mateiaassAI commited on
Commit
675bd10
1 Parent(s): 8ec4021

Upload 12 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 64099,
3
+ "<extra_id_10>": 64089,
4
+ "<extra_id_11>": 64088,
5
+ "<extra_id_12>": 64087,
6
+ "<extra_id_13>": 64086,
7
+ "<extra_id_14>": 64085,
8
+ "<extra_id_15>": 64084,
9
+ "<extra_id_16>": 64083,
10
+ "<extra_id_17>": 64082,
11
+ "<extra_id_18>": 64081,
12
+ "<extra_id_19>": 64080,
13
+ "<extra_id_1>": 64098,
14
+ "<extra_id_20>": 64079,
15
+ "<extra_id_21>": 64078,
16
+ "<extra_id_22>": 64077,
17
+ "<extra_id_23>": 64076,
18
+ "<extra_id_24>": 64075,
19
+ "<extra_id_25>": 64074,
20
+ "<extra_id_26>": 64073,
21
+ "<extra_id_27>": 64072,
22
+ "<extra_id_28>": 64071,
23
+ "<extra_id_29>": 64070,
24
+ "<extra_id_2>": 64097,
25
+ "<extra_id_30>": 64069,
26
+ "<extra_id_31>": 64068,
27
+ "<extra_id_32>": 64067,
28
+ "<extra_id_33>": 64066,
29
+ "<extra_id_34>": 64065,
30
+ "<extra_id_35>": 64064,
31
+ "<extra_id_36>": 64063,
32
+ "<extra_id_37>": 64062,
33
+ "<extra_id_38>": 64061,
34
+ "<extra_id_39>": 64060,
35
+ "<extra_id_3>": 64096,
36
+ "<extra_id_40>": 64059,
37
+ "<extra_id_41>": 64058,
38
+ "<extra_id_42>": 64057,
39
+ "<extra_id_43>": 64056,
40
+ "<extra_id_44>": 64055,
41
+ "<extra_id_45>": 64054,
42
+ "<extra_id_46>": 64053,
43
+ "<extra_id_47>": 64052,
44
+ "<extra_id_48>": 64051,
45
+ "<extra_id_49>": 64050,
46
+ "<extra_id_4>": 64095,
47
+ "<extra_id_50>": 64049,
48
+ "<extra_id_51>": 64048,
49
+ "<extra_id_52>": 64047,
50
+ "<extra_id_53>": 64046,
51
+ "<extra_id_54>": 64045,
52
+ "<extra_id_55>": 64044,
53
+ "<extra_id_56>": 64043,
54
+ "<extra_id_57>": 64042,
55
+ "<extra_id_58>": 64041,
56
+ "<extra_id_59>": 64040,
57
+ "<extra_id_5>": 64094,
58
+ "<extra_id_60>": 64039,
59
+ "<extra_id_61>": 64038,
60
+ "<extra_id_62>": 64037,
61
+ "<extra_id_63>": 64036,
62
+ "<extra_id_64>": 64035,
63
+ "<extra_id_65>": 64034,
64
+ "<extra_id_66>": 64033,
65
+ "<extra_id_67>": 64032,
66
+ "<extra_id_68>": 64031,
67
+ "<extra_id_69>": 64030,
68
+ "<extra_id_6>": 64093,
69
+ "<extra_id_70>": 64029,
70
+ "<extra_id_71>": 64028,
71
+ "<extra_id_72>": 64027,
72
+ "<extra_id_73>": 64026,
73
+ "<extra_id_74>": 64025,
74
+ "<extra_id_75>": 64024,
75
+ "<extra_id_76>": 64023,
76
+ "<extra_id_77>": 64022,
77
+ "<extra_id_78>": 64021,
78
+ "<extra_id_79>": 64020,
79
+ "<extra_id_7>": 64092,
80
+ "<extra_id_80>": 64019,
81
+ "<extra_id_81>": 64018,
82
+ "<extra_id_82>": 64017,
83
+ "<extra_id_83>": 64016,
84
+ "<extra_id_84>": 64015,
85
+ "<extra_id_85>": 64014,
86
+ "<extra_id_86>": 64013,
87
+ "<extra_id_87>": 64012,
88
+ "<extra_id_88>": 64011,
89
+ "<extra_id_89>": 64010,
90
+ "<extra_id_8>": 64091,
91
+ "<extra_id_90>": 64009,
92
+ "<extra_id_91>": 64008,
93
+ "<extra_id_92>": 64007,
94
+ "<extra_id_93>": 64006,
95
+ "<extra_id_94>": 64005,
96
+ "<extra_id_95>": 64004,
97
+ "<extra_id_96>": 64003,
98
+ "<extra_id_97>": 64002,
99
+ "<extra_id_98>": 64001,
100
+ "<extra_id_99>": 64000,
101
+ "<extra_id_9>": 64090,
102
+ "<pad>": 64100
103
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mateiaassAI/MEID1000",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.3",
31
+ "use_cache": true,
32
+ "vocab_size": 64101
33
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "max_new_tokens": 256,
6
+ "min_new_tokens": 0,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.39.3"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47710bdf71eaa424c5d49680faf34823e4688dad83b0f7989290d676eb6628ac
3
+ size 1186787176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e69722b6723c2ab3f63b022dc6fc867a8bbc27de1768a68e23298de008041c
3
+ size 2373744634
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c036f1c0183847f6a8e33f459efacd537e7d9db6f4cae3e1aefe98cee8a6892
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6376c4334bb290adc62d94be7742465bcff904e545c6115bee335ddb377fea
3
+ size 1064
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:e8b0c94f9d6e9e75161a1365e73132f35666ab675de0d5ae10ec9f6f5eacda09
3
+ size 1457188
tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "2": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "64000": {
