Tnt3o5 commited on
Commit
33177c8
·
verified ·
1 Parent(s): 5728cb2

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 36099,
3
+ "<extra_id_10>": 36089,
4
+ "<extra_id_11>": 36088,
5
+ "<extra_id_12>": 36087,
6
+ "<extra_id_13>": 36086,
7
+ "<extra_id_14>": 36085,
8
+ "<extra_id_15>": 36084,
9
+ "<extra_id_16>": 36083,
10
+ "<extra_id_17>": 36082,
11
+ "<extra_id_18>": 36081,
12
+ "<extra_id_19>": 36080,
13
+ "<extra_id_1>": 36098,
14
+ "<extra_id_20>": 36079,
15
+ "<extra_id_21>": 36078,
16
+ "<extra_id_22>": 36077,
17
+ "<extra_id_23>": 36076,
18
+ "<extra_id_24>": 36075,
19
+ "<extra_id_25>": 36074,
20
+ "<extra_id_26>": 36073,
21
+ "<extra_id_27>": 36072,
22
+ "<extra_id_28>": 36071,
23
+ "<extra_id_29>": 36070,
24
+ "<extra_id_2>": 36097,
25
+ "<extra_id_30>": 36069,
26
+ "<extra_id_31>": 36068,
27
+ "<extra_id_32>": 36067,
28
+ "<extra_id_33>": 36066,
29
+ "<extra_id_34>": 36065,
30
+ "<extra_id_35>": 36064,
31
+ "<extra_id_36>": 36063,
32
+ "<extra_id_37>": 36062,
33
+ "<extra_id_38>": 36061,
34
+ "<extra_id_39>": 36060,
35
+ "<extra_id_3>": 36096,
36
+ "<extra_id_40>": 36059,
37
+ "<extra_id_41>": 36058,
38
+ "<extra_id_42>": 36057,
39
+ "<extra_id_43>": 36056,
40
+ "<extra_id_44>": 36055,
41
+ "<extra_id_45>": 36054,
42
+ "<extra_id_46>": 36053,
43
+ "<extra_id_47>": 36052,
44
+ "<extra_id_48>": 36051,
45
+ "<extra_id_49>": 36050,
46
+ "<extra_id_4>": 36095,
47
+ "<extra_id_50>": 36049,
48
+ "<extra_id_51>": 36048,
49
+ "<extra_id_52>": 36047,
50
+ "<extra_id_53>": 36046,
51
+ "<extra_id_54>": 36045,
52
+ "<extra_id_55>": 36044,
53
+ "<extra_id_56>": 36043,
54
+ "<extra_id_57>": 36042,
55
+ "<extra_id_58>": 36041,
56
+ "<extra_id_59>": 36040,
57
+ "<extra_id_5>": 36094,
58
+ "<extra_id_60>": 36039,
59
+ "<extra_id_61>": 36038,
60
+ "<extra_id_62>": 36037,
61
+ "<extra_id_63>": 36036,
62
+ "<extra_id_64>": 36035,
63
+ "<extra_id_65>": 36034,
64
+ "<extra_id_66>": 36033,
65
+ "<extra_id_67>": 36032,
66
+ "<extra_id_68>": 36031,
67
+ "<extra_id_69>": 36030,
68
+ "<extra_id_6>": 36093,
69
+ "<extra_id_70>": 36029,
70
+ "<extra_id_71>": 36028,
71
+ "<extra_id_72>": 36027,
72
+ "<extra_id_73>": 36026,
73
+ "<extra_id_74>": 36025,
74
+ "<extra_id_75>": 36024,
75
+ "<extra_id_76>": 36023,
76
+ "<extra_id_77>": 36022,
77
+ "<extra_id_78>": 36021,
78
+ "<extra_id_79>": 36020,
79
+ "<extra_id_7>": 36092,
80
+ "<extra_id_80>": 36019,
81
+ "<extra_id_81>": 36018,
82
+ "<extra_id_82>": 36017,
83
+ "<extra_id_83>": 36016,
84
+ "<extra_id_84>": 36015,
85
+ "<extra_id_85>": 36014,
86
+ "<extra_id_86>": 36013,
87
+ "<extra_id_87>": 36012,
88
+ "<extra_id_88>": 36011,
89
+ "<extra_id_89>": 36010,
90
+ "<extra_id_8>": 36091,
91
+ "<extra_id_90>": 36009,
92
+ "<extra_id_91>": 36008,
93
+ "<extra_id_92>": 36007,
94
+ "<extra_id_93>": 36006,
95
+ "<extra_id_94>": 36005,
96
+ "<extra_id_95>": 36004,
97
+ "<extra_id_96>": 36003,
98
+ "<extra_id_97>": 36002,
99
+ "<extra_id_98>": 36001,
100
+ "<extra_id_99>": 36000,
101
+ "<extra_id_9>": 36090
102
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "num_decoder_layers": 24,
20
+ "num_heads": 16,
21
+ "num_layers": 24,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "task_specific_params": {
27
+ "summarization": {
28
+ "early_stopping": true,
29
+ "length_penalty": 2.0,
30
+ "max_length": 256,
31
+ "no_repeat_ngram_size": 3,
32
+ "num_beams": 4,
33
+ "prefix": "summarization: "
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.51.3",
39
+ "use_cache": true,
40
+ "vocab_size": 36096
41
+ }
