Sabbir772 commited on
Commit
e605e4d
·
verified ·
1 Parent(s): 7128a42

Upload checkpoint folder via API

Browse files
checkpoint-3170/added_tokens.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<BH>": 32101,
3
+ "<BN>": 32100,
4
+ "<extra_id_0>": 32099,
5
+ "<extra_id_10>": 32089,
6
+ "<extra_id_11>": 32088,
7
+ "<extra_id_12>": 32087,
8
+ "<extra_id_13>": 32086,
9
+ "<extra_id_14>": 32085,
10
+ "<extra_id_15>": 32084,
11
+ "<extra_id_16>": 32083,
12
+ "<extra_id_17>": 32082,
13
+ "<extra_id_18>": 32081,
14
+ "<extra_id_19>": 32080,
15
+ "<extra_id_1>": 32098,
16
+ "<extra_id_20>": 32079,
17
+ "<extra_id_21>": 32078,
18
+ "<extra_id_22>": 32077,
19
+ "<extra_id_23>": 32076,
20
+ "<extra_id_24>": 32075,
21
+ "<extra_id_25>": 32074,
22
+ "<extra_id_26>": 32073,
23
+ "<extra_id_27>": 32072,
24
+ "<extra_id_28>": 32071,
25
+ "<extra_id_29>": 32070,
26
+ "<extra_id_2>": 32097,
27
+ "<extra_id_30>": 32069,
28
+ "<extra_id_31>": 32068,
29
+ "<extra_id_32>": 32067,
30
+ "<extra_id_33>": 32066,
31
+ "<extra_id_34>": 32065,
32
+ "<extra_id_35>": 32064,
33
+ "<extra_id_36>": 32063,
34
+ "<extra_id_37>": 32062,
35
+ "<extra_id_38>": 32061,
36
+ "<extra_id_39>": 32060,
37
+ "<extra_id_3>": 32096,
38
+ "<extra_id_40>": 32059,
39
+ "<extra_id_41>": 32058,
40
+ "<extra_id_42>": 32057,
41
+ "<extra_id_43>": 32056,
42
+ "<extra_id_44>": 32055,
43
+ "<extra_id_45>": 32054,
44
+ "<extra_id_46>": 32053,
45
+ "<extra_id_47>": 32052,
46
+ "<extra_id_48>": 32051,
47
+ "<extra_id_49>": 32050,
48
+ "<extra_id_4>": 32095,
49
+ "<extra_id_50>": 32049,
50
+ "<extra_id_51>": 32048,
51
+ "<extra_id_52>": 32047,
52
+ "<extra_id_53>": 32046,
53
+ "<extra_id_54>": 32045,
54
+ "<extra_id_55>": 32044,
55
+ "<extra_id_56>": 32043,
56
+ "<extra_id_57>": 32042,
57
+ "<extra_id_58>": 32041,
58
+ "<extra_id_59>": 32040,
59
+ "<extra_id_5>": 32094,
60
+ "<extra_id_60>": 32039,
61
+ "<extra_id_61>": 32038,
62
+ "<extra_id_62>": 32037,
63
+ "<extra_id_63>": 32036,
64
+ "<extra_id_64>": 32035,
65
+ "<extra_id_65>": 32034,
66
+ "<extra_id_66>": 32033,
67
+ "<extra_id_67>": 32032,
68
+ "<extra_id_68>": 32031,
69
+ "<extra_id_69>": 32030,
70
+ "<extra_id_6>": 32093,
71
+ "<extra_id_70>": 32029,
72
+ "<extra_id_71>": 32028,
73
+ "<extra_id_72>": 32027,
74
+ "<extra_id_73>": 32026,
75
+ "<extra_id_74>": 32025,
76
+ "<extra_id_75>": 32024,
77
+ "<extra_id_76>": 32023,
78
+ "<extra_id_77>": 32022,
79
+ "<extra_id_78>": 32021,
80
+ "<extra_id_79>": 32020,
81
+ "<extra_id_7>": 32092,
82
+ "<extra_id_80>": 32019,
83
+ "<extra_id_81>": 32018,
84
+ "<extra_id_82>": 32017,
85
+ "<extra_id_83>": 32016,
86
+ "<extra_id_84>": 32015,
87
+ "<extra_id_85>": 32014,
88
+ "<extra_id_86>": 32013,
89
+ "<extra_id_87>": 32012,
90
+ "<extra_id_88>": 32011,
91
+ "<extra_id_89>": 32010,
92
+ "<extra_id_8>": 32091,
93
+ "<extra_id_90>": 32009,
94
+ "<extra_id_91>": 32008,
95
+ "<extra_id_92>": 32007,
96
+ "<extra_id_93>": 32006,
97
+ "<extra_id_94>": 32005,
98
+ "<extra_id_95>": 32004,
99
