_extraction": 0.6776353690773249,
23
+ "similarity_qa": 0.7660255491733551,
24
+ "similarity_summarization": 0.7428409457206726,
25
+ "similarity_unanswerable": 0.7166690183803439,
26
+ "word_count_diff_boolean": 1.9,
27
+ "word_count_diff_extraction": 3.1,
28
+ "word_count_diff_qa": 4.7,
29
+ "word_count_diff_summarization": 19.25,
30
+ "word_count_diff_unanswerable": 2.9375
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 0.1633770614862442,
35
+ "learning_rate": 4.8333333333333334e-05,
36
+ "loss": 0.0597,
37
+ "step": 186
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 0.02993270382285118,
42
+ "eval_runtime": 4.3173,
43
+ "eval_samples_per_second": 15.287,
44
+ "eval_steps_per_second": 2.085,
45
+ "step": 186
46
+ },
47
+ {
48
+ "em_boolean": 0.4,
49
+ "em_extraction": 0.4,
50
+ "em_qa": 0.2,
51
+ "em_summarization": 0.0,
52
+ "em_unanswerable": 0.03125,
53
+ "epoch": 2.0,
54
+ "mean_em": 0.16666666666666666,
55
+ "mean_similarity": 0.6823387349193747,
56
+ "mean_word_count_diff": 4.393939393939394,
57
+ "similarity_boolean": 0.6429030410945415,
58
+ "similarity_extraction": 0.5662426881492137,
59
+ "similarity_qa": 0.8177247762680053,
60
+ "similarity_summarization": 0.6609117537736893,
61
+ "similarity_unanswerable": 0.6913126385770738,
62
+ "word_count_diff_boolean": 2.0,
63
+ "word_count_diff_extraction": 4.5,
64
+ "word_count_diff_qa": 4.4,
65
+ "word_count_diff_summarization": 18.25,
66
+ "word_count_diff_unanswerable": 3.375
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.11337712407112122,
71
+ "learning_rate": 4.666666666666667e-05,
72
+ "loss": 0.0236,
73
+ "step": 372
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.02781366929411888,
78
+ "eval_runtime": 4.3427,
79
+ "eval_samples_per_second": 15.198,
80
+ "eval_steps_per_second": 2.072,
81
+ "step": 372
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 5580,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 30,
88
+ "save_steps": 500,
89
+ "stateful_callbacks": {
90
+ "TrainerControl": {
91
+ "args": {
92
+ "should_epoch_stop": false,
93
+ "should_evaluate": false,
94
+ "should_log": false,
95
+ "should_save": true,
96
+ "should_training_stop": false
97
+ },
98
+ "attributes": {}
99
+ }
100
+ },
101
+ "total_flos": 1714747355430912.0,
102
+ "train_batch_size": 2,
103
+ "trial_name": null,
104
+ "trial_params": null
105
+ }
checkpoint-372/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefc726fb5e7550afc92974b096c16ac389aea67b613748fe71126ede98eda9b
3
+ size 5304
checkpoint-5580/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-5580/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./teapotllmbase",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
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": 24,
22
+ "num_heads": 16,
23
+ "num_layers": 24,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.48.3",
31
+ "use_cache": true,
32
+ "vocab_size": 32128
33
+ }
checkpoint-5580/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-5580/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363d3d95a4787722e222c3314126f55e8713961e50fe9aeb8924b07f4c31c28e
3
+ size 3132668808
checkpoint-5580/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09de6760b9e327cbb979d5dea10e450f1cf53f7779881912f3c58b157dddb1b1
3
+ size 6265677800
checkpoint-5580/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6c9ce3b122fe4cd4522a5b2215c6cbb9b017dd061e0937410845fc983e9181
3
+ size 14244
checkpoint-5580/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1abf951734ca22418d5039ff6ec8d3c30d392864fd5399b59927e6c02bfb6c
3
+ size 1064
checkpoint-5580/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-5580/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-5580/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-5580/trainer_state.json ADDED
@@ -0,0 +1,1113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.02781366929411888,
3
+ "best_model_checkpoint": "./teapotllm/checkpoint-372",
4
+ "epoch": 30.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5580,
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": 0.4,
13
+ "em_extraction": 0.5,
14
+ "em_qa": 0.0,
15
+ "em_summarization": 0.0,
16
+ "em_unanswerable": 0.0,
17
+ "epoch": 1.0,
18
+ "mean_em": 0.13636363636363635,
19
+ "mean_similarity": 0.7151702378848286,
20
+ "mean_word_count_diff": 4.0606060606060606,
21
+ "similarity_boolean": 0.6859854146838188,
22
+ "similarity_extraction": 0.6776353690773249,
23
+ "similarity_qa": 0.7660255491733551,
24
+ "similarity_summarization": 0.7428409457206726,
25
+ "similarity_unanswerable": 0.7166690183803439,
26
+ "word_count_diff_boolean": 1.9,
27
+ "word_count_diff_extraction": 3.1,
28
+ "word_count_diff_qa": 4.7,
29
+ "word_count_diff_summarization": 19.25,
30
+ "word_count_diff_unanswerable": 2.9375
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 0.1633770614862442,
35
