mateiaassAI commited on
Commit
ca08fcb
·
verified ·
1 Parent(s): ca3f8a5

Upload 12 files

Browse files
.gitattributes CHANGED
@@ -1 +1,4 @@
1
  T5Large-8e5-8-checkpoint.zip filter=lfs diff=lfs merge=lfs -text
 
 
 
 
1
  T5Large-8e5-8-checkpoint.zip filter=lfs diff=lfs merge=lfs -text
2
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
3
+ optimizer.pt filter=lfs diff=lfs merge=lfs -text
4
+ spiece.model filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 64099,
3
+ "<extra_id_10>": 64089,
4
+ "<extra_id_11>": 64088,
5
+ "<extra_id_12>": 64087,
6
+ "<extra_id_13>": 64086,
7
+ "<extra_id_14>": 64085,
8
+ "<extra_id_15>": 64084,
9
+ "<extra_id_16>": 64083,
10
+ "<extra_id_17>": 64082,
11
+ "<extra_id_18>": 64081,
12
+ "<extra_id_19>": 64080,
13
+ "<extra_id_1>": 64098,
14
+ "<extra_id_20>": 64079,
15
+ "<extra_id_21>": 64078,
16
+ "<extra_id_22>": 64077,
17
+ "<extra_id_23>": 64076,
18
+ "<extra_id_24>": 64075,
19
+ "<extra_id_25>": 64074,
20
+ "<extra_id_26>": 64073,
21
+ "<extra_id_27>": 64072,
22
+ "<extra_id_28>": 64071,
23
+ "<extra_id_29>": 64070,
24
+ "<extra_id_2>": 64097,
25
+ "<extra_id_30>": 64069,
26
+ "<extra_id_31>": 64068,
27
+ "<extra_id_32>": 64067,
28
+ "<extra_id_33>": 64066,
29
+ "<extra_id_34>": 64065,
30
+ "<extra_id_35>": 64064,
31
+ "<extra_id_36>": 64063,
32
+ "<extra_id_37>": 64062,
33
+ "<extra_id_38>": 64061,
34
+ "<extra_id_39>": 64060,
35
+ "<extra_id_3>": 64096,
36
+ "<extra_id_40>": 64059,
37
+ "<extra_id_41>": 64058,
38
+ "<extra_id_42>": 64057,
39
+ "<extra_id_43>": 64056,
40
+ "<extra_id_44>": 64055,
41
+ "<extra_id_45>": 64054,
42
+ "<extra_id_46>": 64053,
43
+ "<extra_id_47>": 64052,
44
+ "<extra_id_48>": 64051,
45
+ "<extra_id_49>": 64050,
46
+ "<extra_id_4>": 64095,
47
+ "<extra_id_50>": 64049,
48
+ "<extra_id_51>": 64048,
49
+ "<extra_id_52>": 64047,
50
+ "<extra_id_53>": 64046,
51
+ "<extra_id_54>": 64045,
52
+ "<extra_id_55>": 64044,
53
+ "<extra_id_56>": 64043,
54
+ "<extra_id_57>": 64042,
55
+ "<extra_id_58>": 64041,
56
+ "<extra_id_59>": 64040,
57
+ "<extra_id_5>": 64094,
58
+ "<extra_id_60>": 64039,
59
+ "<extra_id_61>": 64038,
60
+ "<extra_id_62>": 64037,
61
+ "<extra_id_63>": 64036,
62
+ "<extra_id_64>": 64035,
63
+ "<extra_id_65>": 64034,
64
+ "<extra_id_66>": 64033,
65
+ "<extra_id_67>": 64032,
66
+ "<extra_id_68>": 64031,
67
+ "<extra_id_69>": 64030,
68
+ "<extra_id_6>": 64093,
69
+ "<extra_id_70>": 64029,
70
+ "<extra_id_71>": 64028,
71
+ "<extra_id_72>": 64027,
72
+ "<extra_id_73>": 64026,
73
+ "<extra_id_74>": 64025,
74
+ "<extra_id_75>": 64024,
75
+ "<extra_id_76>": 64023,
76
+ "<extra_id_77>": 64022,
77
+ "<extra_id_78>": 64021,
78
+ "<extra_id_79>": 64020,
79
+ "<extra_id_7>": 64092,
80
+ "<extra_id_80>": 64019,
81
+ "<extra_id_81>": 64018,
82
+ "<extra_id_82>": 64017,
83
+ "<extra_id_83>": 64016,
84
+ "<extra_id_84>": 64015,
85
+ "<extra_id_85>": 64014,
86
+ "<extra_id_86>": 64013,
87
+ "<extra_id_87>": 64012,
88
+ "<extra_id_88>": 64011,
89
+ "<extra_id_89>": 64010,
90
+ "<extra_id_8>": 64091,
91
+ "<extra_id_90>": 64009,
92
+ "<extra_id_91>": 64008,
93
+ "<extra_id_92>": 64007,
94
+ "<extra_id_93>": 64006,
95
+ "<extra_id_94>": 64005,
96
+ "<extra_id_95>": 64004,
97
+ "<extra_id_96>": 64003,
98
+ "<extra_id_97>": 64002,
99
+ "<extra_id_98>": 64001,
100
+ "<extra_id_99>": 64000,
101
+ "<extra_id_9>": 64090,
102
+ "<pad>": 64100
103
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dumitrescustefan/t5-v1_1-large-romanian",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.2,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.2",
31
+ "use_cache": true,
32
+ "vocab_size": 64101
33
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "max_new_tokens": 512,
6
+ "min_new_tokens": 0,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.45.2"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa6cb39e264d2312b3768294a5f939dd421ee3884d5e20b2472cbb6e3095e72
3
+ size 3394591624
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c9683c80987d9a0727227d49558958389ebfc64612c268ccabc525b9648df6
3
+ size 6789524884
rng_state.pth ADDED
Binary file (14.2 kB). View file
 
scheduler.pt ADDED
Binary file (1.06 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b0c94f9d6e9e75161a1365e73132f35666ab675de0d5ae10ec9f6f5eacda09
3
+ size 1457188
tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "2": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "64000": {
21
+ "content": "<extra_id_99>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "64001": {
29
+ "content": "<extra_id_98>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "64002": {
37
+ "content": "<extra_id_97>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "64003": {
45
+ "content": "<extra_id_96>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "64004": {
53
+ "content": "<extra_id_95>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "64005": {
61
+ "content": "<extra_id_94>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "64006": {
69
+ "content": "<extra_id_93>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "64007": {
77
+ "content": "<extra_id_92>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "64008": {
85
+ "content": "<extra_id_91>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "64009": {
93
+ "content": "<extra_id_90>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "64010": {
101
+ "content": "<extra_id_89>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "64011": {
109
+ "content": "<extra_id_88>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "64012": {
117
+ "content": "<extra_id_87>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "64013": {
125
+ "content": "<extra_id_86>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "64014": {
133
+ "content": "<extra_id_85>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "64015": {
141
+ "content": "<extra_id_84>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "64016": {
149
+ "content": "<extra_id_83>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "64017": {
157
+ "content": "<extra_id_82>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "64018": {
165
+ "content": "<extra_id_81>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "64019": {
173
+ "content": "<extra_id_80>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "64020": {
181
