Vallarasu-05 commited on
Commit
99b0cec
·
verified ·
1 Parent(s): 0725423

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.41.2",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
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": "4.41.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cffa2924515aefbbfdee463acb5b47ca5007b9d60fdeb8aa2f988977a647d8e5
3
+ size 242041896
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9281b0b04595d6e988361727e3220ccc97eaa71aa09065b8a643f85308f79ff8
3
+ size 484163514
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d1c961d9cf84cf3cf6812014e2b4765326c2adf32b4da88a5e7ca3f3b31a93
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e545555c08ba7039c64971be0448fa45c0e2dc48a5dc3fb4e2efcbbb01581927
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:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
trainer_state.json ADDED
@@ -0,0 +1,1947 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.13630929589271545,
3
+ "best_model_checkpoint": "/kaggle/working/t5_grammar/checkpoint-87000",
4
+ "epoch": 2.5482925826294056,
5
+ "eval_steps": 1000,
6
+ "global_step": 87000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017134143207168925,
13
+ "grad_norm": 14133.65234375,
14
+ "learning_rate": 0.00029828655632089374,
15
+ "loss": 0.1896,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.03426828641433785,
20
+ "grad_norm": 15056.099609375,
21
+ "learning_rate": 0.00029657311264178745,
22
+ "loss": 0.1842,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.03426828641433785,
27
+ "eval_loss": 0.17125742137432098,
28
+ "eval_runtime": 399.4518,
29
+ "eval_samples_per_second": 259.749,
30
+ "eval_steps_per_second": 16.235,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.051402429621506776,
35
+ "grad_norm": 14070.4892578125,
36
+ "learning_rate": 0.00029485966896268117,
37
+ "loss": 0.1749,
38
+ "step": 1500
39
+ },
40
+ {
41
+ "epoch": 0.0685365728286757,
42
+ "grad_norm": 17216.447265625,
43
+ "learning_rate": 0.0002931462252835749,
44
+ "loss": 0.1786,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 0.0685365728286757,
49
+ "eval_loss": 0.1643916219472885,
50
+ "eval_runtime": 390.3871,
51
+ "eval_samples_per_second": 265.78,
52
+ "eval_steps_per_second": 16.612,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.08567071603584463,
57
+ "grad_norm": 16958.8359375,
58
+ "learning_rate": 0.00029143278160446864,
59
+ "loss": 0.1767,
60
+ "step": 2500
61
+ },
62
+ {
63
+ "epoch": 0.10280485924301355,
64
+ "grad_norm": 13057.439453125,
65
+ "learning_rate": 0.00028971933792536236,
66
+ "loss": 0.1695,
67
+ "step": 3000
68
+ },
69
+ {
70
+ "epoch": 0.10280485924301355,
71
+ "eval_loss": 0.16071277856826782,
72
+ "eval_runtime": 390.2545,
73
+ "eval_samples_per_second": 265.87,
74
+ "eval_steps_per_second": 16.617,
75
+ "step": 3000
76
+ },
77
+ {
78
+ "epoch": 0.11993900245018248,
79
+ "grad_norm": 13630.955078125,
80
+ "learning_rate": 0.0002880058942462561,
81
+ "loss": 0.1706,
82
+ "step": 3500
83
+ },
84
+ {
85
+ "epoch": 0.1370731456573514,
86
+ "grad_norm": 10731.69140625,
87
+ "learning_rate": 0.00028629245056714984,
88
+ "loss": 0.1674,
89
+ "step": 4000
90
+ },
91
+ {
92
+ "epoch": 0.1370731456573514,
93
+ "eval_loss": 0.15802307426929474,
94
+ "eval_runtime": 389.4206,
95
+ "eval_samples_per_second": 266.439,
96
+ "eval_steps_per_second": 16.653,
97
+ "step": 4000
98
+ },
99
+ {
100
+ "epoch": 0.15420728886452034,
101
+ "grad_norm": 7941.6083984375,
102
+ "learning_rate": 0.00028457900688804355,
103
+ "loss": 0.1672,
104
+ "step": 4500
105
+ },
106
+ {
107
+ "epoch": 0.17134143207168925,
108
+ "grad_norm": 8430.94921875,
109
+ "learning_rate": 0.00028286556320893726,
110
+ "loss": 0.1676,
111
+ "step": 5000
112
+ },
113
+ {
114
+ "epoch": 0.17134143207168925,
115
+ "eval_loss": 0.1548711508512497,
116
+ "eval_runtime": 389.6735,
117
+ "eval_samples_per_second": 266.267,
118
+ "eval_steps_per_second": 16.642,
119
+ "step": 5000
120
+ },
121
+ {
122
+ "epoch": 0.1884755752788582,
123
+ "grad_norm": 13760.44921875,
124
+ "learning_rate": 0.00028115211952983103,
125
+ "loss": 0.1689,
126
+ "step": 5500
127
+ },
128
+ {
129
+ "epoch": 0.2056097184860271,
130
+ "grad_norm": 10262.0078125,
131
+ "learning_rate": 0.00027943867585072474,
132
+ "loss": 0.1666,
133
+ "step": 6000
134
+ },
135
+ {
136
+ "epoch": 0.2056097184860271,
137
+ "eval_loss": 0.15408402681350708,
138
+ "eval_runtime": 387.9599,
139
+ "eval_samples_per_second": 267.443,
140
+ "eval_steps_per_second": 16.716,
141
+ "step": 6000
142
+ },
143
+ {
144
+ "epoch": 0.22274386169319604,
145
+ "grad_norm": 12889.4384765625,
146
+ "learning_rate": 0.0002777252321716185,
147
+ "loss": 0.1616,
148
+ "step": 6500
149
+ },
150
+ {
151
+ "epoch": 0.23987800490036496,
152
+ "grad_norm": 10746.7578125,
153
+ "learning_rate": 0.0002760117884925122,
154
+ "loss": 0.1635,
155
+ "step": 7000
156
+ },
157
+ {
158
+ "epoch": 0.23987800490036496,
159
+ "eval_loss": 0.15506142377853394,
160
+ "eval_runtime": 387.477,
161
+ "eval_samples_per_second": 267.776,
162
+ "eval_steps_per_second": 16.736,
163
+ "step": 7000
164
+ },
165
+ {
166
+ "epoch": 0.25701214810753387,
167
+ "grad_norm": 10404.8330078125,
168
+ "learning_rate": 0.00027429834481340593,
169
+ "loss": 0.1602,
170
+ "step": 7500
171
+ },
172
+ {
173
+ "epoch": 0.2741462913147028,
174
+ "grad_norm": 7665.7255859375,
175
+ "learning_rate": 0.0002725849011342997,
176
+ "loss": 0.1639,
177
+ "step": 8000
178
+ },
179
+ {
180
+ "epoch": 0.2741462913147028,
181
+ "eval_loss": 0.1529487818479538,
182
+ "eval_runtime": 387.9978,
183
+ "eval_samples_per_second": 267.416,
184
+ "eval_steps_per_second": 16.714,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 0.29128043452187175,
189
+ "grad_norm": 9427.958984375,
190
+ "learning_rate": 0.0002708714574551934,
191
+ "loss": 0.1634,
192
+ "step": 8500
193
+ },
194
+ {
195
+ "epoch": 0.3084145777290407,
196
+ "grad_norm": 11038.125,
197
+ "learning_rate": 0.0002691580137760872,
198
+ "loss": 0.1627,
199
+ "step": 9000
200
+ },
201
+ {
202
+ "epoch": 0.3084145777290407,
203
+ "eval_loss": 0.1524902731180191,
204
+ "eval_runtime": 387.8935,
205
+ "eval_samples_per_second": 267.488,
206
+ "eval_steps_per_second": 16.719,
207
+ "step": 9000
208
+ },
209
+ {
210
+ "epoch": 0.32554872093620957,
211
+ "grad_norm": 8801.658203125,
212
+ "learning_rate": 0.0002674445700969809,
213
+ "loss": 0.1608,
214
+ "step": 9500
215
+ },
216
+ {
217
+ "epoch": 0.3426828641433785,
218
+ "grad_norm": 8749.40234375,
219
+ "learning_rate": 0.0002657311264178746,
220
+ "loss": 0.1574,
221
+ "step": 10000
222
+ },