+ "learning_rate": 4.8333333333333334e-05,
36
+ "loss": 0.0597,
37
+ "step": 186
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 0.02993270382285118,
42
+ "eval_runtime": 4.3173,
43
+ "eval_samples_per_second": 15.287,
44
+ "eval_steps_per_second": 2.085,
45
+ "step": 186
46
+ },
47
+ {
48
+ "em_boolean": 0.4,
49
+ "em_extraction": 0.4,
50
+ "em_qa": 0.2,
51
+ "em_summarization": 0.0,
52
+ "em_unanswerable": 0.03125,
53
+ "epoch": 2.0,
54
+ "mean_em": 0.16666666666666666,
55
+ "mean_similarity": 0.6823387349193747,
56
+ "mean_word_count_diff": 4.393939393939394,
57
+ "similarity_boolean": 0.6429030410945415,
58
+ "similarity_extraction": 0.5662426881492137,
59
+ "similarity_qa": 0.8177247762680053,
60
+ "similarity_summarization": 0.6609117537736893,
61
+ "similarity_unanswerable": 0.6913126385770738,
62
+ "word_count_diff_boolean": 2.0,
63
+ "word_count_diff_extraction": 4.5,
64
+ "word_count_diff_qa": 4.4,
65
+ "word_count_diff_summarization": 18.25,
66
+ "word_count_diff_unanswerable": 3.375
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.11337712407112122,
71
+ "learning_rate": 4.666666666666667e-05,
72
+ "loss": 0.0236,
73
+ "step": 372
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.02781366929411888,
78
+ "eval_runtime": 4.3427,
79
+ "eval_samples_per_second": 15.198,
80
+ "eval_steps_per_second": 2.072,
81
+ "step": 372
82
+ },
83
+ {
84
+ "em_boolean": 0.7,
85
+ "em_extraction": 0.4,
86
+ "em_qa": 0.1,
87
+ "em_summarization": 0.0,
88
+ "em_unanswerable": 0.03125,
89
+ "epoch": 3.0,
90
+ "mean_em": 0.19696969696969696,
91
+ "mean_similarity": 0.7136092173556486,
92
+ "mean_word_count_diff": 4.0606060606060606,
93
+ "similarity_boolean": 0.7808200724422931,
94
+ "similarity_extraction": 0.5972317367792129,
95
+ "similarity_qa": 0.8595586240291595,
96
+ "similarity_summarization": 0.624700665473938,
97
+ "similarity_unanswerable": 0.6944781672209501,
98
+ "word_count_diff_boolean": 1.2,
99
+ "word_count_diff_extraction": 5.3,
100
+ "word_count_diff_qa": 3.5,
101
+ "word_count_diff_summarization": 18.0,
102
+ "word_count_diff_unanswerable": 3.0
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "grad_norm": 0.3930008113384247,
107
+ "learning_rate": 4.5e-05,
108
+ "loss": 0.015,
109
+ "step": 558
110
+ },
111
+ {
112
+ "epoch": 3.0,
113
+ "eval_loss": 0.02964785322546959,
114
+ "eval_runtime": 4.3399,
115
+ "eval_samples_per_second": 15.208,
116
+ "eval_steps_per_second": 2.074,
117
+ "step": 558
118
+ },
119
+ {
120
+ "em_boolean": 0.6,
121
+ "em_extraction": 0.3,
122
+ "em_qa": 0.0,
123
+ "em_summarization": 0.0,
124
+ "em_unanswerable": 0.09375,
125
+ "epoch": 4.0,
126
+ "mean_em": 0.18181818181818182,
127
+ "mean_similarity": 0.7020406423305924,
128
+ "mean_word_count_diff": 4.287878787878788,
129
+ "similarity_boolean": 0.7741398263722659,
130
+ "similarity_extraction": 0.5548319160938263,
131
+ "similarity_qa": 0.8464474320411682,
132
+ "similarity_summarization": 0.6931064277887344,
133
+ "similarity_unanswerable": 0.681502029299736,
134
+ "word_count_diff_boolean": 1.4,
135
+ "word_count_diff_extraction": 4.6,
136
+ "word_count_diff_qa": 3.8,
137
+ "word_count_diff_summarization": 18.75,
138
+ "word_count_diff_unanswerable": 3.4375
139
+ },
140
+ {
141
+ "epoch": 4.0,
142
+ "grad_norm": 0.2295440137386322,
143
+ "learning_rate": 4.3333333333333334e-05,
144
+ "loss": 0.0102,
145
+ "step": 744
146
+ },
147
+ {
148
+ "epoch": 4.0,
149
+ "eval_loss": 0.03305710479617119,
150
+ "eval_runtime": 4.326,
151
+ "eval_samples_per_second": 15.257,
152
+ "eval_steps_per_second": 2.08,
153
+ "step": 744
154
+ },
155
+ {
156
+ "em_boolean": 0.6,
157
+ "em_extraction": 0.4,
158
+ "em_qa": 0.0,
159
+ "em_summarization": 0.0,
160
+ "em_unanswerable": 0.125,
161
+ "epoch": 5.0,
162
+ "mean_em": 0.21212121212121213,
163
+ "mean_similarity": 0.7231389704075727,
164
+ "mean_word_count_diff": 4.363636363636363,
165
+ "similarity_boolean": 0.7543415576219559,
166
+ "similarity_extraction": 0.5749588221311569,
167
+ "similarity_qa": 0.7916842460632324,
168
+ "similarity_summarization": 0.8001345098018646,
169
+ "similarity_unanswerable": 0.7286496171727777,
170
+ "word_count_diff_boolean": 1.6,
171
+ "word_count_diff_extraction": 5.9,
172
+ "word_count_diff_qa": 6.0,
173
+ "word_count_diff_summarization": 15.75,
174
+ "word_count_diff_unanswerable": 2.8125
175
+ },
176
+ {
177
+ "epoch": 5.0,
178
+ "grad_norm": 0.16206224262714386,
179
+ "learning_rate": 4.166666666666667e-05,
180
+ "loss": 0.0073,
181
+ "step": 930
182
+ },
183
+ {
184
+ "epoch": 5.0,
185
+ "eval_loss": 0.03383969888091087,
186
+ "eval_runtime": 4.3253,
187
+ "eval_samples_per_second": 15.259,
188
+ "eval_steps_per_second": 2.081,
189
+ "step": 930
190
+ },
191
+ {
192
+ "em_boolean": 0.5,
193
+ "em_extraction": 0.4,
194
+ "em_qa": 0.0,
195
+ "em_summarization": 0.0,
196
+ "em_unanswerable": 0.09375,
197
+ "epoch": 6.0,
198
