Sabbir772 commited on
Commit
523a006
·
verified ·
1 Parent(s): 17be1be

Upload full training checkpoint inside 'checkpoint' folder

Browse files
checkpoint/added_tokens.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<BN>": 32100,
3
+ "<CH>": 32101,
4
+ "<extra_id_0>": 32099,
5
+ "<extra_id_10>": 32089,
6
+ "<extra_id_11>": 32088,
7
+ "<extra_id_12>": 32087,
8
+ "<extra_id_13>": 32086,
9
+ "<extra_id_14>": 32085,
10
+ "<extra_id_15>": 32084,
11
+ "<extra_id_16>": 32083,
12
+ "<extra_id_17>": 32082,
13
+ "<extra_id_18>": 32081,
14
+ "<extra_id_19>": 32080,
15
+ "<extra_id_1>": 32098,
16
+ "<extra_id_20>": 32079,
17
+ "<extra_id_21>": 32078,
18
+ "<extra_id_22>": 32077,
19
+ "<extra_id_23>": 32076,
20
+ "<extra_id_24>": 32075,
21
+ "<extra_id_25>": 32074,
22
+ "<extra_id_26>": 32073,
23
+ "<extra_id_27>": 32072,
24
+ "<extra_id_28>": 32071,
25
+ "<extra_id_29>": 32070,
26
+ "<extra_id_2>": 32097,
27
+ "<extra_id_30>": 32069,
28
+ "<extra_id_31>": 32068,
29
+ "<extra_id_32>": 32067,
30
+ "<extra_id_33>": 32066,
31
+ "<extra_id_34>": 32065,
32
+ "<extra_id_35>": 32064,
33
+ "<extra_id_36>": 32063,
34
+ "<extra_id_37>": 32062,
35
+ "<extra_id_38>": 32061,
36
+ "<extra_id_39>": 32060,
37
+ "<extra_id_3>": 32096,
38
+ "<extra_id_40>": 32059,
39
+ "<extra_id_41>": 32058,
40
+ "<extra_id_42>": 32057,
41
+ "<extra_id_43>": 32056,
42
+ "<extra_id_44>": 32055,
43
+ "<extra_id_45>": 32054,
44
+ "<extra_id_46>": 32053,
45
+ "<extra_id_47>": 32052,
46
+ "<extra_id_48>": 32051,
47
+ "<extra_id_49>": 32050,
48
+ "<extra_id_4>": 32095,
49
+ "<extra_id_50>": 32049,
50
+ "<extra_id_51>": 32048,
51
+ "<extra_id_52>": 32047,
52
+ "<extra_id_53>": 32046,
53
+ "<extra_id_54>": 32045,
54
+ "<extra_id_55>": 32044,
55
+ "<extra_id_56>": 32043,
56
+ "<extra_id_57>": 32042,
57
+ "<extra_id_58>": 32041,
58
+ "<extra_id_59>": 32040,
59
+ "<extra_id_5>": 32094,
60
+ "<extra_id_60>": 32039,
61
+ "<extra_id_61>": 32038,
62
+ "<extra_id_62>": 32037,
63
+ "<extra_id_63>": 32036,
64
+ "<extra_id_64>": 32035,
65
+ "<extra_id_65>": 32034,
66
+ "<extra_id_66>": 32033,
67
+ "<extra_id_67>": 32032,
68
+ "<extra_id_68>": 32031,
69
+ "<extra_id_69>": 32030,
70
+ "<extra_id_6>": 32093,
71
+ "<extra_id_70>": 32029,
72
+ "<extra_id_71>": 32028,
73
+ "<extra_id_72>": 32027,
74
+ "<extra_id_73>": 32026,
75
+ "<extra_id_74>": 32025,
76
+ "<extra_id_75>": 32024,
77
+ "<extra_id_76>": 32023,
78
+ "<extra_id_77>": 32022,
79
+ "<extra_id_78>": 32021,
80
+ "<extra_id_79>": 32020,
81
+ "<extra_id_7>": 32092,
82
+ "<extra_id_80>": 32019,
83
+ "<extra_id_81>": 32018,
84
+ "<extra_id_82>": 32017,
85
+ "<extra_id_83>": 32016,
86
+ "<extra_id_84>": 32015,
87
+ "<extra_id_85>": 32014,
88
+ "<extra_id_86>": 32013,
89
+ "<extra_id_87>": 32012,
90
+ "<extra_id_88>": 32011,
91
+ "<extra_id_89>": 32010,
92
+ "<extra_id_8>": 32091,
93
+ "<extra_id_90>": 32009,
94
+ "<extra_id_91>": 32008,
95
+ "<extra_id_92>": 32007,
96
+ "<extra_id_93>": 32006,
97
+ "<extra_id_94>": 32005,
98
+ "<extra_id_95>": 32004,
99
+ "<extra_id_96>": 32003,
100
+ "<extra_id_97>": 32002,
101
+ "<extra_id_98>": 32001,
102
+ "<extra_id_99>": 32000,
103
+ "<extra_id_9>": 32090
104
+ }
checkpoint/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.54.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32102
32
+ }
checkpoint/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": "4.54.1"
7
+ }
checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d9005889552e029ae0f4ad6c88f14926c5f00dadfc9d159f3073b9bd1ed7e5
3
+ size 990185320
checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc2f647bccc068bd4031b56c17c84cc33de7c9cbadfbc3408e9aad88ac8b8cf
3
+ size 1980540922
checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3a3008648501d24764fe333294c85c928d239dc3b0530f6dceccd81d60bc59
3
+ size 14244
checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f0268140834c71b91899b9158c0b00cd62b9c624ee206b9aa4ff7a0e9ff469
3
+ size 1064
checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<BN>",
4
+ "<CH>",
5
+ "<extra_id_0>",
6
+ "<extra_id_1>",
7
+ "<extra_id_2>",
8
+ "<extra_id_3>",
9
+ "<extra_id_4>",
10
+ "<extra_id_5>",
11
+ "<extra_id_6>",
12
+ "<extra_id_7>",
13
+ "<extra_id_8>",
14
+ "<extra_id_9>",
15
+ "<extra_id_10>",
16
+ "<extra_id_11>",
17
+ "<extra_id_12>",
18
+ "<extra_id_13>",
19
+ "<extra_id_14>",
20
+ "<extra_id_15>",
21
+ "<extra_id_16>",
22
+ "<extra_id_17>",
23
+ "<extra_id_18>",
24
+ "<extra_id_19>",
25
+ "<extra_id_20>",
26
+ "<extra_id_21>",
27
+ "<extra_id_22>",
28
+ "<extra_id_23>",
29
+ "<extra_id_24>",
30
+ "<extra_id_25>",
31
+ "<extra_id_26>",
32
+ "<extra_id_27>",
33
+ "<extra_id_28>",
34
+ "<extra_id_29>",
35
+ "<extra_id_30>",
36
+ "<extra_id_31>",
37
+ "<extra_id_32>",
38
+ "<extra_id_33>",
39
+ "<extra_id_34>",
40
+ "<extra_id_35>",
41
+ "<extra_id_36>",
42
+ "<extra_id_37>",
43
+ "<extra_id_38>",
44
+ "<extra_id_39>",
45
+ "<extra_id_40>",
46
+ "<extra_id_41>",
47
+ "<extra_id_42>",
48
+ "<extra_id_43>",
49
+ "<extra_id_44>",
50
+ "<extra_id_45>",
51
+ "<extra_id_46>",
52
+ "<extra_id_47>",
53
+ "<extra_id_48>",
54
+ "<extra_id_49>",
55
+ "<extra_id_50>",
56
+ "<extra_id_51>",
57
+ "<extra_id_52>",
58
+ "<extra_id_53>",
59
+ "<extra_id_54>",
60
+ "<extra_id_55>",
61
+ "<extra_id_56>",
62
+ "<extra_id_57>",
63
+ "<extra_id_58>",
64
+ "<extra_id_59>",
65
+ "<extra_id_60>",
66
+ "<extra_id_61>",
67
+ "<extra_id_62>",
68
+ "<extra_id_63>",
69
+ "<extra_id_64>",
70
+ "<extra_id_65>",
71
+ "<extra_id_66>",
72
+ "<extra_id_67>",
73
+ "<extra_id_68>",
74
+ "<extra_id_69>",
75
+ "<extra_id_70>",
76
+ "<extra_id_71>",
77
+ "<extra_id_72>",
78
+ "<extra_id_73>",
79
+ "<extra_id_74>",
80
+ "<extra_id_75>",
81
+ "<extra_id_76>",
82
+ "<extra_id_77>",
83
+ "<extra_id_78>",
84
+ "<extra_id_79>",
85
+ "<extra_id_80>",
86
+ "<extra_id_81>",
87
+ "<extra_id_82>",
88
+ "<extra_id_83>",
89
+ "<extra_id_84>",
90
+ "<extra_id_85>",
91
+ "<extra_id_86>",
92
+ "<extra_id_87>",
93
+ "<extra_id_88>",
94
+ "<extra_id_89>",
95
+ "<extra_id_90>",
96
+ "<extra_id_91>",
97
+ "<extra_id_92>",
98
+ "<extra_id_93>",
99
+ "<extra_id_94>",
100
+ "<extra_id_95>",
101
+ "<extra_id_96>",
102
+ "<extra_id_97>",
103
+ "<extra_id_98>",
104
+ "<extra_id_99>"
105
+ ],
106
+ "eos_token": {
107
+ "content": "</s>",
108
+ "lstrip": false,
109
+ "normalized": false,
110
+ "rstrip": false,
111
+ "single_word": false
112
+ },
113
+ "pad_token": {
114
+ "content": "<pad>",
115
+ "lstrip": false,
116
+ "normalized": false,
117
+ "rstrip": false,
118
+ "single_word": false
119
+ },
120
+ "unk_token": {
121
+ "content": "<unk>",
122
+ "lstrip": false,
123
+ "normalized": false,
124
+ "rstrip": false,
125
+ "single_word": false
126
+ }
127
+ }
checkpoint/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
3
+ size 1111492
checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,959 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32100": {
829
+ "content": "<BN>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32101": {
837
+ "content": "<CH>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<BN>",
847
+ "<CH>",
848
+ "<extra_id_0>",
849
+ "<extra_id_1>",
850
+ "<extra_id_2>",
851
+ "<extra_id_3>",
852
+ "<extra_id_4>",
853
+ "<extra_id_5>",
854
+ "<extra_id_6>",
855
+ "<extra_id_7>",
856
+ "<extra_id_8>",
857
+ "<extra_id_9>",
858
+ "<extra_id_10>",
859
+ "<extra_id_11>",
860
+ "<extra_id_12>",
861
+ "<extra_id_13>",
862
+ "<extra_id_14>",
863
+ "<extra_id_15>",
864
+ "<extra_id_16>",
865
+ "<extra_id_17>",
866
+ "<extra_id_18>",
867
+ "<extra_id_19>",
868
+ "<extra_id_20>",
869
+ "<extra_id_21>",
870
+ "<extra_id_22>",
871
+ "<extra_id_23>",
872
+ "<extra_id_24>",
873
+ "<extra_id_25>",
874
+ "<extra_id_26>",
875
+ "<extra_id_27>",
876
+ "<extra_id_28>",
877
+ "<extra_id_29>",
878
+ "<extra_id_30>",
879
+ "<extra_id_31>",
880
+ "<extra_id_32>",
881
+ "<extra_id_33>",
882
+ "<extra_id_34>",
883
+ "<extra_id_35>",
884
+ "<extra_id_36>",
885
+ "<extra_id_37>",
886
+ "<extra_id_38>",
887
+ "<extra_id_39>",
888
+ "<extra_id_40>",
889
+ "<extra_id_41>",
890
+ "<extra_id_42>",
891
+ "<extra_id_43>",
892
+ "<extra_id_44>",
893
+ "<extra_id_45>",
894
+ "<extra_id_46>",
895
+ "<extra_id_47>",
896
+ "<extra_id_48>",
897
+ "<extra_id_49>",
898
+ "<extra_id_50>",
899
+ "<extra_id_51>",
900
+ "<extra_id_52>",
901
+ "<extra_id_53>",
902
+ "<extra_id_54>",
903
+ "<extra_id_55>",
904
+ "<extra_id_56>",
905
+ "<extra_id_57>",
906
+ "<extra_id_58>",
907
+ "<extra_id_59>",
908
+ "<extra_id_60>",
909
+ "<extra_id_61>",
910
+ "<extra_id_62>",
911
+ "<extra_id_63>",
912
+ "<extra_id_64>",
913
+ "<extra_id_65>",
914
+ "<extra_id_66>",
915
+ "<extra_id_67>",
916
+ "<extra_id_68>",
917
+ "<extra_id_69>",
918
+ "<extra_id_70>",
919
+ "<extra_id_71>",
920
+ "<extra_id_72>",
921
+ "<extra_id_73>",
922
+ "<extra_id_74>",
923
+ "<extra_id_75>",
924
+ "<extra_id_76>",
925
+ "<extra_id_77>",
926
+ "<extra_id_78>",
927
+ "<extra_id_79>",
928
+ "<extra_id_80>",
929
+ "<extra_id_81>",
930
+ "<extra_id_82>",
931
+ "<extra_id_83>",
932
+ "<extra_id_84>",
933
+ "<extra_id_85>",
934
+ "<extra_id_86>",
935
+ "<extra_id_87>",
936
+ "<extra_id_88>",
937
+ "<extra_id_89>",
938
+ "<extra_id_90>",
939
+ "<extra_id_91>",
940
+ "<extra_id_92>",
941
+ "<extra_id_93>",
942
+ "<extra_id_94>",
943
+ "<extra_id_95>",
944
+ "<extra_id_96>",
945
+ "<extra_id_97>",
946
+ "<extra_id_98>",
947
+ "<extra_id_99>"
948
+ ],
949
+ "clean_up_tokenization_spaces": false,
950
+ "eos_token": "</s>",
951
+ "extra_ids": 100,
952
+ "extra_special_tokens": {},
953
+ "legacy": true,
954
+ "model_max_length": 512,
955
+ "pad_token": "<pad>",
956
+ "sp_model_kwargs": {},
957
+ "tokenizer_class": "T5Tokenizer",
958
+ "unk_token": "<unk>"
959
+ }
checkpoint/trainer_state.json ADDED
@@ -0,0 +1,3722 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 20.0,
6
+ "eval_steps": 500,
7
+ "global_step": 50420,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.039666798889329634,
14
+ "grad_norm": 46.122135162353516,
15
+ "learning_rate": 4.990182467274891e-05,
16
+ "loss": 11.8425,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.07933359777865927,