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": "4.51.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60075e8ba6bb41ea77d1f033aa67d45b87967f0e798aef196694fe14a9d207d
3
+ size 3165174664
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c5a43579726adb9b7b0784bc7bed76becc75226e92e9ac2d4dca887beaf327
3
+ size 6330693741
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e61ab708427870acd94294823064ef783185e22a315721c9f098e946d8b906
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4c71827701888b1efe5ab82a58befc77a15d11ca79ae9595253c1702d57d87
3
+ size 1465
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
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
3
+ size 820370
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
+ "36000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "36001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "36002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "36003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "36004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "36005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "36006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "36007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "36008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "36009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "36010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "36011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "36012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "36013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "36014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "36015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "36016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "36017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "36018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "36019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "36020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "36021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "36022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "36023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "36024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "36025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "36026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "36027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "36028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "36029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "36030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "36031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "36032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "36033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "36034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "36035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "36036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "36037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "36038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "36039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "36040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "36041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "36042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "36043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "36044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "36045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "36046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "36047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "36048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "36049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "36050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "36051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "36052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "36053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "36054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "36055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "36056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "36057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "36058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "36059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "36060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "36061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "36062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "36063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "36064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "36065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "36066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "36067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "36068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "36069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "36070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "36071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "36072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "36073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "36074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "36075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "36076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "36077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "36078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "36079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "36080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "36081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "36082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "36083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "36084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "36085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "36086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "36087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "36088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "36089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "36090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "36091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "36092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "36093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "36094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "36095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "36096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "36097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "36098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "36099": {
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": 1000000000000000019884624838656,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
trainer_state.json ADDED
@@ -0,0 +1,556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.9874861980125138,
6
+ "eval_steps": 300,
7
+ "global_step": 5400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0368052999631947,
14
+ "grad_norm": 10.38057804107666,
15