223
+ {
224
+ "epoch": 0.3426828641433785,
225
+ "eval_loss": 0.14999626576900482,
226
+ "eval_runtime": 387.6526,
227
+ "eval_samples_per_second": 267.655,
228
+ "eval_steps_per_second": 16.729,
229
+ "step": 10000
230
+ },
231
+ {
232
+ "epoch": 0.35981700735054745,
233
+ "grad_norm": 13740.5712890625,
234
+ "learning_rate": 0.00026401768273876837,
235
+ "loss": 0.1618,
236
+ "step": 10500
237
+ },
238
+ {
239
+ "epoch": 0.3769511505577164,
240
+ "grad_norm": 8747.478515625,
241
+ "learning_rate": 0.0002623042390596621,
242
+ "loss": 0.1602,
243
+ "step": 11000
244
+ },
245
+ {
246
+ "epoch": 0.3769511505577164,
247
+ "eval_loss": 0.1501392126083374,
248
+ "eval_runtime": 388.8587,
249
+ "eval_samples_per_second": 266.824,
250
+ "eval_steps_per_second": 16.677,
251
+ "step": 11000
252
+ },
253
+ {
254
+ "epoch": 0.39408529376488527,
255
+ "grad_norm": 11463.224609375,
256
+ "learning_rate": 0.0002605907953805558,
257
+ "loss": 0.1588,
258
+ "step": 11500
259
+ },
260
+ {
261
+ "epoch": 0.4112194369720542,
262
+ "grad_norm": 11067.5341796875,
263
+ "learning_rate": 0.00025887735170144956,
264
+ "loss": 0.1579,
265
+ "step": 12000
266
+ },
267
+ {
268
+ "epoch": 0.4112194369720542,
269
+ "eval_loss": 0.14851456880569458,
270
+ "eval_runtime": 387.548,
271
+ "eval_samples_per_second": 267.727,
272
+ "eval_steps_per_second": 16.733,
273
+ "step": 12000
274
+ },
275
+ {
276
+ "epoch": 0.42835358017922315,
277
+ "grad_norm": 14145.041015625,
278
+ "learning_rate": 0.0002571639080223433,
279
+ "loss": 0.1582,
280
+ "step": 12500
281
+ },
282
+ {
283
+ "epoch": 0.4454877233863921,
284
+ "grad_norm": 11157.630859375,
285
+ "learning_rate": 0.00025545046434323704,
286
+ "loss": 0.1549,
287
+ "step": 13000
288
+ },
289
+ {
290
+ "epoch": 0.4454877233863921,
291
+ "eval_loss": 0.14914636313915253,
292
+ "eval_runtime": 387.8263,
293
+ "eval_samples_per_second": 267.535,
294
+ "eval_steps_per_second": 16.721,
295
+ "step": 13000
296
+ },
297
+ {
298
+ "epoch": 0.46262186659356097,
299
+ "grad_norm": 11304.8388671875,
300
+ "learning_rate": 0.00025373702066413075,
301
+ "loss": 0.1614,
302
+ "step": 13500
303
+ },
304
+ {
305
+ "epoch": 0.4797560098007299,
306
+ "grad_norm": 9183.751953125,
307
+ "learning_rate": 0.00025202357698502447,
308
+ "loss": 0.1583,
309
+ "step": 14000
310
+ },
311
+ {
312
+ "epoch": 0.4797560098007299,
313
+ "eval_loss": 0.14881567656993866,
314
+ "eval_runtime": 388.06,
315
+ "eval_samples_per_second": 267.374,
316
+ "eval_steps_per_second": 16.711,
317
+ "step": 14000
318
+ },
319
+ {
320
+ "epoch": 0.49689015300789885,
321
+ "grad_norm": 8175.90185546875,
322
+ "learning_rate": 0.00025031013330591823,
323
+ "loss": 0.1551,
324
+ "step": 14500
325
+ },
326
+ {
327
+ "epoch": 0.5140242962150677,
328
+ "grad_norm": 9153.2412109375,
329
+ "learning_rate": 0.00024859668962681194,
330
+ "loss": 0.1569,
331
+ "step": 15000
332
+ },
333
+ {
334
+ "epoch": 0.5140242962150677,
335
+ "eval_loss": 0.1471492052078247,
336
+ "eval_runtime": 387.7855,
337
+ "eval_samples_per_second": 267.563,
338
+ "eval_steps_per_second": 16.723,
339
+ "step": 15000
340
+ },
341
+ {
342
+ "epoch": 0.5311584394222367,
343
+ "grad_norm": 13883.2724609375,
344
+ "learning_rate": 0.0002468832459477057,
345
+ "loss": 0.1589,
346
+ "step": 15500
347
+ },
348
+ {
349
+ "epoch": 0.5482925826294056,
350
+ "grad_norm": 10793.9423828125,
351
+ "learning_rate": 0.0002451698022685994,
352
+ "loss": 0.1538,
353
+ "step": 16000
354
+ },
355
+ {
356
+ "epoch": 0.5482925826294056,
357
+ "eval_loss": 0.1467715948820114,
358
+ "eval_runtime": 388.0782,
359
+ "eval_samples_per_second": 267.361,
360
+ "eval_steps_per_second": 16.711,
361
+ "step": 16000
362
+ },
363
+ {
364
+ "epoch": 0.5654267258365745,
365
+ "grad_norm": 10652.046875,
366
+ "learning_rate": 0.00024345635858949316,
367
+ "loss": 0.1608,
368
+ "step": 16500
369
+ },
370
+ {
371
+ "epoch": 0.5825608690437435,
372
+ "grad_norm": 8967.8564453125,
373
+ "learning_rate": 0.00024174291491038688,
374
+ "loss": 0.1539,
375
+ "step": 17000
376
+ },
377
+ {
378
+ "epoch": 0.5825608690437435,
379
+ "eval_loss": 0.1449543684720993,
380
+ "eval_runtime": 391.2206,
381
+ "eval_samples_per_second": 265.214,
382
+ "eval_steps_per_second": 16.576,
383
+ "step": 17000
384
+ },
385
+ {
386
+ "epoch": 0.5996950122509124,
387
+ "grad_norm": 12113.2939453125,
388
+ "learning_rate": 0.00024002947123128062,
389
+ "loss": 0.1565,
390
+ "step": 17500
391
+ },
392
+ {
393
+ "epoch": 0.6168291554580814,
394
+ "grad_norm": 13096.2333984375,
395
+ "learning_rate": 0.00023831602755217433,
396
+ "loss": 0.1551,
397
+ "step": 18000
398
+ },
399
+ {
400
+ "epoch": 0.6168291554580814,
401
+ "eval_loss": 0.14633049070835114,
402
+ "eval_runtime": 393.2601,
403
+ "eval_samples_per_second": 263.838,
404
+ "eval_steps_per_second": 16.49,
405
+ "step": 18000
406
+ },
407
+ {
408
+ "epoch": 0.6339632986652503,
409
+ "grad_norm": 8567.408203125,
410
+ "learning_rate": 0.00023660258387306807,
411
+ "loss": 0.1558,
412
+ "step": 18500
413
+ },
414
+ {
415
+ "epoch": 0.6510974418724191,
416
+ "grad_norm": 7009.94482421875,
417
+ "learning_rate": 0.00023488914019396178,
418
+ "loss": 0.1567,
419
+ "step": 19000
420
+ },
421
+ {
422
+ "epoch": 0.6510974418724191,
423
+ "eval_loss": 0.14441940188407898,
424
+ "eval_runtime": 396.0054,
425
+ "eval_samples_per_second": 262.009,
426
+ "eval_steps_per_second": 16.376,
427
+ "step": 19000
428
+ },
429
+ {
430
+ "epoch": 0.6682315850795881,
431
+ "grad_norm": 11680.794921875,
432
+ "learning_rate": 0.00023317569651485555,
433
+ "loss": 0.1511,
434
+ "step": 19500
435
+ },
436
+ {
437
+ "epoch": 0.685365728286757,
438
+ "grad_norm": 12115.5126953125,
439
+ "learning_rate": 0.00023146225283574929,
440
+ "loss": 0.1565,
441
+ "step": 20000
442
+ },
443
+ {
444
+ "epoch": 0.685365728286757,
445
+ "eval_loss": 0.14564944803714752,
446
+ "eval_runtime": 395.959,
447
+ "eval_samples_per_second": 262.04,
448
+ "eval_steps_per_second": 16.378,
449
+ "step": 20000
450
+ },
451
+ {
452
+ "epoch": 0.7024998714939259,
453
+ "grad_norm": 15042.001953125,
454
+ "learning_rate": 0.000229748809156643,
455
+ "loss": 0.1566,
456
+ "step": 20500
457
+ },
458
+ {
459
+ "epoch": 0.7196340147010949,
460
+ "grad_norm": 10541.1025390625,
461
+ "learning_rate": 0.00022803536547753674,
462
+ "loss": 0.1579,
463
+ "step": 21000
464
+ },
465
+ {
466
+ "epoch": 0.7196340147010949,
467
+ "eval_loss": 0.14396682381629944,
468
+ "eval_runtime": 383.3319,
469
+ "eval_samples_per_second": 270.671,
470
+ "eval_steps_per_second": 16.917,
471
+ "step": 21000
472
+ },
473
+ {
474
+ "epoch": 0.7367681579082638,