21
+ "grad_norm": 23.861114501953125,
22
+ "learning_rate": 4.9802657675525586e-05,
23
+ "loss": 9.0419,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.1190003966679889,
28
+ "grad_norm": 11.361534118652344,
29
+ "learning_rate": 4.970349067830226e-05,
30
+ "loss": 7.4942,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.15866719555731854,
35
+ "grad_norm": 9.868680000305176,
36
+ "learning_rate": 4.960432368107894e-05,
37
+ "loss": 6.5606,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.19833399444664815,
42
+ "grad_norm": 19.773534774780273,
43
+ "learning_rate": 4.9505156683855616e-05,
44
+ "loss": 6.0234,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.2380007933359778,
49
+ "grad_norm": 6.297336101531982,
50
+ "learning_rate": 4.9405989686632294e-05,
51
+ "loss": 5.7502,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.2776675922253074,
56
+ "grad_norm": 6.993984222412109,
57
+ "learning_rate": 4.9306822689408966e-05,
58
+ "loss": 5.4746,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.31733439111463707,
63
+ "grad_norm": 5.947575569152832,
64
+ "learning_rate": 4.9207655692185645e-05,
65
+ "loss": 5.2263,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.3570011900039667,
70
+ "grad_norm": 6.459949493408203,
71
+ "learning_rate": 4.9108488694962317e-05,
72
+ "loss": 5.071,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.3966679888932963,
77
+ "grad_norm": 6.12597131729126,
78
+ "learning_rate": 4.9009321697738995e-05,
79
+ "loss": 4.9277,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.43633478778262597,
84
+ "grad_norm": 7.8361406326293945,
85
+ "learning_rate": 4.891015470051567e-05,
86
+ "loss": 4.7178,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.4760015866719556,
91
+ "grad_norm": 8.883167266845703,
92
+ "learning_rate": 4.881098770329235e-05,
93
+ "loss": 4.5832,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.5156683855612852,
98
+ "grad_norm": 5.529339790344238,
99
+ "learning_rate": 4.8711820706069024e-05,
100
+ "loss": 4.5019,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.5553351844506148,
105
+ "grad_norm": 5.6431121826171875,
106
+ "learning_rate": 4.86126537088457e-05,
107
+ "loss": 4.4477,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.5950019833399445,
112
+ "grad_norm": 5.4094367027282715,
113
+ "learning_rate": 4.8513486711622375e-05,
114
+ "loss": 4.317,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.6346687822292741,
119
+ "grad_norm": 4.631023406982422,
120
+ "learning_rate": 4.841431971439905e-05,
121
+ "loss": 4.2006,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.6743355811186037,
126
+ "grad_norm": 5.530189037322998,
127
+ "learning_rate": 4.8315152717175725e-05,
128
+ "loss": 4.0726,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.7140023800079334,
133
+ "grad_norm": 6.281075477600098,
134
+ "learning_rate": 4.82159857199524e-05,
135
+ "loss": 4.005,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.753669178897263,
140
+ "grad_norm": 8.573356628417969,
141
+ "learning_rate": 4.8116818722729076e-05,
142
+ "loss": 3.8903,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.7933359777865926,
147
+ "grad_norm": 7.195920467376709,
148
+ "learning_rate": 4.8017651725505754e-05,
149
+ "loss": 3.8038,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.8330027766759223,
154
+ "grad_norm": 6.207021236419678,
155
+ "learning_rate": 4.791848472828243e-05,
156
+ "loss": 3.775,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.8726695755652519,
161
+ "grad_norm": 6.628279685974121,
162
+ "learning_rate": 4.7819317731059105e-05,
163
+ "loss": 3.711,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.9123363744545815,
168
+ "grad_norm": 5.220765590667725,
169
+ "learning_rate": 4.7720150733835784e-05,
170
+ "loss": 3.6694,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.9520031733439112,
175
+ "grad_norm": 4.995284557342529,
176
+ "learning_rate": 4.7620983736612455e-05,
177
+ "loss": 3.5359,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.9916699722332408,
182
+ "grad_norm": 5.370284557342529,
183
+ "learning_rate": 4.7521816739389134e-05,
184
+ "loss": 3.5537,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 1.0,
189
+ "eval_loss": 2.6742756366729736,
190
+ "eval_runtime": 33.2175,
191
+ "eval_samples_per_second": 45.699,
192
+ "eval_steps_per_second": 5.72,
193
+ "step": 2521
194
+ },
195
+ {
196
+ "epoch": 1.0313367711225705,
197
+ "grad_norm": 6.217808246612549,
198
+ "learning_rate": 4.7422649742165806e-05,
199
+ "loss": 3.4208,
200
+ "step": 2600
201
+ },
202
+ {
203
+ "epoch": 1.0710035700119,
204
+ "grad_norm": 5.972238540649414,
205
+ "learning_rate": 4.7323482744942484e-05,
206
+ "loss": 3.3766,
207
+ "step": 2700
208
+ },
209
+ {
210
+ "epoch": 1.1106703689012296,
211
+ "grad_norm": 6.439736366271973,
212
+ "learning_rate": 4.722431574771916e-05,
213
+ "loss": 3.2706,
214
+ "step": 2800
215
+ },
216
+ {
217
+ "epoch": 1.1503371677905594,
218
+ "grad_norm": 4.722689151763916,
219
+ "learning_rate": 4.712514875049584e-05,
220
+ "loss": 3.1785,
221
+ "step": 2900
222
+ },
223
+ {
224
+ "epoch": 1.190003966679889,
225
+ "grad_norm": 4.344363689422607,
226
+ "learning_rate": 4.7025981753272514e-05,
227
+ "loss": 3.2959,
228
+ "step": 3000
229
+ },
230
+ {
231
+ "epoch": 1.2296707655692185,
232
+ "grad_norm": 5.724086284637451,
233
+ "learning_rate": 4.6926814756049185e-05,
234
+ "loss": 3.1135,
235
+ "step": 3100
236
+ },
237
+ {
238
+ "epoch": 1.269337564458548,
239
+ "grad_norm": 5.9762163162231445,
240
+ "learning_rate": 4.6827647758825864e-05,
241
+ "loss": 3.2194,
242
+ "step": 3200
243
+ },
244
+ {
245
+ "epoch": 1.3090043633478778,
246
+ "grad_norm": 5.490255355834961,
247
+ "learning_rate": 4.6728480761602536e-05,
248
+ "loss": 3.1226,
249
+ "step": 3300
250
+ },
251
+ {
252
+ "epoch": 1.3486711622372074,
253
+ "grad_norm": 5.34173583984375,
254
+ "learning_rate": 4.6629313764379215e-05,
255
+ "loss": 3.0641,
256
+ "step": 3400
257
+ },
258
+ {
259
+ "epoch": 1.388337961126537,
260
+ "grad_norm": 6.500023365020752,
261
+ "learning_rate": 4.653014676715589e-05,
262
+ "loss": 3.0342,
263
+ "step": 3500
264
+ },
265
+ {
266
+ "epoch": 1.4280047600158667,
267
+ "grad_norm": 4.705812931060791,
268
+ "learning_rate": 4.643097976993257e-05,
269
+ "loss": 2.9638,
270
+ "step": 3600
271
+ },
272
+ {
273
+ "epoch": 1.4676715589051963,
274
+ "grad_norm": 5.796449661254883,
275
+ "learning_rate": 4.6331812772709244e-05,
276
+ "loss": 2.9635,
277
+ "step": 3700
278
+ },
279
+ {
280
+ "epoch": 1.5073383577945259,
281
+ "grad_norm": 5.73616886138916,
282
+ "learning_rate": 4.623264577548592e-05,
283
+ "loss": 2.9933,
284
+ "step": 3800
285
+ },
286
+ {
287
+ "epoch": 1.5470051566838556,
288
+ "grad_norm": 5.073670864105225,
289
+ "learning_rate": 4.6133478778262594e-05,
290
+ "loss": 2.9872,
291
+ "step": 3900
292
+ },
293
+ {
294
+ "epoch": 1.5866719555731852,
295
+ "grad_norm": 5.04343318939209,
296
+ "learning_rate": 4.603431178103927e-05,
297
+ "loss": 2.9624,
298
+ "step": 4000
299
+ },
300
+ {
301
+ "epoch": 1.6263387544625147,
302
+ "grad_norm": 4.266116619110107,
303
+ "learning_rate": 4.5935144783815945e-05,
304
+ "loss": 2.9711,
305
+ "step": 4100
306
+ },
307
+ {
308
+ "epoch": 1.6660055533518445,
309
+ "grad_norm": 4.732306957244873,
310
+ "learning_rate": 4.583597778659262e-05,
311
+ "loss": 2.8238,
312
+ "step": 4200
313
+ },
314
+ {
315
+ "epoch": 1.705672352241174,
316
+ "grad_norm": 5.156635284423828,
317
+ "learning_rate": 4.57368107893693e-05,
318
+ "loss": 2.839,
319
+ "step": 4300
320
+ },
321
+ {
322
+ "epoch": 1.7453391511305036,
323
+ "grad_norm": 6.178804874420166,
324
+ "learning_rate": 4.563764379214598e-05,
325
+ "loss": 2.7441,
326
+ "step": 4400
327
+ },
328
+ {
329
+ "epoch": 1.7850059500198334,
330
+ "grad_norm": 6.307518482208252,
331
+ "learning_rate": 4.553847679492265e-05,
332
+ "loss": 2.7271,
333
+ "step": 4500
334
+ },
335
+ {
336
+ "epoch": 1.824672748909163,
337
+ "grad_norm": 4.5322136878967285,
338
+ "learning_rate": 4.5439309797699324e-05,
339
+ "loss": 2.6839,
340
+ "step": 4600
341
+ },
342
+ {
343
+ "epoch": 1.8643395477984925,
344
+ "grad_norm": 4.728321552276611,
345
+ "learning_rate": 4.5340142800476e-05,
346
+ "loss": 2.815,
347
+ "step": 4700
348
+ },
349
+ {
350
+ "epoch": 1.9040063466878223,
351
+ "grad_norm": 5.051918029785156,
352
+ "learning_rate": 4.5240975803252675e-05,
353
+ "loss": 2.6735,
354
+ "step": 4800
355
+ },
356
+ {
357
+ "epoch": 1.9436731455771519,
358
+ "grad_norm": 4.968688011169434,
359
+ "learning_rate": 4.5141808806029353e-05,
360
+ "loss": 2.6604,
361
+ "step": 4900
362
+ },
363
+ {
364
+ "epoch": 1.9833399444664814,
365
+ "grad_norm": 4.792623996734619,
366
+ "learning_rate": 4.504264180880603e-05,
367
+ "loss": 2.6375,
368
+ "step": 5000
369
+ },
370
+ {
371
+ "epoch": 2.0,
372
+ "eval_loss": 2.0515847206115723,
373
+ "eval_runtime": 33.0931,
374
+ "eval_samples_per_second": 45.871,
375
+ "eval_steps_per_second": 5.741,
376
+ "step": 5042
377
+ },
378
+ {
379
+ "epoch": 2.023006743355811,
380
+ "grad_norm": 7.228871822357178,
381
+ "learning_rate": 4.494347481158271e-05,
382
+ "loss": 2.5813,
383
+ "step": 5100
384
+ },
385
+ {
386
+ "epoch": 2.062673542245141,
387
+ "grad_norm": 4.44078254699707,
388
+ "learning_rate": 4.484430781435938e-05,
389
+ "loss": 2.5798,
390
+ "step": 5200
391
+ },
392
+ {
393
+ "epoch": 2.1023403411344703,
394
+ "grad_norm": 5.475325107574463,
395
+ "learning_rate": 4.474514081713606e-05,
396
+ "loss": 2.5297,
397
+ "step": 5300
398
+ },
399
+ {
400
+ "epoch": 2.1420071400238,
401
+ "grad_norm": 4.271339416503906,
402
+ "learning_rate": 4.464597381991273e-05,
403
+ "loss": 2.5595,
404
+ "step": 5400
405
+ },
406
+ {
407
+ "epoch": 2.18167393891313,
408
+ "grad_norm": 3.9716315269470215,
409
+ "learning_rate": 4.454680682268941e-05,
410
+ "loss": 2.5629,
411
+ "step": 5500
412
+ },
413
+ {
414
+ "epoch": 2.221340737802459,
415
+ "grad_norm": 5.6469807624816895,
416
+ "learning_rate": 4.4447639825466084e-05,