+ "mean_em": 0.18181818181818182,
199
+ "mean_similarity": 0.7190481367887873,
200
+ "mean_word_count_diff": 3.712121212121212,
201
+ "similarity_boolean": 0.7263102680444717,
202
+ "similarity_extraction": 0.5906288996338844,
203
+ "similarity_qa": 0.8479191601276398,
204
+ "similarity_summarization": 0.7078308612108231,
205
+ "similarity_unanswerable": 0.7180396970361471,
206
+ "word_count_diff_boolean": 1.6,
207
+ "word_count_diff_extraction": 4.1,
208
+ "word_count_diff_qa": 3.7,
209
+ "word_count_diff_summarization": 18.5,
210
+ "word_count_diff_unanswerable": 2.40625
211
+ },
212
+ {
213
+ "epoch": 6.0,
214
+ "grad_norm": 0.11092964559793472,
215
+ "learning_rate": 4e-05,
216
+ "loss": 0.0063,
217
+ "step": 1116
218
+ },
219
+ {
220
+ "epoch": 6.0,
221
+ "eval_loss": 0.036639757454395294,
222
+ "eval_runtime": 4.3411,
223
+ "eval_samples_per_second": 15.204,
224
+ "eval_steps_per_second": 2.073,
225
+ "step": 1116
226
+ },
227
+ {
228
+ "em_boolean": 0.5,
229
+ "em_extraction": 0.4,
230
+ "em_qa": 0.1,
231
+ "em_summarization": 0.0,
232
+ "em_unanswerable": 0.09375,
233
+ "epoch": 7.0,
234
+ "mean_em": 0.19696969696969696,
235
+ "mean_similarity": 0.7222502547683138,
236
+ "mean_word_count_diff": 3.4696969696969697,
237
+ "similarity_boolean": 0.7063896596431732,
238
+ "similarity_extraction": 0.613977988064289,
239
+ "similarity_qa": 0.8624586880207061,
240
+ "similarity_summarization": 0.7022114843130112,
241
+ "similarity_unanswerable": 0.7197314850054681,
242
+ "word_count_diff_boolean": 0.0,
243
+ "word_count_diff_extraction": 3.8,
244
+ "word_count_diff_qa": 4.0,
245
+ "word_count_diff_summarization": 18.25,
246
+ "word_count_diff_unanswerable": 2.4375
247
+ },
248
+ {
249
+ "epoch": 7.0,
250
+ "grad_norm": 0.0025342688895761967,
251
+ "learning_rate": 3.8333333333333334e-05,
252
+ "loss": 0.0051,
253
+ "step": 1302
254
+ },
255
+ {
256
+ "epoch": 7.0,
257
+ "eval_loss": 0.03565499931573868,
258
+ "eval_runtime": 4.3456,
259
+ "eval_samples_per_second": 15.188,
260
+ "eval_steps_per_second": 2.071,
261
+ "step": 1302
262
+ },
263
+ {
264
+ "em_boolean": 0.7,
265
+ "em_extraction": 0.5,
266
+ "em_qa": 0.0,
267
+ "em_summarization": 0.0,
268
+ "em_unanswerable": 0.09375,
269
+ "epoch": 8.0,
270
+ "mean_em": 0.22727272727272727,
271
+ "mean_similarity": 0.7595055665482174,
272
+ "mean_word_count_diff": 3.6363636363636362,
273
+ "similarity_boolean": 0.827492555975914,
274
+ "similarity_extraction": 0.6385330930352211,
275
+ "similarity_qa": 0.8492773473262787,
276
+ "similarity_summarization": 0.7314918637275696,
277
+ "similarity_unanswerable": 0.7515115616843104,
278
+ "word_count_diff_boolean": 0.0,
279
+ "word_count_diff_extraction": 3.0,
280
+ "word_count_diff_qa": 4.7,
281
+ "word_count_diff_summarization": 17.75,
282
+ "word_count_diff_unanswerable": 2.875
283
+ },
284
+ {
285
+ "epoch": 8.0,
286
+ "grad_norm": 0.015746578574180603,
287
+ "learning_rate": 3.6666666666666666e-05,
288
+ "loss": 0.0059,
289
+ "step": 1488
290
+ },
291
+ {
292
+ "epoch": 8.0,
293
+ "eval_loss": 0.03911704570055008,
294
+ "eval_runtime": 4.3337,
295
+ "eval_samples_per_second": 15.229,
296
+ "eval_steps_per_second": 2.077,
297
+ "step": 1488
298
+ },
299
+ {
300
+ "em_boolean": 0.8,
301
+ "em_extraction": 0.5,
302
+ "em_qa": 0.0,
303
+ "em_summarization": 0.0,
304
+ "em_unanswerable": 0.1875,
305
+ "epoch": 9.0,
306
+ "mean_em": 0.2878787878787879,
307
+ "mean_similarity": 0.7606699131993633,
308
+ "mean_word_count_diff": 3.621212121212121,
309
+ "similarity_boolean": 0.8291448082774877,
310
+ "similarity_extraction": 0.7344626411795616,
311
+ "similarity_qa": 0.8531238198280334,
312
+ "similarity_summarization": 0.6869091093540192,
313
+ "similarity_unanswerable": 0.7277895356528461,
314
+ "word_count_diff_boolean": 1.7,
315
+ "word_count_diff_extraction": 2.5,
316
+ "word_count_diff_qa": 4.3,
317
+ "word_count_diff_summarization": 18.25,
318
+ "word_count_diff_unanswerable": 2.53125
319
+ },
320
+ {
321
+ "epoch": 9.0,
322
+ "grad_norm": 0.2743629217147827,
323
+ "learning_rate": 3.5e-05,
324
+ "loss": 0.0032,
325
+ "step": 1674
326
+ },
327
+ {
328
+ "epoch": 9.0,
329
+ "eval_loss": 0.04249922186136246,
330
+ "eval_runtime": 4.3316,
331
+ "eval_samples_per_second": 15.237,
332
+ "eval_steps_per_second": 2.078,
333
+ "step": 1674
334
+ },
335
+ {
336
+ "em_boolean": 0.9,
337
+ "em_extraction": 0.5,
338
+ "em_qa": 0.1,
339
+ "em_summarization": 0.0,
340
+ "em_unanswerable": 0.1875,
341
+ "epoch": 10.0,
342
+ "mean_em": 0.3181818181818182,
343
+ "mean_similarity": 0.7545153351895737,
344
+ "mean_word_count_diff": 3.5606060606060606,
345
+ "similarity_boolean": 0.9258624315261841,
346
+ "similarity_extraction": 0.6548894591629505,
347
+ "similarity_qa": 0.7920802533626556,
348
+ "similarity_summarization": 0.7080870717763901,
349
+ "similarity_unanswerable": 0.7261669498402625,
350