+ "<extra_id_96>": 32003,
100
+ "<extra_id_97>": 32002,
101
+ "<extra_id_98>": 32001,
102
+ "<extra_id_99>": 32000,
103
+ "<extra_id_9>": 32090
104
+ }
checkpoint-3170/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": false,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "4.57.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32102
32
+ }
checkpoint-3170/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": [
4
+ 1
5
+ ],
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.57.1"
8
+ }
checkpoint-3170/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c84f1b0acf51f7659903a7414017188e0fe1ad64cdc301c04e20b6a500d86c2
3
+ size 990185320
checkpoint-3170/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff23dde3babd7e5c28558ad25a796dae0e8ab2c2ee1b93c031870bd6deddf2d
3
+ size 1980545291
checkpoint-3170/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05ce86810370338cd7c7c89a6c4f1b11bf40abaa2cad3a3c5e8ae60c235d8e3
3
+ size 14645
checkpoint-3170/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcc096e266d3559cbd90c02675e1b549c4594a071ac40ca54e898b8f676c24c
3
+ size 1465
checkpoint-3170/special_tokens_map.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<BN>",
4
+ "<BH>",
5
+ "<extra_id_0>",
6
+ "<extra_id_1>",
7
+ "<extra_id_2>",
8
+ "<extra_id_3>",
9
+ "<extra_id_4>",
10
+ "<extra_id_5>",
11
+ "<extra_id_6>",
12
+ "<extra_id_7>",
13
+ "<extra_id_8>",
14
+ "<extra_id_9>",
15
+ "<extra_id_10>",
16
+ "<extra_id_11>",
17
+ "<extra_id_12>",
18
+ "<extra_id_13>",
19
+ "<extra_id_14>",
20
+ "<extra_id_15>",
21
+ "<extra_id_16>",
22
+ "<extra_id_17>",
23
+ "<extra_id_18>",
24
+ "<extra_id_19>",
25
+ "<extra_id_20>",
26
+ "<extra_id_21>",
27
+ "<extra_id_22>",
28
+ "<extra_id_23>",
29
+ "<extra_id_24>",
30
+ "<extra_id_25>",
31
+ "<extra_id_26>",
32
+ "<extra_id_27>",
33
+ "<extra_id_28>",
34
+ "<extra_id_29>",
35
+ "<extra_id_30>",
36
+ "<extra_id_31>",
37
+ "<extra_id_32>",
38
+ "<extra_id_33>",
39
+ "<extra_id_34>",
40
+ "<extra_id_35>",
41
+ "<extra_id_36>",
42
+ "<extra_id_37>",
43
+ "<extra_id_38>",
44
+ "<extra_id_39>",
45
+ "<extra_id_40>",
46
+ "<extra_id_41>",
47
+ "<extra_id_42>",
48
+ "<extra_id_43>",
49
+ "<extra_id_44>",
50
+ "<extra_id_45>",
51
+ "<extra_id_46>",
52
+ "<extra_id_47>",
53
+ "<extra_id_48>",
54
+ "<extra_id_49>",
55
+ "<extra_id_50>",
56
+ "<extra_id_51>",
57
+ "<extra_id_52>",
58
+ "<extra_id_53>",
59
+ "<extra_id_54>",
60
+ "<extra_id_55>",
61
+ "<extra_id_56>",
62
+ "<extra_id_57>",
63
+ "<extra_id_58>",
64
+ "<extra_id_59>",
65
+ "<extra_id_60>",
66
+ "<extra_id_61>",
67
+ "<extra_id_62>",
68
+ "<extra_id_63>",
69
+ "<extra_id_64>",
70
+ "<extra_id_65>",
71
+ "<extra_id_66>",
72
+ "<extra_id_67>",
73
+ "<extra_id_68>",
74
+ "<extra_id_69>",
75
+ "<extra_id_70>",
76
+ "<extra_id_71>",
77
+ "<extra_id_72>",
78
+ "<extra_id_73>",
79
+ "<extra_id_74>",
80
+ "<extra_id_75>",
81
+ "<extra_id_76>",
82
+ "<extra_id_77>",
83
+ "<extra_id_78>",
84
+ "<extra_id_79>",
85
+ "<extra_id_80>",
86