475
+ "grad_norm": 12583.2978515625,
476
+ "learning_rate": 0.00022632192179843045,
477
+ "loss": 0.1563,
478
+ "step": 21500
479
+ },
480
+ {
481
+ "epoch": 0.7539023011154328,
482
+ "grad_norm": 14151.1279296875,
483
+ "learning_rate": 0.00022460847811932422,
484
+ "loss": 0.1549,
485
+ "step": 22000
486
+ },
487
+ {
488
+ "epoch": 0.7539023011154328,
489
+ "eval_loss": 0.14402377605438232,
490
+ "eval_runtime": 381.7851,
491
+ "eval_samples_per_second": 271.768,
492
+ "eval_steps_per_second": 16.986,
493
+ "step": 22000
494
+ },
495
+ {
496
+ "epoch": 0.7710364443226017,
497
+ "grad_norm": 12230.4326171875,
498
+ "learning_rate": 0.00022289503444021793,
499
+ "loss": 0.1519,
500
+ "step": 22500
501
+ },
502
+ {
503
+ "epoch": 0.7881705875297705,
504
+ "grad_norm": 10088.81640625,
505
+ "learning_rate": 0.00022118159076111167,
506
+ "loss": 0.1567,
507
+ "step": 23000
508
+ },
509
+ {
510
+ "epoch": 0.7881705875297705,
511
+ "eval_loss": 0.14262937009334564,
512
+ "eval_runtime": 379.3635,
513
+ "eval_samples_per_second": 273.503,
514
+ "eval_steps_per_second": 17.094,
515
+ "step": 23000
516
+ },
517
+ {
518
+ "epoch": 0.8053047307369395,
519
+ "grad_norm": 11425.5810546875,
520
+ "learning_rate": 0.00021946814708200538,
521
+ "loss": 0.1538,
522
+ "step": 23500
523
+ },
524
+ {
525
+ "epoch": 0.8224388739441084,
526
+ "grad_norm": 12657.4892578125,
527
+ "learning_rate": 0.00021775470340289912,
528
+ "loss": 0.1544,
529
+ "step": 24000
530
+ },
531
+ {
532
+ "epoch": 0.8224388739441084,
533
+ "eval_loss": 0.14293000102043152,
534
+ "eval_runtime": 372.1601,
535
+ "eval_samples_per_second": 278.797,
536
+ "eval_steps_per_second": 17.425,
537
+ "step": 24000
538
+ },
539
+ {
540
+ "epoch": 0.017134143207168925,
541
+ "grad_norm": 10302.099609375,
542
+ "learning_rate": 0.00021604125972379286,
543
+ "loss": 0.1456,
544
+ "step": 24500
545
+ },
546
+ {
547
+ "epoch": 0.03426828641433785,
548
+ "grad_norm": 10120.05859375,
549
+ "learning_rate": 0.0002143278160446866,
550
+ "loss": 0.1472,
551
+ "step": 25000
552
+ },
553
+ {
554
+ "epoch": 0.03426828641433785,
555
+ "eval_loss": 0.142826110124588,
556
+ "eval_runtime": 381.9908,
557
+ "eval_samples_per_second": 271.622,
558
+ "eval_steps_per_second": 16.977,
559
+ "step": 25000
560
+ },
561
+ {
562
+ "epoch": 0.017134143207168925,
563
+ "grad_norm": 9663.3359375,
564
+ "learning_rate": 0.0002126143723655803,
565
+ "loss": 0.1374,
566
+ "step": 25500
567
+ },
568
+ {
569
+ "epoch": 0.03426828641433785,
570
+ "grad_norm": 9667.6220703125,
571
+ "learning_rate": 0.00021090092868647405,
572
+ "loss": 0.14,
573
+ "step": 26000
574
+ },
575
+ {
576
+ "epoch": 0.03426828641433785,
577
+ "eval_loss": 0.14417503774166107,
578
+ "eval_runtime": 380.9982,
579
+ "eval_samples_per_second": 272.329,
580
+ "eval_steps_per_second": 17.021,
581
+ "step": 26000
582
+ },
583
+ {
584
+ "epoch": 0.051402429621506776,
585
+ "grad_norm": 10547.4658203125,
586
+ "learning_rate": 0.0002091874850073678,
587
+ "loss": 0.1461,
588
+ "step": 26500
589
+ },
590
+ {
591
+ "epoch": 0.0685365728286757,
592
+ "grad_norm": 12416.5400390625,
593
+ "learning_rate": 0.00020747404132826153,
594
+ "loss": 0.1512,
595
+ "step": 27000
596
+ },
597
+ {
598
+ "epoch": 0.0685365728286757,
599
+ "eval_loss": 0.1423807442188263,
600
+ "eval_runtime": 380.5337,
601
+ "eval_samples_per_second": 272.662,
602
+ "eval_steps_per_second": 17.042,
603
+ "step": 27000
604
+ },
605
+ {
606
+ "epoch": 0.08567071603584463,
607
+ "grad_norm": 14124.9072265625,
608
+ "learning_rate": 0.00020576059764915527,
609
+ "loss": 0.1509,
610
+ "step": 27500
611
+ },
612
+ {
613
+ "epoch": 0.10280485924301355,
614
+ "grad_norm": 7792.5,
615
+ "learning_rate": 0.00020404715397004898,
616
+ "loss": 0.1461,
617
+ "step": 28000
618
+ },
619
+ {
620
+ "epoch": 0.10280485924301355,
621
+ "eval_loss": 0.1423524022102356,
622
+ "eval_runtime": 380.58,
623
+ "eval_samples_per_second": 272.629,
624
+ "eval_steps_per_second": 17.04,
625
+ "step": 28000
626
+ },
627
+ {
628
+ "epoch": 0.017134143207168925,
629
+ "grad_norm": 13279.173828125,
630
+ "learning_rate": 0.00020233371029094272,
631
+ "loss": 0.1214,
632
+ "step": 28500
633
+ },
634
+ {
635
+ "epoch": 0.03426828641433785,
636
+ "grad_norm": 10616.5771484375,
637
+ "learning_rate": 0.00020062026661183644,
638
+ "loss": 0.1221,
639
+ "step": 29000
640
+ },
641
+ {
642
+ "epoch": 0.03426828641433785,
643
+ "eval_loss": 0.1469964236021042,
644
+ "eval_runtime": 383.8032,
645
+ "eval_samples_per_second": 270.339,
646
+ "eval_steps_per_second": 16.897,
647
+ "step": 29000
648
+ },
649
+ {
650
+ "epoch": 0.051402429621506776,
651
+ "grad_norm": 13246.1318359375,
652
+ "learning_rate": 0.0001989068229327302,
653
+ "loss": 0.1347,
654
+ "step": 29500
655
+ },
656
+ {
657
+ "epoch": 0.0685365728286757,
658
+ "grad_norm": 16495.373046875,
659
+ "learning_rate": 0.00019719337925362392,
660
+ "loss": 0.1388,
661
+ "step": 30000
662
+ },
663
+ {
664
+ "epoch": 0.0685365728286757,
665
+ "eval_loss": 0.1429709792137146,
666
+ "eval_runtime": 382.9436,
667
+ "eval_samples_per_second": 270.946,
668
+ "eval_steps_per_second": 16.935,
669
+ "step": 30000
670
+ },
671
+ {
672
+ "epoch": 0.08567071603584463,
673
+ "grad_norm": 12161.38671875,
674
+ "learning_rate": 0.00019547993557451765,
675
+ "loss": 0.1388,
676
+ "step": 30500
677
+ },
678
+ {
679
+ "epoch": 0.10280485924301355,
680
+ "grad_norm": 10506.4306640625,
681
+ "learning_rate": 0.00019376649189541137,
682
+ "loss": 0.1343,
683
+ "step": 31000
684
+ },
685
+ {
686
+ "epoch": 0.10280485924301355,
687
+ "eval_loss": 0.14420585334300995,
688
+ "eval_runtime": 382.79,
689
+ "eval_samples_per_second": 271.055,
690
+ "eval_steps_per_second": 16.941,
691
+ "step": 31000
692
+ },
693
+ {
694
+ "epoch": 0.11993900245018248,
695
+ "grad_norm": 12089.09375,
696
+ "learning_rate": 0.0001920530482163051,
697
+ "loss": 0.144,
698
+ "step": 31500
699
+ },
700
+ {
701
+ "epoch": 0.1370731456573514,
702
+ "grad_norm": 12573.53515625,
703
+ "learning_rate": 0.00019033960453719882,
704
+ "loss": 0.141,
705
+ "step": 32000
706
+ },
707
+ {
708
+ "epoch": 0.1370731456573514,
709
+ "eval_loss": 0.14102041721343994,
710
+ "eval_runtime": 383.4366,
711
+ "eval_samples_per_second": 270.598,
712
+ "eval_steps_per_second": 16.913,
713
+ "step": 32000
714
+ },
715
+ {
716
+ "epoch": 0.15420728886452034,
717
+ "grad_norm": 6979.53076171875,
718
+ "learning_rate": 0.00018862616085809259,
719
+ "loss": 0.1418,
720
+ "step": 32500
721
+ },
722
+ {
723
+ "epoch": 0.17134143207168925,
724
+ "grad_norm": 8123.474609375,
725
+ "learning_rate": 0.00018691271717898633,