+ "word_count_diff_boolean": 0.0,
351
+ "word_count_diff_extraction": 3.5,
352
+ "word_count_diff_qa": 4.3,
353
+ "word_count_diff_summarization": 17.75,
354
+ "word_count_diff_unanswerable": 2.6875
355
+ },
356
+ {
357
+ "epoch": 10.0,
358
+ "grad_norm": 0.19264960289001465,
359
+ "learning_rate": 3.3333333333333335e-05,
360
+ "loss": 0.0023,
361
+ "step": 1860
362
+ },
363
+ {
364
+ "epoch": 10.0,
365
+ "eval_loss": 0.044133350253105164,
366
+ "eval_runtime": 4.332,
367
+ "eval_samples_per_second": 15.236,
368
+ "eval_steps_per_second": 2.078,
369
+ "step": 1860
370
+ },
371
+ {
372
+ "em_boolean": 0.7,
373
+ "em_extraction": 0.5,
374
+ "em_qa": 0.0,
375
+ "em_summarization": 0.0,
376
+ "em_unanswerable": 0.21875,
377
+ "epoch": 11.0,
378
+ "mean_em": 0.2878787878787879,
379
+ "mean_similarity": 0.7554914088863315,
380
+ "mean_word_count_diff": 3.4545454545454546,
381
+ "similarity_boolean": 0.8498284339904785,
382
+ "similarity_extraction": 0.6388141810894012,
383
+ "similarity_qa": 0.8062415808439255,
384
+ "similarity_summarization": 0.7252775132656097,
385
+ "similarity_unanswerable": 0.7503900304436684,
386
+ "word_count_diff_boolean": 0.0,
387
+ "word_count_diff_extraction": 3.4,
388
+ "word_count_diff_qa": 5.3,
389
+ "word_count_diff_summarization": 15.25,
390
+ "word_count_diff_unanswerable": 2.5
391
+ },
392
+ {
393
+ "epoch": 11.0,
394
+ "grad_norm": 0.026405496522784233,
395
+ "learning_rate": 3.1666666666666666e-05,
396
+ "loss": 0.0018,
397
+ "step": 2046
398
+ },
399
+ {
400
+ "epoch": 11.0,
401
+ "eval_loss": 0.04769740626215935,
402
+ "eval_runtime": 4.3231,
403
+ "eval_samples_per_second": 15.267,
404
+ "eval_steps_per_second": 2.082,
405
+ "step": 2046
406
+ },
407
+ {
408
+ "em_boolean": 0.4,
409
+ "em_extraction": 0.5,
410
+ "em_qa": 0.0,
411
+ "em_summarization": 0.0,
412
+ "em_unanswerable": 0.09375,
413
+ "epoch": 12.0,
414
+ "mean_em": 0.18181818181818182,
415
+ "mean_similarity": 0.70488141804482,
416
+ "mean_word_count_diff": 3.712121212121212,
417
+ "similarity_boolean": 0.6591130249202252,
418
+ "similarity_extraction": 0.7003911420702934,
419
+ "similarity_qa": 0.7918749868869781,
420
+ "similarity_summarization": 0.6370653212070465,
421
+ "similarity_unanswerable": 0.7018787739798427,
422
+ "word_count_diff_boolean": 1.6,
423
+ "word_count_diff_extraction": 3.2,
424
+ "word_count_diff_qa": 3.5,
425
+ "word_count_diff_summarization": 18.75,
426
+ "word_count_diff_unanswerable": 2.71875
427
+ },
428
+ {
429
+ "epoch": 12.0,
430
+ "grad_norm": 0.009582425467669964,
431
+ "learning_rate": 3e-05,
432
+ "loss": 0.0021,
433
+ "step": 2232
434
+ },
435
+ {
436
+ "epoch": 12.0,
437
+ "eval_loss": 0.04564819857478142,
438
+ "eval_runtime": 4.3388,
439
+ "eval_samples_per_second": 15.211,
440
+ "eval_steps_per_second": 2.074,
441
+ "step": 2232
442
+ },
443
+ {
444
+ "em_boolean": 0.6,
445
+ "em_extraction": 0.4,
446
+ "em_qa": 0.1,
447
+ "em_summarization": 0.0,
448
+ "em_unanswerable": 0.21875,
449
+ "epoch": 13.0,
450
+ "mean_em": 0.2727272727272727,
451
+ "mean_similarity": 0.732733571506811,
452
+ "mean_word_count_diff": 3.5303030303030303,
453
+ "similarity_boolean": 0.7299912668764591,
454
+ "similarity_extraction": 0.6099361270666123,
455
+ "similarity_qa": 0.8338733792304993,
456
+ "similarity_summarization": 0.6718393042683601,
457
+ "similarity_unanswerable": 0.7479703365825117,
458
+ "word_count_diff_boolean": 1.4,
459
+ "word_count_diff_extraction": 4.2,
460
+ "word_count_diff_qa": 3.3,
461
+ "word_count_diff_summarization": 16.75,
462
+ "word_count_diff_unanswerable": 2.40625
463
+ },
464
+ {
465
+ "epoch": 13.0,
466
+ "grad_norm": 0.015427525155246258,
467
+ "learning_rate": 2.8333333333333335e-05,
468
+ "loss": 0.006,
469
+ "step": 2418
470
+ },
471
+ {
472
+ "epoch": 13.0,
473
+ "eval_loss": 0.0508425235748291,
474
+ "eval_runtime": 4.3235,
475
+ "eval_samples_per_second": 15.265,
476
+ "eval_steps_per_second": 2.082,
477
+ "step": 2418
478
+ },
479
+ {
480
+ "em_boolean": 0.7,
481
+ "em_extraction": 0.5,
482
+ "em_qa": 0.0,
483
+ "em_summarization": 0.0,
484
+ "em_unanswerable": 0.1875,
485
+ "epoch": 14.0,
486
+ "mean_em": 0.2727272727272727,
487
+ "mean_similarity": 0.7405690112800309,
488
+ "mean_word_count_diff": 3.4242424242424243,
489
+ "similarity_boolean": 0.8725614547729492,
490
+ "similarity_extraction": 0.6553262293338775,
491
+ "similarity_qa": 0.7748158514499665,
492
+ "similarity_summarization": 0.7374982982873917,
493
+ "similarity_unanswerable": 0.7156414436176419,
494
+ "word_count_diff_boolean": 0.0,
495
+ "word_count_diff_extraction": 3.3,
496
+ "word_count_diff_qa": 5.1,
497
+ "word_count_diff_summarization": 18.0,
498
+ "word_count_diff_unanswerable": 2.1875
499
+ },
500
+ {
501
+ "epoch": 14.0,
502
+ "grad_norm": 0.02267725020647049,
503
+ "learning_rate": 2.6666666666666667e-05,
504
+ "loss": 0.0014,
505
+ "step": 2604
506
+ },
507
+ {
508