+ "learning_rate": 4.981781376518219e-05,
16
+ "loss": 2.8223,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.0736105999263894,
21
+ "grad_norm": 22.28519630432129,
22
+ "learning_rate": 4.963378726536622e-05,
23
+ "loss": 2.2838,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.1104158998895841,
28
+ "grad_norm": 7.458190441131592,
29
+ "learning_rate": 4.944976076555024e-05,
30
+ "loss": 2.222,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.1104158998895841,
35
+ "eval_loss": 2.0901951789855957,
36
+ "eval_runtime": 662.284,
37
+ "eval_samples_per_second": 8.206,
38
+ "eval_steps_per_second": 1.027,
39
+ "step": 300
40
+ },
41
+ {
42
+ "epoch": 0.1472211998527788,
43
+ "grad_norm": 6.754058837890625,
44
+ "learning_rate": 4.926573426573427e-05,
45
+ "loss": 2.2149,
46
+ "step": 400
47
+ },
48
+ {
49
+ "epoch": 0.1840264998159735,
50
+ "grad_norm": 7.67477560043335,
51
+ "learning_rate": 4.9081707765918294e-05,
52
+ "loss": 2.1027,
53
+ "step": 500
54
+ },
55
+ {
56
+ "epoch": 0.2208317997791682,
57
+ "grad_norm": 7.060691833496094,
58
+ "learning_rate": 4.889768126610232e-05,
59
+ "loss": 2.0664,
60
+ "step": 600
61
+ },
62
+ {
63
+ "epoch": 0.2208317997791682,
64
+ "eval_loss": 2.0013794898986816,
65
+ "eval_runtime": 664.5154,
66
+ "eval_samples_per_second": 8.179,
67
+ "eval_steps_per_second": 1.023,
68
+ "step": 600
69
+ },
70
+ {
71
+ "epoch": 0.2576370997423629,
72
+ "grad_norm": 7.3001909255981445,
73
+ "learning_rate": 4.871365476628635e-05,
74
+ "loss": 2.0262,
75
+ "step": 700
76
+ },
77
+ {
78
+ "epoch": 0.2944423997055576,
79
+ "grad_norm": 6.993441581726074,
80
+ "learning_rate": 4.852962826647037e-05,
81
+ "loss": 2.0506,
82
+ "step": 800
83
+ },
84
+ {
85
+ "epoch": 0.3312476996687523,
86
+ "grad_norm": 6.8796796798706055,
87
+ "learning_rate": 4.83456017666544e-05,
88
+ "loss": 2.0443,
89
+ "step": 900
90
+ },
91
+ {
92
+ "epoch": 0.3312476996687523,
93
+ "eval_loss": 1.9335800409317017,
94
+ "eval_runtime": 663.2859,
95
+ "eval_samples_per_second": 8.194,
96
+ "eval_steps_per_second": 1.025,
97
+ "step": 900
98
+ },
99
+ {
100
+ "epoch": 0.368052999631947,
101
+ "grad_norm": 8.510578155517578,
102
+ "learning_rate": 4.8161575266838426e-05,
103
+ "loss": 2.0214,
104
+ "step": 1000
105
+ },
106
+ {
107
+ "epoch": 0.4048582995951417,
108
+ "grad_norm": 5.925055503845215,
109
+ "learning_rate": 4.797754876702245e-05,
110
+ "loss": 1.9283,
111
+ "step": 1100
112
+ },
113
+ {
114
+ "epoch": 0.4416635995583364,
115
+ "grad_norm": 7.067410469055176,
116
+ "learning_rate": 4.779352226720648e-05,
117
+ "loss": 1.9905,
118
+ "step": 1200
119
+ },
120
+ {
121
+ "epoch": 0.4416635995583364,
122
+ "eval_loss": 1.8977280855178833,
123
+ "eval_runtime": 663.3777,
124
+ "eval_samples_per_second": 8.193,
125
+ "eval_steps_per_second": 1.025,
126
+ "step": 1200
127
+ },
128
+ {
129
+ "epoch": 0.4784688995215311,
130
+ "grad_norm": 5.874550819396973,
131
+ "learning_rate": 4.7609495767390503e-05,
132
+ "loss": 1.9665,
133
+ "step": 1300
134
+ },
135
+ {
136
+ "epoch": 0.5152741994847257,
137
+ "grad_norm": 8.402749061584473,
138
+ "learning_rate": 4.7425469267574534e-05,
139
+ "loss": 1.9342,
140
+ "step": 1400
141
+ },
142
+ {
143
+ "epoch": 0.5520794994479205,
144
+ "grad_norm": 6.955828666687012,
145
+ "learning_rate": 4.724144276775856e-05,
146
+ "loss": 1.9158,
147
+ "step": 1500
148
+ },
149
+ {
150
+ "epoch": 0.5520794994479205,
151
+ "eval_loss": 1.877929925918579,
152
+ "eval_runtime": 661.5674,
153
+ "eval_samples_per_second": 8.215,