+ "<extra_id_81>",
87
+ "<extra_id_82>",
88
+ "<extra_id_83>",
89
+ "<extra_id_84>",
90
+ "<extra_id_85>",
91
+ "<extra_id_86>",
92
+ "<extra_id_87>",
93
+ "<extra_id_88>",
94
+ "<extra_id_89>",
95
+ "<extra_id_90>",
96
+ "<extra_id_91>",
97
+ "<extra_id_92>",
98
+ "<extra_id_93>",
99
+ "<extra_id_94>",
100
+ "<extra_id_95>",
101
+ "<extra_id_96>",
102
+ "<extra_id_97>",
103
+ "<extra_id_98>",
104
+ "<extra_id_99>"
105
+ ],
106
+ "eos_token": {
107
+ "content": "</s>",
108
+ "lstrip": false,
109
+ "normalized": false,
110
+ "rstrip": false,
111
+ "single_word": false
112
+ },
113
+ "pad_token": {
114
+ "content": "<pad>",
115
+ "lstrip": false,
116
+ "normalized": false,
117
+ "rstrip": false,
118
+ "single_word": false
119
+ },
120
+ "unk_token": {
121
+ "content": "<unk>",
122
+ "lstrip": false,
123
+ "normalized": false,
124
+ "rstrip": false,
125
+ "single_word": false
126
+ }
127
+ }
checkpoint-3170/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
3
+ size 1111492
checkpoint-3170/tokenizer_config.json ADDED
@@ -0,0 +1,959 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32100": {
829
+ "content": "<BN>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32101": {
837
+ "content": "<BH>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<BN>",
847
+ "<BH>",
848
+ "<extra_id_0>",
849
+ "<extra_id_1>",
850
+ "<extra_id_2>",
851
+ "<extra_id_3>",
852
+ "<extra_id_4>",
853
+ "<extra_id_5>",
854
+ "<extra_id_6>",
855
+ "<extra_id_7>",
856
+ "<extra_id_8>",
857
+ "<extra_id_9>",
858
+ "<extra_id_10>",
859
+ "<extra_id_11>",
860
+ "<extra_id_12>",
861
+ "<extra_id_13>",
862
+ "<extra_id_14>",
863
+ "<extra_id_15>",
864
+ "<extra_id_16>",
865
+ "<extra_id_17>",
866
+ "<extra_id_18>",
867
+ "<extra_id_19>",
868
+ "<extra_id_20>",
869
+ "<extra_id_21>",
870
+ "<extra_id_22>",
871
+ "<extra_id_23>",
872
+ "<extra_id_24>",
873
+ "<extra_id_25>",
874
+ "<extra_id_26>",
875
+ "<extra_id_27>",
876
+ "<extra_id_28>",
877
+ "<extra_id_29>",
878
+ "<extra_id_30>",
879
+ "<extra_id_31>",
880
+ "<extra_id_32>",
881
+ "<extra_id_33>",
882
+ "<extra_id_34>",
883
+ "<extra_id_35>",
884
+ "<extra_id_36>",
885
+ "<extra_id_37>",
886
+ "<extra_id_38>",
887
+ "<extra_id_39>",
888
+ "<extra_id_40>",
889
+ "<extra_id_41>",
890
+ "<extra_id_42>",
891
+ "<extra_id_43>",
892
+ "<extra_id_44>",
893
+ "<extra_id_45>",
894
+ "<extra_id_46>",
895
+ "<extra_id_47>",
896
+ "<extra_id_48>",
897
+ "<extra_id_49>",
898
+ "<extra_id_50>",
899
+ "<extra_id_51>",
900
+ "<extra_id_52>",
901
+ "<extra_id_53>",
902
+ "<extra_id_54>",
903
+ "<extra_id_55>",
904
+ "<extra_id_56>",
905
+ "<extra_id_57>",
906
+ "<extra_id_58>",
907
+ "<extra_id_59>",
908
+ "<extra_id_60>",
909
+ "<extra_id_61>",
910
+ "<extra_id_62>",
911
+ "<extra_id_63>",
912
+ "<extra_id_64>",
913
+ "<extra_id_65>",
914
+ "<extra_id_66>",
915
+ "<extra_id_67>",
916
+ "<extra_id_68>",
917
+ "<extra_id_69>",
918
+ "<extra_id_70>",
919
+ "<extra_id_71>",
920
+ "<extra_id_72>",
921
+ "<extra_id_73>",
922