21
+ "content": "<extra_id_99>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "64001": {
29
+ "content": "<extra_id_98>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "64002": {
37
+ "content": "<extra_id_97>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "64003": {
45
+ "content": "<extra_id_96>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "64004": {
53
+ "content": "<extra_id_95>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "64005": {
61
+ "content": "<extra_id_94>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "64006": {
69
+ "content": "<extra_id_93>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "64007": {
77
+ "content": "<extra_id_92>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "64008": {
85
+ "content": "<extra_id_91>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "64009": {
93
+ "content": "<extra_id_90>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "64010": {
101
+ "content": "<extra_id_89>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "64011": {
109
+ "content": "<extra_id_88>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "64012": {
117
+ "content": "<extra_id_87>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "64013": {
125
+ "content": "<extra_id_86>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "64014": {
133
+ "content": "<extra_id_85>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "64015": {
141
+ "content": "<extra_id_84>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "64016": {
149
+ "content": "<extra_id_83>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "64017": {
157
+ "content": "<extra_id_82>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "64018": {
165
+ "content": "<extra_id_81>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "64019": {
173
+ "content": "<extra_id_80>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "64020": {
181
+ "content": "<extra_id_79>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "64021": {
189
+ "content": "<extra_id_78>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "64022": {
197
+ "content": "<extra_id_77>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "64023": {
205
+ "content": "<extra_id_76>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "64024": {
213
+ "content": "<extra_id_75>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "64025": {
221
+ "content": "<extra_id_74>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "64026": {
229
+ "content": "<extra_id_73>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "64027": {
237
+ "content": "<extra_id_72>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "64028": {
245
+ "content": "<extra_id_71>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "64029": {
253
+ "content": "<extra_id_70>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "64030": {
261
+ "content": "<extra_id_69>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "64031": {
269
+ "content": "<extra_id_68>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "64032": {
277
+ "content": "<extra_id_67>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "64033": {
285
+ "content": "<extra_id_66>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "64034": {
293
+ "content": "<extra_id_65>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "64035": {
301
+ "content": "<extra_id_64>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "64036": {
309
+ "content": "<extra_id_63>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "64037": {
317
+ "content": "<extra_id_62>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "64038": {
325
+ "content": "<extra_id_61>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "64039": {
333
+ "content": "<extra_id_60>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "64040": {
341
+ "content": "<extra_id_59>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "64041": {
349
+ "content": "<extra_id_58>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "64042": {
357
+ "content": "<extra_id_57>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "64043": {
365
+ "content": "<extra_id_56>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "64044": {