+ "content": "<extra_id_79>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "64021": {
189
+ "content": "<extra_id_78>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "64022": {
197
+ "content": "<extra_id_77>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "64023": {
205
+ "content": "<extra_id_76>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "64024": {
213
+ "content": "<extra_id_75>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "64025": {
221
+ "content": "<extra_id_74>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "64026": {
229
+ "content": "<extra_id_73>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "64027": {
237
+ "content": "<extra_id_72>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "64028": {
245
+ "content": "<extra_id_71>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "64029": {
253
+ "content": "<extra_id_70>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "64030": {
261
+ "content": "<extra_id_69>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "64031": {
269
+ "content": "<extra_id_68>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "64032": {
277
+ "content": "<extra_id_67>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "64033": {
285
+ "content": "<extra_id_66>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "64034": {
293
+ "content": "<extra_id_65>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "64035": {
301
+ "content": "<extra_id_64>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "64036": {
309
+ "content": "<extra_id_63>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "64037": {
317
+ "content": "<extra_id_62>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "64038": {
325
+ "content": "<extra_id_61>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "64039": {
333
+ "content": "<extra_id_60>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "64040": {
341
+ "content": "<extra_id_59>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "64041": {
349
+ "content": "<extra_id_58>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "64042": {
357
+ "content": "<extra_id_57>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "64043": {
365
+ "content": "<extra_id_56>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "64044": {
373
+ "content": "<extra_id_55>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "64045": {
381
+ "content": "<extra_id_54>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "64046": {
389
+ "content": "<extra_id_53>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "64047": {
397
+ "content": "<extra_id_52>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "64048": {
405
+ "content": "<extra_id_51>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "64049": {
413
+ "content": "<extra_id_50>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "64050": {
421
+ "content": "<extra_id_49>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "64051": {
429
+ "content": "<extra_id_48>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "64052": {
437
+ "content": "<extra_id_47>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "64053": {
445
+ "content": "<extra_id_46>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "64054": {
453
+ "content": "<extra_id_45>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "64055": {
461
+ "content": "<extra_id_44>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "64056": {
469
+ "content": "<extra_id_43>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "64057": {
477
+ "content": "<extra_id_42>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "64058": {
485
+ "content": "<extra_id_41>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "64059": {
493
+ "content": "<extra_id_40>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "64060": {
501
+ "content": "<extra_id_39>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "64061": {
509
+ "content": "<extra_id_38>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "64062": {
517
+ "content": "<extra_id_37>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "64063": {
525
+ "content": "<extra_id_36>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "64064": {
533
+ "content": "<extra_id_35>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "64065": {
541
+ "content": "<extra_id_34>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "64066": {
549
+ "content": "<extra_id_33>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "64067": {
557
+ "content": "<extra_id_32>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "64068": {
565
+ "content": "<extra_id_31>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "64069": {
573
+ "content": "<extra_id_30>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "64070": {
581
+ "content": "<extra_id_29>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "64071": {
589
+ "content": "<extra_id_28>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "64072": {
597
+ "content": "<extra_id_27>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "64073": {
605
+ "content": "<extra_id_26>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "64074": {
613
+ "content": "<extra_id_25>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "64075": {
621
+ "content": "<extra_id_24>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "64076": {
629
+ "content": "<extra_id_23>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "64077": {
637
+ "content": "<extra_id_22>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "64078": {
645
+ "content": "<extra_id_21>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "64079": {
653
+ "content": "<extra_id_20>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "64080": {
661
+ "content": "<extra_id_19>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "64081": {
669
+ "content": "<extra_id_18>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "64082": {
677
+ "content": "<extra_id_17>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "64083": {
685
+ "content": "<extra_id_16>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "64084": {
693
+ "content": "<extra_id_15>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "64085": {
701
+ "content": "<extra_id_14>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "64086": {
709