+ "epoch": 14.0,
509
+ "eval_loss": 0.0475737489759922,
510
+ "eval_runtime": 4.3517,
511
+ "eval_samples_per_second": 15.166,
512
+ "eval_steps_per_second": 2.068,
513
+ "step": 2604
514
+ },
515
+ {
516
+ "em_boolean": 0.5,
517
+ "em_extraction": 0.6,
518
+ "em_qa": 0.1,
519
+ "em_summarization": 0.0,
520
+ "em_unanswerable": 0.21875,
521
+ "epoch": 15.0,
522
+ "mean_em": 0.2878787878787879,
523
+ "mean_similarity": 0.7692180305267825,
524
+ "mean_word_count_diff": 3.1666666666666665,
525
+ "similarity_boolean": 0.7965274572372436,
526
+ "similarity_extraction": 0.7734156735241413,
527
+ "similarity_qa": 0.8109998881816864,
528
+ "similarity_summarization": 0.6901126950979233,
529
+ "similarity_unanswerable": 0.7562034076545388,
530
+ "word_count_diff_boolean": 0.0,
531
+ "word_count_diff_extraction": 1.5,
532
+ "word_count_diff_qa": 3.8,
533
+ "word_count_diff_summarization": 18.5,
534
+ "word_count_diff_unanswerable": 2.5625
535
+ },
536
+ {
537
+ "epoch": 15.0,
538
+ "grad_norm": 0.04372488334774971,
539
+ "learning_rate": 2.5e-05,
540
+ "loss": 0.0014,
541
+ "step": 2790
542
+ },
543
+ {
544
+ "epoch": 15.0,
545
+ "eval_loss": 0.04670372232794762,
546
+ "eval_runtime": 4.3278,
547
+ "eval_samples_per_second": 15.25,
548
+ "eval_steps_per_second": 2.08,
549
+ "step": 2790
550
+ },
551
+ {
552
+ "em_boolean": 0.4,
553
+ "em_extraction": 0.7,
554
+ "em_qa": 0.0,
555
+ "em_summarization": 0.0,
556
+ "em_unanswerable": 0.21875,
557
+ "epoch": 16.0,
558
+ "mean_em": 0.2727272727272727,
559
+ "mean_similarity": 0.7683560192923654,
560
+ "mean_word_count_diff": 3.5757575757575757,
561
+ "similarity_boolean": 0.6552163552492857,
562
+ "similarity_extraction": 0.7891500160098076,
563
+ "similarity_qa": 0.8301358222961426,
564
+ "similarity_summarization": 0.7006907612085342,
565
+ "similarity_unanswerable": 0.7863660091534257,
566
+ "word_count_diff_boolean": 1.7,
567
+ "word_count_diff_extraction": 1.9,
568
+ "word_count_diff_qa": 4.9,
569
+ "word_count_diff_summarization": 21.25,
570
+ "word_count_diff_unanswerable": 2.0625
571
+ },
572
+ {
573
+ "epoch": 16.0,
574
+ "grad_norm": 0.017858723178505898,
575
+ "learning_rate": 2.3333333333333336e-05,
576
+ "loss": 0.0013,
577
+ "step": 2976
578
+ },
579
+ {
580
+ "epoch": 16.0,
581
+ "eval_loss": 0.0506870336830616,
582
+ "eval_runtime": 4.3168,
583
+ "eval_samples_per_second": 15.289,
584
+ "eval_steps_per_second": 2.085,
585
+ "step": 2976
586
+ },
587
+ {
588
+ "em_boolean": 0.4,
589
+ "em_extraction": 0.3,
590
+ "em_qa": 0.0,
591
+ "em_summarization": 0.0,
592
+ "em_unanswerable": 0.21875,
593
+ "epoch": 17.0,
594
+ "mean_em": 0.21212121212121213,
595
+ "mean_similarity": 0.7196075666808721,
596
+ "mean_word_count_diff": 3.803030303030303,
597
+ "similarity_boolean": 0.6327047817409038,
598
+ "similarity_extraction": 0.6252625986933709,
599
+ "similarity_qa": 0.8158903121948242,
600
+ "similarity_summarization": 0.6718292534351349,
601
+ "similarity_unanswerable": 0.7521314206533134,
602
+ "word_count_diff_boolean": 1.6,
603
+ "word_count_diff_extraction": 3.6,
604
+ "word_count_diff_qa": 3.9,
605
+ "word_count_diff_summarization": 18.25,
606
+ "word_count_diff_unanswerable": 2.71875
607
+ },
608
+ {
609
+ "epoch": 17.0,
610
+ "grad_norm": 0.0030904498416930437,
611
+ "learning_rate": 2.1666666666666667e-05,
612
+ "loss": 0.0009,
613
+ "step": 3162
614
+ },
615
+ {
616
+ "epoch": 17.0,
617
+ "eval_loss": 0.05454666167497635,
618
+ "eval_runtime": 4.3302,
619
+ "eval_samples_per_second": 15.242,
620
+ "eval_steps_per_second": 2.078,
621
+ "step": 3162
622
+ },
623
+ {
624
+ "em_boolean": 0.4,
625
+ "em_extraction": 0.5,
626
+ "em_qa": 0.0,
627
+ "em_summarization": 0.0,
628
+ "em_unanswerable": 0.1875,
629
+ "epoch": 18.0,
630
+ "mean_em": 0.22727272727272727,
631
+ "mean_similarity": 0.7074560875524626,
632
+ "mean_word_count_diff": 3.6818181818181817,
633
+ "similarity_boolean": 0.6091547535732389,
634
+ "similarity_extraction": 0.6446325138211251,
635
+ "similarity_qa": 0.8525063633918762,
636
+ "similarity_summarization": 0.6083656400442123,
637
+ "similarity_unanswerable": 0.7248657159507275,
638
+ "word_count_diff_boolean": 1.7,
639
+ "word_count_diff_extraction": 2.6,
640
+ "word_count_diff_qa": 4.0,
641
+ "word_count_diff_summarization": 18.75,
642
+ "word_count_diff_unanswerable": 2.65625
643
+ },
644
+ {
645
+ "epoch": 18.0,
646
+ "grad_norm": 0.0558372437953949,
647
+ "learning_rate": 2e-05,
648
+ "loss": 0.0008,
649
+ "step": 3348
650
+ },
651
+ {
652
+ "epoch": 18.0,
653
+ "eval_loss": 0.054993122816085815,
654
+ "eval_runtime": 4.3426,
655
+ "eval_samples_per_second": 15.198,
656
+ "eval_steps_per_second": 2.073,
657
+ "step": 3348
658
+ },
659
+ {
660
+ "em_boolean": 0.6,
661
+ "em_extraction": 0.6,
662
+ "em_qa": 0.0,
663
+ "em_summarization": 0.0,
664
+ "em_unanswerable": 0.21875,
665
+ "epoch": 19.0,
666
+ "mean_em": 0.2878787878787879,