373
+ "content": "<extra_id_55>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "64045": {
381
+ "content": "<extra_id_54>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "64046": {
389
+ "content": "<extra_id_53>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "64047": {
397
+ "content": "<extra_id_52>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "64048": {
405
+ "content": "<extra_id_51>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "64049": {
413
+ "content": "<extra_id_50>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "64050": {
421
+ "content": "<extra_id_49>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "64051": {
429
+ "content": "<extra_id_48>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "64052": {
437
+ "content": "<extra_id_47>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "64053": {
445
+ "content": "<extra_id_46>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "64054": {
453
+ "content": "<extra_id_45>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "64055": {
461
+ "content": "<extra_id_44>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "64056": {
469
+ "content": "<extra_id_43>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "64057": {
477
+ "content": "<extra_id_42>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "64058": {
485
+ "content": "<extra_id_41>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "64059": {
493
+ "content": "<extra_id_40>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "64060": {
501
+ "content": "<extra_id_39>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "64061": {
509
+ "content": "<extra_id_38>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "64062": {
517
+ "content": "<extra_id_37>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "64063": {
525
+ "content": "<extra_id_36>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "64064": {
533
+ "content": "<extra_id_35>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "64065": {
541
+ "content": "<extra_id_34>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "64066": {
549
+ "content": "<extra_id_33>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "64067": {
557
+ "content": "<extra_id_32>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "64068": {
565
+ "content": "<extra_id_31>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "64069": {
573
+ "content": "<extra_id_30>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "64070": {
581
+ "content": "<extra_id_29>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "64071": {
589
+ "content": "<extra_id_28>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "64072": {
597
+ "content": "<extra_id_27>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "64073": {
605
+ "content": "<extra_id_26>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "64074": {
613
+ "content": "<extra_id_25>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "64075": {
621
+ "content": "<extra_id_24>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "64076": {
629
+ "content": "<extra_id_23>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "64077": {
637
+ "content": "<extra_id_22>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "64078": {
645
+ "content": "<extra_id_21>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "64079": {
653
+ "content": "<extra_id_20>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "64080": {
661
+ "content": "<extra_id_19>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "64081": {
669
+ "content": "<extra_id_18>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "64082": {
677
+ "content": "<extra_id_17>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "64083": {
685
+ "content": "<extra_id_16>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "64084": {
693
+ "content": "<extra_id_15>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "64085": {
701
+ "content": "<extra_id_14>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "64086": {
709
+ "content": "<extra_id_13>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "64087": {
717