+ "content": "<extra_id_13>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "64087": {
717
+ "content": "<extra_id_12>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "64088": {
725
+ "content": "<extra_id_11>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "64089": {
733
+ "content": "<extra_id_10>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "64090": {
741
+ "content": "<extra_id_9>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "64091": {
749
+ "content": "<extra_id_8>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "64092": {
757
+ "content": "<extra_id_7>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "64093": {
765
+ "content": "<extra_id_6>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "64094": {
773
+ "content": "<extra_id_5>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "64095": {
781
+ "content": "<extra_id_4>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "64096": {
789
+ "content": "<extra_id_3>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "64097": {
797
+ "content": "<extra_id_2>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "64098": {
805
+ "content": "<extra_id_1>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "64099": {
813
+ "content": "<extra_id_0>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "64100": {
821
+ "content": "<pad>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 1000000000000000019884624838656,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
trainer_state.json ADDED
@@ -0,0 +1,1497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.4,
5
+ "eval_steps": 12500,
6
+ "global_step": 100000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.032,
13
+ "grad_norm": 3.001525402069092,
14
+ "learning_rate": 8e-05,
15
+ "loss": 13.1617,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.064,
20
+ "grad_norm": 0.5208349227905273,
21
+ "learning_rate": 7.967871485943775e-05,
22
+ "loss": 1.4028,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.096,
27
+ "grad_norm": 0.43057793378829956,
28
+ "learning_rate": 7.93574297188755e-05,
29
+ "loss": 1.0426,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.128,
34
+ "grad_norm": 0.53807532787323,
35
+ "learning_rate": 7.903614457831325e-05,
36
+ "loss": 0.8407,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.16,
41
+ "grad_norm": 0.7076811194419861,
42
+ "learning_rate": 7.8714859437751e-05,
43
+ "loss": 0.7035,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.192,
48
+ "grad_norm": 0.5321575999259949,
49
+ "learning_rate": 7.839357429718876e-05,
50
+ "loss": 0.4479,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.224,
55
+ "grad_norm": 0.5099969506263733,
56
+ "learning_rate": 7.807228915662652e-05,
57
+ "loss": 0.4085,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.256,
62
+ "grad_norm": 0.3821808099746704,
63
+ "learning_rate": 7.775100401606426e-05,
64
+ "loss": 0.3811,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.288,
69
+ "grad_norm": 0.45157989859580994,
70
+ "learning_rate": 7.742971887550202e-05,
71
+ "loss": 0.3604,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.32,
76
+ "grad_norm": 0.3053194582462311,
77
+ "learning_rate": 7.710843373493976e-05,
78
+ "loss": 0.3442,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.352,
83
+ "grad_norm": 0.45309627056121826,
84
+ "learning_rate": 7.678714859437751e-05,
85
+ "loss": 0.3308,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.384,
90
+ "grad_norm": 0.40403613448143005,
91
+ "learning_rate": 7.646586345381526e-05,
92
+ "loss": 0.3254,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.416,
97
+ "grad_norm": 0.32140398025512695,
98
+ "learning_rate": 7.614457831325302e-05,
99
+ "loss": 0.3142,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.448,
104
+ "grad_norm": 0.36259984970092773,
105
+ "learning_rate": 7.582329317269078e-05,
106
+ "loss": 0.304,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.48,
111
+ "grad_norm": 27.76270294189453,
112
+ "learning_rate": 7.550200803212852e-05,
113
+ "loss": 0.7921,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.512,
118
+ "grad_norm": 0.35605108737945557,
119
+ "learning_rate": 7.518072289156628e-05,
120
+ "loss": 0.4819,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.544,
125
+ "grad_norm": 0.29919707775115967,
126
+ "learning_rate": 7.485943775100402e-05,
127
+ "loss": 0.2955,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.576,
132
+ "grad_norm": 0.27910181879997253,
133
+ "learning_rate": 7.453815261044178e-05,
134
+ "loss": 0.2891,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.608,
139
+ "grad_norm": 0.3084375858306885,
140
+ "learning_rate": 7.421686746987952e-05,
141
+ "loss": 0.2839,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.64,
146
+ "grad_norm": 1.0127158164978027,
147
+ "learning_rate": 7.389558232931728e-05,
148
+ "loss": 0.2975,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.672,
153
+ "grad_norm": 0.29704657196998596,
154
+ "learning_rate": 7.357429718875502e-05,
155
+ "loss": 0.2784,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.704,
160
+ "grad_norm": 0.26352909207344055,
161
+ "learning_rate": 7.325301204819278e-05,
162
+ "loss": 0.2722,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.736,
167
+ "grad_norm": 0.3012610077857971,
168
+ "learning_rate": 7.293172690763053e-05,
169
+ "loss": 0.2671,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.768,
174
+ "grad_norm": 239.10655212402344,
175
+ "learning_rate": 7.261044176706828e-05,
176
+ "loss": 0.268,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.8,
181
+ "grad_norm": 0.2739589214324951,
182
+ "learning_rate": 7.228915662650603e-05,
183
+ "loss": 0.2758,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.8,
188
+ "eval_loss": 0.1865103393793106,
189
+ "eval_runtime": 13.4887,
190
+ "eval_samples_per_second": 148.272,
191
+ "eval_steps_per_second": 6.227,
192
+ "step": 12500
193
+ },
194
+ {
195
+ "epoch": 0.832,
196
+ "grad_norm": 0.3086440861225128,
197
+ "learning_rate": 7.196787148594378e-05,
198
+ "loss": 0.258,
199
+ "step": 13000
200
+ },
201
+ {
202
+ "epoch": 0.864,
203
+ "grad_norm": 0.25051313638687134,
204
+ "learning_rate": 7.164658634538153e-05,
205
+ "loss": 0.255,
206
+ "step": 13500
207
+ },
208
+ {
209
+ "epoch": 0.896,
210
+ "grad_norm": 0.2483261674642563,
211