726
+ "loss": 0.1428,
727
+ "step": 33000
728
+ },
729
+ {
730
+ "epoch": 0.17134143207168925,
731
+ "eval_loss": 0.14070653915405273,
732
+ "eval_runtime": 382.7425,
733
+ "eval_samples_per_second": 271.088,
734
+ "eval_steps_per_second": 16.944,
735
+ "step": 33000
736
+ },
737
+ {
738
+ "epoch": 0.1884755752788582,
739
+ "grad_norm": 11290.353515625,
740
+ "learning_rate": 0.00018519927349988004,
741
+ "loss": 0.1443,
742
+ "step": 33500
743
+ },
744
+ {
745
+ "epoch": 0.2056097184860271,
746
+ "grad_norm": 9288.3798828125,
747
+ "learning_rate": 0.00018348582982077378,
748
+ "loss": 0.1431,
749
+ "step": 34000
750
+ },
751
+ {
752
+ "epoch": 0.2056097184860271,
753
+ "eval_loss": 0.1410551220178604,
754
+ "eval_runtime": 382.105,
755
+ "eval_samples_per_second": 271.541,
756
+ "eval_steps_per_second": 16.972,
757
+ "step": 34000
758
+ },
759
+ {
760
+ "epoch": 0.22274386169319604,
761
+ "grad_norm": 17436.396484375,
762
+ "learning_rate": 0.0001817723861416675,
763
+ "loss": 0.1387,
764
+ "step": 34500
765
+ },
766
+ {
767
+ "epoch": 0.23987800490036496,
768
+ "grad_norm": 11314.029296875,
769
+ "learning_rate": 0.00018005894246256126,
770
+ "loss": 0.1401,
771
+ "step": 35000
772
+ },
773
+ {
774
+ "epoch": 0.23987800490036496,
775
+ "eval_loss": 0.14164981245994568,
776
+ "eval_runtime": 382.2614,
777
+ "eval_samples_per_second": 271.429,
778
+ "eval_steps_per_second": 16.965,
779
+ "step": 35000
780
+ },
781
+ {
782
+ "epoch": 0.25701214810753387,
783
+ "grad_norm": 9253.1806640625,
784
+ "learning_rate": 0.00017834549878345497,
785
+ "loss": 0.138,
786
+ "step": 35500
787
+ },
788
+ {
789
+ "epoch": 0.2741462913147028,
790
+ "grad_norm": 7572.0107421875,
791
+ "learning_rate": 0.0001766320551043487,
792
+ "loss": 0.142,
793
+ "step": 36000
794
+ },
795
+ {
796
+ "epoch": 0.2741462913147028,
797
+ "eval_loss": 0.14141882956027985,
798
+ "eval_runtime": 382.6766,
799
+ "eval_samples_per_second": 271.135,
800
+ "eval_steps_per_second": 16.946,
801
+ "step": 36000
802
+ },
803
+ {
804
+ "epoch": 1.017134143207169,
805
+ "grad_norm": 9368.7783203125,
806
+ "learning_rate": 0.00017491861142524242,
807
+ "loss": 0.1464,
808
+ "step": 36500
809
+ },
810
+ {
811
+ "epoch": 1.0342682864143378,
812
+ "grad_norm": 9459.5390625,
813
+ "learning_rate": 0.0001732051677461362,
814
+ "loss": 0.1454,
815
+ "step": 37000
816
+ },
817
+ {
818
+ "epoch": 1.0342682864143378,
819
+ "eval_loss": 0.1406838744878769,
820
+ "eval_runtime": 434.2891,
821
+ "eval_samples_per_second": 238.912,
822
+ "eval_steps_per_second": 14.932,
823
+ "step": 37000
824
+ },
825
+ {
826
+ "epoch": 1.0514024296215068,
827
+ "grad_norm": 12301.96875,
828
+ "learning_rate": 0.0001714917240670299,
829
+ "loss": 0.1445,
830
+ "step": 37500
831
+ },
832
+ {
833
+ "epoch": 1.0685365728286758,
834
+ "grad_norm": 8720.6884765625,
835
+ "learning_rate": 0.00016977828038792364,
836
+ "loss": 0.1433,
837
+ "step": 38000
838
+ },
839
+ {
840
+ "epoch": 1.0685365728286758,
841
+ "eval_loss": 0.13989166915416718,
842
+ "eval_runtime": 433.3424,
843
+ "eval_samples_per_second": 239.434,
844
+ "eval_steps_per_second": 14.965,
845
+ "step": 38000
846
+ },
847
+ {
848
+ "epoch": 1.0856707160358445,
849
+ "grad_norm": 10000.41015625,
850
+ "learning_rate": 0.00016806483670881735,
851
+ "loss": 0.144,
852
+ "step": 38500
853
+ },
854
+ {
855
+ "epoch": 1.1028048592430135,
856
+ "grad_norm": 18150.453125,
857
+ "learning_rate": 0.0001663513930297111,
858
+ "loss": 0.1442,
859
+ "step": 39000
860
+ },
861
+ {
862
+ "epoch": 1.1028048592430135,
863
+ "eval_loss": 0.14073656499385834,
864
+ "eval_runtime": 430.7988,
865
+ "eval_samples_per_second": 240.848,
866
+ "eval_steps_per_second": 15.053,
867
+ "step": 39000
868
+ },
869
+ {
870
+ "epoch": 1.1199390024501825,
871
+ "grad_norm": 10784.6708984375,
872
+ "learning_rate": 0.00016463794935060486,
873
+ "loss": 0.1424,
874
+ "step": 39500
875
+ },
876
+ {
877
+ "epoch": 1.1370731456573515,
878
+ "grad_norm": 13316.978515625,
879
+ "learning_rate": 0.00016292450567149857,
880
+ "loss": 0.141,
881
+ "step": 40000
882
+ },
883
+ {
884
+ "epoch": 1.1370731456573515,
885
+ "eval_loss": 0.1395416557788849,
886
+ "eval_runtime": 431.1224,
887
+ "eval_samples_per_second": 240.667,
888
+ "eval_steps_per_second": 15.042,
889
+ "step": 40000
890
+ },
891
+ {
892
+ "epoch": 1.1542072888645203,
893
+ "grad_norm": 22079.833984375,
894
+ "learning_rate": 0.0001612110619923923,
895
+ "loss": 0.1447,
896
+ "step": 40500
897
+ },
898
+ {
899
+ "epoch": 1.1713414320716893,
900
+ "grad_norm": 8438.4111328125,
901
+ "learning_rate": 0.00015949761831328602,
902
+ "loss": 0.1381,
903
+ "step": 41000
904
+ },
905
+ {
906
+ "epoch": 1.1713414320716893,
907
+ "eval_loss": 0.13986870646476746,
908
+ "eval_runtime": 429.1361,
909
+ "eval_samples_per_second": 241.781,
910
+ "eval_steps_per_second": 15.112,
911
+ "step": 41000
912
+ },
913
+ {
914
+ "epoch": 1.017134143207169,
915
+ "grad_norm": 11648.904296875,
916
+ "learning_rate": 0.00015778417463417976,
917
+ "loss": 0.1323,
918
+ "step": 41500
919
+ },
920
+ {
921
+ "epoch": 1.0342682864143378,
922
+ "grad_norm": 11085.5673828125,
923
+ "learning_rate": 0.00015607073095507348,
924
+ "loss": 0.1304,
925
+ "step": 42000
926
+ },
927
+ {
928
+ "epoch": 1.0342682864143378,
929
+ "eval_loss": 0.14177943766117096,
930
+ "eval_runtime": 384.9186,
931
+ "eval_samples_per_second": 269.556,
932
+ "eval_steps_per_second": 16.848,
933
+ "step": 42000
934
+ },
935
+ {
936
+ "epoch": 1.0514024296215068,
937
+ "grad_norm": 12665.556640625,
938
+ "learning_rate": 0.00015435728727596724,
939
+ "loss": 0.1293,
940
+ "step": 42500
941
+ },
942
+ {
943
+ "epoch": 1.0685365728286758,
944
+ "grad_norm": 9982.4189453125,
945
+ "learning_rate": 0.00015264384359686095,
946
+ "loss": 0.1288,
947
+ "step": 43000
948
+ },
949
+ {
950
+ "epoch": 1.0685365728286758,
951
+ "eval_loss": 0.14150947332382202,
952
+ "eval_runtime": 383.6699,
953
+ "eval_samples_per_second": 270.433,
954
+ "eval_steps_per_second": 16.903,
955
+ "step": 43000
956
+ },
957
+ {
958
+ "epoch": 1.0856707160358445,
959
+ "grad_norm": 16450.314453125,
960
+ "learning_rate": 0.0001509303999177547,
961
+ "loss": 0.1291,
962
+ "step": 43500
963
+ },
964
+ {
965
+ "epoch": 1.1028048592430135,
966
+ "grad_norm": 18497.755859375,
967
+ "learning_rate": 0.00014921695623864843,
968
+ "loss": 0.13,
969
+ "step": 44000
970
+ },
971
+ {
972
+ "epoch": 1.1028048592430135,
973
+ "eval_loss": 0.14215722680091858,
974
+ "eval_runtime": 384.9189,
975
+ "eval_samples_per_second": 269.556,
976
+ "eval_steps_per_second": 16.848,
977
+ "step": 44000
978
+ },
979