417
+ "loss": 2.4691,
418
+ "step": 5600
419
+ },
420
+ {
421
+ "epoch": 2.261007536691789,
422
+ "grad_norm": 4.760526657104492,
423
+ "learning_rate": 4.434847282824276e-05,
424
+ "loss": 2.606,
425
+ "step": 5700
426
+ },
427
+ {
428
+ "epoch": 2.300674335581119,
429
+ "grad_norm": 5.259726047515869,
430
+ "learning_rate": 4.424930583101944e-05,
431
+ "loss": 2.4984,
432
+ "step": 5800
433
+ },
434
+ {
435
+ "epoch": 2.340341134470448,
436
+ "grad_norm": 4.372512340545654,
437
+ "learning_rate": 4.415013883379612e-05,
438
+ "loss": 2.4104,
439
+ "step": 5900
440
+ },
441
+ {
442
+ "epoch": 2.380007933359778,
443
+ "grad_norm": 5.21671724319458,
444
+ "learning_rate": 4.405097183657279e-05,
445
+ "loss": 2.4612,
446
+ "step": 6000
447
+ },
448
+ {
449
+ "epoch": 2.4196747322491077,
450
+ "grad_norm": 4.706778049468994,
451
+ "learning_rate": 4.395180483934946e-05,
452
+ "loss": 2.3845,
453
+ "step": 6100
454
+ },
455
+ {
456
+ "epoch": 2.459341531138437,
457
+ "grad_norm": 4.4265217781066895,
458
+ "learning_rate": 4.385263784212614e-05,
459
+ "loss": 2.4508,
460
+ "step": 6200
461
+ },
462
+ {
463
+ "epoch": 2.499008330027767,
464
+ "grad_norm": 112.53572082519531,
465
+ "learning_rate": 4.3753470844902814e-05,
466
+ "loss": 2.3788,
467
+ "step": 6300
468
+ },
469
+ {
470
+ "epoch": 2.538675128917096,
471
+ "grad_norm": 5.193419933319092,
472
+ "learning_rate": 4.365430384767949e-05,
473
+ "loss": 2.3999,
474
+ "step": 6400
475
+ },
476
+ {
477
+ "epoch": 2.578341927806426,
478
+ "grad_norm": 4.786646842956543,
479
+ "learning_rate": 4.355513685045617e-05,
480
+ "loss": 2.3964,
481
+ "step": 6500
482
+ },
483
+ {
484
+ "epoch": 2.6180087266957557,
485
+ "grad_norm": 4.764982223510742,
486
+ "learning_rate": 4.345596985323285e-05,
487
+ "loss": 2.2939,
488
+ "step": 6600
489
+ },
490
+ {
491
+ "epoch": 2.657675525585085,
492
+ "grad_norm": 8.752727508544922,
493
+ "learning_rate": 4.335680285600952e-05,
494
+ "loss": 2.2859,
495
+ "step": 6700
496
+ },
497
+ {
498
+ "epoch": 2.697342324474415,
499
+ "grad_norm": 5.419288158416748,
500
+ "learning_rate": 4.32576358587862e-05,
501
+ "loss": 2.3073,
502
+ "step": 6800
503
+ },
504
+ {
505
+ "epoch": 2.7370091233637446,
506
+ "grad_norm": 3.573631763458252,
507
+ "learning_rate": 4.315846886156287e-05,
508
+ "loss": 2.1833,
509
+ "step": 6900
510
+ },
511
+ {
512
+ "epoch": 2.776675922253074,
513
+ "grad_norm": 5.297525882720947,
514
+ "learning_rate": 4.305930186433955e-05,
515
+ "loss": 2.4245,
516
+ "step": 7000
517
+ },
518
+ {
519
+ "epoch": 2.8163427211424037,
520
+ "grad_norm": 4.3615827560424805,
521
+ "learning_rate": 4.296013486711622e-05,
522
+ "loss": 2.2811,
523
+ "step": 7100
524
+ },
525
+ {
526
+ "epoch": 2.8560095200317335,
527
+ "grad_norm": 6.935328960418701,
528
+ "learning_rate": 4.28609678698929e-05,
529
+ "loss": 2.2544,
530
+ "step": 7200
531
+ },
532
+ {
533
+ "epoch": 2.895676318921063,
534
+ "grad_norm": 3.9425063133239746,
535
+ "learning_rate": 4.276180087266958e-05,
536
+ "loss": 2.2934,
537
+ "step": 7300
538
+ },
539
+ {
540
+ "epoch": 2.9353431178103926,
541
+ "grad_norm": 6.062328815460205,
542
+ "learning_rate": 4.266263387544626e-05,
543
+ "loss": 2.3048,
544
+ "step": 7400
545
+ },
546
+ {
547
+ "epoch": 2.9750099166997224,
548
+ "grad_norm": 4.808726787567139,
549
+ "learning_rate": 4.256346687822293e-05,
550
+ "loss": 2.2118,
551
+ "step": 7500
552
+ },
553
+ {
554
+ "epoch": 3.0,
555
+ "eval_loss": 1.770484209060669,
556
+ "eval_runtime": 33.1033,
557
+ "eval_samples_per_second": 45.856,
558
+ "eval_steps_per_second": 5.74,
559
+ "step": 7563
560
+ },
561
+ {
562
+ "epoch": 3.014676715589052,
563
+ "grad_norm": 4.881776809692383,
564
+ "learning_rate": 4.24642998809996e-05,
565
+ "loss": 2.2472,
566
+ "step": 7600
567
+ },
568
+ {
569
+ "epoch": 3.0543435144783815,
570
+ "grad_norm": 6.6921706199646,
571
+ "learning_rate": 4.236513288377628e-05,
572
+ "loss": 2.1728,
573
+ "step": 7700
574
+ },
575
+ {
576
+ "epoch": 3.0940103133677113,
577
+ "grad_norm": 3.29506254196167,
578
+ "learning_rate": 4.226596588655295e-05,
579
+ "loss": 2.0689,
580
+ "step": 7800
581
+ },
582
+ {
583
+ "epoch": 3.133677112257041,
584
+ "grad_norm": 4.864801406860352,
585
+ "learning_rate": 4.216679888932963e-05,
586
+ "loss": 2.2328,
587
+ "step": 7900
588
+ },
589
+ {
590
+ "epoch": 3.1733439111463704,
591
+ "grad_norm": 3.8594539165496826,
592
+ "learning_rate": 4.206763189210631e-05,
593
+ "loss": 2.0911,
594
+ "step": 8000
595
+ },
596
+ {
597
+ "epoch": 3.2130107100357,
598
+ "grad_norm": 5.1737380027771,
599
+ "learning_rate": 4.196846489488299e-05,
600
+ "loss": 2.0999,
601
+ "step": 8100
602
+ },
603
+ {
604
+ "epoch": 3.25267750892503,
605
+ "grad_norm": 4.454146385192871,
606
+ "learning_rate": 4.186929789765966e-05,
607
+ "loss": 2.0902,
608
+ "step": 8200
609
+ },
610
+ {
611
+ "epoch": 3.2923443078143593,
612
+ "grad_norm": 5.417801380157471,
613
+ "learning_rate": 4.177013090043634e-05,
614
+ "loss": 2.0971,
615
+ "step": 8300
616
+ },
617
+ {
618
+ "epoch": 3.332011106703689,
619
+ "grad_norm": 2.7768959999084473,
620
+ "learning_rate": 4.167096390321301e-05,
621
+ "loss": 2.1635,
622
+ "step": 8400
623
+ },
624
+ {
625
+ "epoch": 3.371677905593019,
626
+ "grad_norm": 4.387384414672852,
627
+ "learning_rate": 4.157179690598969e-05,
628
+ "loss": 2.0166,
629
+ "step": 8500
630
+ },
631
+ {
632
+ "epoch": 3.411344704482348,
633
+ "grad_norm": 4.593613624572754,
634
+ "learning_rate": 4.147262990876636e-05,
635
+ "loss": 2.0944,
636
+ "step": 8600
637
+ },
638
+ {
639
+ "epoch": 3.451011503371678,
640
+ "grad_norm": 5.243652820587158,
641
+ "learning_rate": 4.137346291154304e-05,
642
+ "loss": 2.0518,
643
+ "step": 8700
644
+ },
645
+ {
646
+ "epoch": 3.4906783022610077,
647
+ "grad_norm": 5.076266765594482,
648
+ "learning_rate": 4.127429591431972e-05,
649
+ "loss": 2.0412,
650
+ "step": 8800
651
+ },
652
+ {
653
+ "epoch": 3.530345101150337,
654
+ "grad_norm": 5.36345911026001,
655
+ "learning_rate": 4.11751289170964e-05,
656
+ "loss": 2.0586,
657
+ "step": 8900
658
+ },
659
+ {
660
+ "epoch": 3.570011900039667,
661
+ "grad_norm": 6.591952800750732,
662
+ "learning_rate": 4.107596191987307e-05,
663
+ "loss": 2.059,
664
+ "step": 9000
665
+ },
666
+ {
667
+ "epoch": 3.609678698928996,
668
+ "grad_norm": 5.091315746307373,
669
+ "learning_rate": 4.097679492264974e-05,
670
+ "loss": 2.0451,
671
+ "step": 9100
672
+ },
673
+ {
674
+ "epoch": 3.649345497818326,
675
+ "grad_norm": 4.647657871246338,
676
+ "learning_rate": 4.087762792542642e-05,
677
+ "loss": 2.0488,
678
+ "step": 9200
679
+ },
680
+ {
681
+ "epoch": 3.6890122967076557,
682
+ "grad_norm": 5.167809963226318,
683
+ "learning_rate": 4.077846092820309e-05,
684
+ "loss": 2.0688,
685
+ "step": 9300
686
+ },
687
+ {
688
+ "epoch": 3.728679095596985,
689
+ "grad_norm": 67.48959350585938,
690
+ "learning_rate": 4.067929393097977e-05,
691
+ "loss": 2.0513,
692
+ "step": 9400
693
+ },
694
+ {
695
+ "epoch": 3.768345894486315,
696
+ "grad_norm": 3.942390203475952,
697
+ "learning_rate": 4.058012693375645e-05,
698
+ "loss": 1.9697,
699
+ "step": 9500
700
+ },
701
+ {
702
+ "epoch": 3.8080126933756446,
703
+ "grad_norm": 5.491151332855225,
704
+ "learning_rate": 4.048095993653313e-05,
705
+ "loss": 2.0849,
706
+ "step": 9600
707
+ },
708
+ {
709
+ "epoch": 3.847679492264974,
710
+ "grad_norm": 4.637006759643555,
711
+ "learning_rate": 4.03817929393098e-05,
712
+ "loss": 1.9753,
713
+ "step": 9700
714
+ },
715
+ {
716
+ "epoch": 3.8873462911543037,
717
+ "grad_norm": 4.818416595458984,
718
+ "learning_rate": 4.028262594208648e-05,
719
+ "loss": 2.0526,
720
+ "step": 9800
721
+ },
722
+ {
723
+ "epoch": 3.9270130900436335,
724
+ "grad_norm": 4.810122013092041,
725
+ "learning_rate": 4.018345894486315e-05,
726
+ "loss": 2.0148,
727
+ "step": 9900
728
+ },
729
+ {
730
+ "epoch": 3.966679888932963,
731
+ "grad_norm": 4.372331142425537,
732
+ "learning_rate": 4.008429194763983e-05,
733
+ "loss": 2.0324,
734
+ "step": 10000
735
+ },
736
+ {
737
+ "epoch": 4.0,
738
+ "eval_loss": 1.5883285999298096,
739
+ "eval_runtime": 33.141,
740
+ "eval_samples_per_second": 45.804,
741
+ "eval_steps_per_second": 5.733,
742
+ "step": 10084
743
+ },
744
+ {
745
+ "epoch": 4.006346687822293,
746
+ "grad_norm": 4.643691539764404,
747
+ "learning_rate": 3.99851249504165e-05,
748
+ "loss": 2.0171,
749
+ "step": 10100
750
+ },
751
+ {
752
+ "epoch": 4.046013486711622,
753
+ "grad_norm": 5.210694789886475,
754
+ "learning_rate": 3.988595795319318e-05,
755
+ "loss": 1.9401,
756
+ "step": 10200
757
+ },
758
+ {
759
+ "epoch": 4.085680285600952,
760
+ "grad_norm": 5.724204063415527,
761
+ "learning_rate": 3.978679095596986e-05,
762
+ "loss": 1.9012,
763
+ "step": 10300
764
+ },
765
+ {
766
+ "epoch": 4.125347084490282,
767
+ "grad_norm": 3.6750075817108154,
768
+ "learning_rate": 3.9687623958746536e-05,
769
+ "loss": 1.7982,
770
+ "step": 10400
771
+ },
772
+ {
773
+ "epoch": 4.165013883379611,
774
+ "grad_norm": 4.948938369750977,
775
+ "learning_rate": 3.958845696152321e-05,
776
+ "loss": 1.9426,
777
+ "step": 10500
778
+ },
779
+ {
780
+ "epoch": 4.204680682268941,
781
+ "grad_norm": 5.098011016845703,
782
+ "learning_rate": 3.948928996429988e-05,
783
+ "loss": 1.9476,
784
+ "step": 10600
785
+ },
786
+ {
787
+ "epoch": 4.244347481158271,
788
+ "grad_norm": 3.605708599090576,
789
+ "learning_rate": 3.939012296707656e-05,
790
+ "loss": 1.91,
791
+ "step": 10700
792
+ },
793
+ {
794
+ "epoch": 4.2840142800476,
795
+ "grad_norm": 4.1741766929626465,
796
+ "learning_rate": 3.929095596985323e-05,
797
+ "loss": 1.9512,
798
+ "step": 10800
799
+ },
800
+ {
801
+ "epoch": 4.3236810789369295,
802
+ "grad_norm": 4.427469730377197,
803
+ "learning_rate": 3.919178897262991e-05,
804
+ "loss": 1.859,
805
+ "step": 10900
806
+ },
807
+ {
808
+ "epoch": 4.36334787782626,
809
+ "grad_norm": 4.128306865692139,
810
+ "learning_rate": 3.909262197540659e-05,
811
+ "loss": 1.8465,
812
+ "step": 11000
813
+ },
814
+ {
815
+ "epoch": 4.403014676715589,
816
+ "grad_norm": 3.959047317504883,