+ "learning_rate": 7.132530120481928e-05,
212
+ "loss": 0.2505,
213
+ "step": 14000
214
+ },
215
+ {
216
+ "epoch": 0.928,
217
+ "grad_norm": 0.2732410728931427,
218
+ "learning_rate": 7.100401606425703e-05,
219
+ "loss": 0.2456,
220
+ "step": 14500
221
+ },
222
+ {
223
+ "epoch": 0.96,
224
+ "grad_norm": 0.2605254054069519,
225
+ "learning_rate": 7.068273092369479e-05,
226
+ "loss": 0.2487,
227
+ "step": 15000
228
+ },
229
+ {
230
+ "epoch": 0.992,
231
+ "grad_norm": 0.294114887714386,
232
+ "learning_rate": 7.036144578313253e-05,
233
+ "loss": 0.2448,
234
+ "step": 15500
235
+ },
236
+ {
237
+ "epoch": 1.024,
238
+ "grad_norm": 0.27836671471595764,
239
+ "learning_rate": 7.004016064257029e-05,
240
+ "loss": 0.2342,
241
+ "step": 16000
242
+ },
243
+ {
244
+ "epoch": 1.056,
245
+ "grad_norm": 0.2619302272796631,
246
+ "learning_rate": 6.971887550200803e-05,
247
+ "loss": 0.2282,
248
+ "step": 16500
249
+ },
250
+ {
251
+ "epoch": 1.088,
252
+ "grad_norm": 0.2845689058303833,
253
+ "learning_rate": 6.939759036144579e-05,
254
+ "loss": 0.2254,
255
+ "step": 17000
256
+ },
257
+ {
258
+ "epoch": 1.12,
259
+ "grad_norm": 0.3349343538284302,
260
+ "learning_rate": 6.907630522088353e-05,
261
+ "loss": 0.2226,
262
+ "step": 17500
263
+ },
264
+ {
265
+ "epoch": 1.152,
266
+ "grad_norm": 0.293632835149765,
267
+ "learning_rate": 6.875502008032129e-05,
268
+ "loss": 0.2195,
269
+ "step": 18000
270
+ },
271
+ {
272
+ "epoch": 1.184,
273
+ "grad_norm": 0.2546076476573944,
274
+ "learning_rate": 6.843373493975903e-05,
275
+ "loss": 0.2212,
276
+ "step": 18500
277
+ },
278
+ {
279
+ "epoch": 1.216,
280
+ "grad_norm": 0.25859034061431885,
281
+ "learning_rate": 6.811244979919679e-05,
282
+ "loss": 0.2197,
283
+ "step": 19000
284
+ },
285
+ {
286
+ "epoch": 1.248,
287
+ "grad_norm": 0.25642773509025574,
288
+ "learning_rate": 6.779116465863455e-05,
289
+ "loss": 0.2167,
290
+ "step": 19500
291
+ },
292
+ {
293
+ "epoch": 1.28,
294
+ "grad_norm": 0.25777679681777954,
295
+ "learning_rate": 6.74698795180723e-05,
296
+ "loss": 0.2171,
297
+ "step": 20000
298
+ },
299
+ {
300
+ "epoch": 1.312,
301
+ "grad_norm": 0.28767868876457214,
302
+ "learning_rate": 6.714859437751005e-05,
303
+ "loss": 0.2122,
304
+ "step": 20500
305
+ },
306
+ {
307
+ "epoch": 1.3439999999999999,
308
+ "grad_norm": 0.24645094573497772,
309
+ "learning_rate": 6.682730923694779e-05,
310
+ "loss": 0.2121,
311
+ "step": 21000
312
+ },
313
+ {
314
+ "epoch": 1.376,
315
+ "grad_norm": 0.27973559498786926,
316
+ "learning_rate": 6.650602409638555e-05,
317
+ "loss": 0.209,
318
+ "step": 21500
319
+ },
320
+ {
321
+ "epoch": 1.408,
322
+ "grad_norm": 0.2312808781862259,
323
+ "learning_rate": 6.618473895582329e-05,
324
+ "loss": 0.207,
325
+ "step": 22000
326
+ },
327
+ {
328
+ "epoch": 1.44,
329
+ "grad_norm": 0.32198190689086914,
330
+ "learning_rate": 6.586345381526105e-05,
331
+ "loss": 0.2062,
332
+ "step": 22500
333
+ },
334
+ {
335
+ "epoch": 1.472,
336
+ "grad_norm": 0.26178357005119324,
337
+ "learning_rate": 6.55421686746988e-05,
338
+ "loss": 0.2054,
339
+ "step": 23000
340
+ },
341
+ {
342
+ "epoch": 1.504,
343
+ "grad_norm": 0.2309255599975586,
344
+ "learning_rate": 6.522088353413655e-05,
345
+ "loss": 0.2029,
346
+ "step": 23500
347
+ },
348
+ {
349
+ "epoch": 1.536,
350
+ "grad_norm": 0.22608640789985657,
351
+ "learning_rate": 6.48995983935743e-05,
352
+ "loss": 0.2038,
353
+ "step": 24000
354
+ },
355
+ {
356
+ "epoch": 1.568,
357
+ "grad_norm": 0.20961375534534454,
358
+ "learning_rate": 6.457831325301206e-05,
359
+ "loss": 0.2016,
360
+ "step": 24500
361
+ },
362
+ {
363
+ "epoch": 1.6,
364
+ "grad_norm": 0.1852613389492035,
365
+ "learning_rate": 6.42570281124498e-05,
366
+ "loss": 0.2003,
367
+ "step": 25000
368
+ },
369
+ {
370
+ "epoch": 1.6,
371
+ "eval_loss": 0.13480305671691895,
372
+ "eval_runtime": 13.4963,
373
+ "eval_samples_per_second": 148.189,
374
+ "eval_steps_per_second": 6.224,
375
+ "step": 25000
376
+ },
377
+ {
378
+ "epoch": 1.6320000000000001,
379
+ "grad_norm": 0.25356176495552063,
380
+ "learning_rate": 6.393574297188755e-05,
381
+ "loss": 0.1991,
382
+ "step": 25500
383
+ },
384
+ {
385
+ "epoch": 1.6640000000000001,
386
+ "grad_norm": 0.23418042063713074,
387
+ "learning_rate": 6.36144578313253e-05,
388
+ "loss": 0.1993,
389
+ "step": 26000
390
+ },
391
+ {
392
+ "epoch": 1.696,
393
+ "grad_norm": 0.4756409823894501,
394
+ "learning_rate": 6.329317269076305e-05,
395
+ "loss": 0.1962,
396
+ "step": 26500
397
+ },
398
+ {
399
+ "epoch": 1.728,
400
+ "grad_norm": 0.31074902415275574,
401
+ "learning_rate": 6.29718875502008e-05,
402
+ "loss": 0.1946,
403
+ "step": 27000
404
+ },
405
+ {
406
+ "epoch": 1.76,
407
+ "grad_norm": 0.2518517076969147,
408
+ "learning_rate": 6.265060240963856e-05,
409
+ "loss": 0.1936,
410
+ "step": 27500
411
+ },
412
+ {
413
+ "epoch": 1.792,
414
+ "grad_norm": 0.23294122517108917,
415
+ "learning_rate": 6.232931726907632e-05,
416
+ "loss": 0.1931,
417
+ "step": 28000
418
+ },
419
+ {
420
+ "epoch": 1.8239999999999998,
421
+ "grad_norm": 0.30960217118263245,
422
+ "learning_rate": 6.200803212851406e-05,
423
+ "loss": 0.1916,
424
+ "step": 28500
425
+ },
426
+ {
427
+ "epoch": 1.8559999999999999,
428
+ "grad_norm": 0.2612380385398865,
429
+ "learning_rate": 6.168674698795182e-05,
430
+ "loss": 0.1941,
431
+ "step": 29000
432
+ },
433
+ {
434
+ "epoch": 1.888,
435
+ "grad_norm": 0.23748044669628143,
436
+ "learning_rate": 6.136546184738956e-05,
437
+ "loss": 0.1912,
438
+ "step": 29500
439
+ },
440
+ {
441
+ "epoch": 1.92,
442
+ "grad_norm": 0.21203479170799255,
443
+ "learning_rate": 6.104417670682732e-05,
444
+ "loss": 0.1905,
445
+ "step": 30000
446
+ },
447
+ {
448
+ "epoch": 1.952,
449
+ "grad_norm": 0.23570066690444946,
450
+ "learning_rate": 6.072289156626506e-05,
451
+ "loss": 0.1882,
452
+ "step": 30500
453
+ },
454
+ {
455
+ "epoch": 1.984,
456
+ "grad_norm": 0.24766422808170319,
457
+ "learning_rate": 6.040160642570281e-05,
458
+ "loss": 0.1908,
459
+ "step": 31000
460
+ },
461
+ {
462
+ "epoch": 2.016,
463
+ "grad_norm": 0.21270865201950073,
464
+ "learning_rate": 6.008032128514057e-05,
465
+ "loss": 0.1835,
466
+ "step": 31500
467
+ },
468
+ {
469
+ "epoch": 2.048,
470
+ "grad_norm": 0.2123081386089325,
471
+ "learning_rate": 5.975903614457831e-05,