667
+ "mean_similarity": 0.7609088637612083,
668
+ "mean_word_count_diff": 3.196969696969697,
669
+ "similarity_boolean": 0.7781090468168259,
670
+ "similarity_extraction": 0.7332883447408676,
671
+ "similarity_qa": 0.7839098423719406,
672
+ "similarity_summarization": 0.6715002506971359,
673
+ "similarity_unanswerable": 0.7681534895673394,
674
+ "word_count_diff_boolean": 0.0,
675
+ "word_count_diff_extraction": 1.9,
676
+ "word_count_diff_qa": 4.7,
677
+ "word_count_diff_summarization": 18.25,
678
+ "word_count_diff_unanswerable": 2.25
679
+ },
680
+ {
681
+ "epoch": 19.0,
682
+ "grad_norm": 0.2534376084804535,
683
+ "learning_rate": 1.8333333333333333e-05,
684
+ "loss": 0.001,
685
+ "step": 3534
686
+ },
687
+ {
688
+ "epoch": 19.0,
689
+ "eval_loss": 0.05550788715481758,
690
+ "eval_runtime": 4.3349,
691
+ "eval_samples_per_second": 15.225,
692
+ "eval_steps_per_second": 2.076,
693
+ "step": 3534
694
+ },
695
+ {
696
+ "em_boolean": 0.5,
697
+ "em_extraction": 0.5,
698
+ "em_qa": 0.0,
699
+ "em_summarization": 0.0,
700
+ "em_unanswerable": 0.21875,
701
+ "epoch": 20.0,
702
+ "mean_em": 0.25757575757575757,
703
+ "mean_similarity": 0.7586507165070736,
704
+ "mean_word_count_diff": 3.5454545454545454,
705
+ "similarity_boolean": 0.6818089708685875,
706
+ "similarity_extraction": 0.6717077270150185,
707
+ "similarity_qa": 0.8592052400112152,
708
+ "similarity_summarization": 0.6685295552015305,
709
+ "similarity_unanswerable": 0.7896753028035164,
710
+ "word_count_diff_boolean": 1.7,
711
+ "word_count_diff_extraction": 2.1,
712
+ "word_count_diff_qa": 4.4,
713
+ "word_count_diff_summarization": 18.0,
714
+ "word_count_diff_unanswerable": 2.5
715
+ },
716
+ {
717
+ "epoch": 20.0,
718
+ "grad_norm": 0.011831851676106453,
719
+ "learning_rate": 1.6666666666666667e-05,
720
+ "loss": 0.0008,
721
+ "step": 3720
722
+ },
723
+ {
724
+ "epoch": 20.0,
725
+ "eval_loss": 0.053514618426561356,
726
+ "eval_runtime": 4.3467,
727
+ "eval_samples_per_second": 15.184,
728
+ "eval_steps_per_second": 2.071,
729
+ "step": 3720
730
+ },
731
+ {
732
+ "em_boolean": 0.8,
733
+ "em_extraction": 0.5,
734
+ "em_qa": 0.0,
735
+ "em_summarization": 0.0,
736
+ "em_unanswerable": 0.21875,
737
+ "epoch": 21.0,
738
+ "mean_em": 0.30303030303030304,
739
+ "mean_similarity": 0.7693727000644712,
740
+ "mean_word_count_diff": 3.212121212121212,
741
+ "similarity_boolean": 0.8541430443525314,
742
+ "similarity_extraction": 0.7111731946468354,
743
+ "similarity_qa": 0.8433568000793457,
744
+ "similarity_summarization": 0.538779329508543,
745
+ "similarity_unanswerable": 0.7667734529823065,
746
+ "word_count_diff_boolean": 0.0,
747
+ "word_count_diff_extraction": 1.8,
748
+ "word_count_diff_qa": 4.5,
749
+ "word_count_diff_summarization": 17.0,
750
+ "word_count_diff_unanswerable": 2.53125
751
+ },
752
+ {
753
+ "epoch": 21.0,
754
+ "grad_norm": 0.021487198770046234,
755
+ "learning_rate": 1.5e-05,
756
+ "loss": 0.0007,
757
+ "step": 3906
758
+ },
759
+ {
760
+ "epoch": 21.0,
761
+ "eval_loss": 0.05830617994070053,
762
+ "eval_runtime": 4.3417,
763
+ "eval_samples_per_second": 15.201,
764
+ "eval_steps_per_second": 2.073,
765
+ "step": 3906
766
+ },
767
+ {
768
+ "em_boolean": 0.5,
769
+ "em_extraction": 0.3,
770
+ "em_qa": 0.0,
771
+ "em_summarization": 0.0,
772
+ "em_unanswerable": 0.21875,
773
+ "epoch": 22.0,
774
+ "mean_em": 0.22727272727272727,
775
+ "mean_similarity": 0.7141596485267986,
776
+ "mean_word_count_diff": 3.5303030303030303,
777
+ "similarity_boolean": 0.7537968754768372,
778
+ "similarity_extraction": 0.5005216524004936,
779
+ "similarity_qa": 0.8255742013454437,
780
+ "similarity_summarization": 0.6753722429275513,
781
+ "similarity_unanswerable": 0.7385662668384612,
782
+ "word_count_diff_boolean": 1.2,
783
+ "word_count_diff_extraction": 3.1,
784
+ "word_count_diff_qa": 3.6,
785
+ "word_count_diff_summarization": 18.75,
786
+ "word_count_diff_unanswerable": 2.46875
787
+ },
788
+ {
789
+ "epoch": 22.0,
790
+ "grad_norm": 0.001079858047887683,
791
+ "learning_rate": 1.3333333333333333e-05,
792
+ "loss": 0.0009,
793
+ "step": 4092
794
+ },
795
+ {
796
+ "epoch": 22.0,
797
+ "eval_loss": 0.0558372400701046,
798
+ "eval_runtime": 4.3409,
799
+ "eval_samples_per_second": 15.204,
800
+ "eval_steps_per_second": 2.073,
801
+ "step": 4092
802
+ },
803
+ {
804
+ "em_boolean": 0.5,
805
+ "em_extraction": 0.4,
806
+ "em_qa": 0.0,
807
+ "em_summarization": 0.0,
808
+ "em_unanswerable": 0.21875,
809
+ "epoch": 23.0,
810
+ "mean_em": 0.24242424242424243,
811
+ "mean_similarity": 0.7432461308710503,
812
+ "mean_word_count_diff": 3.272727272727273,
813
+ "similarity_boolean": 0.7965274572372436,
814
+ "similarity_extraction": 0.6360977619886399,
815
+ "similarity_qa": 0.8315042436122895,
816
+ "similarity_summarization": 0.7279509454965591,
817
+ "similarity_unanswerable": 0.7344108195975423,
818