817
+ "learning_rate": 3.8993454978183266e-05,
818
+ "loss": 1.9168,
819
+ "step": 11100
820
+ },
821
+ {
822
+ "epoch": 4.442681475604918,
823
+ "grad_norm": 5.283690452575684,
824
+ "learning_rate": 3.889428798095994e-05,
825
+ "loss": 1.8212,
826
+ "step": 11200
827
+ },
828
+ {
829
+ "epoch": 4.482348274494249,
830
+ "grad_norm": 4.190108299255371,
831
+ "learning_rate": 3.8795120983736616e-05,
832
+ "loss": 1.7881,
833
+ "step": 11300
834
+ },
835
+ {
836
+ "epoch": 4.522015073383578,
837
+ "grad_norm": 5.957630157470703,
838
+ "learning_rate": 3.869595398651329e-05,
839
+ "loss": 1.8606,
840
+ "step": 11400
841
+ },
842
+ {
843
+ "epoch": 4.561681872272907,
844
+ "grad_norm": 4.41494607925415,
845
+ "learning_rate": 3.859678698928997e-05,
846
+ "loss": 1.8808,
847
+ "step": 11500
848
+ },
849
+ {
850
+ "epoch": 4.601348671162238,
851
+ "grad_norm": 4.355372428894043,
852
+ "learning_rate": 3.849761999206664e-05,
853
+ "loss": 1.8034,
854
+ "step": 11600
855
+ },
856
+ {
857
+ "epoch": 4.641015470051567,
858
+ "grad_norm": 4.594727993011475,
859
+ "learning_rate": 3.839845299484332e-05,
860
+ "loss": 1.8631,
861
+ "step": 11700
862
+ },
863
+ {
864
+ "epoch": 4.680682268940896,
865
+ "grad_norm": 3.8081648349761963,
866
+ "learning_rate": 3.8299285997619996e-05,
867
+ "loss": 1.7664,
868
+ "step": 11800
869
+ },
870
+ {
871
+ "epoch": 4.7203490678302265,
872
+ "grad_norm": 5.383887767791748,
873
+ "learning_rate": 3.8200119000396675e-05,
874
+ "loss": 1.8918,
875
+ "step": 11900
876
+ },
877
+ {
878
+ "epoch": 4.760015866719556,
879
+ "grad_norm": 4.703048229217529,
880
+ "learning_rate": 3.8100952003173347e-05,
881
+ "loss": 1.7821,
882
+ "step": 12000
883
+ },
884
+ {
885
+ "epoch": 4.799682665608885,
886
+ "grad_norm": 5.115866661071777,
887
+ "learning_rate": 3.800178500595002e-05,
888
+ "loss": 1.8276,
889
+ "step": 12100
890
+ },
891
+ {
892
+ "epoch": 4.839349464498215,
893
+ "grad_norm": 4.647130012512207,
894
+ "learning_rate": 3.79026180087267e-05,
895
+ "loss": 1.7743,
896
+ "step": 12200
897
+ },
898
+ {
899
+ "epoch": 4.879016263387545,
900
+ "grad_norm": 4.2948994636535645,
901
+ "learning_rate": 3.780345101150337e-05,
902
+ "loss": 1.7567,
903
+ "step": 12300
904
+ },
905
+ {
906
+ "epoch": 4.918683062276874,
907
+ "grad_norm": 4.055002212524414,
908
+ "learning_rate": 3.770428401428005e-05,
909
+ "loss": 1.832,
910
+ "step": 12400
911
+ },
912
+ {
913
+ "epoch": 4.958349861166204,
914
+ "grad_norm": 4.373877048492432,
915
+ "learning_rate": 3.7605117017056726e-05,
916
+ "loss": 1.7995,
917
+ "step": 12500
918
+ },
919
+ {
920
+ "epoch": 4.998016660055534,
921
+ "grad_norm": 5.246423721313477,
922
+ "learning_rate": 3.7505950019833405e-05,
923
+ "loss": 1.7464,
924
+ "step": 12600
925
+ },
926
+ {
927
+ "epoch": 5.0,
928
+ "eval_loss": 1.4670053720474243,
929
+ "eval_runtime": 33.135,
930
+ "eval_samples_per_second": 45.813,
931
+ "eval_steps_per_second": 5.734,
932
+ "step": 12605
933
+ },
934
+ {
935
+ "epoch": 5.037683458944863,
936
+ "grad_norm": 5.669796943664551,
937
+ "learning_rate": 3.740678302261008e-05,
938
+ "loss": 1.6803,
939
+ "step": 12700
940
+ },
941
+ {
942
+ "epoch": 5.077350257834193,
943
+ "grad_norm": 4.203566074371338,
944
+ "learning_rate": 3.7307616025386755e-05,
945
+ "loss": 1.665,
946
+ "step": 12800
947
+ },
948
+ {
949
+ "epoch": 5.1170170567235225,
950
+ "grad_norm": 3.6892035007476807,
951
+ "learning_rate": 3.720844902816343e-05,
952
+ "loss": 1.7269,
953
+ "step": 12900
954
+ },
955
+ {
956
+ "epoch": 5.156683855612852,
957
+ "grad_norm": 4.452983379364014,
958
+ "learning_rate": 3.7109282030940106e-05,
959
+ "loss": 1.7276,
960
+ "step": 13000
961
+ },
962
+ {
963
+ "epoch": 5.196350654502182,
964
+ "grad_norm": 3.7172744274139404,
965
+ "learning_rate": 3.701011503371678e-05,
966
+ "loss": 1.6838,
967
+ "step": 13100
968
+ },
969
+ {
970
+ "epoch": 5.236017453391511,
971
+ "grad_norm": 4.209805488586426,
972
+ "learning_rate": 3.6910948036493456e-05,
973
+ "loss": 1.6982,
974
+ "step": 13200
975
+ },
976
+ {
977
+ "epoch": 5.275684252280841,
978
+ "grad_norm": 4.2851362228393555,
979
+ "learning_rate": 3.6811781039270135e-05,
980
+ "loss": 1.6656,
981
+ "step": 13300
982
+ },
983
+ {
984
+ "epoch": 5.315351051170171,
985
+ "grad_norm": 3.345033884048462,
986
+ "learning_rate": 3.6712614042046814e-05,
987
+ "loss": 1.7176,
988
+ "step": 13400
989
+ },
990
+ {
991
+ "epoch": 5.3550178500595,
992
+ "grad_norm": 7.854482173919678,
993
+ "learning_rate": 3.6613447044823485e-05,
994
+ "loss": 1.7395,
995
+ "step": 13500
996
+ },
997
+ {
998
+ "epoch": 5.39468464894883,
999
+ "grad_norm": 5.201159477233887,
1000
+ "learning_rate": 3.651428004760016e-05,
1001
+ "loss": 1.7159,
1002
+ "step": 13600
1003
+ },
1004
+ {
1005
+ "epoch": 5.43435144783816,
1006
+ "grad_norm": 5.032053470611572,
1007
+ "learning_rate": 3.6415113050376836e-05,
1008
+ "loss": 1.7993,
1009
+ "step": 13700
1010
+ },
1011
+ {
1012
+ "epoch": 5.474018246727489,
1013
+ "grad_norm": 4.350612640380859,
1014
+ "learning_rate": 3.631594605315351e-05,
1015
+ "loss": 1.722,
1016
+ "step": 13800
1017
+ },
1018
+ {
1019
+ "epoch": 5.5136850456168185,
1020
+ "grad_norm": 5.67685604095459,
1021
+ "learning_rate": 3.6216779055930186e-05,
1022
+ "loss": 1.5882,
1023
+ "step": 13900
1024
+ },
1025
+ {
1026
+ "epoch": 5.553351844506149,
1027
+ "grad_norm": 3.8744733333587646,
1028
+ "learning_rate": 3.6117612058706865e-05,
1029
+ "loss": 1.6864,
1030
+ "step": 14000
1031
+ },
1032
+ {
1033
+ "epoch": 5.593018643395478,
1034
+ "grad_norm": 3.0556750297546387,
1035
+ "learning_rate": 3.6018445061483544e-05,
1036
+ "loss": 1.6494,
1037
+ "step": 14100
1038
+ },
1039
+ {
1040
+ "epoch": 5.632685442284807,
1041
+ "grad_norm": 5.0797343254089355,
1042
+ "learning_rate": 3.5919278064260215e-05,
1043
+ "loss": 1.747,
1044
+ "step": 14200
1045
+ },
1046
+ {
1047
+ "epoch": 5.672352241174138,
1048
+ "grad_norm": 4.625453948974609,
1049
+ "learning_rate": 3.5820111067036894e-05,
1050
+ "loss": 1.689,
1051
+ "step": 14300
1052
+ },
1053
+ {
1054
+ "epoch": 5.712019040063467,
1055
+ "grad_norm": 5.2560133934021,
1056
+ "learning_rate": 3.5720944069813566e-05,
1057
+ "loss": 1.6218,
1058
+ "step": 14400
1059
+ },
1060
+ {
1061
+ "epoch": 5.751685838952796,
1062
+ "grad_norm": 4.45328950881958,
1063
+ "learning_rate": 3.5621777072590245e-05,
1064
+ "loss": 1.7095,
1065
+ "step": 14500
1066
+ },
1067
+ {
1068
+ "epoch": 5.7913526378421265,
1069
+ "grad_norm": 3.0788328647613525,
1070
+ "learning_rate": 3.5522610075366916e-05,
1071
+ "loss": 1.7223,
1072
+ "step": 14600
1073
+ },
1074
+ {
1075
+ "epoch": 5.831019436731456,
1076
+ "grad_norm": 6.247290134429932,
1077
+ "learning_rate": 3.5423443078143595e-05,
1078
+ "loss": 1.6158,
1079
+ "step": 14700
1080
+ },
1081
+ {
1082
+ "epoch": 5.870686235620785,
1083
+ "grad_norm": 4.095520973205566,
1084
+ "learning_rate": 3.5324276080920274e-05,
1085
+ "loss": 1.6313,
1086
+ "step": 14800
1087
+ },
1088
+ {
1089
+ "epoch": 5.910353034510115,
1090
+ "grad_norm": 4.251845836639404,
1091
+ "learning_rate": 3.522510908369695e-05,
1092
+ "loss": 1.6458,
1093
+ "step": 14900
1094
+ },
1095
+ {
1096
+ "epoch": 5.950019833399445,
1097
+ "grad_norm": 3.833702802658081,
1098
+ "learning_rate": 3.5125942086473624e-05,
1099
+ "loss": 1.6425,
1100
+ "step": 15000
1101
+ },
1102
+ {
1103
+ "epoch": 5.989686632288774,
1104
+ "grad_norm": 4.577655792236328,
1105
+ "learning_rate": 3.5026775089250296e-05,
1106
+ "loss": 1.6747,
1107
+ "step": 15100
1108
+ },
1109
+ {
1110
+ "epoch": 6.0,
1111
+ "eval_loss": 1.3812555074691772,
1112
+ "eval_runtime": 33.4674,
1113
+ "eval_samples_per_second": 45.358,
1114
+ "eval_steps_per_second": 5.677,
1115
+ "step": 15126
1116
+ },
1117
+ {
1118
+ "epoch": 6.029353431178104,
1119
+ "grad_norm": 3.609616279602051,
1120
+ "learning_rate": 3.4927608092026975e-05,
1121
+ "loss": 1.6579,
1122
+ "step": 15200
1123
+ },
1124
+ {
1125
+ "epoch": 6.069020230067434,
1126
+ "grad_norm": 3.5658130645751953,
1127
+ "learning_rate": 3.4828441094803647e-05,
1128
+ "loss": 1.6842,
1129
+ "step": 15300
1130
+ },
1131
+ {
1132
+ "epoch": 6.108687028956763,
1133
+ "grad_norm": 4.586058139801025,
1134
+ "learning_rate": 3.4729274097580325e-05,
1135
+ "loss": 1.5563,
1136
+ "step": 15400
1137
+ },
1138
+ {
1139
+ "epoch": 6.148353827846093,
1140
+ "grad_norm": 5.103824615478516,
1141
+ "learning_rate": 3.4630107100357004e-05,
1142
+ "loss": 1.5386,
1143
+ "step": 15500
1144
+ },
1145
+ {
1146
+ "epoch": 6.1880206267354225,
1147
+ "grad_norm": 5.14306116104126,
1148
+ "learning_rate": 3.453094010313368e-05,
1149
+ "loss": 1.6081,
1150
+ "step": 15600
1151
+ },
1152
+ {
1153
+ "epoch": 6.227687425624752,
1154
+ "grad_norm": 4.270661354064941,
1155
+ "learning_rate": 3.4431773105910354e-05,
1156
+ "loss": 1.5569,
1157
+ "step": 15700
1158
+ },
1159
+ {
1160
+ "epoch": 6.267354224514082,
1161
+ "grad_norm": 13.869562149047852,
1162
+ "learning_rate": 3.433260610868703e-05,
1163
+ "loss": 1.5484,
1164
+ "step": 15800
1165
+ },
1166
+ {
1167
+ "epoch": 6.307021023403411,
1168
+ "grad_norm": 3.9378180503845215,
1169
+ "learning_rate": 3.4233439111463705e-05,
1170
+ "loss": 1.5441,
1171
+ "step": 15900
1172
+ },
1173
+ {
1174
+ "epoch": 6.346687822292741,
1175
+ "grad_norm": 4.3542656898498535,
1176
+ "learning_rate": 3.4134272114240383e-05,
1177
+ "loss": 1.58,
1178
+ "step": 16000
1179
+ },
1180
+ {
1181
+ "epoch": 6.386354621182071,
1182
+ "grad_norm": 3.8545126914978027,
1183
+ "learning_rate": 3.4035105117017055e-05,
1184
+ "loss": 1.4445,
1185
+ "step": 16100
1186
+ },
1187
+ {
1188
+ "epoch": 6.4260214200714,
1189
+ "grad_norm": 3.9810452461242676,
1190
+ "learning_rate": 3.3935938119793734e-05,
1191
+ "loss": 1.6052,
1192
+ "step": 16200
1193
+ },
1194
+ {
1195
+ "epoch": 6.46568821896073,
1196
+ "grad_norm": 7.306039333343506,
1197
+ "learning_rate": 3.383677112257041e-05,
1198
+ "loss": 1.608,
1199
+ "step": 16300
1200
+ },
1201
+ {
1202
+ "epoch": 6.50535501785006,
1203
+ "grad_norm": 4.018649578094482,
1204