472
+ "loss": 0.1765,
473
+ "step": 32000
474
+ },
475
+ {
476
+ "epoch": 2.08,
477
+ "grad_norm": 0.3412201404571533,
478
+ "learning_rate": 5.943775100401607e-05,
479
+ "loss": 0.1931,
480
+ "step": 32500
481
+ },
482
+ {
483
+ "epoch": 2.112,
484
+ "grad_norm": 0.2280445396900177,
485
+ "learning_rate": 5.911646586345382e-05,
486
+ "loss": 0.1893,
487
+ "step": 33000
488
+ },
489
+ {
490
+ "epoch": 2.144,
491
+ "grad_norm": 0.2307668924331665,
492
+ "learning_rate": 5.8795180722891576e-05,
493
+ "loss": 0.1826,
494
+ "step": 33500
495
+ },
496
+ {
497
+ "epoch": 2.176,
498
+ "grad_norm": 0.22051069140434265,
499
+ "learning_rate": 5.847389558232932e-05,
500
+ "loss": 0.1751,
501
+ "step": 34000
502
+ },
503
+ {
504
+ "epoch": 2.208,
505
+ "grad_norm": 0.28806522488594055,
506
+ "learning_rate": 5.8152610441767076e-05,
507
+ "loss": 0.1771,
508
+ "step": 34500
509
+ },
510
+ {
511
+ "epoch": 2.24,
512
+ "grad_norm": 0.19143815338611603,
513
+ "learning_rate": 5.7831325301204826e-05,
514
+ "loss": 0.1774,
515
+ "step": 35000
516
+ },
517
+ {
518
+ "epoch": 2.2720000000000002,
519
+ "grad_norm": 0.2986365556716919,
520
+ "learning_rate": 5.751004016064257e-05,
521
+ "loss": 0.1752,
522
+ "step": 35500
523
+ },
524
+ {
525
+ "epoch": 2.304,
526
+ "grad_norm": 0.19981278479099274,
527
+ "learning_rate": 5.7188755020080326e-05,
528
+ "loss": 0.1756,
529
+ "step": 36000
530
+ },
531
+ {
532
+ "epoch": 2.336,
533
+ "grad_norm": 0.2546658515930176,
534
+ "learning_rate": 5.6867469879518076e-05,
535
+ "loss": 0.1741,
536
+ "step": 36500
537
+ },
538
+ {
539
+ "epoch": 2.368,
540
+ "grad_norm": 0.1719229370355606,
541
+ "learning_rate": 5.6546184738955826e-05,
542
+ "loss": 0.174,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 2.4,
547
+ "grad_norm": 0.22920982539653778,
548
+ "learning_rate": 5.6224899598393576e-05,
549
+ "loss": 0.1707,
550
+ "step": 37500
551
+ },
552
+ {
553
+ "epoch": 2.4,
554
+ "eval_loss": 0.11245977133512497,
555
+ "eval_runtime": 13.3722,
556
+ "eval_samples_per_second": 149.565,
557
+ "eval_steps_per_second": 6.282,
558
+ "step": 37500
559
+ },
560
+ {
561
+ "epoch": 2.432,
562
+ "grad_norm": 0.22950303554534912,
563
+ "learning_rate": 5.590361445783133e-05,
564
+ "loss": 0.1715,
565
+ "step": 38000
566
+ },
567
+ {
568
+ "epoch": 2.464,
569
+ "grad_norm": 0.19281500577926636,
570
+ "learning_rate": 5.5582329317269076e-05,
571
+ "loss": 0.1719,
572
+ "step": 38500
573
+ },
574
+ {
575
+ "epoch": 2.496,
576
+ "grad_norm": 0.3043808043003082,
577
+ "learning_rate": 5.526104417670683e-05,
578
+ "loss": 0.1709,
579
+ "step": 39000
580
+ },
581
+ {
582
+ "epoch": 2.528,
583
+ "grad_norm": 0.2020847350358963,
584
+ "learning_rate": 5.493975903614458e-05,
585
+ "loss": 0.1687,
586
+ "step": 39500
587
+ },
588
+ {
589
+ "epoch": 2.56,
590
+ "grad_norm": 0.2701270878314972,
591
+ "learning_rate": 5.461847389558234e-05,
592
+ "loss": 0.1689,
593
+ "step": 40000
594
+ },
595
+ {
596
+ "epoch": 2.592,
597
+ "grad_norm": 0.20151746273040771,
598
+ "learning_rate": 5.429718875502008e-05,
599
+ "loss": 0.1703,
600
+ "step": 40500
601
+ },
602
+ {
603
+ "epoch": 2.624,
604
+ "grad_norm": 0.28613436222076416,
605
+ "learning_rate": 5.397590361445783e-05,
606
+ "loss": 0.1668,
607
+ "step": 41000
608
+ },
609
+ {
610
+ "epoch": 2.656,
611
+ "grad_norm": 0.24828064441680908,
612
+ "learning_rate": 5.365461847389559e-05,
613
+ "loss": 0.1671,
614
+ "step": 41500
615
+ },
616
+ {
617
+ "epoch": 2.6879999999999997,
618
+ "grad_norm": 0.2424352616071701,
619
+ "learning_rate": 5.333333333333333e-05,
620
+ "loss": 0.1678,
621
+ "step": 42000
622
+ },
623
+ {
624
+ "epoch": 2.7199999999999998,
625
+ "grad_norm": 0.1992502510547638,
626
+ "learning_rate": 5.301204819277109e-05,
627
+ "loss": 0.165,
628
+ "step": 42500
629
+ },
630
+ {
631
+ "epoch": 2.752,
632
+ "grad_norm": 0.19437122344970703,
633
+ "learning_rate": 5.269076305220884e-05,
634
+ "loss": 0.1658,
635
+ "step": 43000
636
+ },
637
+ {
638
+ "epoch": 2.784,
639
+ "grad_norm": 0.2736295461654663,
640
+ "learning_rate": 5.23694779116466e-05,
641
+ "loss": 0.165,
642
+ "step": 43500
643
+ },
644
+ {
645
+ "epoch": 2.816,
646
+ "grad_norm": 0.20108367502689362,
647
+ "learning_rate": 5.204819277108434e-05,
648
+ "loss": 0.1661,
649
+ "step": 44000
650
+ },
651
+ {
652
+ "epoch": 2.848,
653
+ "grad_norm": 0.17667348682880402,
654
+ "learning_rate": 5.17269076305221e-05,
655
+ "loss": 0.163,
656
+ "step": 44500
657
+ },
658
+ {
659
+ "epoch": 2.88,
660
+ "grad_norm": 0.24210619926452637,
661
+ "learning_rate": 5.140562248995984e-05,
662
+ "loss": 0.1634,
663
+ "step": 45000
664
+ },
665
+ {
666
+ "epoch": 2.912,
667
+ "grad_norm": 0.2011321634054184,
668
+ "learning_rate": 5.108433734939759e-05,
669
+ "loss": 0.1634,
670
+ "step": 45500
671
+ },
672
+ {
673
+ "epoch": 2.944,
674
+ "grad_norm": 0.1979280710220337,
675
+ "learning_rate": 5.076305220883535e-05,
676
+ "loss": 0.162,
677
+ "step": 46000
678
+ },
679
+ {
680
+ "epoch": 2.976,
681
+ "grad_norm": 0.23149700462818146,
682
+ "learning_rate": 5.044176706827309e-05,
683
+ "loss": 0.1605,
684
+ "step": 46500
685
+ },
686
+ {
687
+ "epoch": 3.008,
688
+ "grad_norm": 0.1558334231376648,
689
+ "learning_rate": 5.012048192771085e-05,
690
+ "loss": 0.1575,
691
+ "step": 47000
692
+ },
693
+ {
694
+ "epoch": 3.04,
695
+ "grad_norm": 0.251295268535614,
696
+ "learning_rate": 4.97991967871486e-05,
697
+ "loss": 0.1518,
698
+ "step": 47500
699
+ },
700
+ {
701
+ "epoch": 3.072,
702
+ "grad_norm": 0.1870911866426468,
703
+ "learning_rate": 4.9477911646586354e-05,
704
+ "loss": 0.151,
705
+ "step": 48000
706
+ },
707
+ {
708
+ "epoch": 3.104,
709
+ "grad_norm": 0.19055207073688507,
710
+ "learning_rate": 4.91566265060241e-05,
711
+ "loss": 0.1506,
712
+ "step": 48500
713
+ },
714
+ {
715
+ "epoch": 3.136,
716
+ "grad_norm": 0.19039425253868103,
717
+ "learning_rate": 4.8835341365461854e-05,
718
+ "loss": 0.1502,
719
+ "step": 49000
720
+ },
721
+ {
722
+ "epoch": 3.168,
723
+ "grad_norm": 0.2273644655942917,
724
+ "learning_rate": 4.8514056224899604e-05,
725
+ "loss": 0.1515,
726
+ "step": 49500
727
+ },
728
+ {
729
+ "epoch": 3.2,
730
+ "grad_norm": 0.20844458043575287,
731
+ "learning_rate": 4.819277108433736e-05,
732
+ "loss": 0.15,
733
+ "step": 50000
734
+ },
735
+ {
736