+ {
980
+ "epoch": 1.1199390024501825,
981
+ "grad_norm": 9396.0322265625,
982
+ "learning_rate": 0.00014750351255954215,
983
+ "loss": 0.1286,
984
+ "step": 44500
985
+ },
986
+ {
987
+ "epoch": 1.1370731456573515,
988
+ "grad_norm": 14090.4658203125,
989
+ "learning_rate": 0.00014579006888043589,
990
+ "loss": 0.1273,
991
+ "step": 45000
992
+ },
993
+ {
994
+ "epoch": 1.1370731456573515,
995
+ "eval_loss": 0.1416812241077423,
996
+ "eval_runtime": 382.4036,
997
+ "eval_samples_per_second": 271.329,
998
+ "eval_steps_per_second": 16.959,
999
+ "step": 45000
1000
+ },
1001
+ {
1002
+ "epoch": 1.1542072888645203,
1003
+ "grad_norm": 13297.76171875,
1004
+ "learning_rate": 0.00014407662520132963,
1005
+ "loss": 0.1308,
1006
+ "step": 45500
1007
+ },
1008
+ {
1009
+ "epoch": 1.1713414320716893,
1010
+ "grad_norm": 11327.3427734375,
1011
+ "learning_rate": 0.00014236318152222336,
1012
+ "loss": 0.1248,
1013
+ "step": 46000
1014
+ },
1015
+ {
1016
+ "epoch": 1.1713414320716893,
1017
+ "eval_loss": 0.14259684085845947,
1018
+ "eval_runtime": 382.6496,
1019
+ "eval_samples_per_second": 271.154,
1020
+ "eval_steps_per_second": 16.948,
1021
+ "step": 46000
1022
+ },
1023
+ {
1024
+ "epoch": 1.1884755752788583,
1025
+ "grad_norm": 16370.40625,
1026
+ "learning_rate": 0.00014064973784311708,
1027
+ "loss": 0.1454,
1028
+ "step": 46500
1029
+ },
1030
+ {
1031
+ "epoch": 1.205609718486027,
1032
+ "grad_norm": 9618.501953125,
1033
+ "learning_rate": 0.00013893629416401082,
1034
+ "loss": 0.1445,
1035
+ "step": 47000
1036
+ },
1037
+ {
1038
+ "epoch": 1.205609718486027,
1039
+ "eval_loss": 0.13921518623828888,
1040
+ "eval_runtime": 384.9467,
1041
+ "eval_samples_per_second": 269.536,
1042
+ "eval_steps_per_second": 16.846,
1043
+ "step": 47000
1044
+ },
1045
+ {
1046
+ "epoch": 1.222743861693196,
1047
+ "grad_norm": 11777.8916015625,
1048
+ "learning_rate": 0.00013722285048490456,
1049
+ "loss": 0.1395,
1050
+ "step": 47500
1051
+ },
1052
+ {
1053
+ "epoch": 1.239878004900365,
1054
+ "grad_norm": 9422.962890625,
1055
+ "learning_rate": 0.00013550940680579827,
1056
+ "loss": 0.1439,
1057
+ "step": 48000
1058
+ },
1059
+ {
1060
+ "epoch": 1.239878004900365,
1061
+ "eval_loss": 0.13896773755550385,
1062
+ "eval_runtime": 382.3752,
1063
+ "eval_samples_per_second": 271.349,
1064
+ "eval_steps_per_second": 16.96,
1065
+ "step": 48000
1066
+ },
1067
+ {
1068
+ "epoch": 1.017134143207169,
1069
+ "grad_norm": 11418.8759765625,
1070
+ "learning_rate": 0.000133795963126692,
1071
+ "loss": 0.1215,
1072
+ "step": 48500
1073
+ },
1074
+ {
1075
+ "epoch": 1.0342682864143378,
1076
+ "grad_norm": 12255.0244140625,
1077
+ "learning_rate": 0.00013208251944758575,
1078
+ "loss": 0.1196,
1079
+ "step": 49000
1080
+ },
1081
+ {
1082
+ "epoch": 1.0342682864143378,
1083
+ "eval_loss": 0.14390338957309723,
1084
+ "eval_runtime": 401.2711,
1085
+ "eval_samples_per_second": 258.571,
1086
+ "eval_steps_per_second": 16.161,
1087
+ "step": 49000
1088
+ },
1089
+ {
1090
+ "epoch": 1.0514024296215068,
1091
+ "grad_norm": 11574.6875,
1092
+ "learning_rate": 0.0001303690757684795,
1093
+ "loss": 0.1183,
1094
+ "step": 49500
1095
+ },
1096
+ {
1097
+ "epoch": 1.0685365728286758,
1098
+ "grad_norm": 11228.0185546875,
1099
+ "learning_rate": 0.00012865563208937323,
1100
+ "loss": 0.1173,
1101
+ "step": 50000
1102
+ },
1103
+ {
1104
+ "epoch": 1.0685365728286758,
1105
+ "eval_loss": 0.14367318153381348,
1106
+ "eval_runtime": 400.614,
1107
+ "eval_samples_per_second": 258.995,
1108
+ "eval_steps_per_second": 16.188,
1109
+ "step": 50000
1110
+ },
1111
+ {
1112
+ "epoch": 1.0856707160358445,
1113
+ "grad_norm": 12285.71484375,
1114
+ "learning_rate": 0.00012694218841026694,
1115
+ "loss": 0.1181,
1116
+ "step": 50500
1117
+ },
1118
+ {
1119
+ "epoch": 1.1028048592430135,
1120
+ "grad_norm": 16199.8427734375,
1121
+ "learning_rate": 0.00012522874473116068,
1122
+ "loss": 0.119,
1123
+ "step": 51000
1124
+ },
1125
+ {
1126
+ "epoch": 1.1028048592430135,
1127
+ "eval_loss": 0.14494740962982178,
1128
+ "eval_runtime": 400.4616,
1129
+ "eval_samples_per_second": 259.093,
1130
+ "eval_steps_per_second": 16.194,
1131
+ "step": 51000
1132
+ },
1133
+ {
1134
+ "epoch": 1.017134143207169,
1135
+ "grad_norm": 10808.3095703125,
1136
+ "learning_rate": 0.00012351530105205442,
1137
+ "loss": 0.1095,
1138
+ "step": 51500
1139
+ },
1140
+ {
1141
+ "epoch": 1.0342682864143378,
1142
+ "grad_norm": 10598.76171875,
1143
+ "learning_rate": 0.00012180185737294815,
1144
+ "loss": 0.1081,
1145
+ "step": 52000
1146
+ },
1147
+ {
1148
+ "epoch": 1.0342682864143378,
1149
+ "eval_loss": 0.14752106368541718,
1150
+ "eval_runtime": 381.4284,
1151
+ "eval_samples_per_second": 272.022,
1152
+ "eval_steps_per_second": 17.002,
1153
+ "step": 52000
1154
+ },
1155
+ {
1156
+ "epoch": 1.0514024296215068,
1157
+ "grad_norm": 15928.1953125,
1158
+ "learning_rate": 0.00012008841369384187,
1159
+ "loss": 0.1065,
1160
+ "step": 52500
1161
+ },
1162
+ {
1163
+ "epoch": 1.0685365728286758,
1164
+ "grad_norm": 11003.04296875,
1165
+ "learning_rate": 0.00011837497001473561,
1166
+ "loss": 0.1063,
1167
+ "step": 53000
1168
+ },
1169
+ {
1170
+ "epoch": 1.0685365728286758,
1171
+ "eval_loss": 0.14847944676876068,
1172
+ "eval_runtime": 381.1852,
1173
+ "eval_samples_per_second": 272.196,
1174
+ "eval_steps_per_second": 17.013,
1175
+ "step": 53000
1176
+ },
1177
+ {
1178
+ "epoch": 1.0856707160358445,
1179
+ "grad_norm": 18801.296875,
1180
+ "learning_rate": 0.00011666152633562934,
1181
+ "loss": 0.1075,
1182
+ "step": 53500
1183
+ },
1184
+ {
1185
+ "epoch": 1.1028048592430135,
1186
+ "grad_norm": 15937.283203125,
1187
+ "learning_rate": 0.00011494808265652306,
1188
+ "loss": 0.1086,
1189
+ "step": 54000
1190
+ },
1191
+ {
1192
+ "epoch": 1.1028048592430135,
1193
+ "eval_loss": 0.14870062470436096,
1194
+ "eval_runtime": 380.8304,
1195
+ "eval_samples_per_second": 272.449,
1196
+ "eval_steps_per_second": 17.029,
1197
+ "step": 54000
1198
+ },
1199
+ {
1200
+ "epoch": 1.1199390024501825,
1201
+ "grad_norm": 15939.4482421875,
1202
+ "learning_rate": 0.0001132346389774168,
1203
+ "loss": 0.1194,
1204
+ "step": 54500
1205
+ },
1206
+ {
1207
+ "epoch": 1.1370731456573515,
1208
+ "grad_norm": 12881.474609375,
1209
+ "learning_rate": 0.00011152119529831053,
1210
+ "loss": 0.1178,
1211
+ "step": 55000
1212
+ },
1213
+ {
1214
+ "epoch": 1.1370731456573515,
1215
+ "eval_loss": 0.14446598291397095,
1216
+ "eval_runtime": 380.6783,
1217
+ "eval_samples_per_second": 272.558,
1218
+ "eval_steps_per_second": 17.035,
1219
+ "step": 55000
1220
+ },
1221
+ {
1222
+ "epoch": 1.1542072888645203,
1223
+ "grad_norm": 15115.6953125,