+ "learning_rate": 3.373760412534709e-05,
1205
+ "loss": 1.581,
1206
+ "step": 16400
1207
+ },
1208
+ {
1209
+ "epoch": 6.545021816739389,
1210
+ "grad_norm": 5.1577019691467285,
1211
+ "learning_rate": 3.363843712812376e-05,
1212
+ "loss": 1.548,
1213
+ "step": 16500
1214
+ },
1215
+ {
1216
+ "epoch": 6.5846886156287185,
1217
+ "grad_norm": 6.858482837677002,
1218
+ "learning_rate": 3.3539270130900435e-05,
1219
+ "loss": 1.5823,
1220
+ "step": 16600
1221
+ },
1222
+ {
1223
+ "epoch": 6.624355414518049,
1224
+ "grad_norm": 4.213831901550293,
1225
+ "learning_rate": 3.3440103133677114e-05,
1226
+ "loss": 1.5199,
1227
+ "step": 16700
1228
+ },
1229
+ {
1230
+ "epoch": 6.664022213407378,
1231
+ "grad_norm": 3.531313180923462,
1232
+ "learning_rate": 3.3340936136453785e-05,
1233
+ "loss": 1.5993,
1234
+ "step": 16800
1235
+ },
1236
+ {
1237
+ "epoch": 6.703689012296707,
1238
+ "grad_norm": 4.222484588623047,
1239
+ "learning_rate": 3.3241769139230464e-05,
1240
+ "loss": 1.5839,
1241
+ "step": 16900
1242
+ },
1243
+ {
1244
+ "epoch": 6.743355811186038,
1245
+ "grad_norm": 3.11354660987854,
1246
+ "learning_rate": 3.314260214200714e-05,
1247
+ "loss": 1.5302,
1248
+ "step": 17000
1249
+ },
1250
+ {
1251
+ "epoch": 6.783022610075367,
1252
+ "grad_norm": 3.699721574783325,
1253
+ "learning_rate": 3.304343514478382e-05,
1254
+ "loss": 1.5662,
1255
+ "step": 17100
1256
+ },
1257
+ {
1258
+ "epoch": 6.822689408964696,
1259
+ "grad_norm": 6.095912456512451,
1260
+ "learning_rate": 3.294426814756049e-05,
1261
+ "loss": 1.6208,
1262
+ "step": 17200
1263
+ },
1264
+ {
1265
+ "epoch": 6.862356207854027,
1266
+ "grad_norm": 3.0489301681518555,
1267
+ "learning_rate": 3.284510115033717e-05,
1268
+ "loss": 1.4306,
1269
+ "step": 17300
1270
+ },
1271
+ {
1272
+ "epoch": 6.902023006743356,
1273
+ "grad_norm": 4.094913005828857,
1274
+ "learning_rate": 3.2745934153113844e-05,
1275
+ "loss": 1.438,
1276
+ "step": 17400
1277
+ },
1278
+ {
1279
+ "epoch": 6.941689805632685,
1280
+ "grad_norm": 3.900447130203247,
1281
+ "learning_rate": 3.264676715589052e-05,
1282
+ "loss": 1.4798,
1283
+ "step": 17500
1284
+ },
1285
+ {
1286
+ "epoch": 6.9813566045220155,
1287
+ "grad_norm": 4.244141578674316,
1288
+ "learning_rate": 3.2547600158667194e-05,
1289
+ "loss": 1.5627,
1290
+ "step": 17600
1291
+ },
1292
+ {
1293
+ "epoch": 7.0,
1294
+ "eval_loss": 1.3121882677078247,
1295
+ "eval_runtime": 33.1418,
1296
+ "eval_samples_per_second": 45.803,
1297
+ "eval_steps_per_second": 5.733,
1298
+ "step": 17647
1299
+ },
1300
+ {
1301
+ "epoch": 7.021023403411345,
1302
+ "grad_norm": 5.134289264678955,
1303
+ "learning_rate": 3.244843316144387e-05,
1304
+ "loss": 1.4704,
1305
+ "step": 17700
1306
+ },
1307
+ {
1308
+ "epoch": 7.060690202300674,
1309
+ "grad_norm": 4.705554008483887,
1310
+ "learning_rate": 3.234926616422055e-05,
1311
+ "loss": 1.4257,
1312
+ "step": 17800
1313
+ },
1314
+ {
1315
+ "epoch": 7.100357001190004,
1316
+ "grad_norm": 5.20936918258667,
1317
+ "learning_rate": 3.225009916699723e-05,
1318
+ "loss": 1.4684,
1319
+ "step": 17900
1320
+ },
1321
+ {
1322
+ "epoch": 7.140023800079334,
1323
+ "grad_norm": 5.669763565063477,
1324
+ "learning_rate": 3.21509321697739e-05,
1325
+ "loss": 1.4626,
1326
+ "step": 18000
1327
+ },
1328
+ {
1329
+ "epoch": 7.179690598968663,
1330
+ "grad_norm": 4.726533889770508,
1331
+ "learning_rate": 3.2051765172550574e-05,
1332
+ "loss": 1.4362,
1333
+ "step": 18100
1334
+ },
1335
+ {
1336
+ "epoch": 7.219357397857993,
1337
+ "grad_norm": 3.413167715072632,
1338
+ "learning_rate": 3.195259817532725e-05,
1339
+ "loss": 1.4591,
1340
+ "step": 18200
1341
+ },
1342
+ {
1343
+ "epoch": 7.259024196747323,
1344
+ "grad_norm": 3.3368911743164062,
1345
+ "learning_rate": 3.1853431178103924e-05,
1346
+ "loss": 1.5077,
1347
+ "step": 18300
1348
+ },
1349
+ {
1350
+ "epoch": 7.298690995636652,
1351
+ "grad_norm": 3.5089704990386963,
1352
+ "learning_rate": 3.17542641808806e-05,
1353
+ "loss": 1.509,
1354
+ "step": 18400
1355
+ },
1356
+ {
1357
+ "epoch": 7.338357794525982,
1358
+ "grad_norm": 4.13053035736084,
1359
+ "learning_rate": 3.165509718365728e-05,
1360
+ "loss": 1.5048,
1361
+ "step": 18500
1362
+ },
1363
+ {
1364
+ "epoch": 7.3780245934153115,
1365
+ "grad_norm": 4.646170139312744,
1366
+ "learning_rate": 3.155593018643396e-05,
1367
+ "loss": 1.474,
1368
+ "step": 18600
1369
+ },
1370
+ {
1371
+ "epoch": 7.417691392304641,
1372
+ "grad_norm": 4.4724812507629395,
1373
+ "learning_rate": 3.145676318921063e-05,
1374
+ "loss": 1.5448,
1375
+ "step": 18700
1376
+ },
1377
+ {
1378
+ "epoch": 7.457358191193971,
1379
+ "grad_norm": 3.79464054107666,
1380
+ "learning_rate": 3.135759619198731e-05,
1381
+ "loss": 1.4379,
1382
+ "step": 18800
1383
+ },
1384
+ {
1385
+ "epoch": 7.4970249900833,
1386
+ "grad_norm": 3.2396161556243896,
1387
+ "learning_rate": 3.125842919476398e-05,
1388
+ "loss": 1.4857,
1389
+ "step": 18900
1390
+ },
1391
+ {
1392
+ "epoch": 7.53669178897263,
1393
+ "grad_norm": 3.6047024726867676,
1394
+ "learning_rate": 3.115926219754066e-05,
1395
+ "loss": 1.453,
1396
+ "step": 19000
1397
+ },
1398
+ {
1399
+ "epoch": 7.57635858786196,
1400
+ "grad_norm": 4.998748779296875,
1401
+ "learning_rate": 3.106009520031733e-05,
1402
+ "loss": 1.4062,
1403
+ "step": 19100
1404
+ },
1405
+ {
1406
+ "epoch": 7.616025386751289,
1407
+ "grad_norm": 4.068435192108154,
1408
+ "learning_rate": 3.096092820309401e-05,
1409
+ "loss": 1.3582,
1410
+ "step": 19200
1411
+ },
1412
+ {
1413
+ "epoch": 7.655692185640619,
1414
+ "grad_norm": 5.680367469787598,
1415
+ "learning_rate": 3.086176120587069e-05,
1416
+ "loss": 1.4897,
1417
+ "step": 19300
1418
+ },
1419
+ {
1420
+ "epoch": 7.695358984529949,
1421
+ "grad_norm": 3.917802333831787,
1422
+ "learning_rate": 3.076259420864737e-05,
1423
+ "loss": 1.4195,
1424
+ "step": 19400
1425
+ },
1426
+ {
1427
+ "epoch": 7.735025783419278,
1428
+ "grad_norm": 3.1522891521453857,
1429
+ "learning_rate": 3.066342721142404e-05,
1430
+ "loss": 1.4599,
1431
+ "step": 19500
1432
+ },
1433
+ {
1434
+ "epoch": 7.7746925823086075,
1435
+ "grad_norm": 4.597601890563965,
1436
+ "learning_rate": 3.056426021420071e-05,
1437
+ "loss": 1.4701,
1438
+ "step": 19600
1439
+ },
1440
+ {
1441
+ "epoch": 7.814359381197937,
1442
+ "grad_norm": 4.217317581176758,
1443
+ "learning_rate": 3.046509321697739e-05,
1444
+ "loss": 1.4263,
1445
+ "step": 19700
1446
+ },
1447
+ {
1448
+ "epoch": 7.854026180087267,
1449
+ "grad_norm": 4.17954158782959,
1450
+ "learning_rate": 3.0365926219754066e-05,
1451
+ "loss": 1.4155,
1452
+ "step": 19800
1453
+ },
1454
+ {
1455
+ "epoch": 7.893692978976596,
1456
+ "grad_norm": 4.049231052398682,
1457
+ "learning_rate": 3.0266759222530745e-05,
1458
+ "loss": 1.4343,
1459
+ "step": 19900
1460
+ },
1461
+ {
1462
+ "epoch": 7.933359777865926,
1463
+ "grad_norm": 3.9351389408111572,
1464
+ "learning_rate": 3.0167592225307417e-05,
1465
+ "loss": 1.4247,
1466
+ "step": 20000
1467
+ },
1468
+ {
1469
+ "epoch": 7.973026576755256,
1470
+ "grad_norm": 6.478794097900391,
1471
+ "learning_rate": 3.0068425228084096e-05,
1472
+ "loss": 1.4336,
1473
+ "step": 20100
1474
+ },
1475
+ {
1476
+ "epoch": 8.0,
1477
+ "eval_loss": 1.2493535280227661,
1478
+ "eval_runtime": 33.1532,
1479
+ "eval_samples_per_second": 45.787,
1480
+ "eval_steps_per_second": 5.731,
1481
+ "step": 20168
1482
+ },
1483
+ {
1484
+ "epoch": 8.012693375644586,
1485
+ "grad_norm": 7.988471508026123,
1486
+ "learning_rate": 2.996925823086077e-05,
1487
+ "loss": 1.4408,
1488
+ "step": 20200
1489
+ },
1490
+ {
1491
+ "epoch": 8.052360174533915,
1492
+ "grad_norm": 3.978797674179077,
1493
+ "learning_rate": 2.987009123363745e-05,
1494
+ "loss": 1.4227,
1495
+ "step": 20300
1496
+ },
1497
+ {
1498
+ "epoch": 8.092026973423245,
1499
+ "grad_norm": 2.8589699268341064,
1500
+ "learning_rate": 2.977092423641412e-05,
1501
+ "loss": 1.3348,
1502
+ "step": 20400
1503
+ },
1504
+ {
1505
+ "epoch": 8.131693772312575,
1506
+ "grad_norm": 4.3820061683654785,
1507
+ "learning_rate": 2.96717572391908e-05,
1508
+ "loss": 1.3374,
1509
+ "step": 20500
1510
+ },
1511
+ {
1512
+ "epoch": 8.171360571201904,
1513
+ "grad_norm": 4.421834468841553,
1514
+ "learning_rate": 2.9572590241967475e-05,
1515
+ "loss": 1.379,
1516
+ "step": 20600
1517
+ },
1518
+ {
1519
+ "epoch": 8.211027370091234,
1520
+ "grad_norm": 3.6717193126678467,
1521
+ "learning_rate": 2.9473423244744154e-05,
1522
+ "loss": 1.3878,
1523
+ "step": 20700
1524
+ },
1525
+ {
1526
+ "epoch": 8.250694168980564,
1527
+ "grad_norm": 5.8960466384887695,
1528
+ "learning_rate": 2.9374256247520826e-05,
1529
+ "loss": 1.418,
1530
+ "step": 20800
1531
+ },
1532
+ {
1533
+ "epoch": 8.290360967869892,
1534
+ "grad_norm": 4.1541428565979,
1535
+ "learning_rate": 2.9275089250297504e-05,
1536
+ "loss": 1.3427,
1537
+ "step": 20900
1538
+ },
1539
+ {
1540
+ "epoch": 8.330027766759223,
1541
+ "grad_norm": 4.0375566482543945,
1542
+ "learning_rate": 2.917592225307418e-05,
1543
+ "loss": 1.3659,
1544
+ "step": 21000
1545
+ },
1546
+ {
1547
+ "epoch": 8.369694565648553,
1548
+ "grad_norm": 2.6886465549468994,
1549
+ "learning_rate": 2.907675525585085e-05,
1550
+ "loss": 1.3568,
1551
+ "step": 21100
1552
+ },
1553
+ {
1554
+ "epoch": 8.409361364537881,
1555
+ "grad_norm": 4.069731712341309,
1556
+ "learning_rate": 2.897758825862753e-05,
1557
+ "loss": 1.4326,
1558
+ "step": 21200
1559
+ },
1560
+ {
1561
+ "epoch": 8.449028163427212,
1562
+ "grad_norm": 4.844085693359375,
1563
+ "learning_rate": 2.8878421261404205e-05,
1564
+ "loss": 1.4363,
1565
+ "step": 21300
1566
+ },
1567
+ {
1568
+ "epoch": 8.488694962316542,
1569
+ "grad_norm": 2.894545316696167,
1570
+ "learning_rate": 2.8779254264180884e-05,
1571
+ "loss": 1.362,
1572
+ "step": 21400
1573
+ },
1574
+ {
1575
+ "epoch": 8.52836176120587,
1576
+ "grad_norm": 3.8921375274658203,
1577
+ "learning_rate": 2.8680087266957556e-05,
1578
+ "loss": 1.3303,
1579
+ "step": 21500
1580
+ },
1581
+ {
1582
+ "epoch": 8.5680285600952,
1583
+ "grad_norm": 3.6468684673309326,
1584
+ "learning_rate": 2.8580920269734234e-05,
1585