+ "<extra_id_74>",
923
+ "<extra_id_75>",
924
+ "<extra_id_76>",
925
+ "<extra_id_77>",
926
+ "<extra_id_78>",
927
+ "<extra_id_79>",
928
+ "<extra_id_80>",
929
+ "<extra_id_81>",
930
+ "<extra_id_82>",
931
+ "<extra_id_83>",
932
+ "<extra_id_84>",
933
+ "<extra_id_85>",
934
+ "<extra_id_86>",
935
+ "<extra_id_87>",
936
+ "<extra_id_88>",
937
+ "<extra_id_89>",
938
+ "<extra_id_90>",
939
+ "<extra_id_91>",
940
+ "<extra_id_92>",
941
+ "<extra_id_93>",
942
+ "<extra_id_94>",
943
+ "<extra_id_95>",
944
+ "<extra_id_96>",
945
+ "<extra_id_97>",
946
+ "<extra_id_98>",
947
+ "<extra_id_99>"
948
+ ],
949
+ "clean_up_tokenization_spaces": false,
950
+ "eos_token": "</s>",
951
+ "extra_ids": 100,
952
+ "extra_special_tokens": {},
953
+ "legacy": true,
954
+ "model_max_length": 512,
955
+ "pad_token": "<pad>",
956
+ "sp_model_kwargs": {},
957
+ "tokenizer_class": "T5Tokenizer",
958
+ "unk_token": "<unk>"
959
+ }
checkpoint-3170/trainer_state.json ADDED
@@ -0,0 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3170,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.15772870662460567,
14
+ "grad_norm": 8.993573188781738,
15
+ "learning_rate": 3.390694006309148e-05,
16
+ "loss": 2.6552,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.31545741324921134,
21
+ "grad_norm": 6.61809778213501,
22
+ "learning_rate": 3.280283911671924e-05,
23
+ "loss": 2.2263,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.47318611987381703,
28
+ "grad_norm": 10.127768516540527,
29
+ "learning_rate": 3.1698738170347005e-05,
30
+ "loss": 1.9796,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.6309148264984227,
35
+ "grad_norm": 4.960940361022949,
36
+ "learning_rate": 3.0594637223974764e-05,
37
+ "loss": 2.0323,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.7886435331230284,
42
+ "grad_norm": 5.231279373168945,
43
+ "learning_rate": 2.9490536277602523e-05,
44
+ "loss": 2.0473,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.7886435331230284,
49
+ "eval_bleu": 57.32056474546698,
50
+ "eval_chrf": 81.52338542769736,
51
+ "eval_loss": 0.7680727243423462,
52
+ "eval_runtime": 43.2314,
53
+ "eval_samples_per_second": 5.181,
54
+ "eval_steps_per_second": 0.648,
55
+ "step": 500
56
+ },
57
+ {
58
+ "epoch": 0.9463722397476341,
59
+ "grad_norm": 4.041931629180908,
60
+ "learning_rate": 2.838643533123028e-05,
61
+ "loss": 1.9593,
62
+ "step": 600
63
+ },
64
+ {
65
+ "epoch": 1.1041009463722398,
66
+ "grad_norm": 5.660284519195557,
67
+ "learning_rate": 2.728233438485804e-05,
68
+ "loss": 1.9291,
69
+ "step": 700
70
+ },
71
+ {
72
+ "epoch": 1.2618296529968454,
73
+ "grad_norm": 4.831106662750244,
74
+ "learning_rate": 2.6178233438485802e-05,
75
+ "loss": 1.9062,
76
+ "step": 800
77
+ },
78
+ {
79
+ "epoch": 1.4195583596214512,
80
+ "grad_norm": 5.246473789215088,
81
+ "learning_rate": 2.5074132492113564e-05,
82
+ "loss": 1.8709,
83
+ "step": 900
84
+ },
85
+ {
86
+ "epoch": 1.5772870662460567,
87
+ "grad_norm": 6.091129779815674,
88