+ "word_count_diff_boolean": 0.0,
819
+ "word_count_diff_extraction": 3.4,
820
+ "word_count_diff_qa": 4.2,
821
+ "word_count_diff_summarization": 15.25,
822
+ "word_count_diff_unanswerable": 2.46875
823
+ },
824
+ {
825
+ "epoch": 23.0,
826
+ "grad_norm": 0.1313343644142151,
827
+ "learning_rate": 1.1666666666666668e-05,
828
+ "loss": 0.0005,
829
+ "step": 4278
830
+ },
831
+ {
832
+ "epoch": 23.0,
833
+ "eval_loss": 0.05678420513868332,
834
+ "eval_runtime": 4.3484,
835
+ "eval_samples_per_second": 15.178,
836
+ "eval_steps_per_second": 2.07,
837
+ "step": 4278
838
+ },
839
+ {
840
+ "em_boolean": 0.5,
841
+ "em_extraction": 0.5,
842
+ "em_qa": 0.0,
843
+ "em_summarization": 0.0,
844
+ "em_unanswerable": 0.21875,
845
+ "epoch": 24.0,
846
+ "mean_em": 0.25757575757575757,
847
+ "mean_similarity": 0.733292786009384,
848
+ "mean_word_count_diff": 3.3333333333333335,
849
+ "similarity_boolean": 0.6607738882303238,
850
+ "similarity_extraction": 0.6927396818995476,
851
+ "similarity_qa": 0.8479106187820434,
852
+ "similarity_summarization": 0.6271217167377472,
853
+ "similarity_unanswerable": 0.7460810975171626,
854
+ "word_count_diff_boolean": 1.4,
855
+ "word_count_diff_extraction": 2.5,
856
+ "word_count_diff_qa": 4.7,
857
+ "word_count_diff_summarization": 17.75,
858
+ "word_count_diff_unanswerable": 1.96875
859
+ },
860
+ {
861
+ "epoch": 24.0,
862
+ "grad_norm": 0.00035786593798547983,
863
+ "learning_rate": 1e-05,
864
+ "loss": 0.0004,
865
+ "step": 4464
866
+ },
867
+ {
868
+ "epoch": 24.0,
869
+ "eval_loss": 0.058857183903455734,
870
+ "eval_runtime": 4.3529,
871
+ "eval_samples_per_second": 15.162,
872
+ "eval_steps_per_second": 2.068,
873
+ "step": 4464
874
+ },
875
+ {
876
+ "em_boolean": 0.7,
877
+ "em_extraction": 0.5,
878
+ "em_qa": 0.0,
879
+ "em_summarization": 0.0,
880
+ "em_unanswerable": 0.21875,
881
+ "epoch": 25.0,
882
+ "mean_em": 0.2878787878787879,
883
+ "mean_similarity": 0.7524795749535164,
884
+ "mean_word_count_diff": 3.6515151515151514,
885
+ "similarity_boolean": 0.7810821939259768,
886
+ "similarity_extraction": 0.6710324764251709,
887
+ "similarity_qa": 0.820537006855011,
888
+ "similarity_summarization": 0.6545907258987427,
889
+ "similarity_unanswerable": 0.75996163347736,
890
+ "word_count_diff_boolean": 1.7,
891
+ "word_count_diff_extraction": 3.1,
892
+ "word_count_diff_qa": 3.8,
893
+ "word_count_diff_summarization": 17.75,
894
+ "word_count_diff_unanswerable": 2.625
895
+ },
896
+ {
897
+ "epoch": 25.0,
898
+ "grad_norm": 0.2973511815071106,
899
+ "learning_rate": 8.333333333333334e-06,
900
+ "loss": 0.0006,
901
+ "step": 4650
902
+ },
903
+ {
904
+ "epoch": 25.0,
905
+ "eval_loss": 0.05786564573645592,
906
+ "eval_runtime": 4.3502,
907
+ "eval_samples_per_second": 15.172,
908
+ "eval_steps_per_second": 2.069,
909
+ "step": 4650
910
+ },
911
+ {
912
+ "em_boolean": 0.5,
913
+ "em_extraction": 0.6,
914
+ "em_qa": 0.0,
915
+ "em_summarization": 0.0,
916
+ "em_unanswerable": 0.25,
917
+ "epoch": 26.0,
918
+ "mean_em": 0.2878787878787879,
919
+ "mean_similarity": 0.7584869705817916,
920
+ "mean_word_count_diff": 3.0303030303030303,
921
+ "similarity_boolean": 0.7514585584402085,
922
+ "similarity_extraction": 0.7340315699577331,
923
+ "similarity_qa": 0.8186799943447113,
924
+ "similarity_summarization": 0.7270446717739105,
925
+ "similarity_unanswerable": 0.7534456294961274,
926
+ "word_count_diff_boolean": 0.0,
927
+ "word_count_diff_extraction": 2.4,
928
+ "word_count_diff_qa": 4.2,
929
+ "word_count_diff_summarization": 17.0,
930
+ "word_count_diff_unanswerable": 2.0625
931
+ },
932
+ {
933
+ "epoch": 26.0,
934
+ "grad_norm": 0.03420831263065338,
935
+ "learning_rate": 6.666666666666667e-06,
936
+ "loss": 0.0005,
937
+ "step": 4836
938
+ },
939
+ {
940
+ "epoch": 26.0,
941
+ "eval_loss": 0.05816643312573433,
942
+ "eval_runtime": 4.3476,
943
+ "eval_samples_per_second": 15.181,
944
+ "eval_steps_per_second": 2.07,
945
+ "step": 4836
946
+ },
947
+ {
948
+ "em_boolean": 0.6,
949
+ "em_extraction": 0.4,
950
+ "em_qa": 0.0,
951
+ "em_summarization": 0.0,
952
+ "em_unanswerable": 0.21875,
953
+ "epoch": 27.0,
954
+ "mean_em": 0.25757575757575757,
955
+ "mean_similarity": 0.7683728897210323,
956
+ "mean_word_count_diff": 3.227272727272727,
957
+ "similarity_boolean": 0.823177945613861,
958
+ "similarity_extraction": 0.674461716413498,
959
+ "similarity_qa": 0.8566352903842926,
960
+ "similarity_summarization": 0.6613511592149734,
961
+ "similarity_unanswerable": 0.7663892675191164,
962
+ "word_count_diff_boolean": 0.0,
963
+ "word_count_diff_extraction": 2.8,
964
+ "word_count_diff_qa": 4.6,
965
+ "word_count_diff_summarization": 17.25,
966
+ "word_count_diff_unanswerable": 2.1875
967
+ },
968
+ {
969
+ "epoch": 27.0,
970
+ "grad_norm": 0.20164477825164795,
971
+ "learning_rate": 5e-06,
972
+ "loss": 0.0006,
973
+ "step": 5022
974
+ },
975
+ {
976
+ "epoch": 27.0,