+ "epoch": 3.2,
737
+ "eval_loss": 0.09431243687868118,
738
+ "eval_runtime": 13.3841,
739
+ "eval_samples_per_second": 149.431,
740
+ "eval_steps_per_second": 6.276,
741
+ "step": 50000
742
+ },
743
+ {
744
+ "epoch": 3.232,
745
+ "grad_norm": 0.21888093650341034,
746
+ "learning_rate": 4.7871485943775104e-05,
747
+ "loss": 0.1514,
748
+ "step": 50500
749
+ },
750
+ {
751
+ "epoch": 3.2640000000000002,
752
+ "grad_norm": 0.1797676682472229,
753
+ "learning_rate": 4.7550200803212854e-05,
754
+ "loss": 0.1505,
755
+ "step": 51000
756
+ },
757
+ {
758
+ "epoch": 3.296,
759
+ "grad_norm": 0.17472127079963684,
760
+ "learning_rate": 4.7228915662650604e-05,
761
+ "loss": 0.15,
762
+ "step": 51500
763
+ },
764
+ {
765
+ "epoch": 3.328,
766
+ "grad_norm": 0.1877003014087677,
767
+ "learning_rate": 4.6907630522088354e-05,
768
+ "loss": 0.1501,
769
+ "step": 52000
770
+ },
771
+ {
772
+ "epoch": 3.36,
773
+ "grad_norm": 0.2039192020893097,
774
+ "learning_rate": 4.658634538152611e-05,
775
+ "loss": 0.1509,
776
+ "step": 52500
777
+ },
778
+ {
779
+ "epoch": 3.392,
780
+ "grad_norm": 0.19264955818653107,
781
+ "learning_rate": 4.6265060240963854e-05,
782
+ "loss": 0.147,
783
+ "step": 53000
784
+ },
785
+ {
786
+ "epoch": 3.424,
787
+ "grad_norm": 0.2461443841457367,
788
+ "learning_rate": 4.594377510040161e-05,
789
+ "loss": 0.1473,
790
+ "step": 53500
791
+ },
792
+ {
793
+ "epoch": 3.456,
794
+ "grad_norm": 0.245579794049263,
795
+ "learning_rate": 4.562248995983936e-05,
796
+ "loss": 0.148,
797
+ "step": 54000
798
+ },
799
+ {
800
+ "epoch": 3.488,
801
+ "grad_norm": 0.2419605553150177,
802
+ "learning_rate": 4.530120481927712e-05,
803
+ "loss": 0.1483,
804
+ "step": 54500
805
+ },
806
+ {
807
+ "epoch": 3.52,
808
+ "grad_norm": 0.21280065178871155,
809
+ "learning_rate": 4.497991967871486e-05,
810
+ "loss": 0.1465,
811
+ "step": 55000
812
+ },
813
+ {
814
+ "epoch": 3.552,
815
+ "grad_norm": 0.19970615208148956,
816
+ "learning_rate": 4.465863453815261e-05,
817
+ "loss": 0.1479,
818
+ "step": 55500
819
+ },
820
+ {
821
+ "epoch": 3.584,
822
+ "grad_norm": 0.178068608045578,
823
+ "learning_rate": 4.433734939759037e-05,
824
+ "loss": 0.1469,
825
+ "step": 56000
826
+ },
827
+ {
828
+ "epoch": 3.616,
829
+ "grad_norm": 0.2007550597190857,
830
+ "learning_rate": 4.401606425702811e-05,
831
+ "loss": 0.1484,
832
+ "step": 56500
833
+ },
834
+ {
835
+ "epoch": 3.648,
836
+ "grad_norm": 0.2703693211078644,
837
+ "learning_rate": 4.369477911646587e-05,
838
+ "loss": 0.1461,
839
+ "step": 57000
840
+ },
841
+ {
842
+ "epoch": 3.68,
843
+ "grad_norm": 0.18838930130004883,
844
+ "learning_rate": 4.337349397590362e-05,
845
+ "loss": 0.1467,
846
+ "step": 57500
847
+ },
848
+ {
849
+ "epoch": 3.7119999999999997,
850
+ "grad_norm": 0.22705510258674622,
851
+ "learning_rate": 4.3052208835341375e-05,
852
+ "loss": 0.1471,
853
+ "step": 58000
854
+ },
855
+ {
856
+ "epoch": 3.7439999999999998,
857
+ "grad_norm": 0.18866540491580963,
858
+ "learning_rate": 4.273092369477912e-05,
859
+ "loss": 0.1464,
860
+ "step": 58500
861
+ },
862
+ {
863
+ "epoch": 3.776,
864
+ "grad_norm": 0.16808009147644043,
865
+ "learning_rate": 4.2409638554216875e-05,
866
+ "loss": 0.1469,
867
+ "step": 59000
868
+ },
869
+ {
870
+ "epoch": 3.808,
871
+ "grad_norm": 0.20790338516235352,
872
+ "learning_rate": 4.208835341365462e-05,
873
+ "loss": 0.1455,
874
+ "step": 59500
875
+ },
876
+ {
877
+ "epoch": 3.84,
878
+ "grad_norm": 0.20283524692058563,
879
+ "learning_rate": 4.1767068273092375e-05,
880
+ "loss": 0.1453,
881
+ "step": 60000
882
+ },
883
+ {
884
+ "epoch": 3.872,
885
+ "grad_norm": 0.18522211909294128,
886
+ "learning_rate": 4.1445783132530125e-05,
887
+ "loss": 0.1449,
888
+ "step": 60500
889
+ },
890
+ {
891
+ "epoch": 3.904,
892
+ "grad_norm": 0.2298567146062851,
893
+ "learning_rate": 4.112449799196787e-05,
894
+ "loss": 0.1442,
895
+ "step": 61000
896
+ },
897
+ {
898
+ "epoch": 3.936,
899
+ "grad_norm": 0.23237478733062744,
900
+ "learning_rate": 4.0803212851405625e-05,
901
+ "loss": 0.1445,
902
+ "step": 61500
903
+ },
904
+ {
905
+ "epoch": 3.968,
906
+ "grad_norm": 0.18708902597427368,
907
+ "learning_rate": 4.0481927710843375e-05,
908
+ "loss": 0.1436,
909
+ "step": 62000
910
+ },
911
+ {
912
+ "epoch": 4.0,
913
+ "grad_norm": 0.2235335260629654,
914
+ "learning_rate": 4.016064257028113e-05,
915
+ "loss": 0.145,
916
+ "step": 62500
917
+ },
918
+ {
919
+ "epoch": 4.0,
920
+ "eval_loss": 0.08151204138994217,
921
+ "eval_runtime": 13.1737,
922
+ "eval_samples_per_second": 151.818,
923
+ "eval_steps_per_second": 6.376,
924
+ "step": 62500
925
+ },
926
+ {
927
+ "epoch": 4.032,
928
+ "grad_norm": 0.27586033940315247,
929
+ "learning_rate": 3.9839357429718875e-05,
930
+ "loss": 0.1361,
931
+ "step": 63000
932
+ },
933
+ {
934
+ "epoch": 4.064,
935
+ "grad_norm": 0.20399342477321625,
936
+ "learning_rate": 3.9518072289156625e-05,
937
+ "loss": 0.1359,
938
+ "step": 63500
939
+ },
940
+ {
941
+ "epoch": 4.096,
942
+ "grad_norm": 0.2167077660560608,
943
+ "learning_rate": 3.919678714859438e-05,
944
+ "loss": 0.1349,
945
+ "step": 64000
946
+ },
947
+ {
948
+ "epoch": 4.128,
949
+ "grad_norm": 0.2217278927564621,
950
+ "learning_rate": 3.887550200803213e-05,
951
+ "loss": 0.1343,
952
+ "step": 64500
953
+ },
954
+ {
955
+ "epoch": 4.16,
956
+ "grad_norm": 0.17411163449287415,
957
+ "learning_rate": 3.855421686746988e-05,
958
+ "loss": 0.1353,
959
+ "step": 65000
960
+ },
961
+ {
962
+ "epoch": 4.192,
963
+ "grad_norm": 0.2262706607580185,
964
+ "learning_rate": 3.823293172690763e-05,
965
+ "loss": 0.1355,
966
+ "step": 65500
967
+ },
968
+ {
969
+ "epoch": 4.224,
970
+ "grad_norm": 0.21051813662052155,
971
+ "learning_rate": 3.791164658634539e-05,
972
+ "loss": 0.1351,
973
+ "step": 66000
974
+ },
975
+ {
976
+ "epoch": 4.256,
977
+ "grad_norm": 0.2202002853155136,
978
+ "learning_rate": 3.759036144578314e-05,
979
+ "loss": 0.1362,
980
+ "step": 66500
981
+ },
982
+ {
983
+ "epoch": 4.288,
984
+ "grad_norm": 0.1532248854637146,
985
+ "learning_rate": 3.726907630522089e-05,
986
+ "loss": 0.1338,
987
+ "step": 67000
988
+ },
989
+ {
990
+ "epoch": 4.32,
991
+ "grad_norm": 0.25249359011650085,
992
+ "learning_rate": 3.694779116465864e-05,
993
+ "loss": 0.1334,
994
+ "step": 67500
995
+ },
996
+ {
997
+ "epoch": 4.352,
998