+ "learning_rate": 2.3970031545741323e-05,
89
+ "loss": 1.8274,
90
+ "step": 1000
91
+ },
92
+ {
93
+ "epoch": 1.5772870662460567,
94
+ "eval_bleu": 56.853343569870646,
95
+ "eval_chrf": 81.1312982973412,
96
+ "eval_loss": 0.8501662015914917,
97
+ "eval_runtime": 25.1617,
98
+ "eval_samples_per_second": 8.902,
99
+ "eval_steps_per_second": 1.113,
100
+ "step": 1000
101
+ },
102
+ {
103
+ "epoch": 1.7350157728706623,
104
+ "grad_norm": 4.976201057434082,
105
+ "learning_rate": 2.286593059936908e-05,
106
+ "loss": 1.8565,
107
+ "step": 1100
108
+ },
109
+ {
110
+ "epoch": 1.8927444794952681,
111
+ "grad_norm": 6.352173805236816,
112
+ "learning_rate": 2.1761829652996844e-05,
113
+ "loss": 1.7704,
114
+ "step": 1200
115
+ },
116
+ {
117
+ "epoch": 2.050473186119874,
118
+ "grad_norm": 5.1022233963012695,
119
+ "learning_rate": 2.0657728706624606e-05,
120
+ "loss": 1.7229,
121
+ "step": 1300
122
+ },
123
+ {
124
+ "epoch": 2.2082018927444795,
125
+ "grad_norm": 3.9384002685546875,
126
+ "learning_rate": 1.9553627760252364e-05,
127
+ "loss": 1.6988,
128
+ "step": 1400
129
+ },
130
+ {
131
+ "epoch": 2.365930599369085,
132
+ "grad_norm": 9.005499839782715,
133
+ "learning_rate": 1.8449526813880123e-05,
134
+ "loss": 1.7559,
135
+ "step": 1500
136
+ },
137
+ {
138
+ "epoch": 2.365930599369085,
139
+ "eval_bleu": 55.558969113821774,
140
+ "eval_chrf": 79.91366807649794,
141
+ "eval_loss": 0.8783891797065735,
142
+ "eval_runtime": 25.3515,
143
+ "eval_samples_per_second": 8.836,
144
+ "eval_steps_per_second": 1.104,
145
+ "step": 1500
146
+ },
147
+ {
148
+ "epoch": 2.5236593059936907,
149
+ "grad_norm": 5.816145420074463,
150
+ "learning_rate": 1.7345425867507885e-05,
151
+ "loss": 1.7198,
152
+ "step": 1600
153
+ },
154
+ {
155
+ "epoch": 2.6813880126182967,
156
+ "grad_norm": 4.037476062774658,
157
+ "learning_rate": 1.6241324921135647e-05,
158
+ "loss": 1.7311,
159
+ "step": 1700
160
+ },
161
+ {
162
+ "epoch": 2.8391167192429023,
163
+ "grad_norm": 4.826643943786621,
164
+ "learning_rate": 1.5137223974763406e-05,
165
+ "loss": 1.7583,
166
+ "step": 1800
167
+ },
168
+ {
169
+ "epoch": 2.996845425867508,
170
+ "grad_norm": 5.530210018157959,
171
+ "learning_rate": 1.4033123028391166e-05,
172
+ "loss": 1.6305,
173
+ "step": 1900
174
+ },
175
+ {
176
+ "epoch": 3.1545741324921135,
177
+ "grad_norm": 5.22488260269165,
178
+ "learning_rate": 1.2929022082018927e-05,
179
+ "loss": 1.7053,
180
+ "step": 2000
181
+ },
182
+ {
183
+ "epoch": 3.1545741324921135,
184
+ "eval_bleu": 55.323355114843025,
185
+ "eval_chrf": 79.52359278149143,
186
+ "eval_loss": 0.9229835271835327,
187
+ "eval_runtime": 24.6216,
188
+ "eval_samples_per_second": 9.098,
189
+ "eval_steps_per_second": 1.137,
190
+ "step": 2000
191
+ },
192
+ {
193
+ "epoch": 3.312302839116719,
194
+ "grad_norm": 6.181191444396973,
195
+ "learning_rate": 1.1824921135646685e-05,
196
+ "loss": 1.6653,
197
+ "step": 2100
198
+ },
199
+ {
200
+ "epoch": 3.470031545741325,
201
+ "grad_norm": 3.005113363265991,