1224
+ "learning_rate": 0.00010980775161920425,
1225
+ "loss": 0.1209,
1226
+ "step": 55500
1227
+ },
1228
+ {
1229
+ "epoch": 1.1713414320716893,
1230
+ "grad_norm": 15284.248046875,
1231
+ "learning_rate": 0.00010809430794009801,
1232
+ "loss": 0.1154,
1233
+ "step": 56000
1234
+ },
1235
+ {
1236
+ "epoch": 1.1713414320716893,
1237
+ "eval_loss": 0.14571955800056458,
1238
+ "eval_runtime": 380.447,
1239
+ "eval_samples_per_second": 272.724,
1240
+ "eval_steps_per_second": 17.046,
1241
+ "step": 56000
1242
+ },
1243
+ {
1244
+ "epoch": 1.1884755752788583,
1245
+ "grad_norm": 11027.8671875,
1246
+ "learning_rate": 0.00010638086426099173,
1247
+ "loss": 0.1338,
1248
+ "step": 56500
1249
+ },
1250
+ {
1251
+ "epoch": 1.205609718486027,
1252
+ "grad_norm": 11408.830078125,
1253
+ "learning_rate": 0.00010466742058188547,
1254
+ "loss": 0.1329,
1255
+ "step": 57000
1256
+ },
1257
+ {
1258
+ "epoch": 1.205609718486027,
1259
+ "eval_loss": 0.1407667100429535,
1260
+ "eval_runtime": 380.4069,
1261
+ "eval_samples_per_second": 272.753,
1262
+ "eval_steps_per_second": 17.048,
1263
+ "step": 57000
1264
+ },
1265
+ {
1266
+ "epoch": 1.017134143207169,
1267
+ "grad_norm": 13528.7822265625,
1268
+ "learning_rate": 0.0001029539769027792,
1269
+ "loss": 0.1027,
1270
+ "step": 57500
1271
+ },
1272
+ {
1273
+ "epoch": 1.0342682864143378,
1274
+ "grad_norm": 10699.703125,
1275
+ "learning_rate": 0.00010124053322367293,
1276
+ "loss": 0.1014,
1277
+ "step": 58000
1278
+ },
1279
+ {
1280
+ "epoch": 1.0342682864143378,
1281
+ "eval_loss": 0.15047687292099,
1282
+ "eval_runtime": 381.4985,
1283
+ "eval_samples_per_second": 271.972,
1284
+ "eval_steps_per_second": 16.999,
1285
+ "step": 58000
1286
+ },
1287
+ {
1288
+ "epoch": 1.0514024296215068,
1289
+ "grad_norm": 12470.2578125,
1290
+ "learning_rate": 9.952708954456666e-05,
1291
+ "loss": 0.0997,
1292
+ "step": 58500
1293
+ },
1294
+ {
1295
+ "epoch": 1.0685365728286758,
1296
+ "grad_norm": 12190.787109375,
1297
+ "learning_rate": 9.781364586546039e-05,
1298
+ "loss": 0.0995,
1299
+ "step": 59000
1300
+ },
1301
+ {
1302
+ "epoch": 1.0685365728286758,
1303
+ "eval_loss": 0.1521664261817932,
1304
+ "eval_runtime": 381.0212,
1305
+ "eval_samples_per_second": 272.313,
1306
+ "eval_steps_per_second": 17.02,
1307
+ "step": 59000
1308
+ },
1309
+ {
1310
+ "epoch": 1.0856707160358445,
1311
+ "grad_norm": 24466.048828125,
1312
+ "learning_rate": 9.610020218635413e-05,
1313
+ "loss": 0.1011,
1314
+ "step": 59500
1315
+ },
1316
+ {
1317
+ "epoch": 1.1028048592430135,
1318
+ "grad_norm": 24096.17578125,
1319
+ "learning_rate": 9.438675850724786e-05,
1320
+ "loss": 0.1022,
1321
+ "step": 60000
1322
+ },
1323
+ {
1324
+ "epoch": 1.1028048592430135,
1325
+ "eval_loss": 0.15228863060474396,
1326
+ "eval_runtime": 382.3671,
1327
+ "eval_samples_per_second": 271.354,
1328
+ "eval_steps_per_second": 16.96,
1329
+ "step": 60000
1330
+ },
1331
+ {
1332
+ "epoch": 1.1199390024501825,
1333
+ "grad_norm": 15070.212890625,
1334
+ "learning_rate": 9.267331482814158e-05,
1335
+ "loss": 0.1102,
1336
+ "step": 60500
1337
+ },
1338
+ {
1339
+ "epoch": 1.1370731456573515,
1340
+ "grad_norm": 14697.5048828125,
1341
+ "learning_rate": 9.095987114903532e-05,
1342
+ "loss": 0.1092,
1343
+ "step": 61000
1344
+ },
1345
+ {
1346
+ "epoch": 1.1370731456573515,
1347
+ "eval_loss": 0.1474626064300537,
1348
+ "eval_runtime": 380.495,
1349
+ "eval_samples_per_second": 272.69,
1350
+ "eval_steps_per_second": 17.044,
1351
+ "step": 61000
1352
+ },
1353
+ {
1354
+ "epoch": 1.1542072888645203,
1355
+ "grad_norm": 18294.603515625,
1356
+ "learning_rate": 8.924642746992905e-05,
1357
+ "loss": 0.112,
1358
+ "step": 61500
1359
+ },
1360
+ {
1361
+ "epoch": 1.1713414320716893,
1362
+ "grad_norm": 10764.7861328125,
1363
+ "learning_rate": 8.753298379082277e-05,
1364
+ "loss": 0.1069,
1365
+ "step": 62000
1366
+ },
1367
+ {
1368
+ "epoch": 1.1713414320716893,
1369
+ "eval_loss": 0.14934998750686646,
1370
+ "eval_runtime": 379.9338,
1371
+ "eval_samples_per_second": 273.092,
1372
+ "eval_steps_per_second": 17.069,
1373
+ "step": 62000
1374
+ },
1375
+ {
1376
+ "epoch": 1.1884755752788583,
1377
+ "grad_norm": 11444.263671875,
1378
+ "learning_rate": 8.581954011171653e-05,
1379
+ "loss": 0.1242,
1380
+ "step": 62500
1381
+ },
1382
+ {
1383
+ "epoch": 1.205609718486027,
1384
+ "grad_norm": 12379.88671875,
1385
+ "learning_rate": 8.410609643261025e-05,
1386
+ "loss": 0.1237,
1387
+ "step": 63000
1388
+ },
1389
+ {
1390
+ "epoch": 1.205609718486027,
1391
+ "eval_loss": 0.14393246173858643,
1392
+ "eval_runtime": 379.5264,
1393
+ "eval_samples_per_second": 273.385,
1394
+ "eval_steps_per_second": 17.087,
1395
+ "step": 63000
1396
+ },
1397
+ {
1398
+ "epoch": 1.222743861693196,
1399
+ "grad_norm": 10521.537109375,
1400
+ "learning_rate": 8.239265275350399e-05,
1401
+ "loss": 0.1297,
1402
+ "step": 63500
1403
+ },
1404
+ {
1405
+ "epoch": 1.239878004900365,
1406
+ "grad_norm": 10706.994140625,
1407
+ "learning_rate": 8.067920907439772e-05,
1408
+ "loss": 0.1341,
1409
+ "step": 64000
1410
+ },
1411
+ {
1412
+ "epoch": 1.239878004900365,
1413
+ "eval_loss": 0.14115196466445923,
1414
+ "eval_runtime": 380.0221,
1415
+ "eval_samples_per_second": 273.029,
1416
+ "eval_steps_per_second": 17.065,
1417
+ "step": 64000
1418
+ },
1419
+ {
1420
+ "epoch": 1.2570121481075338,
1421
+ "grad_norm": 10388.8046875,
1422
+ "learning_rate": 7.896576539529146e-05,
1423
+ "loss": 0.1441,
1424
+ "step": 64500
1425
+ },
1426
+ {
1427
+ "epoch": 1.2741462913147028,
1428
+ "grad_norm": 16037.6279296875,
1429
+ "learning_rate": 7.725232171618518e-05,
1430
+ "loss": 0.1443,
1431
+ "step": 65000
1432
+ },
1433
+ {
1434
+ "epoch": 1.2741462913147028,
1435
+ "eval_loss": 0.13837191462516785,
1436
+ "eval_runtime": 382.3765,
1437
+ "eval_samples_per_second": 271.348,
1438
+ "eval_steps_per_second": 16.96,
1439
+ "step": 65000
1440
+ },
1441
+ {
1442
+ "epoch": 2.0171341432071688,
1443
+ "grad_norm": 11637.4296875,
1444
+ "learning_rate": 7.553887803707891e-05,
1445
+ "loss": 0.1419,
1446
+ "step": 65500
1447
+ },
1448
+ {
1449
+ "epoch": 2.034268286414338,
1450
+ "grad_norm": 13926.060546875,
1451
+ "learning_rate": 7.382543435797265e-05,
1452
+ "loss": 0.1388,
1453
+ "step": 66000
1454
+ },
1455
+ {
1456
+ "epoch": 2.034268286414338,
1457
+ "eval_loss": 0.13917547464370728,
1458
+ "eval_runtime": 381.91,
1459
+ "eval_samples_per_second": 271.679,
1460
+ "eval_steps_per_second": 16.98,
1461
+ "step": 66000
1462
+ },
1463
+ {
1464
+ "epoch": 2.0514024296215068,
1465
+ "grad_norm": 15675.0810546875,
1466
+ "learning_rate": 7.211199067886638e-05,
1467