+ "grad_norm": 0.2392909973859787,
999
+ "learning_rate": 3.662650602409639e-05,
1000
+ "loss": 0.1354,
1001
+ "step": 68000
1002
+ },
1003
+ {
1004
+ "epoch": 4.384,
1005
+ "grad_norm": 0.3180345892906189,
1006
+ "learning_rate": 3.630522088353414e-05,
1007
+ "loss": 0.1353,
1008
+ "step": 68500
1009
+ },
1010
+ {
1011
+ "epoch": 4.416,
1012
+ "grad_norm": 0.27343523502349854,
1013
+ "learning_rate": 3.598393574297189e-05,
1014
+ "loss": 0.1354,
1015
+ "step": 69000
1016
+ },
1017
+ {
1018
+ "epoch": 4.448,
1019
+ "grad_norm": 0.17806372046470642,
1020
+ "learning_rate": 3.566265060240964e-05,
1021
+ "loss": 0.1351,
1022
+ "step": 69500
1023
+ },
1024
+ {
1025
+ "epoch": 4.48,
1026
+ "grad_norm": 0.17694541811943054,
1027
+ "learning_rate": 3.5341365461847396e-05,
1028
+ "loss": 0.135,
1029
+ "step": 70000
1030
+ },
1031
+ {
1032
+ "epoch": 4.5120000000000005,
1033
+ "grad_norm": 0.1796264797449112,
1034
+ "learning_rate": 3.5020080321285146e-05,
1035
+ "loss": 0.1326,
1036
+ "step": 70500
1037
+ },
1038
+ {
1039
+ "epoch": 4.5440000000000005,
1040
+ "grad_norm": 0.16896295547485352,
1041
+ "learning_rate": 3.4698795180722896e-05,
1042
+ "loss": 0.1327,
1043
+ "step": 71000
1044
+ },
1045
+ {
1046
+ "epoch": 4.576,
1047
+ "grad_norm": 0.16427506506443024,
1048
+ "learning_rate": 3.4377510040160646e-05,
1049
+ "loss": 0.1341,
1050
+ "step": 71500
1051
+ },
1052
+ {
1053
+ "epoch": 4.608,
1054
+ "grad_norm": 0.15947696566581726,
1055
+ "learning_rate": 3.4056224899598396e-05,
1056
+ "loss": 0.1336,
1057
+ "step": 72000
1058
+ },
1059
+ {
1060
+ "epoch": 4.64,
1061
+ "grad_norm": 0.24063943326473236,
1062
+ "learning_rate": 3.373493975903615e-05,
1063
+ "loss": 0.1326,
1064
+ "step": 72500
1065
+ },
1066
+ {
1067
+ "epoch": 4.672,
1068
+ "grad_norm": 0.2784833610057831,
1069
+ "learning_rate": 3.3413654618473896e-05,
1070
+ "loss": 0.1313,
1071
+ "step": 73000
1072
+ },
1073
+ {
1074
+ "epoch": 4.704,
1075
+ "grad_norm": 0.1624738872051239,
1076
+ "learning_rate": 3.3092369477911646e-05,
1077
+ "loss": 0.1343,
1078
+ "step": 73500
1079
+ },
1080
+ {
1081
+ "epoch": 4.736,
1082
+ "grad_norm": 0.163747176527977,
1083
+ "learning_rate": 3.27710843373494e-05,
1084
+ "loss": 0.1332,
1085
+ "step": 74000
1086
+ },
1087
+ {
1088
+ "epoch": 4.768,
1089
+ "grad_norm": 0.19286634027957916,
1090
+ "learning_rate": 3.244979919678715e-05,
1091
+ "loss": 0.1314,
1092
+ "step": 74500
1093
+ },
1094
+ {
1095
+ "epoch": 4.8,
1096
+ "grad_norm": 0.2070024311542511,
1097
+ "learning_rate": 3.21285140562249e-05,
1098
+ "loss": 0.1323,
1099
+ "step": 75000
1100
+ },
1101
+ {
1102
+ "epoch": 4.8,
1103
+ "eval_loss": 0.07321055233478546,
1104
+ "eval_runtime": 13.3287,
1105
+ "eval_samples_per_second": 150.052,
1106
+ "eval_steps_per_second": 6.302,
1107
+ "step": 75000
1108
+ },
1109
+ {
1110
+ "epoch": 4.832,
1111
+ "grad_norm": 0.25665566325187683,
1112
+ "learning_rate": 3.180722891566265e-05,
1113
+ "loss": 0.133,
1114
+ "step": 75500
1115
+ },
1116
+ {
1117
+ "epoch": 4.864,
1118
+ "grad_norm": 0.18933174014091492,
1119
+ "learning_rate": 3.14859437751004e-05,
1120
+ "loss": 0.1334,
1121
+ "step": 76000
1122
+ },
1123
+ {
1124
+ "epoch": 4.896,
1125
+ "grad_norm": 0.20106372237205505,
1126
+ "learning_rate": 3.116465863453816e-05,
1127
+ "loss": 0.1318,
1128
+ "step": 76500
1129
+ },
1130
+ {
1131
+ "epoch": 4.928,
1132
+ "grad_norm": 0.23300665616989136,
1133
+ "learning_rate": 3.084337349397591e-05,
1134
+ "loss": 0.1314,
1135
+ "step": 77000
1136
+ },
1137
+ {
1138
+ "epoch": 4.96,
1139
+ "grad_norm": 0.2776864171028137,
1140
+ "learning_rate": 3.052208835341366e-05,
1141
+ "loss": 0.1307,
1142
+ "step": 77500
1143
+ },
1144
+ {
1145
+ "epoch": 4.992,
1146
+ "grad_norm": 0.17158937454223633,
1147
+ "learning_rate": 3.0200803212851406e-05,
1148
+ "loss": 0.1328,
1149
+ "step": 78000
1150
+ },
1151
+ {
1152
+ "epoch": 5.024,
1153
+ "grad_norm": 0.19341541826725006,
1154
+ "learning_rate": 2.9879518072289156e-05,
1155
+ "loss": 0.1255,
1156
+ "step": 78500
1157
+ },
1158
+ {
1159
+ "epoch": 5.056,
1160
+ "grad_norm": 0.1820104718208313,
1161
+ "learning_rate": 2.955823293172691e-05,
1162
+ "loss": 0.1239,
1163
+ "step": 79000
1164
+ },
1165
+ {
1166
+ "epoch": 5.088,
1167
+ "grad_norm": 0.19204023480415344,
1168
+ "learning_rate": 2.923694779116466e-05,
1169
+ "loss": 0.1251,
1170
+ "step": 79500
1171
+ },
1172
+ {
1173
+ "epoch": 5.12,
1174
+ "grad_norm": 0.20374265313148499,
1175
+ "learning_rate": 2.8915662650602413e-05,
1176
+ "loss": 0.1238,
1177
+ "step": 80000
1178
+ },
1179
+ {
1180
+ "epoch": 5.152,
1181
+ "grad_norm": 0.17607811093330383,
1182
+ "learning_rate": 2.8594377510040163e-05,
1183
+ "loss": 0.1242,
1184
+ "step": 80500
1185
+ },
1186
+ {
1187
+ "epoch": 5.184,
1188
+ "grad_norm": 0.18394358456134796,
1189
+ "learning_rate": 2.8273092369477913e-05,
1190
+ "loss": 0.1246,
1191
+ "step": 81000
1192
+ },
1193
+ {
1194
+ "epoch": 5.216,
1195
+ "grad_norm": 0.1720678061246872,
1196
+ "learning_rate": 2.7951807228915666e-05,
1197
+ "loss": 0.1234,
1198
+ "step": 81500
1199
+ },
1200
+ {
1201
+ "epoch": 5.248,
1202
+ "grad_norm": 0.1649816781282425,
1203
+ "learning_rate": 2.7630522088353417e-05,
1204
+ "loss": 0.1246,
1205
+ "step": 82000
1206
+ },
1207
+ {
1208
+ "epoch": 5.28,
1209
+ "grad_norm": 0.24089868366718292,
1210
+ "learning_rate": 2.730923694779117e-05,
1211
+ "loss": 0.1236,
1212
+ "step": 82500
1213
+ },
1214
+ {
1215
+ "epoch": 5.312,
1216
+ "grad_norm": 0.16703809797763824,
1217
+ "learning_rate": 2.6987951807228917e-05,
1218
+ "loss": 0.1235,
1219
+ "step": 83000
1220
+ },
1221
+ {
1222
+ "epoch": 5.344,
1223
+ "grad_norm": 0.2375577837228775,
1224
+ "learning_rate": 2.6666666666666667e-05,
1225
+ "loss": 0.1255,
1226
+ "step": 83500
1227
+ },
1228
+ {
1229
+ "epoch": 5.376,
1230
+ "grad_norm": 0.20844422280788422,
1231
+ "learning_rate": 2.634538152610442e-05,
1232
+ "loss": 0.124,
1233
+ "step": 84000
1234
+ },
1235
+ {
1236
+ "epoch": 5.408,
1237
+ "grad_norm": 0.15090999007225037,
1238
+ "learning_rate": 2.602409638554217e-05,
1239
+ "loss": 0.1236,
1240
+ "step": 84500
1241
+ },
1242
+ {
1243
+ "epoch": 5.44,
1244
+ "grad_norm": 0.1982196420431137,
1245
+ "learning_rate": 2.570281124497992e-05,
1246
+ "loss": 0.1234,
1247
+ "step": 85000
1248
+ },
1249
+ {
1250