202
+ "learning_rate": 1.0720820189274447e-05,
203
+ "loss": 1.6738,
204
+ "step": 2200
205
+ },
206
+ {
207
+ "epoch": 3.6277602523659307,
208
+ "grad_norm": 4.87603759765625,
209
+ "learning_rate": 9.616719242902206e-06,
210
+ "loss": 1.6694,
211
+ "step": 2300
212
+ },
213
+ {
214
+ "epoch": 3.7854889589905363,
215
+ "grad_norm": 3.4485676288604736,
216
+ "learning_rate": 8.512618296529968e-06,
217
+ "loss": 1.6154,
218
+ "step": 2400
219
+ },
220
+ {
221
+ "epoch": 3.943217665615142,
222
+ "grad_norm": 4.3030219078063965,
223
+ "learning_rate": 7.4085173501577285e-06,
224
+ "loss": 1.5943,
225
+ "step": 2500
226
+ },
227
+ {
228
+ "epoch": 3.943217665615142,
229
+ "eval_bleu": 55.5956316646253,
230
+ "eval_chrf": 79.72369308541496,
231
+ "eval_loss": 0.9278033375740051,
232
+ "eval_runtime": 25.7316,
233
+ "eval_samples_per_second": 8.705,
234
+ "eval_steps_per_second": 1.088,
235
+ "step": 2500
236
+ },
237
+ {
238
+ "epoch": 4.100946372239748,
239
+ "grad_norm": 4.7534284591674805,
240
+ "learning_rate": 6.304416403785489e-06,
241
+ "loss": 1.6937,
242
+ "step": 2600
243
+ },
244
+ {
245
+ "epoch": 4.2586750788643535,
246
+ "grad_norm": 5.381317138671875,
247
+ "learning_rate": 5.200315457413248e-06,
248
+ "loss": 1.5835,
249
+ "step": 2700
250
+ },
251
+ {
252
+ "epoch": 4.416403785488959,
253
+ "grad_norm": 7.387664794921875,
254
+ "learning_rate": 4.09621451104101e-06,
255
+ "loss": 1.6145,
256
+ "step": 2800
257
+ },
258
+ {
259
+ "epoch": 4.574132492113565,
260
+ "grad_norm": 4.751382827758789,
261
+ "learning_rate": 2.9921135646687696e-06,
262
+ "loss": 1.6218,
263
+ "step": 2900
264
+ },
265
+ {
266
+ "epoch": 4.73186119873817,
267
+ "grad_norm": 4.115559101104736,
268
+ "learning_rate": 1.8880126182965297e-06,
269
+ "loss": 1.6476,
270
+ "step": 3000
271
+ },
272
+ {
273
+ "epoch": 4.73186119873817,
274
+ "eval_bleu": 55.67318568538766,
275
+ "eval_chrf": 79.82548413247255,
276
+ "eval_loss": 0.9428688287734985,
277
+ "eval_runtime": 24.3618,
278
+ "eval_samples_per_second": 9.195,
279
+ "eval_steps_per_second": 1.149,
280
+ "step": 3000
281
+ },
282
+ {
283
+ "epoch": 4.889589905362776,
284
+ "grad_norm": 8.612651824951172,
285
+ "learning_rate": 7.839116719242902e-07,
286
+ "loss": 1.6411,
287
+ "step": 3100
288
+ }
289
+ ],
290
+ "logging_steps": 100,
291
+ "max_steps": 3170,
292
+ "num_input_tokens_seen": 0,
293
+ "num_train_epochs": 5,
294
+ "save_steps": 500,
295
+ "stateful_callbacks": {
296
+ "TrainerControl": {
297
+ "args": {
298
+ "should_epoch_stop": false,
299
+ "should_evaluate": false,
300
+ "should_log": false,
301
+ "should_save": true,
302
+ "should_training_stop": true
303
+ },
304
+ "attributes": {}
305
+ }
306
+ },
307
+ "total_flos": 8671674976174080.0,
308
+ "train_batch_size": 8,
309
+ "trial_name": null,
310
+ "trial_params": null
311
+ }
checkpoint-3170/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d959935e7e4549a66b0b310440f8c722b6eacdffde599d9fd1cb402dcd2ff8d7
3
+ size 5905