+ "loss": 0.1418,
1468
+ "step": 66500
1469
+ },
1470
+ {
1471
+ "epoch": 2.0685365728286755,
1472
+ "grad_norm": 12723.23828125,
1473
+ "learning_rate": 7.03985469997601e-05,
1474
+ "loss": 0.1434,
1475
+ "step": 67000
1476
+ },
1477
+ {
1478
+ "epoch": 2.0685365728286755,
1479
+ "eval_loss": 0.1389508992433548,
1480
+ "eval_runtime": 383.0763,
1481
+ "eval_samples_per_second": 270.852,
1482
+ "eval_steps_per_second": 16.929,
1483
+ "step": 67000
1484
+ },
1485
+ {
1486
+ "epoch": 2.0171341432071688,
1487
+ "grad_norm": 11802.2138671875,
1488
+ "learning_rate": 6.868510332065384e-05,
1489
+ "loss": 0.132,
1490
+ "step": 67500
1491
+ },
1492
+ {
1493
+ "epoch": 2.034268286414338,
1494
+ "grad_norm": 10293.4375,
1495
+ "learning_rate": 6.697165964154758e-05,
1496
+ "loss": 0.1289,
1497
+ "step": 68000
1498
+ },
1499
+ {
1500
+ "epoch": 2.034268286414338,
1501
+ "eval_loss": 0.1404309868812561,
1502
+ "eval_runtime": 381.6827,
1503
+ "eval_samples_per_second": 271.841,
1504
+ "eval_steps_per_second": 16.991,
1505
+ "step": 68000
1506
+ },
1507
+ {
1508
+ "epoch": 2.0514024296215068,
1509
+ "grad_norm": 13533.08203125,
1510
+ "learning_rate": 6.525821596244131e-05,
1511
+ "loss": 0.1321,
1512
+ "step": 68500
1513
+ },
1514
+ {
1515
+ "epoch": 2.0685365728286755,
1516
+ "grad_norm": 13180.3115234375,
1517
+ "learning_rate": 6.354477228333505e-05,
1518
+ "loss": 0.1346,
1519
+ "step": 69000
1520
+ },
1521
+ {
1522
+ "epoch": 2.0685365728286755,
1523
+ "eval_loss": 0.14006280899047852,
1524
+ "eval_runtime": 381.5656,
1525
+ "eval_samples_per_second": 271.924,
1526
+ "eval_steps_per_second": 16.996,
1527
+ "step": 69000
1528
+ },
1529
+ {
1530
+ "epoch": 2.0856707160358448,
1531
+ "grad_norm": 11419.6455078125,
1532
+ "learning_rate": 6.183132860422877e-05,
1533
+ "loss": 0.1372,
1534
+ "step": 69500
1535
+ },
1536
+ {
1537
+ "epoch": 2.1028048592430135,
1538
+ "grad_norm": 17743.39453125,
1539
+ "learning_rate": 6.0117884925122506e-05,
1540
+ "loss": 0.1417,
1541
+ "step": 70000
1542
+ },
1543
+ {
1544
+ "epoch": 2.1028048592430135,
1545
+ "eval_loss": 0.1381361186504364,
1546
+ "eval_runtime": 381.5041,
1547
+ "eval_samples_per_second": 271.968,
1548
+ "eval_steps_per_second": 16.999,
1549
+ "step": 70000
1550
+ },
1551
+ {
1552
+ "epoch": 2.1199390024501823,
1553
+ "grad_norm": 14155.6220703125,
1554
+ "learning_rate": 5.840444124601623e-05,
1555
+ "loss": 0.1377,
1556
+ "step": 70500
1557
+ },
1558
+ {
1559
+ "epoch": 2.1370731456573515,
1560
+ "grad_norm": 11799.7041015625,
1561
+ "learning_rate": 5.669099756690997e-05,
1562
+ "loss": 0.1372,
1563
+ "step": 71000
1564
+ },
1565
+ {
1566
+ "epoch": 2.1370731456573515,
1567
+ "eval_loss": 0.13801340758800507,
1568
+ "eval_runtime": 380.8925,
1569
+ "eval_samples_per_second": 272.405,
1570
+ "eval_steps_per_second": 17.026,
1571
+ "step": 71000
1572
+ },
1573
+ {
1574
+ "epoch": 2.0171341432071688,
1575
+ "grad_norm": 0.17098644375801086,
1576
+ "learning_rate": 5.4977553887803704e-05,
1577
+ "loss": 0.1344,
1578
+ "step": 71500
1579
+ },
1580
+ {
1581
+ "epoch": 2.034268286414338,
1582
+ "grad_norm": 0.14380662143230438,
1583
+ "learning_rate": 5.326411020869744e-05,
1584
+ "loss": 0.1309,
1585
+ "step": 72000
1586
+ },
1587
+ {
1588
+ "epoch": 2.034268286414338,
1589
+ "eval_loss": 0.13835684955120087,
1590
+ "eval_runtime": 272.8156,
1591
+ "eval_samples_per_second": 380.319,
1592
+ "eval_steps_per_second": 47.541,
1593
+ "step": 72000
1594
+ },
1595
+ {
1596
+ "epoch": 2.0514024296215068,
1597
+ "grad_norm": 0.2219686359167099,
1598
+ "learning_rate": 5.155066652959117e-05,
1599
+ "loss": 0.1341,
1600
+ "step": 72500
1601
+ },
1602
+ {
1603
+ "epoch": 2.0685365728286755,
1604
+ "grad_norm": 0.17280732095241547,
1605
+ "learning_rate": 4.9837222850484896e-05,
1606
+ "loss": 0.1364,
1607
+ "step": 73000
1608
+ },
1609
+ {
1610
+ "epoch": 2.0685365728286755,
1611
+ "eval_loss": 0.13844849169254303,
1612
+ "eval_runtime": 272.3757,
1613
+ "eval_samples_per_second": 380.933,
1614
+ "eval_steps_per_second": 47.618,
1615
+ "step": 73000
1616
+ },
1617
+ {
1618
+ "epoch": 2.0856707160358448,
1619
+ "grad_norm": 0.18860286474227905,
1620
+ "learning_rate": 4.812377917137863e-05,
1621
+ "loss": 0.1327,
1622
+ "step": 73500
1623
+ },
1624
+ {
1625
+ "epoch": 2.1028048592430135,
1626
+ "grad_norm": 0.20777860283851624,
1627
+ "learning_rate": 4.641033549227237e-05,
1628
+ "loss": 0.1376,
1629
+ "step": 74000
1630
+ },
1631
+ {
1632
+ "epoch": 2.1028048592430135,
1633
+ "eval_loss": 0.13777725398540497,
1634
+ "eval_runtime": 274.843,
1635
+ "eval_samples_per_second": 377.514,
1636
+ "eval_steps_per_second": 47.191,
1637
+ "step": 74000
1638
+ },
1639
+ {
1640
+ "epoch": 2.1199390024501823,
1641
+ "grad_norm": 0.15439967811107635,
1642
+ "learning_rate": 4.46968918131661e-05,
1643
+ "loss": 0.1339,
1644
+ "step": 74500
1645
+ },
1646
+ {
1647
+ "epoch": 2.1370731456573515,
1648
+ "grad_norm": 0.1989327371120453,
1649
+ "learning_rate": 4.2983448134059834e-05,
1650
+ "loss": 0.1339,
1651
+ "step": 75000
1652
+ },
1653
+ {
1654
+ "epoch": 2.1370731456573515,
1655
+ "eval_loss": 0.1380227655172348,
1656
+ "eval_runtime": 272.0295,
1657
+ "eval_samples_per_second": 381.418,
1658
+ "eval_steps_per_second": 47.679,
1659
+ "step": 75000
1660
+ },
1661
+ {
1662
+ "epoch": 2.1542072888645203,
1663
+ "grad_norm": 0.21188005805015564,
1664
+ "learning_rate": 4.127000445495356e-05,
1665
+ "loss": 0.1429,
1666
+ "step": 75500
1667
+ },
1668
+ {
1669
+ "epoch": 2.171341432071689,
1670
+ "grad_norm": 0.24548035860061646,
1671
+ "learning_rate": 3.955656077584729e-05,
1672
+ "loss": 0.1371,
1673
+ "step": 76000
1674
+ },
1675
+ {
1676
+ "epoch": 2.171341432071689,
1677
+ "eval_loss": 0.1369466930627823,
1678
+ "eval_runtime": 269.5383,
1679
+ "eval_samples_per_second": 384.943,
1680
+ "eval_steps_per_second": 48.119,
1681
+ "step": 76000
1682
+ },
1683
+ {
1684
+ "epoch": 2.1884755752788583,
1685
+ "grad_norm": 0.20731587707996368,
1686
+ "learning_rate": 3.7843117096741026e-05,
1687
+ "loss": 0.1425,
1688
+ "step": 76500
1689
+ },
1690
+ {
1691
+ "epoch": 2.205609718486027,
1692
+ "grad_norm": 0.2300683856010437,
1693
+ "learning_rate": 3.612967341763476e-05,
1694
+ "loss": 0.1404,
1695
+ "step": 77000
1696
+ },
1697
+ {
1698
+ "epoch": 2.205609718486027,
1699
+ "eval_loss": 0.13709671795368195,
1700
+ "eval_runtime": 272.2809,
1701
+ "eval_samples_per_second": 381.066,
1702
+ "eval_steps_per_second": 47.635,
1703
+ "step": 77000
1704
+ },
1705
+ {
1706
+ "epoch": 2.2227438616931963,
1707
+ "grad_norm": 0.26204827427864075,
1708
+ "learning_rate": 3.4419656625886704e-05,
1709