154
+ "eval_steps_per_second": 1.028,
155
+ "step": 1500
156
+ },
157
+ {
158
+ "epoch": 0.5888847994111152,
159
+ "grad_norm": 5.033380031585693,
160
+ "learning_rate": 4.705741626794258e-05,
161
+ "loss": 1.9417,
162
+ "step": 1600
163
+ },
164
+ {
165
+ "epoch": 0.6256900993743099,
166
+ "grad_norm": 6.041861534118652,
167
+ "learning_rate": 4.687338976812661e-05,
168
+ "loss": 1.9268,
169
+ "step": 1700
170
+ },
171
+ {
172
+ "epoch": 0.6624953993375046,
173
+ "grad_norm": 6.134337902069092,
174
+ "learning_rate": 4.6689363268310635e-05,
175
+ "loss": 1.9385,
176
+ "step": 1800
177
+ },
178
+ {
179
+ "epoch": 0.6624953993375046,
180
+ "eval_loss": 1.8483961820602417,
181
+ "eval_runtime": 661.8464,
182
+ "eval_samples_per_second": 8.212,
183
+ "eval_steps_per_second": 1.027,
184
+ "step": 1800
185
+ },
186
+ {
187
+ "epoch": 0.6993006993006993,
188
+ "grad_norm": 6.114970684051514,
189
+ "learning_rate": 4.6505336768494665e-05,
190
+ "loss": 1.9318,
191
+ "step": 1900
192
+ },
193
+ {
194
+ "epoch": 0.736105999263894,
195
+ "grad_norm": 5.7990312576293945,
196
+ "learning_rate": 4.632131026867869e-05,
197
+ "loss": 1.8713,
198
+ "step": 2000
199
+ },
200
+ {
201
+ "epoch": 0.7729112992270887,
202
+ "grad_norm": 6.675479412078857,
203
+ "learning_rate": 4.613728376886272e-05,
204
+ "loss": 1.8822,
205
+ "step": 2100
206
+ },
207
+ {
208
+ "epoch": 0.7729112992270887,
209
+ "eval_loss": 1.8329029083251953,
210
+ "eval_runtime": 664.1992,
211
+ "eval_samples_per_second": 8.183,
212
+ "eval_steps_per_second": 1.024,
213
+ "step": 2100
214
+ },
215
+ {
216
+ "epoch": 0.8097165991902834,
217
+ "grad_norm": 6.004710674285889,
218
+ "learning_rate": 4.595325726904674e-05,
219
+ "loss": 1.8906,
220
+ "step": 2200
221
+ },
222
+ {
223
+ "epoch": 0.8465218991534781,
224
+ "grad_norm": 6.8489460945129395,
225
+ "learning_rate": 4.576923076923077e-05,
226
+ "loss": 1.8894,
227
+ "step": 2300
228
+ },
229
+ {
230
+ "epoch": 0.8833271991166728,
231
+ "grad_norm": 5.640189170837402,
232
+ "learning_rate": 4.55852042694148e-05,
233
+ "loss": 1.8616,
234
+ "step": 2400
235
+ },
236
+ {
237
+ "epoch": 0.8833271991166728,
238
+ "eval_loss": 1.8137404918670654,
239
+ "eval_runtime": 664.8043,
240
+ "eval_samples_per_second": 8.175,
241
+ "eval_steps_per_second": 1.023,
242
+ "step": 2400
243
+ },
244
+ {
245
+ "epoch": 0.9201324990798675,
246
+ "grad_norm": 6.615390300750732,
247
+ "learning_rate": 4.540117776959883e-05,
248
+ "loss": 1.8822,
249
+ "step": 2500
250
+ },
251
+ {
252
+ "epoch": 0.9569377990430622,
253
+ "grad_norm": 5.047032356262207,
254
+ "learning_rate": 4.521715126978285e-05,
255
+ "loss": 1.9137,
256
+ "step": 2600
257
+ },
258
+ {
259
+ "epoch": 0.9937430990062569,
260
+ "grad_norm": 5.454547882080078,
261
+ "learning_rate": 4.503312476996688e-05,
262
+ "loss": 1.8511,
263
+ "step": 2700
264
+ },
265
+ {
266
+ "epoch": 0.9937430990062569,
267
+ "eval_loss": 1.8019059896469116,
268
+ "eval_runtime": 664.5344,
269
+ "eval_samples_per_second": 8.179,
270
+ "eval_steps_per_second": 1.023,
271
+ "step": 2700
272
+ },
273
+ {
274
+ "epoch": 1.0305483989694515,
275
+ "grad_norm": 6.134690284729004,
276
+ "learning_rate": 4.4849098270150904e-05,
277
+ "loss": 1.4587,
278
+ "step": 2800
279
+ },
280
+ {
281
+ "epoch": 1.0673536989326462,
282
+ "grad_norm": 7.562436103820801,
283
+ "learning_rate": 4.4665071770334935e-05,
284
+ "loss": 1.3743,
285
+ "step": 2900
286
+ },
287
+ {
288
+ "epoch": 1.104158998895841,
289
+ "grad_norm": 7.055426120758057,