+ "epoch": 5.4719999999999995,
1251
+ "grad_norm": 0.20548874139785767,
1252
+ "learning_rate": 2.5381526104417673e-05,
1253
+ "loss": 0.1237,
1254
+ "step": 85500
1255
+ },
1256
+ {
1257
+ "epoch": 5.504,
1258
+ "grad_norm": 0.1553628295660019,
1259
+ "learning_rate": 2.5060240963855423e-05,
1260
+ "loss": 0.1241,
1261
+ "step": 86000
1262
+ },
1263
+ {
1264
+ "epoch": 5.536,
1265
+ "grad_norm": 0.20827996730804443,
1266
+ "learning_rate": 2.4738955823293177e-05,
1267
+ "loss": 0.1236,
1268
+ "step": 86500
1269
+ },
1270
+ {
1271
+ "epoch": 5.568,
1272
+ "grad_norm": 0.26525431871414185,
1273
+ "learning_rate": 2.4417670682730927e-05,
1274
+ "loss": 0.1244,
1275
+ "step": 87000
1276
+ },
1277
+ {
1278
+ "epoch": 5.6,
1279
+ "grad_norm": 0.16824448108673096,
1280
+ "learning_rate": 2.409638554216868e-05,
1281
+ "loss": 0.124,
1282
+ "step": 87500
1283
+ },
1284
+ {
1285
+ "epoch": 5.6,
1286
+ "eval_loss": 0.06600421667098999,
1287
+ "eval_runtime": 13.2001,
1288
+ "eval_samples_per_second": 151.514,
1289
+ "eval_steps_per_second": 6.364,
1290
+ "step": 87500
1291
+ },
1292
+ {
1293
+ "epoch": 5.632,
1294
+ "grad_norm": 0.19588659703731537,
1295
+ "learning_rate": 2.3775100401606427e-05,
1296
+ "loss": 0.1239,
1297
+ "step": 88000
1298
+ },
1299
+ {
1300
+ "epoch": 5.664,
1301
+ "grad_norm": 0.20829927921295166,
1302
+ "learning_rate": 2.3453815261044177e-05,
1303
+ "loss": 0.1236,
1304
+ "step": 88500
1305
+ },
1306
+ {
1307
+ "epoch": 5.696,
1308
+ "grad_norm": 0.17067208886146545,
1309
+ "learning_rate": 2.3132530120481927e-05,
1310
+ "loss": 0.1246,
1311
+ "step": 89000
1312
+ },
1313
+ {
1314
+ "epoch": 5.728,
1315
+ "grad_norm": 0.17796407639980316,
1316
+ "learning_rate": 2.281124497991968e-05,
1317
+ "loss": 0.123,
1318
+ "step": 89500
1319
+ },
1320
+ {
1321
+ "epoch": 5.76,
1322
+ "grad_norm": 0.17811580002307892,
1323
+ "learning_rate": 2.248995983935743e-05,
1324
+ "loss": 0.1247,
1325
+ "step": 90000
1326
+ },
1327
+ {
1328
+ "epoch": 5.792,
1329
+ "grad_norm": 0.16586844623088837,
1330
+ "learning_rate": 2.2168674698795184e-05,
1331
+ "loss": 0.1226,
1332
+ "step": 90500
1333
+ },
1334
+ {
1335
+ "epoch": 5.824,
1336
+ "grad_norm": 0.16634885966777802,
1337
+ "learning_rate": 2.1847389558232934e-05,
1338
+ "loss": 0.1239,
1339
+ "step": 91000
1340
+ },
1341
+ {
1342
+ "epoch": 5.856,
1343
+ "grad_norm": 0.1891159564256668,
1344
+ "learning_rate": 2.1526104417670687e-05,
1345
+ "loss": 0.1234,
1346
+ "step": 91500
1347
+ },
1348
+ {
1349
+ "epoch": 5.888,
1350
+ "grad_norm": 0.2127494215965271,
1351
+ "learning_rate": 2.1204819277108437e-05,
1352
+ "loss": 0.1227,
1353
+ "step": 92000
1354
+ },
1355
+ {
1356
+ "epoch": 5.92,
1357
+ "grad_norm": 0.15109600126743317,
1358
+ "learning_rate": 2.0883534136546187e-05,
1359
+ "loss": 0.1218,
1360
+ "step": 92500
1361
+ },
1362
+ {
1363
+ "epoch": 5.952,
1364
+ "grad_norm": 0.14382487535476685,
1365
+ "learning_rate": 2.0562248995983934e-05,
1366
+ "loss": 0.1216,
1367
+ "step": 93000
1368
+ },
1369
+ {
1370
+ "epoch": 5.984,
1371
+ "grad_norm": 0.2122729867696762,
1372
+ "learning_rate": 2.0240963855421687e-05,
1373
+ "loss": 0.1248,
1374
+ "step": 93500
1375
+ },
1376
+ {
1377
+ "epoch": 6.016,
1378
+ "grad_norm": 0.19725599884986877,
1379
+ "learning_rate": 1.9919678714859437e-05,
1380
+ "loss": 0.12,
1381
+ "step": 94000
1382
+ },
1383
+ {
1384
+ "epoch": 6.048,
1385
+ "grad_norm": 0.18302911520004272,
1386
+ "learning_rate": 1.959839357429719e-05,
1387
+ "loss": 0.1174,
1388
+ "step": 94500
1389
+ },
1390
+ {
1391
+ "epoch": 6.08,
1392
+ "grad_norm": 0.19952338933944702,
1393
+ "learning_rate": 1.927710843373494e-05,
1394
+ "loss": 0.1176,
1395
+ "step": 95000
1396
+ },
1397
+ {
1398
+ "epoch": 6.112,
1399
+ "grad_norm": 0.16824807226657867,
1400
+ "learning_rate": 1.8955823293172694e-05,
1401
+ "loss": 0.1174,
1402
+ "step": 95500
1403
+ },
1404
+ {
1405
+ "epoch": 6.144,
1406
+ "grad_norm": 0.22110256552696228,
1407
+ "learning_rate": 1.8634538152610444e-05,
1408
+ "loss": 0.1172,
1409
+ "step": 96000
1410
+ },
1411
+ {
1412
+ "epoch": 6.176,
1413
+ "grad_norm": 0.20097705721855164,
1414
+ "learning_rate": 1.8313253012048194e-05,
1415
+ "loss": 0.1171,
1416
+ "step": 96500
1417
+ },
1418
+ {
1419
+ "epoch": 6.208,
1420
+ "grad_norm": 0.1569439023733139,
1421
+ "learning_rate": 1.7991967871485944e-05,
1422
+ "loss": 0.1177,
1423
+ "step": 97000
1424
+ },
1425
+ {
1426
+ "epoch": 6.24,
1427
+ "grad_norm": 0.1618974804878235,
1428
+ "learning_rate": 1.7670682730923698e-05,
1429
+ "loss": 0.1169,
1430
+ "step": 97500
1431
+ },
1432
+ {
1433
+ "epoch": 6.272,
1434
+ "grad_norm": 0.2146083265542984,
1435
+ "learning_rate": 1.7349397590361448e-05,
1436
+ "loss": 0.1172,
1437
+ "step": 98000
1438
+ },
1439
+ {
1440
+ "epoch": 6.304,
1441
+ "grad_norm": 0.16460789740085602,
1442
+ "learning_rate": 1.7028112449799198e-05,
1443
+ "loss": 0.1166,
1444
+ "step": 98500
1445
+ },
1446
+ {
1447
+ "epoch": 6.336,
1448
+ "grad_norm": 0.20428918302059174,
1449
+ "learning_rate": 1.6706827309236948e-05,
1450
+ "loss": 0.1177,
1451
+ "step": 99000
1452
+ },
1453
+ {
1454
+ "epoch": 6.368,
1455
+ "grad_norm": 0.1996203064918518,
1456
+ "learning_rate": 1.63855421686747e-05,
1457
+ "loss": 0.1172,
1458
+ "step": 99500
1459
+ },
1460
+ {
1461
+ "epoch": 6.4,
1462
+ "grad_norm": 0.22684213519096375,
1463
+ "learning_rate": 1.606425702811245e-05,
1464
+ "loss": 0.118,
1465
+ "step": 100000
1466
+ },
1467
+ {
1468
+ "epoch": 6.4,
1469
+ "eval_loss": 0.061658285558223724,
1470
+ "eval_runtime": 13.1578,
1471
+ "eval_samples_per_second": 152.001,
1472
+ "eval_steps_per_second": 6.384,
1473
+ "step": 100000
1474
+ }
1475
+ ],
1476
+ "logging_steps": 500,
1477
+ "max_steps": 125000,
1478
+ "num_input_tokens_seen": 0,
1479
+ "num_train_epochs": 8,
1480
+ "save_steps": 12500,
1481
+ "stateful_callbacks": {
1482
+ "TrainerControl": {
1483
+ "args": {
1484
+ "should_epoch_stop": false,
1485
+ "should_evaluate": false,
1486
+ "should_log": false,
1487
+ "should_save": true,
1488
+ "should_training_stop": false
1489
+ },
1490
+ "attributes": {}
1491
+ }
1492
+ },
1493
+ "total_flos": 6.459712365560463e+18,
1494
+ "train_batch_size": 24,
1495
+ "trial_name": null,
1496
+ "trial_params": null
1497
+ }
training_args.bin ADDED
Binary file (5.37 kB). View file