+ "loss": 1.387,
1586
+ "step": 21600
1587
+ },
1588
+ {
1589
+ "epoch": 8.60769535898453,
1590
+ "grad_norm": 4.2180938720703125,
1591
+ "learning_rate": 2.848175327251091e-05,
1592
+ "loss": 1.366,
1593
+ "step": 21700
1594
+ },
1595
+ {
1596
+ "epoch": 8.647362157873859,
1597
+ "grad_norm": 4.113888263702393,
1598
+ "learning_rate": 2.8382586275287588e-05,
1599
+ "loss": 1.4047,
1600
+ "step": 21800
1601
+ },
1602
+ {
1603
+ "epoch": 8.68702895676319,
1604
+ "grad_norm": 4.009461402893066,
1605
+ "learning_rate": 2.828341927806426e-05,
1606
+ "loss": 1.3446,
1607
+ "step": 21900
1608
+ },
1609
+ {
1610
+ "epoch": 8.72669575565252,
1611
+ "grad_norm": 3.8195252418518066,
1612
+ "learning_rate": 2.818425228084094e-05,
1613
+ "loss": 1.3304,
1614
+ "step": 22000
1615
+ },
1616
+ {
1617
+ "epoch": 8.766362554541848,
1618
+ "grad_norm": 4.5541300773620605,
1619
+ "learning_rate": 2.8085085283617614e-05,
1620
+ "loss": 1.4156,
1621
+ "step": 22100
1622
+ },
1623
+ {
1624
+ "epoch": 8.806029353431178,
1625
+ "grad_norm": 4.221588611602783,
1626
+ "learning_rate": 2.7985918286394293e-05,
1627
+ "loss": 1.3258,
1628
+ "step": 22200
1629
+ },
1630
+ {
1631
+ "epoch": 8.845696152320508,
1632
+ "grad_norm": 3.7638354301452637,
1633
+ "learning_rate": 2.7886751289170964e-05,
1634
+ "loss": 1.2697,
1635
+ "step": 22300
1636
+ },
1637
+ {
1638
+ "epoch": 8.885362951209837,
1639
+ "grad_norm": 3.7174267768859863,
1640
+ "learning_rate": 2.7787584291947643e-05,
1641
+ "loss": 1.3468,
1642
+ "step": 22400
1643
+ },
1644
+ {
1645
+ "epoch": 8.925029750099167,
1646
+ "grad_norm": 4.4955153465271,
1647
+ "learning_rate": 2.768841729472432e-05,
1648
+ "loss": 1.3074,
1649
+ "step": 22500
1650
+ },
1651
+ {
1652
+ "epoch": 8.964696548988497,
1653
+ "grad_norm": 4.170012950897217,
1654
+ "learning_rate": 2.758925029750099e-05,
1655
+ "loss": 1.3324,
1656
+ "step": 22600
1657
+ },
1658
+ {
1659
+ "epoch": 9.0,
1660
+ "eval_loss": 1.204575538635254,
1661
+ "eval_runtime": 33.1963,
1662
+ "eval_samples_per_second": 45.728,
1663
+ "eval_steps_per_second": 5.724,
1664
+ "step": 22689
1665
+ },
1666
+ {
1667
+ "epoch": 9.004363347877826,
1668
+ "grad_norm": 3.331163167953491,
1669
+ "learning_rate": 2.749008330027767e-05,
1670
+ "loss": 1.3285,
1671
+ "step": 22700
1672
+ },
1673
+ {
1674
+ "epoch": 9.044030146767156,
1675
+ "grad_norm": 3.822847843170166,
1676
+ "learning_rate": 2.7390916303054344e-05,
1677
+ "loss": 1.3589,
1678
+ "step": 22800
1679
+ },
1680
+ {
1681
+ "epoch": 9.083696945656486,
1682
+ "grad_norm": 3.4321391582489014,
1683
+ "learning_rate": 2.7291749305831023e-05,
1684
+ "loss": 1.2863,
1685
+ "step": 22900
1686
+ },
1687
+ {
1688
+ "epoch": 9.123363744545815,
1689
+ "grad_norm": 4.23520040512085,
1690
+ "learning_rate": 2.7192582308607695e-05,
1691
+ "loss": 1.297,
1692
+ "step": 23000
1693
+ },
1694
+ {
1695
+ "epoch": 9.163030543435145,
1696
+ "grad_norm": 3.0839881896972656,
1697
+ "learning_rate": 2.7093415311384373e-05,
1698
+ "loss": 1.272,
1699
+ "step": 23100
1700
+ },
1701
+ {
1702
+ "epoch": 9.202697342324475,
1703
+ "grad_norm": 5.115342617034912,
1704
+ "learning_rate": 2.699424831416105e-05,
1705
+ "loss": 1.2667,
1706
+ "step": 23200
1707
+ },
1708
+ {
1709
+ "epoch": 9.242364141213804,
1710
+ "grad_norm": 3.8965401649475098,
1711
+ "learning_rate": 2.6895081316937727e-05,
1712
+ "loss": 1.2995,
1713
+ "step": 23300
1714
+ },
1715
+ {
1716
+ "epoch": 9.282030940103134,
1717
+ "grad_norm": 3.395707368850708,
1718
+ "learning_rate": 2.67959143197144e-05,
1719
+ "loss": 1.2064,
1720
+ "step": 23400
1721
+ },
1722
+ {
1723
+ "epoch": 9.321697738992464,
1724
+ "grad_norm": 3.7783238887786865,
1725
+ "learning_rate": 2.6696747322491078e-05,
1726
+ "loss": 1.354,
1727
+ "step": 23500
1728
+ },
1729
+ {
1730
+ "epoch": 9.361364537881792,
1731
+ "grad_norm": 3.6201136112213135,
1732
+ "learning_rate": 2.6597580325267753e-05,
1733
+ "loss": 1.318,
1734
+ "step": 23600
1735
+ },
1736
+ {
1737
+ "epoch": 9.401031336771123,
1738
+ "grad_norm": 7.127315044403076,
1739
+ "learning_rate": 2.649841332804443e-05,
1740
+ "loss": 1.2809,
1741
+ "step": 23700
1742
+ },
1743
+ {
1744
+ "epoch": 9.440698135660453,
1745
+ "grad_norm": 3.341298818588257,
1746
+ "learning_rate": 2.6399246330821103e-05,
1747
+ "loss": 1.3285,
1748
+ "step": 23800
1749
+ },
1750
+ {
1751
+ "epoch": 9.480364934549781,
1752
+ "grad_norm": 3.38814377784729,
1753
+ "learning_rate": 2.6300079333597782e-05,
1754
+ "loss": 1.3326,
1755
+ "step": 23900
1756
+ },
1757
+ {
1758
+ "epoch": 9.520031733439112,
1759
+ "grad_norm": 2.880125045776367,
1760
+ "learning_rate": 2.6200912336374457e-05,
1761
+ "loss": 1.3142,
1762
+ "step": 24000
1763
+ },
1764
+ {
1765
+ "epoch": 9.559698532328442,
1766
+ "grad_norm": 3.778383731842041,
1767
+ "learning_rate": 2.610174533915113e-05,
1768
+ "loss": 1.3217,
1769
+ "step": 24100
1770
+ },
1771
+ {
1772
+ "epoch": 9.59936533121777,
1773
+ "grad_norm": 5.5109734535217285,
1774
+ "learning_rate": 2.6002578341927808e-05,
1775
+ "loss": 1.2715,
1776
+ "step": 24200
1777
+ },
1778
+ {
1779
+ "epoch": 9.6390321301071,
1780
+ "grad_norm": 3.931368112564087,
1781
+ "learning_rate": 2.5903411344704483e-05,
1782
+ "loss": 1.318,
1783
+ "step": 24300
1784
+ },
1785
+ {
1786
+ "epoch": 9.67869892899643,
1787
+ "grad_norm": 3.6587719917297363,
1788
+ "learning_rate": 2.580424434748116e-05,
1789
+ "loss": 1.2384,
1790
+ "step": 24400
1791
+ },
1792
+ {
1793
+ "epoch": 9.71836572788576,
1794
+ "grad_norm": 3.4478108882904053,
1795
+ "learning_rate": 2.5705077350257833e-05,
1796
+ "loss": 1.2682,
1797
+ "step": 24500
1798
+ },
1799
+ {
1800
+ "epoch": 9.75803252677509,
1801
+ "grad_norm": 3.9226527214050293,
1802
+ "learning_rate": 2.5605910353034512e-05,
1803
+ "loss": 1.2966,
1804
+ "step": 24600
1805
+ },
1806
+ {
1807
+ "epoch": 9.79769932566442,
1808
+ "grad_norm": 4.621306419372559,
1809
+ "learning_rate": 2.5506743355811187e-05,
1810
+ "loss": 1.2788,
1811
+ "step": 24700
1812
+ },
1813
+ {
1814
+ "epoch": 9.837366124553748,
1815
+ "grad_norm": 3.4298593997955322,
1816
+ "learning_rate": 2.5407576358587866e-05,
1817
+ "loss": 1.3299,
1818
+ "step": 24800
1819
+ },
1820
+ {
1821
+ "epoch": 9.877032923443078,
1822
+ "grad_norm": 3.7832400798797607,
1823
+ "learning_rate": 2.5308409361364538e-05,
1824
+ "loss": 1.2634,
1825
+ "step": 24900
1826
+ },
1827
+ {
1828
+ "epoch": 9.916699722332408,
1829
+ "grad_norm": 5.351818561553955,
1830
+ "learning_rate": 2.5209242364141216e-05,
1831
+ "loss": 1.3117,
1832
+ "step": 25000
1833
+ },
1834
+ {
1835
+ "epoch": 9.956366521221737,
1836
+ "grad_norm": 4.65415096282959,
1837
+ "learning_rate": 2.511007536691789e-05,
1838
+ "loss": 1.2613,
1839
+ "step": 25100
1840
+ },
1841
+ {
1842
+ "epoch": 9.996033320111067,
1843
+ "grad_norm": 3.2736618518829346,
1844
+ "learning_rate": 2.501090836969457e-05,
1845
+ "loss": 1.3156,
1846
+ "step": 25200
1847
+ },
1848
+ {
1849
+ "epoch": 10.0,
1850
+ "eval_loss": 1.164570689201355,
1851
+ "eval_runtime": 33.0846,
1852
+ "eval_samples_per_second": 45.882,
1853
+ "eval_steps_per_second": 5.743,
1854
+ "step": 25210
1855
+ },
1856
+ {
1857
+ "epoch": 10.035700119000397,
1858
+ "grad_norm": 3.6819069385528564,
1859
+ "learning_rate": 2.4911741372471242e-05,
1860
+ "loss": 1.2604,
1861
+ "step": 25300
1862
+ },
1863
+ {
1864
+ "epoch": 10.075366917889726,
1865
+ "grad_norm": 3.9212143421173096,
1866
+ "learning_rate": 2.4812574375247917e-05,
1867
+ "loss": 1.2308,
1868
+ "step": 25400
1869
+ },
1870
+ {
1871
+ "epoch": 10.115033716779056,
1872
+ "grad_norm": 3.3087549209594727,
1873
+ "learning_rate": 2.4713407378024596e-05,
1874
+ "loss": 1.1652,
1875
+ "step": 25500
1876
+ },
1877
+ {
1878
+ "epoch": 10.154700515668386,
1879
+ "grad_norm": 3.8680827617645264,
1880
+ "learning_rate": 2.461424038080127e-05,
1881
+ "loss": 1.2311,
1882
+ "step": 25600
1883
+ },
1884
+ {
1885
+ "epoch": 10.194367314557715,
1886
+ "grad_norm": 5.244319438934326,
1887
+ "learning_rate": 2.4515073383577946e-05,
1888
+ "loss": 1.1819,
1889
+ "step": 25700
1890
+ },
1891
+ {
1892
+ "epoch": 10.234034113447045,
1893
+ "grad_norm": 3.2293717861175537,
1894
+ "learning_rate": 2.4415906386354622e-05,
1895
+ "loss": 1.249,
1896
+ "step": 25800
1897
+ },
1898
+ {
1899
+ "epoch": 10.273700912336375,
1900
+ "grad_norm": 4.391103744506836,
1901
+ "learning_rate": 2.43167393891313e-05,
1902
+ "loss": 1.2283,
1903
+ "step": 25900
1904
+ },
1905
+ {
1906
+ "epoch": 10.313367711225704,
1907
+ "grad_norm": 4.615547180175781,
1908
+ "learning_rate": 2.4217572391907976e-05,
1909
+ "loss": 1.2915,
1910
+ "step": 26000
1911
+ },
1912
+ {
1913
+ "epoch": 10.353034510115034,
1914
+ "grad_norm": 3.3367502689361572,
1915
+ "learning_rate": 2.411840539468465e-05,
1916
+ "loss": 1.2221,
1917
+ "step": 26100
1918
+ },
1919
+ {
1920
+ "epoch": 10.392701309004364,
1921
+ "grad_norm": 5.194177150726318,
1922
+ "learning_rate": 2.4019238397461326e-05,
1923
+ "loss": 1.2611,
1924
+ "step": 26200
1925
+ },
1926
+ {
1927
+ "epoch": 10.432368107893693,
1928
+ "grad_norm": 5.576562404632568,
1929
+ "learning_rate": 2.3920071400238005e-05,
1930
+ "loss": 1.2764,
1931
+ "step": 26300
1932
+ },
1933
+ {
1934
+ "epoch": 10.472034906783023,
1935
+ "grad_norm": 4.902477264404297,
1936
+ "learning_rate": 2.3820904403014677e-05,
1937
+ "loss": 1.2066,
1938
+ "step": 26400
1939
+ },
1940
+ {
1941
+ "epoch": 10.511701705672353,
1942
+ "grad_norm": 4.312764644622803,
1943
+ "learning_rate": 2.3721737405791352e-05,
1944
+ "loss": 1.219,
1945
+ "step": 26500
1946
+ },
1947
+ {
1948
+ "epoch": 10.551368504561681,
1949
+ "grad_norm": 4.345120429992676,
1950
+ "learning_rate": 2.362257040856803e-05,
1951
+ "loss": 1.2679,
1952
+ "step": 26600
1953
+ },
1954
+ {
1955
+ "epoch": 10.591035303451012,
1956
+ "grad_norm": 3.9365150928497314,
1957
+ "learning_rate": 2.3523403411344706e-05,
1958
+ "loss": 1.1752,
1959
+ "step": 26700
1960
+ },
1961
+ {
1962
+ "epoch": 10.630702102340342,
1963
+ "grad_norm": 3.843207597732544,
1964
+ "learning_rate": 2.342423641412138e-05,
1965