290
+ "learning_rate": 4.448104527051896e-05,
291
+ "loss": 1.3846,
292
+ "step": 3000
293
+ },
294
+ {
295
+ "epoch": 1.104158998895841,
296
+ "eval_loss": 1.8608911037445068,
297
+ "eval_runtime": 664.9166,
298
+ "eval_samples_per_second": 8.174,
299
+ "eval_steps_per_second": 1.023,
300
+ "step": 3000
301
+ },
302
+ {
303
+ "epoch": 1.1409642988590356,
304
+ "grad_norm": 5.4267473220825195,
305
+ "learning_rate": 4.429701877070299e-05,
306
+ "loss": 1.4539,
307
+ "step": 3100
308
+ },
309
+ {
310
+ "epoch": 1.1777695988222303,
311
+ "grad_norm": 5.971231937408447,
312
+ "learning_rate": 4.411299227088701e-05,
313
+ "loss": 1.3916,
314
+ "step": 3200
315
+ },
316
+ {
317
+ "epoch": 1.214574898785425,
318
+ "grad_norm": 5.384959697723389,
319
+ "learning_rate": 4.3928965771071036e-05,
320
+ "loss": 1.345,
321
+ "step": 3300
322
+ },
323
+ {
324
+ "epoch": 1.214574898785425,
325
+ "eval_loss": 1.8579978942871094,
326
+ "eval_runtime": 666.0495,
327
+ "eval_samples_per_second": 8.16,
328
+ "eval_steps_per_second": 1.021,
329
+ "step": 3300
330
+ },
331
+ {
332
+ "epoch": 1.2513801987486197,
333
+ "grad_norm": 5.7637457847595215,
334
+ "learning_rate": 4.3744939271255066e-05,
335
+ "loss": 1.3364,
336
+ "step": 3400
337
+ },
338
+ {
339
+ "epoch": 1.2881854987118144,
340
+ "grad_norm": 6.541650295257568,
341
+ "learning_rate": 4.356091277143909e-05,
342
+ "loss": 1.3466,
343
+ "step": 3500
344
+ },
345
+ {
346
+ "epoch": 1.3249907986750091,
347
+ "grad_norm": 5.789462089538574,
348
+ "learning_rate": 4.337688627162312e-05,
349
+ "loss": 1.3263,
350
+ "step": 3600
351
+ },
352
+ {
353
+ "epoch": 1.3249907986750091,
354
+ "eval_loss": 1.8551760911941528,
355
+ "eval_runtime": 665.6557,
356
+ "eval_samples_per_second": 8.165,
357
+ "eval_steps_per_second": 1.022,
358
+ "step": 3600
359
+ },
360
+ {
361
+ "epoch": 1.3617960986382038,
362
+ "grad_norm": 5.502793788909912,
363
+ "learning_rate": 4.3192859771807144e-05,
364
+ "loss": 1.3387,
365
+ "step": 3700
366
+ },
367
+ {
368
+ "epoch": 1.3986013986013985,
369
+ "grad_norm": 5.878416061401367,
370
+ "learning_rate": 4.300883327199117e-05,
371
+ "loss": 1.2795,
372
+ "step": 3800
373
+ },
374
+ {
375
+ "epoch": 1.4354066985645932,
376
+ "grad_norm": 6.2468037605285645,
377
+ "learning_rate": 4.28248067721752e-05,
378
+ "loss": 1.2879,
379
+ "step": 3900
380
+ },
381
+ {
382
+ "epoch": 1.4354066985645932,
383
+ "eval_loss": 1.8737432956695557,
384
+ "eval_runtime": 665.8514,
385
+ "eval_samples_per_second": 8.162,
386
+ "eval_steps_per_second": 1.021,
387
+ "step": 3900
388
+ },
389
+ {
390
+ "epoch": 1.472211998527788,
391
+ "grad_norm": 5.311323165893555,
392
+ "learning_rate": 4.264078027235922e-05,
393
+ "loss": 1.309,
394
+ "step": 4000
395
+ },
396
+ {
397
+ "epoch": 1.5090172984909827,
398
+ "grad_norm": 6.0769758224487305,
399
+ "learning_rate": 4.245675377254325e-05,
400
+ "loss": 1.3078,
401
+ "step": 4100
402
+ },
403
+ {
404
+ "epoch": 1.5458225984541774,
405
+ "grad_norm": 5.616523742675781,
406
+ "learning_rate": 4.2272727272727275e-05,
407
+ "loss": 1.2599,
408
+ "step": 4200
409
+ },
410
+ {
411
+ "epoch": 1.5458225984541774,
412
+ "eval_loss": 1.8690847158432007,
413
+ "eval_runtime": 665.6475,
414
+ "eval_samples_per_second": 8.165,
415
+ "eval_steps_per_second": 1.022,
416
+ "step": 4200
417
+ },
418
+ {
419
+ "epoch": 1.582627898417372,
420
+ "grad_norm": 5.222440242767334,
421
+ "learning_rate": 4.20887007729113e-05,
422
+ "loss": 1.3208,
423
+ "step": 4300
424
+ },