+ "content": "<extra_id_12>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "64088": {
725
+ "content": "<extra_id_11>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "64089": {
733
+ "content": "<extra_id_10>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "64090": {
741
+ "content": "<extra_id_9>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "64091": {
749
+ "content": "<extra_id_8>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "64092": {
757
+ "content": "<extra_id_7>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "64093": {
765
+ "content": "<extra_id_6>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "64094": {
773
+ "content": "<extra_id_5>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "64095": {
781
+ "content": "<extra_id_4>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "64096": {
789
+ "content": "<extra_id_3>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "64097": {
797
+ "content": "<extra_id_2>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "64098": {
805
+ "content": "<extra_id_1>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "64099": {
813
+ "content": "<extra_id_0>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "64100": {
821
+ "content": "<pad>",
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": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 1000000000000000019884624838656,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
trainer_state.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 16.46840148698885,
5
+ "eval_steps": 500,
6
+ "global_step": 8860,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "grad_norm": 1.3550214767456055,
14
+ "learning_rate": 2.8605947955390337e-05,
15
+ "loss": 0.6834,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.93,
20
+ "eval_loss": 0.5703962445259094,
21
+ "eval_runtime": 6.1216,
22
+ "eval_samples_per_second": 248.138,
23
+ "eval_steps_per_second": 15.519,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 1.86,
28
+ "grad_norm": 0.7966482043266296,
29
+ "learning_rate": 2.721189591078067e-05,
30
+ "loss": 0.5019,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 1.86,
35
+ "eval_loss": 0.5145730972290039,
36
+ "eval_runtime": 6.1234,
37
+ "eval_samples_per_second": 248.066,
38
+ "eval_steps_per_second": 15.514,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 2.79,
43
+ "grad_norm": 0.9648380875587463,
44
+ "learning_rate": 2.5817843866171006e-05,
45
+ "loss": 0.4522,
46
+ "step": 1500
47
+ },
48
+ {
49
+ "epoch": 2.79,
50
+ "eval_loss": 0.48453015089035034,
51
+ "eval_runtime": 6.0895,
52
+ "eval_samples_per_second": 249.446,
53
+ "eval_steps_per_second": 15.601,
54
+ "step": 1500
55
+ },
56
+ {
57
+ "epoch": 3.72,
58
+ "grad_norm": 0.7465741038322449,
59
+ "learning_rate": 2.442379182156134e-05,
60
+ "loss": 0.4105,
61
+ "step": 2000
62
+ },
63
+ {
64
+ "epoch": 3.72,
65
+ "eval_loss": 0.4673249125480652,
66
+ "eval_runtime": 6.11,
67
+ "eval_samples_per_second": 248.609,
68
+ "eval_steps_per_second": 15.548,
69
+ "step": 2000
70
+ },
71
+ {
72
+ "epoch": 4.65,
73
+ "grad_norm": 0.8333841562271118,
74
+ "learning_rate": 2.302973977695167e-05,
75
+ "loss": 0.3705,
76
+ "step": 2500
77
+ },
78
+ {
79
+ "epoch": 4.65,
80
+ "eval_loss": 0.4610813856124878,
81
+ "eval_runtime": 6.0863,
82
+ "eval_samples_per_second": 249.578,
83
+ "eval_steps_per_second": 15.609,
84
+ "step": 2500
85
+ },
86
+ {
87
+ "epoch": 5.58,
88
+ "grad_norm": 0.8087735176086426,
89
+ "learning_rate": 2.1635687732342008e-05,
90
+ "loss": 0.3484,
91
+ "step": 3000
92
+ },
93
+ {
94
+ "epoch": 5.58,
95
+ "eval_loss": 0.44604435563087463,
96
+ "eval_runtime": 6.1053,
97
+ "eval_samples_per_second": 248.8,
98
+ "eval_steps_per_second": 15.56,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 6.51,
103
+ "grad_norm": 0.8467231392860413,
104
+ "learning_rate": 2.0241635687732344e-05,
105
+ "loss": 0.33,
106
+ "step": 3500
107
+ },
108
+ {
109
+ "epoch": 6.51,
110
+ "eval_loss": 0.4419492185115814,
111
+ "eval_runtime": 6.1029,
112
+ "eval_samples_per_second": 248.896,
113
+ "eval_steps_per_second": 15.566,
114
+ "step": 3500
115
+ },
116