+ "loss": 1.2706,
1966
+ "step": 26800
1967
+ },
1968
+ {
1969
+ "epoch": 10.67036890122967,
1970
+ "grad_norm": 4.076716423034668,
1971
+ "learning_rate": 2.3325069416898056e-05,
1972
+ "loss": 1.1561,
1973
+ "step": 26900
1974
+ },
1975
+ {
1976
+ "epoch": 10.710035700119,
1977
+ "grad_norm": 4.182331562042236,
1978
+ "learning_rate": 2.3225902419674735e-05,
1979
+ "loss": 1.2027,
1980
+ "step": 27000
1981
+ },
1982
+ {
1983
+ "epoch": 10.74970249900833,
1984
+ "grad_norm": 5.730105876922607,
1985
+ "learning_rate": 2.312673542245141e-05,
1986
+ "loss": 1.2703,
1987
+ "step": 27100
1988
+ },
1989
+ {
1990
+ "epoch": 10.78936929789766,
1991
+ "grad_norm": 5.552068710327148,
1992
+ "learning_rate": 2.3027568425228085e-05,
1993
+ "loss": 1.252,
1994
+ "step": 27200
1995
+ },
1996
+ {
1997
+ "epoch": 10.82903609678699,
1998
+ "grad_norm": 4.406209945678711,
1999
+ "learning_rate": 2.292840142800476e-05,
2000
+ "loss": 1.183,
2001
+ "step": 27300
2002
+ },
2003
+ {
2004
+ "epoch": 10.86870289567632,
2005
+ "grad_norm": 3.434688091278076,
2006
+ "learning_rate": 2.282923443078144e-05,
2007
+ "loss": 1.3214,
2008
+ "step": 27400
2009
+ },
2010
+ {
2011
+ "epoch": 10.908369694565648,
2012
+ "grad_norm": 5.0344085693359375,
2013
+ "learning_rate": 2.2730067433558114e-05,
2014
+ "loss": 1.3043,
2015
+ "step": 27500
2016
+ },
2017
+ {
2018
+ "epoch": 10.948036493454978,
2019
+ "grad_norm": 3.3030033111572266,
2020
+ "learning_rate": 2.263090043633479e-05,
2021
+ "loss": 1.1764,
2022
+ "step": 27600
2023
+ },
2024
+ {
2025
+ "epoch": 10.987703292344309,
2026
+ "grad_norm": 5.79923152923584,
2027
+ "learning_rate": 2.2531733439111465e-05,
2028
+ "loss": 1.2218,
2029
+ "step": 27700
2030
+ },
2031
+ {
2032
+ "epoch": 11.0,
2033
+ "eval_loss": 1.1352205276489258,
2034
+ "eval_runtime": 31.6991,
2035
+ "eval_samples_per_second": 47.888,
2036
+ "eval_steps_per_second": 5.994,
2037
+ "step": 27731
2038
+ },
2039
+ {
2040
+ "epoch": 11.027370091233637,
2041
+ "grad_norm": 4.073122501373291,
2042
+ "learning_rate": 2.2432566441888144e-05,
2043
+ "loss": 1.1861,
2044
+ "step": 27800
2045
+ },
2046
+ {
2047
+ "epoch": 11.067036890122967,
2048
+ "grad_norm": 2.8648433685302734,
2049
+ "learning_rate": 2.2333399444664815e-05,
2050
+ "loss": 1.1659,
2051
+ "step": 27900
2052
+ },
2053
+ {
2054
+ "epoch": 11.106703689012297,
2055
+ "grad_norm": 3.6053709983825684,
2056
+ "learning_rate": 2.223423244744149e-05,
2057
+ "loss": 1.2087,
2058
+ "step": 28000
2059
+ },
2060
+ {
2061
+ "epoch": 11.146370487901626,
2062
+ "grad_norm": 3.5773251056671143,
2063
+ "learning_rate": 2.2135065450218166e-05,
2064
+ "loss": 1.1787,
2065
+ "step": 28100
2066
+ },
2067
+ {
2068
+ "epoch": 11.186037286790956,
2069
+ "grad_norm": 5.5593485832214355,
2070
+ "learning_rate": 2.2035898452994845e-05,
2071
+ "loss": 1.1941,
2072
+ "step": 28200
2073
+ },
2074
+ {
2075
+ "epoch": 11.225704085680286,
2076
+ "grad_norm": 3.9467504024505615,
2077
+ "learning_rate": 2.193673145577152e-05,
2078
+ "loss": 1.2505,
2079
+ "step": 28300
2080
+ },
2081
+ {
2082
+ "epoch": 11.265370884569615,
2083
+ "grad_norm": 4.707422733306885,
2084
+ "learning_rate": 2.1837564458548195e-05,
2085
+ "loss": 1.1165,
2086
+ "step": 28400
2087
+ },
2088
+ {
2089
+ "epoch": 11.305037683458945,
2090
+ "grad_norm": 4.517952919006348,
2091
+ "learning_rate": 2.1738397461324874e-05,
2092
+ "loss": 1.2379,
2093
+ "step": 28500
2094
+ },
2095
+ {
2096
+ "epoch": 11.344704482348275,
2097
+ "grad_norm": 2.318586587905884,
2098
+ "learning_rate": 2.163923046410155e-05,
2099
+ "loss": 1.2098,
2100
+ "step": 28600
2101
+ },
2102
+ {
2103
+ "epoch": 11.384371281237604,
2104
+ "grad_norm": 3.655980110168457,
2105
+ "learning_rate": 2.1540063466878224e-05,
2106
+ "loss": 1.2044,
2107
+ "step": 28700
2108
+ },
2109
+ {
2110
+ "epoch": 11.424038080126934,
2111
+ "grad_norm": 4.038224697113037,
2112
+ "learning_rate": 2.14408964696549e-05,
2113
+ "loss": 1.1651,
2114
+ "step": 28800
2115
+ },
2116
+ {
2117
+ "epoch": 11.463704879016264,
2118
+ "grad_norm": 3.9811367988586426,
2119
+ "learning_rate": 2.1341729472431578e-05,
2120
+ "loss": 1.199,
2121
+ "step": 28900
2122
+ },
2123
+ {
2124
+ "epoch": 11.503371677905593,
2125
+ "grad_norm": 6.200103759765625,
2126
+ "learning_rate": 2.1242562475208253e-05,
2127
+ "loss": 1.1094,
2128
+ "step": 29000
2129
+ },
2130
+ {
2131
+ "epoch": 11.543038476794923,
2132
+ "grad_norm": 3.919187545776367,
2133
+ "learning_rate": 2.114339547798493e-05,
2134
+ "loss": 1.1522,
2135
+ "step": 29100
2136
+ },
2137
+ {
2138
+ "epoch": 11.582705275684253,
2139
+ "grad_norm": 3.701822519302368,
2140
+ "learning_rate": 2.1044228480761604e-05,
2141
+ "loss": 1.1556,
2142
+ "step": 29200
2143
+ },
2144
+ {
2145
+ "epoch": 11.622372074573581,
2146
+ "grad_norm": 4.491922855377197,
2147
+ "learning_rate": 2.0945061483538282e-05,
2148
+ "loss": 1.1779,
2149
+ "step": 29300
2150
+ },
2151
+ {
2152
+ "epoch": 11.662038873462912,
2153
+ "grad_norm": 4.367665767669678,
2154
+ "learning_rate": 2.0845894486314954e-05,
2155
+ "loss": 1.1392,
2156
+ "step": 29400
2157
+ },
2158
+ {
2159
+ "epoch": 11.701705672352242,
2160
+ "grad_norm": 4.0435028076171875,
2161
+ "learning_rate": 2.074672748909163e-05,
2162
+ "loss": 1.1621,
2163
+ "step": 29500
2164
+ },
2165
+ {
2166
+ "epoch": 11.74137247124157,
2167
+ "grad_norm": 4.151968955993652,
2168
+ "learning_rate": 2.0647560491868305e-05,
2169
+ "loss": 1.1983,
2170
+ "step": 29600
2171
+ },
2172
+ {
2173
+ "epoch": 11.7810392701309,
2174
+ "grad_norm": 4.687623500823975,
2175
+ "learning_rate": 2.0548393494644983e-05,
2176
+ "loss": 1.1563,
2177
+ "step": 29700
2178
+ },
2179
+ {
2180
+ "epoch": 11.82070606902023,
2181
+ "grad_norm": 4.415579795837402,
2182
+ "learning_rate": 2.044922649742166e-05,
2183
+ "loss": 1.1497,
2184
+ "step": 29800
2185
+ },
2186
+ {
2187
+ "epoch": 11.86037286790956,
2188
+ "grad_norm": 4.241002082824707,
2189
+ "learning_rate": 2.0350059500198334e-05,
2190
+ "loss": 1.2298,
2191
+ "step": 29900
2192
+ },
2193
+ {
2194
+ "epoch": 11.90003966679889,
2195
+ "grad_norm": 5.38535213470459,
2196
+ "learning_rate": 2.025089250297501e-05,
2197
+ "loss": 1.1403,
2198
+ "step": 30000
2199
+ },
2200
+ {
2201
+ "epoch": 11.93970646568822,
2202
+ "grad_norm": 3.886983633041382,
2203
+ "learning_rate": 2.0151725505751688e-05,
2204
+ "loss": 1.237,
2205
+ "step": 30100
2206
+ },
2207
+ {
2208
+ "epoch": 11.979373264577548,
2209
+ "grad_norm": 4.2845048904418945,
2210
+ "learning_rate": 2.0052558508528363e-05,
2211
+ "loss": 1.2216,
2212
+ "step": 30200
2213
+ },
2214
+ {
2215
+ "epoch": 12.0,
2216
+ "eval_loss": 1.097899317741394,
2217
+ "eval_runtime": 31.7141,
2218
+ "eval_samples_per_second": 47.865,
2219
+ "eval_steps_per_second": 5.991,
2220
+ "step": 30252
2221
+ },
2222
+ {
2223
+ "epoch": 12.019040063466878,
2224
+ "grad_norm": 4.043181896209717,
2225
+ "learning_rate": 1.9953391511305038e-05,
2226
+ "loss": 1.1738,
2227
+ "step": 30300
2228
+ },
2229
+ {
2230
+ "epoch": 12.058706862356209,
2231
+ "grad_norm": 3.213641405105591,
2232
+ "learning_rate": 1.9854224514081713e-05,
2233
+ "loss": 1.1143,
2234
+ "step": 30400
2235
+ },
2236
+ {
2237
+ "epoch": 12.098373661245537,
2238
+ "grad_norm": 4.7294511795043945,
2239
+ "learning_rate": 1.9755057516858392e-05,
2240
+ "loss": 1.142,
2241
+ "step": 30500
2242
+ },
2243
+ {
2244
+ "epoch": 12.138040460134867,
2245
+ "grad_norm": 4.42033052444458,
2246
+ "learning_rate": 1.9655890519635067e-05,
2247
+ "loss": 1.1422,
2248
+ "step": 30600
2249
+ },
2250
+ {
2251
+ "epoch": 12.177707259024197,
2252
+ "grad_norm": 4.57334041595459,
2253
+ "learning_rate": 1.9556723522411743e-05,
2254
+ "loss": 1.1148,
2255
+ "step": 30700
2256
+ },
2257
+ {
2258
+ "epoch": 12.217374057913526,
2259
+ "grad_norm": 4.560477256774902,
2260
+ "learning_rate": 1.945755652518842e-05,
2261
+ "loss": 1.1742,
2262
+ "step": 30800
2263
+ },
2264
+ {
2265
+ "epoch": 12.257040856802856,
2266
+ "grad_norm": 3.4284374713897705,
2267
+ "learning_rate": 1.9358389527965093e-05,
2268
+ "loss": 1.1115,
2269
+ "step": 30900
2270
+ },
2271
+ {
2272
+ "epoch": 12.296707655692186,
2273
+ "grad_norm": 3.185410499572754,
2274
+ "learning_rate": 1.925922253074177e-05,
2275
+ "loss": 1.1542,
2276
+ "step": 31000
2277
+ },
2278
+ {
2279
+ "epoch": 12.336374454581515,
2280
+ "grad_norm": 3.674408435821533,
2281
+ "learning_rate": 1.9160055533518444e-05,
2282
+ "loss": 1.1787,
2283
+ "step": 31100
2284
+ },
2285
+ {
2286
+ "epoch": 12.376041253470845,
2287
+ "grad_norm": 3.7118613719940186,
2288
+ "learning_rate": 1.9060888536295122e-05,
2289
+ "loss": 1.1716,
2290
+ "step": 31200
2291
+ },
2292
+ {
2293
+ "epoch": 12.415708052360175,
2294
+ "grad_norm": 4.5831756591796875,
2295
+ "learning_rate": 1.8961721539071797e-05,
2296
+ "loss": 1.1372,
2297
+ "step": 31300
2298
+ },
2299
+ {
2300
+ "epoch": 12.455374851249504,
2301
+ "grad_norm": 7.098066806793213,
2302
+ "learning_rate": 1.8862554541848473e-05,
2303
+ "loss": 1.1361,
2304
+ "step": 31400
2305
+ },
2306
+ {
2307
+ "epoch": 12.495041650138834,
2308
+ "grad_norm": 3.451817512512207,
2309
+ "learning_rate": 1.8763387544625148e-05,
2310
+ "loss": 1.1458,
2311
+ "step": 31500
2312
+ },
2313
+ {
2314
+ "epoch": 12.534708449028164,
2315
+ "grad_norm": 2.6188955307006836,
2316
+ "learning_rate": 1.8664220547401827e-05,
2317
+ "loss": 1.0782,
2318
+ "step": 31600
2319
+ },
2320
+ {
2321
+ "epoch": 12.574375247917493,
2322
+ "grad_norm": 3.3588056564331055,
2323
+ "learning_rate": 1.8565053550178502e-05,
2324
+ "loss": 1.1593,
2325
+ "step": 31700
2326
+ },
2327
+ {
2328
+ "epoch": 12.614042046806823,
2329
+ "grad_norm": 5.186858654022217,
2330
+ "learning_rate": 1.8465886552955177e-05,
2331
+ "loss": 1.137,
2332
+ "step": 31800
2333
+ },
2334
+ {
2335
+ "epoch": 12.653708845696153,
2336
+ "grad_norm": 4.593524932861328,
2337
+ "learning_rate": 1.8366719555731852e-05,
2338
+ "loss": 1.1715,
2339
+ "step": 31900
2340
+ },
2341
+ {
2342
+ "epoch": 12.693375644585482,
2343
+ "grad_norm": 4.951717853546143,
2344
+ "learning_rate": 1.826755255850853e-05,