425
+ {
426
+ "epoch": 1.6194331983805668,
427
+ "grad_norm": 6.666055679321289,
428
+ "learning_rate": 4.190467427309533e-05,
429
+ "loss": 1.2911,
430
+ "step": 4400
431
+ },
432
+ {
433
+ "epoch": 1.6562384983437615,
434
+ "grad_norm": 6.660887241363525,
435
+ "learning_rate": 4.172064777327935e-05,
436
+ "loss": 1.2618,
437
+ "step": 4500
438
+ },
439
+ {
440
+ "epoch": 1.6562384983437615,
441
+ "eval_loss": 1.874595046043396,
442
+ "eval_runtime": 665.9471,
443
+ "eval_samples_per_second": 8.161,
444
+ "eval_steps_per_second": 1.021,
445
+ "step": 4500
446
+ },
447
+ {
448
+ "epoch": 1.6930437983069562,
449
+ "grad_norm": 6.1277971267700195,
450
+ "learning_rate": 4.153662127346338e-05,
451
+ "loss": 1.299,
452
+ "step": 4600
453
+ },
454
+ {
455
+ "epoch": 1.7298490982701509,
456
+ "grad_norm": 6.3581862449646,
457
+ "learning_rate": 4.135259477364741e-05,
458
+ "loss": 1.2658,
459
+ "step": 4700
460
+ },
461
+ {
462
+ "epoch": 1.7666543982333456,
463
+ "grad_norm": 5.905203819274902,
464
+ "learning_rate": 4.116856827383143e-05,
465
+ "loss": 1.2784,
466
+ "step": 4800
467
+ },
468
+ {
469
+ "epoch": 1.7666543982333456,
470
+ "eval_loss": 1.8622459173202515,
471
+ "eval_runtime": 667.7769,
472
+ "eval_samples_per_second": 8.139,
473
+ "eval_steps_per_second": 1.018,
474
+ "step": 4800
475
+ },
476
+ {
477
+ "epoch": 1.8034596981965403,
478
+ "grad_norm": 5.387886047363281,
479
+ "learning_rate": 4.098454177401546e-05,
480
+ "loss": 1.2877,
481
+ "step": 4900
482
+ },
483
+ {
484
+ "epoch": 1.840264998159735,
485
+ "grad_norm": 5.666168212890625,
486
+ "learning_rate": 4.0800515274199484e-05,
487
+ "loss": 1.2821,
488
+ "step": 5000
489
+ },
490
+ {
491
+ "epoch": 1.8770702981229297,
492
+ "grad_norm": 4.707683086395264,
493
+ "learning_rate": 4.0616488774383514e-05,
494
+ "loss": 1.238,
495
+ "step": 5100
496
+ },
497
+ {
498
+ "epoch": 1.8770702981229297,
499
+ "eval_loss": 1.8723958730697632,
500
+ "eval_runtime": 665.7561,
501
+ "eval_samples_per_second": 8.164,
502
+ "eval_steps_per_second": 1.021,
503
+ "step": 5100
504
+ },
505
+ {
506
+ "epoch": 1.9138755980861244,
507
+ "grad_norm": 5.434847831726074,
508
+ "learning_rate": 4.043246227456754e-05,
509
+ "loss": 1.2613,
510
+ "step": 5200
511
+ },
512
+ {
513
+ "epoch": 1.950680898049319,
514
+ "grad_norm": 6.641855716705322,
515
+ "learning_rate": 4.024843577475156e-05,
516
+ "loss": 1.3182,
517
+ "step": 5300
518
+ },
519
+ {
520
+ "epoch": 1.9874861980125138,
521
+ "grad_norm": 6.376593112945557,
522
+ "learning_rate": 4.006440927493559e-05,
523
+ "loss": 1.2729,
524
+ "step": 5400
525
+ },
526
+ {
527
+ "epoch": 1.9874861980125138,
528
+ "eval_loss": 1.83621346950531,
529
+ "eval_runtime": 664.7946,
530
+ "eval_samples_per_second": 8.175,
531
+ "eval_steps_per_second": 1.023,
532
+ "step": 5400
533
+ }
534
+ ],
535
+ "logging_steps": 100,
536
+ "max_steps": 27170,
537
+ "num_input_tokens_seen": 0,
538
+ "num_train_epochs": 10,
539
+ "save_steps": 100,
540
+ "stateful_callbacks": {
541
+ "TrainerControl": {
542
+ "args": {
543
+ "should_epoch_stop": false,
544
+ "should_evaluate": false,
545
+ "should_log": false,
546
+ "should_save": true,
547
+ "should_training_stop": false
548
+ },
549
+ "attributes": {}
550
+ }
551
+ },
552
+ "total_flos": 1.501578129309696e+17,
553
+ "train_batch_size": 8,
554
+ "trial_name": null,
555
+ "trial_params": null
556
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a45af165c9b4b10ac29d54d577e579792b21aaaa713b168828df64c971d823
3
+ size 5649