+ {
117
+ "epoch": 7.43,
118
+ "grad_norm": 0.9491092562675476,
119
+ "learning_rate": 1.8847583643122676e-05,
120
+ "loss": 0.3068,
121
+ "step": 4000
122
+ },
123
+ {
124
+ "epoch": 7.43,
125
+ "eval_loss": 0.4374473989009857,
126
+ "eval_runtime": 6.0863,
127
+ "eval_samples_per_second": 249.578,
128
+ "eval_steps_per_second": 15.609,
129
+ "step": 4000
130
+ },
131
+ {
132
+ "epoch": 8.36,
133
+ "grad_norm": 0.5728708505630493,
134
+ "learning_rate": 1.7453531598513013e-05,
135
+ "loss": 0.2877,
136
+ "step": 4500
137
+ },
138
+ {
139
+ "epoch": 8.36,
140
+ "eval_loss": 0.4360838234424591,
141
+ "eval_runtime": 6.109,
142
+ "eval_samples_per_second": 248.648,
143
+ "eval_steps_per_second": 15.551,
144
+ "step": 4500
145
+ },
146
+ {
147
+ "epoch": 9.29,
148
+ "grad_norm": 0.9121451377868652,
149
+ "learning_rate": 1.6059479553903345e-05,
150
+ "loss": 0.2774,
151
+ "step": 5000
152
+ },
153
+ {
154
+ "epoch": 9.29,
155
+ "eval_loss": 0.4340021312236786,
156
+ "eval_runtime": 6.1145,
157
+ "eval_samples_per_second": 248.424,
158
+ "eval_steps_per_second": 15.537,
159
+ "step": 5000
160
+ },
161
+ {
162
+ "epoch": 10.22,
163
+ "grad_norm": 0.6917915344238281,
164
+ "learning_rate": 1.4665427509293682e-05,
165
+ "loss": 0.2643,
166
+ "step": 5500
167
+ },
168
+ {
169
+ "epoch": 10.22,
170
+ "eval_loss": 0.4294339716434479,
171
+ "eval_runtime": 6.1237,
172
+ "eval_samples_per_second": 248.054,
173
+ "eval_steps_per_second": 15.514,
174
+ "step": 5500
175
+ },
176
+ {
177
+ "epoch": 11.15,
178
+ "grad_norm": 0.5932989120483398,
179
+ "learning_rate": 1.3271375464684014e-05,
180
+ "loss": 0.2521,
181
+ "step": 6000
182
+ },
183
+ {
184
+ "epoch": 11.15,
185
+ "eval_loss": 0.429922491312027,
186
+ "eval_runtime": 6.1392,
187
+ "eval_samples_per_second": 247.428,
188
+ "eval_steps_per_second": 15.474,
189
+ "step": 6000
190
+ },
191
+ {
192
+ "epoch": 12.08,
193
+ "grad_norm": 0.6674472689628601,
194
+ "learning_rate": 1.187732342007435e-05,
195
+ "loss": 0.2445,
196
+ "step": 6500
197
+ },
198
+ {
199
+ "epoch": 12.08,
200
+ "eval_loss": 0.43110528588294983,
201
+ "eval_runtime": 6.2182,
202
+ "eval_samples_per_second": 244.285,
203
+ "eval_steps_per_second": 15.278,
204
+ "step": 6500
205
+ },
206
+ {
207
+ "epoch": 13.01,
208
+ "grad_norm": 0.8294160962104797,
209
+ "learning_rate": 1.0483271375464685e-05,
210
+ "loss": 0.2343,
211
+ "step": 7000
212
+ },
213
+ {
214
+ "epoch": 13.01,
215
+ "eval_loss": 0.42911913990974426,
216
+ "eval_runtime": 6.1036,
217
+ "eval_samples_per_second": 248.87,
218
+ "eval_steps_per_second": 15.565,
219
+ "step": 7000
220
+ },
221
+ {
222
+ "epoch": 13.94,
223
+ "grad_norm": 0.9937490224838257,
224
+ "learning_rate": 9.089219330855018e-06,
225
+ "loss": 0.227,
226
+ "step": 7500
227
+ },
228
+ {
229
+ "epoch": 13.94,
230
+ "eval_loss": 0.4279896914958954,
231
+ "eval_runtime": 6.1085,
232
+ "eval_samples_per_second": 248.671,
233
+ "eval_steps_per_second": 15.552,
234
+ "step": 7500
235
+ },
236
+ {
237
+ "epoch": 14.87,
238
+ "grad_norm": 0.7265322804450989,
239
+ "learning_rate": 7.695167286245354e-06,
240
+ "loss": 0.2231,
241
+ "step": 8000
242
+ },
243
+ {
244
+ "epoch": 14.87,
245
+ "eval_loss": 0.4289594292640686,
246
+ "eval_runtime": 6.1309,
247
+ "eval_samples_per_second": 247.763,
248
+ "eval_steps_per_second": 15.495,
249
+ "step": 8000
250
+ },
251
+ {
252
+ "epoch": 15.8,
253
+ "grad_norm": 2.6667771339416504,
254
+ "learning_rate": 6.301115241635688e-06,
255
+ "loss": 0.2154,
256
+ "step": 8500
257
+ },
258
+ {
259
+ "epoch": 15.8,
260
+ "eval_loss": 0.4316449761390686,
261
+ "eval_runtime": 6.1029,
262
+ "eval_samples_per_second": 248.899,
263
+ "eval_steps_per_second": 15.566,
264
+ "step": 8500
265
+ }
266
+ ],
267
+ "logging_steps": 500,
268
+ "max_steps": 10760,
269
+ "num_input_tokens_seen": 0,
270
+ "num_train_epochs": 20,
271
+ "save_steps": 4430,
272
+ "total_flos": 1.0656359168606208e+16,
273
+ "train_batch_size": 16,
274
+ "trial_name": null,
275
+ "trial_params": null
276
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cd6cdc42e9952193670c60165a54da61ea8891469e2f736b9e47c25ffa4700
3
+ size 5048