+ "loss": 0.1373,
1710
+ "step": 77500
1711
+ },
1712
+ {
1713
+ "epoch": 2.239878004900365,
1714
+ "grad_norm": 0.14697732031345367,
1715
+ "learning_rate": 3.2706212946780436e-05,
1716
+ "loss": 0.1405,
1717
+ "step": 78000
1718
+ },
1719
+ {
1720
+ "epoch": 2.239878004900365,
1721
+ "eval_loss": 0.13714557886123657,
1722
+ "eval_runtime": 270.2729,
1723
+ "eval_samples_per_second": 383.897,
1724
+ "eval_steps_per_second": 47.989,
1725
+ "step": 78000
1726
+ },
1727
+ {
1728
+ "epoch": 2.257012148107534,
1729
+ "grad_norm": 0.16794049739837646,
1730
+ "learning_rate": 3.099276926767417e-05,
1731
+ "loss": 0.1387,
1732
+ "step": 78500
1733
+ },
1734
+ {
1735
+ "epoch": 2.274146291314703,
1736
+ "grad_norm": 0.16319075226783752,
1737
+ "learning_rate": 2.92793255885679e-05,
1738
+ "loss": 0.1369,
1739
+ "step": 79000
1740
+ },
1741
+ {
1742
+ "epoch": 2.274146291314703,
1743
+ "eval_loss": 0.13730229437351227,
1744
+ "eval_runtime": 270.4432,
1745
+ "eval_samples_per_second": 383.655,
1746
+ "eval_steps_per_second": 47.958,
1747
+ "step": 79000
1748
+ },
1749
+ {
1750
+ "epoch": 2.291280434521872,
1751
+ "grad_norm": 0.15751433372497559,
1752
+ "learning_rate": 2.7569308796819847e-05,
1753
+ "loss": 0.1407,
1754
+ "step": 79500
1755
+ },
1756
+ {
1757
+ "epoch": 2.3084145777290406,
1758
+ "grad_norm": 0.13309995830059052,
1759
+ "learning_rate": 2.5855865117713577e-05,
1760
+ "loss": 0.1371,
1761
+ "step": 80000
1762
+ },
1763
+ {
1764
+ "epoch": 2.3084145777290406,
1765
+ "eval_loss": 0.1367003172636032,
1766
+ "eval_runtime": 268.2067,
1767
+ "eval_samples_per_second": 386.855,
1768
+ "eval_steps_per_second": 48.358,
1769
+ "step": 80000
1770
+ },
1771
+ {
1772
+ "epoch": 2.32554872093621,
1773
+ "grad_norm": 0.17803920805454254,
1774
+ "learning_rate": 2.4142421438607313e-05,
1775
+ "loss": 0.1372,
1776
+ "step": 80500
1777
+ },
1778
+ {
1779
+ "epoch": 2.3426828641433786,
1780
+ "grad_norm": 0.16504187881946564,
1781
+ "learning_rate": 2.2432404646859255e-05,
1782
+ "loss": 0.1393,
1783
+ "step": 81000
1784
+ },
1785
+ {
1786
+ "epoch": 2.3426828641433786,
1787
+ "eval_loss": 0.1365227848291397,
1788
+ "eval_runtime": 268.8503,
1789
+ "eval_samples_per_second": 385.929,
1790
+ "eval_steps_per_second": 48.242,
1791
+ "step": 81000
1792
+ },
1793
+ {
1794
+ "epoch": 2.3598170073505473,
1795
+ "grad_norm": 0.21156391501426697,
1796
+ "learning_rate": 2.071896096775299e-05,
1797
+ "loss": 0.1419,
1798
+ "step": 81500
1799
+ },
1800
+ {
1801
+ "epoch": 2.3769511505577166,
1802
+ "grad_norm": 0.17416013777256012,
1803
+ "learning_rate": 1.900551728864672e-05,
1804
+ "loss": 0.1415,
1805
+ "step": 82000
1806
+ },
1807
+ {
1808
+ "epoch": 2.3769511505577166,
1809
+ "eval_loss": 0.13638699054718018,
1810
+ "eval_runtime": 274.8999,
1811
+ "eval_samples_per_second": 377.436,
1812
+ "eval_steps_per_second": 47.181,
1813
+ "step": 82000
1814
+ },
1815
+ {
1816
+ "epoch": 2.3940852937648853,
1817
+ "grad_norm": 0.17176955938339233,
1818
+ "learning_rate": 1.7292073609540453e-05,
1819
+ "loss": 0.1376,
1820
+ "step": 82500
1821
+ },
1822
+ {
1823
+ "epoch": 2.411219436972054,
1824
+ "grad_norm": 0.20921428501605988,
1825
+ "learning_rate": 1.5578629930434186e-05,
1826
+ "loss": 0.1391,
1827
+ "step": 83000
1828
+ },
1829
+ {
1830
+ "epoch": 2.411219436972054,
1831
+ "eval_loss": 0.13643188774585724,
1832
+ "eval_runtime": 273.5289,
1833
+ "eval_samples_per_second": 379.327,
1834
+ "eval_steps_per_second": 47.417,
1835
+ "step": 83000
1836
+ },
1837
+ {
1838
+ "epoch": 2.4283535801792233,
1839
+ "grad_norm": 0.13489414751529694,
1840
+ "learning_rate": 1.386861313868613e-05,
1841
+ "loss": 0.1392,
1842
+ "step": 83500
1843
+ },
1844
+ {
1845
+ "epoch": 2.445487723386392,
1846
+ "grad_norm": 0.12483478337526321,
1847
+ "learning_rate": 1.2155169459579864e-05,
1848
+ "loss": 0.1385,
1849
+ "step": 84000
1850
+ },
1851
+ {
1852
+ "epoch": 2.445487723386392,
1853
+ "eval_loss": 0.13661223649978638,
1854
+ "eval_runtime": 275.9186,
1855
+ "eval_samples_per_second": 376.042,
1856
+ "eval_steps_per_second": 47.007,
1857
+ "step": 84000
1858
+ },
1859
+ {
1860
+ "epoch": 2.462621866593561,
1861
+ "grad_norm": 0.18394802510738373,
1862
+ "learning_rate": 1.0441725780473595e-05,
1863
+ "loss": 0.1366,
1864
+ "step": 84500
1865
+ },
1866
+ {
1867
+ "epoch": 2.47975600980073,
1868
+ "grad_norm": 0.22474822402000427,
1869
+ "learning_rate": 8.728282101367328e-06,
1870
+ "loss": 0.1392,
1871
+ "step": 85000
1872
+ },
1873
+ {
1874
+ "epoch": 2.47975600980073,
1875
+ "eval_loss": 0.13656428456306458,
1876
+ "eval_runtime": 278.8741,
1877
+ "eval_samples_per_second": 372.057,
1878
+ "eval_steps_per_second": 46.508,
1879
+ "step": 85000
1880
+ },
1881
+ {
1882
+ "epoch": 2.496890153007899,
1883
+ "grad_norm": 0.16141566634178162,
1884
+ "learning_rate": 7.01483842226106e-06,
1885
+ "loss": 0.1381,
1886
+ "step": 85500
1887
+ },
1888
+ {
1889
+ "epoch": 2.5140242962150676,
1890
+ "grad_norm": 0.15223611891269684,
1891
+ "learning_rate": 5.301394743154792e-06,
1892
+ "loss": 0.1396,
1893
+ "step": 86000
1894
+ },
1895
+ {
1896
+ "epoch": 2.5140242962150676,
1897
+ "eval_loss": 0.13632681965827942,
1898
+ "eval_runtime": 273.1354,
1899
+ "eval_samples_per_second": 379.874,
1900
+ "eval_steps_per_second": 47.486,
1901
+ "step": 86000
1902
+ },
1903
+ {
1904
+ "epoch": 2.531158439422237,
1905
+ "grad_norm": 0.17016838490962982,
1906
+ "learning_rate": 3.587951064048524e-06,
1907
+ "loss": 0.1391,
1908
+ "step": 86500
1909
+ },
1910
+ {
1911
+ "epoch": 2.5482925826294056,
1912
+ "grad_norm": 0.17201977968215942,
1913
+ "learning_rate": 1.8745073849422567e-06,
1914
+ "loss": 0.1402,
1915
+ "step": 87000
1916
+ },
1917
+ {
1918
+ "epoch": 2.5482925826294056,
1919
+ "eval_loss": 0.13630929589271545,
1920
+ "eval_runtime": 272.9589,
1921
+ "eval_samples_per_second": 380.12,
1922
+ "eval_steps_per_second": 47.516,
1923
+ "step": 87000
1924
+ }
1925
+ ],
1926
+ "logging_steps": 500,
1927
+ "max_steps": 87543,
1928
+ "num_input_tokens_seen": 0,
1929
+ "num_train_epochs": 3,
1930
+ "save_steps": 1000,
1931
+ "stateful_callbacks": {
1932
+ "TrainerControl": {
1933
+ "args": {
1934
+ "should_epoch_stop": false,
1935
+ "should_evaluate": false,
1936
+ "should_log": false,
1937
+ "should_save": true,
1938
+ "should_training_stop": false
1939
+ },
1940
+ "attributes": {}
1941
+ }
1942
+ },
1943
+ "total_flos": 4.73198247322583e+16,
1944
+ "train_batch_size": 8,
1945
+ "trial_name": null,
1946
+ "trial_params": null
1947
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba40c184e5cab8aa57f4ae275aaedef8774a65c2675503457b3ad5c182ed09e9
3
+ size 5112