977
+ "eval_loss": 0.05884123966097832,
978
+ "eval_runtime": 4.3217,
979
+ "eval_samples_per_second": 15.272,
980
+ "eval_steps_per_second": 2.083,
981
+ "step": 5022
982
+ },
983
+ {
984
+ "em_boolean": 0.7,
985
+ "em_extraction": 0.5,
986
+ "em_qa": 0.1,
987
+ "em_summarization": 0.0,
988
+ "em_unanswerable": 0.21875,
989
+ "epoch": 28.0,
990
+ "mean_em": 0.30303030303030304,
991
+ "mean_similarity": 0.7534916117561586,
992
+ "mean_word_count_diff": 3.378787878787879,
993
+ "similarity_boolean": 0.8725614547729492,
994
+ "similarity_extraction": 0.6645052798092366,
995
+ "similarity_qa": 0.8722499251365662,
996
+ "similarity_summarization": 0.6813686788082123,
997
+ "similarity_unanswerable": 0.7159939082339406,
998
+ "word_count_diff_boolean": 0.0,
999
+ "word_count_diff_extraction": 4.4,
1000
+ "word_count_diff_qa": 3.3,
1001
+ "word_count_diff_summarization": 15.75,
1002
+ "word_count_diff_unanswerable": 2.59375
1003
+ },
1004
+ {
1005
+ "epoch": 28.0,
1006
+ "grad_norm": 0.09254211187362671,
1007
+ "learning_rate": 3.3333333333333333e-06,
1008
+ "loss": 0.0005,
1009
+ "step": 5208
1010
+ },
1011
+ {
1012
+ "epoch": 28.0,
1013
+ "eval_loss": 0.05950010567903519,
1014
+ "eval_runtime": 4.3472,
1015
+ "eval_samples_per_second": 15.182,
1016
+ "eval_steps_per_second": 2.07,
1017
+ "step": 5208
1018
+ },
1019
+ {
1020
+ "em_boolean": 0.3,
1021
+ "em_extraction": 0.5,
1022
+ "em_qa": 0.0,
1023
+ "em_summarization": 0.0,
1024
+ "em_unanswerable": 0.15625,
1025
+ "epoch": 29.0,
1026
+ "mean_em": 0.19696969696969696,
1027
+ "mean_similarity": 0.7206367963755672,
1028
+ "mean_word_count_diff": 3.257575757575758,
1029
+ "similarity_boolean": 0.5599547553807497,
1030
+ "similarity_extraction": 0.6752738565206527,
1031
+ "similarity_qa": 0.826910001039505,
1032
+ "similarity_summarization": 0.6975099295377731,
1033
+ "similarity_unanswerable": 0.7547063347883523,
1034
+ "word_count_diff_boolean": 2.1,
1035
+ "word_count_diff_extraction": 3.4,
1036
+ "word_count_diff_qa": 3.3,
1037
+ "word_count_diff_summarization": 15.5,
1038
+ "word_count_diff_unanswerable": 2.03125
1039
+ },
1040
+ {
1041
+ "epoch": 29.0,
1042
+ "grad_norm": 0.002610220806673169,
1043
+ "learning_rate": 1.6666666666666667e-06,
1044
+ "loss": 0.0003,
1045
+ "step": 5394
1046
+ },
1047
+ {
1048
+ "epoch": 29.0,
1049
+ "eval_loss": 0.05941936746239662,
1050
+ "eval_runtime": 4.3317,
1051
+ "eval_samples_per_second": 15.236,
1052
+ "eval_steps_per_second": 2.078,
1053
+ "step": 5394
1054
+ },
1055
+ {
1056
+ "em_boolean": 0.6,
1057
+ "em_extraction": 0.4,
1058
+ "em_qa": 0.0,
1059
+ "em_summarization": 0.0,
1060
+ "em_unanswerable": 0.1875,
1061
+ "epoch": 30.0,
1062
+ "mean_em": 0.24242424242424243,
1063
+ "mean_similarity": 0.7168677732574217,
1064
+ "mean_word_count_diff": 4.393939393939394,
1065
+ "similarity_boolean": 0.7321859009563922,
1066
+ "similarity_extraction": 0.5674642950296402,
1067
+ "similarity_qa": 0.8223672747612,
1068
+ "similarity_summarization": 0.6349779516458511,
1069
+ "similarity_unanswerable": 0.7360370787791908,
1070
+ "word_count_diff_boolean": 1.7,
1071
+ "word_count_diff_extraction": 5.9,
1072
+ "word_count_diff_qa": 4.9,
1073
+ "word_count_diff_summarization": 18.0,
1074
+ "word_count_diff_unanswerable": 2.90625
1075
+ },
1076
+ {
1077
+ "epoch": 30.0,
1078
+ "grad_norm": 0.08226452767848969,
1079
+ "learning_rate": 0.0,
1080
+ "loss": 0.0004,
1081
+ "step": 5580
1082
+ },
1083
+ {
1084
+ "epoch": 30.0,
1085
+ "eval_loss": 0.05968955159187317,
1086
+ "eval_runtime": 4.3488,
1087
+ "eval_samples_per_second": 15.177,
1088
+ "eval_steps_per_second": 2.07,
1089
+ "step": 5580
1090
+ }
1091
+ ],
1092
+ "logging_steps": 500,
1093
+ "max_steps": 5580,
1094
+ "num_input_tokens_seen": 0,
1095
+ "num_train_epochs": 30,
1096
+ "save_steps": 500,
1097
+ "stateful_callbacks": {
1098
+ "TrainerControl": {
1099
+ "args": {
1100
+ "should_epoch_stop": false,
1101
+ "should_evaluate": false,
1102
+ "should_log": false,
1103
+ "should_save": true,
1104
+ "should_training_stop": true
1105
+ },
1106
+ "attributes": {}
1107
+ }
1108
+ },
1109
+ "total_flos": 2.572121033146368e+16,
1110
+ "train_batch_size": 2,
1111
+ "trial_name": null,
1112
+ "trial_params": null
1113
+ }
checkpoint-5580/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefc726fb5e7550afc92974b096c16ac389aea67b613748fe71126ede98eda9b
3
+ size 5304
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e13c40655c0d31bc648923912f7e606bca14cf66b5e27f1906f2fa67df7b13
3
  size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8904274c493ef5fb3e915279d1af7acb4f5b5057741047082c13c8f3f91fc48
3
  size 3132668808
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e0a1b122b6bddbfaf4d77e01e4e1644e5bf6c44bd00ff772f92775494fac962
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefc726fb5e7550afc92974b096c16ac389aea67b613748fe71126ede98eda9b
3
  size 5304