2345
+ "loss": 1.0765,
2346
+ "step": 32000
2347
+ },
2348
+ {
2349
+ "epoch": 12.733042443474812,
2350
+ "grad_norm": 6.989925384521484,
2351
+ "learning_rate": 1.8168385561285206e-05,
2352
+ "loss": 1.1062,
2353
+ "step": 32100
2354
+ },
2355
+ {
2356
+ "epoch": 12.772709242364142,
2357
+ "grad_norm": 3.6436753273010254,
2358
+ "learning_rate": 1.806921856406188e-05,
2359
+ "loss": 1.1574,
2360
+ "step": 32200
2361
+ },
2362
+ {
2363
+ "epoch": 12.81237604125347,
2364
+ "grad_norm": 4.659509181976318,
2365
+ "learning_rate": 1.7970051566838557e-05,
2366
+ "loss": 1.1257,
2367
+ "step": 32300
2368
+ },
2369
+ {
2370
+ "epoch": 12.8520428401428,
2371
+ "grad_norm": 2.914414882659912,
2372
+ "learning_rate": 1.7870884569615232e-05,
2373
+ "loss": 1.1131,
2374
+ "step": 32400
2375
+ },
2376
+ {
2377
+ "epoch": 12.89170963903213,
2378
+ "grad_norm": 3.9510741233825684,
2379
+ "learning_rate": 1.7771717572391907e-05,
2380
+ "loss": 1.1144,
2381
+ "step": 32500
2382
+ },
2383
+ {
2384
+ "epoch": 12.93137643792146,
2385
+ "grad_norm": 4.820216178894043,
2386
+ "learning_rate": 1.7672550575168582e-05,
2387
+ "loss": 1.1628,
2388
+ "step": 32600
2389
+ },
2390
+ {
2391
+ "epoch": 12.97104323681079,
2392
+ "grad_norm": 4.699492931365967,
2393
+ "learning_rate": 1.757338357794526e-05,
2394
+ "loss": 1.1587,
2395
+ "step": 32700
2396
+ },
2397
+ {
2398
+ "epoch": 13.0,
2399
+ "eval_loss": 1.081364631652832,
2400
+ "eval_runtime": 31.6894,
2401
+ "eval_samples_per_second": 47.902,
2402
+ "eval_steps_per_second": 5.996,
2403
+ "step": 32773
2404
+ },
2405
+ {
2406
+ "epoch": 13.01071003570012,
2407
+ "grad_norm": 3.7646989822387695,
2408
+ "learning_rate": 1.7474216580721936e-05,
2409
+ "loss": 1.1084,
2410
+ "step": 32800
2411
+ },
2412
+ {
2413
+ "epoch": 13.050376834589448,
2414
+ "grad_norm": 4.074378967285156,
2415
+ "learning_rate": 1.737504958349861e-05,
2416
+ "loss": 1.1007,
2417
+ "step": 32900
2418
+ },
2419
+ {
2420
+ "epoch": 13.090043633478778,
2421
+ "grad_norm": 4.0714521408081055,
2422
+ "learning_rate": 1.7275882586275287e-05,
2423
+ "loss": 1.1298,
2424
+ "step": 33000
2425
+ },
2426
+ {
2427
+ "epoch": 13.129710432368109,
2428
+ "grad_norm": 3.7556121349334717,
2429
+ "learning_rate": 1.7176715589051965e-05,
2430
+ "loss": 1.1407,
2431
+ "step": 33100
2432
+ },
2433
+ {
2434
+ "epoch": 13.169377231257437,
2435
+ "grad_norm": 3.3032736778259277,
2436
+ "learning_rate": 1.707754859182864e-05,
2437
+ "loss": 1.1437,
2438
+ "step": 33200
2439
+ },
2440
+ {
2441
+ "epoch": 13.209044030146767,
2442
+ "grad_norm": 4.428369522094727,
2443
+ "learning_rate": 1.6978381594605316e-05,
2444
+ "loss": 1.0659,
2445
+ "step": 33300
2446
+ },
2447
+ {
2448
+ "epoch": 13.248710829036098,
2449
+ "grad_norm": 3.486649990081787,
2450
+ "learning_rate": 1.687921459738199e-05,
2451
+ "loss": 1.0744,
2452
+ "step": 33400
2453
+ },
2454
+ {
2455
+ "epoch": 13.288377627925426,
2456
+ "grad_norm": 4.116626262664795,
2457
+ "learning_rate": 1.678004760015867e-05,
2458
+ "loss": 1.0933,
2459
+ "step": 33500
2460
+ },
2461
+ {
2462
+ "epoch": 13.328044426814756,
2463
+ "grad_norm": 5.455049991607666,
2464
+ "learning_rate": 1.6680880602935345e-05,
2465
+ "loss": 1.0387,
2466
+ "step": 33600
2467
+ },
2468
+ {
2469
+ "epoch": 13.367711225704086,
2470
+ "grad_norm": 4.454029083251953,
2471
+ "learning_rate": 1.658171360571202e-05,
2472
+ "loss": 1.0488,
2473
+ "step": 33700
2474
+ },
2475
+ {
2476
+ "epoch": 13.407378024593415,
2477
+ "grad_norm": 3.605964422225952,
2478
+ "learning_rate": 1.6482546608488695e-05,
2479
+ "loss": 1.1565,
2480
+ "step": 33800
2481
+ },
2482
+ {
2483
+ "epoch": 13.447044823482745,
2484
+ "grad_norm": 3.3428781032562256,
2485
+ "learning_rate": 1.638337961126537e-05,
2486
+ "loss": 1.1255,
2487
+ "step": 33900
2488
+ },
2489
+ {
2490
+ "epoch": 13.486711622372075,
2491
+ "grad_norm": 5.9332709312438965,
2492
+ "learning_rate": 1.6284212614042046e-05,
2493
+ "loss": 1.0814,
2494
+ "step": 34000
2495
+ },
2496
+ {
2497
+ "epoch": 13.526378421261404,
2498
+ "grad_norm": 3.3487417697906494,
2499
+ "learning_rate": 1.618504561681872e-05,
2500
+ "loss": 1.1105,
2501
+ "step": 34100
2502
+ },
2503
+ {
2504
+ "epoch": 13.566045220150734,
2505
+ "grad_norm": 3.4275264739990234,
2506
+ "learning_rate": 1.60858786195954e-05,
2507
+ "loss": 1.0292,
2508
+ "step": 34200
2509
+ },
2510
+ {
2511
+ "epoch": 13.605712019040064,
2512
+ "grad_norm": 5.602040767669678,
2513
+ "learning_rate": 1.5986711622372075e-05,
2514
+ "loss": 1.0629,
2515
+ "step": 34300
2516
+ },
2517
+ {
2518
+ "epoch": 13.645378817929393,
2519
+ "grad_norm": 2.6752493381500244,
2520
+ "learning_rate": 1.588754462514875e-05,
2521
+ "loss": 1.0761,
2522
+ "step": 34400
2523
+ },
2524
+ {
2525
+ "epoch": 13.685045616818723,
2526
+ "grad_norm": 3.2931220531463623,
2527
+ "learning_rate": 1.5788377627925426e-05,
2528
+ "loss": 0.9885,
2529
+ "step": 34500
2530
+ },
2531
+ {
2532
+ "epoch": 13.724712415708053,
2533
+ "grad_norm": 8.223132133483887,
2534
+ "learning_rate": 1.5689210630702104e-05,
2535
+ "loss": 1.1423,
2536
+ "step": 34600
2537
+ },
2538
+ {
2539
+ "epoch": 13.764379214597382,
2540
+ "grad_norm": 4.580158233642578,
2541
+ "learning_rate": 1.559004363347878e-05,
2542
+ "loss": 1.0879,
2543
+ "step": 34700
2544
+ },
2545
+ {
2546
+ "epoch": 13.804046013486712,
2547
+ "grad_norm": 3.891131639480591,
2548
+ "learning_rate": 1.5490876636255455e-05,
2549
+ "loss": 1.0819,
2550
+ "step": 34800
2551
+ },
2552
+ {
2553
+ "epoch": 13.843712812376042,
2554
+ "grad_norm": 5.4781084060668945,
2555
+ "learning_rate": 1.539170963903213e-05,
2556
+ "loss": 1.1007,
2557
+ "step": 34900
2558
+ },
2559
+ {
2560
+ "epoch": 13.88337961126537,
2561
+ "grad_norm": 5.0408220291137695,
2562
+ "learning_rate": 1.529254264180881e-05,
2563
+ "loss": 1.1124,
2564
+ "step": 35000
2565
+ },
2566
+ {
2567
+ "epoch": 13.9230464101547,
2568
+ "grad_norm": 4.6583452224731445,
2569
+ "learning_rate": 1.5193375644585484e-05,
2570
+ "loss": 1.1607,
2571
+ "step": 35100
2572
+ },
2573
+ {
2574
+ "epoch": 13.962713209044031,
2575
+ "grad_norm": 5.026098251342773,
2576
+ "learning_rate": 1.5094208647362159e-05,
2577
+ "loss": 1.0744,
2578
+ "step": 35200
2579
+ },
2580
+ {
2581
+ "epoch": 14.0,
2582
+ "eval_loss": 1.068395733833313,
2583
+ "eval_runtime": 31.6512,
2584
+ "eval_samples_per_second": 47.96,
2585
+ "eval_steps_per_second": 6.003,
2586
+ "step": 35294
2587
+ },
2588
+ {
2589
+ "epoch": 14.00238000793336,
2590
+ "grad_norm": 2.9335262775421143,
2591
+ "learning_rate": 1.4995041650138836e-05,
2592
+ "loss": 1.0841,
2593
+ "step": 35300
2594
+ },
2595
+ {
2596
+ "epoch": 14.04204680682269,
2597
+ "grad_norm": 4.208588123321533,
2598
+ "learning_rate": 1.489587465291551e-05,
2599
+ "loss": 1.0901,
2600
+ "step": 35400
2601
+ },
2602
+ {
2603
+ "epoch": 14.08171360571202,
2604
+ "grad_norm": 5.132387638092041,
2605
+ "learning_rate": 1.4796707655692185e-05,
2606
+ "loss": 1.1201,
2607
+ "step": 35500
2608
+ },
2609
+ {
2610
+ "epoch": 14.121380404601348,
2611
+ "grad_norm": 3.9229278564453125,
2612
+ "learning_rate": 1.4697540658468862e-05,
2613
+ "loss": 1.0782,
2614
+ "step": 35600
2615
+ },
2616
+ {
2617
+ "epoch": 14.161047203490678,
2618
+ "grad_norm": 6.1097259521484375,
2619
+ "learning_rate": 1.4598373661245537e-05,
2620
+ "loss": 1.1051,
2621
+ "step": 35700
2622
+ },
2623
+ {
2624
+ "epoch": 14.200714002380009,
2625
+ "grad_norm": 4.1445417404174805,
2626
+ "learning_rate": 1.4499206664022214e-05,
2627
+ "loss": 1.1283,
2628
+ "step": 35800
2629
+ },
2630
+ {
2631
+ "epoch": 14.240380801269337,
2632
+ "grad_norm": 3.5986008644104004,
2633
+ "learning_rate": 1.440003966679889e-05,
2634
+ "loss": 1.0453,
2635
+ "step": 35900
2636
+ },
2637
+ {
2638
+ "epoch": 14.280047600158667,
2639
+ "grad_norm": 3.8175106048583984,
2640
+ "learning_rate": 1.4300872669575566e-05,
2641
+ "loss": 1.0585,
2642
+ "step": 36000
2643
+ },
2644
+ {
2645
+ "epoch": 14.319714399047998,
2646
+ "grad_norm": 2.821758985519409,
2647
+ "learning_rate": 1.4201705672352241e-05,
2648
+ "loss": 1.06,
2649
+ "step": 36100
2650
+ },
2651
+ {
2652
+ "epoch": 14.359381197937326,
2653
+ "grad_norm": 3.65065860748291,
2654
+ "learning_rate": 1.4102538675128918e-05,
2655
+ "loss": 1.1064,
2656
+ "step": 36200
2657
+ },
2658
+ {
2659
+ "epoch": 14.399047996826656,
2660
+ "grad_norm": 5.7176713943481445,
2661
+ "learning_rate": 1.4003371677905594e-05,
2662
+ "loss": 1.008,
2663
+ "step": 36300
2664
+ },
2665
+ {
2666
+ "epoch": 14.438714795715986,
2667
+ "grad_norm": 5.075132846832275,
2668
+ "learning_rate": 1.390420468068227e-05,
2669
+ "loss": 1.114,
2670
+ "step": 36400
2671
+ },
2672
+ {
2673
+ "epoch": 14.478381594605315,
2674
+ "grad_norm": 5.210816860198975,
2675
+ "learning_rate": 1.3805037683458946e-05,
2676
+ "loss": 1.0944,
2677
+ "step": 36500
2678
+ },
2679
+ {
2680
+ "epoch": 14.518048393494645,
2681
+ "grad_norm": 4.964089870452881,
2682
+ "learning_rate": 1.3705870686235623e-05,
2683
+ "loss": 1.0904,
2684
+ "step": 36600
2685
+ },
2686
+ {
2687
+ "epoch": 14.557715192383975,
2688
+ "grad_norm": 3.131520986557007,
2689
+ "learning_rate": 1.3606703689012298e-05,
2690
+ "loss": 1.063,
2691
+ "step": 36700
2692
+ },
2693
+ {
2694
+ "epoch": 14.597381991273304,
2695
+ "grad_norm": 6.203433036804199,
2696
+ "learning_rate": 1.3507536691788975e-05,
2697
+ "loss": 1.0885,
2698
+ "step": 36800
2699
+ },
2700
+ {
2701
+ "epoch": 14.637048790162634,
2702
+ "grad_norm": 2.8487484455108643,
2703
+ "learning_rate": 1.3408369694565648e-05,
2704
+ "loss": 1.0785,
2705
+ "step": 36900
2706
+ },
2707
+ {
2708
+ "epoch": 14.676715589051964,
2709
+ "grad_norm": 3.4533579349517822,
2710
+ "learning_rate": 1.3309202697342324e-05,
2711
+ "loss": 1.0956,
2712
+ "step": 37000
2713
+ },
2714
+ {
2715
+ "epoch": 14.716382387941293,
2716
+ "grad_norm": 5.409042835235596,
2717
+ "learning_rate": 1.3210035700119e-05,
2718
+ "loss": 1.0635,
2719
+ "step": 37100
2720
+ },
2721
+ {
2722
+ "epoch": 14.756049186830623,
2723
+ "grad_norm": 4.514674186706543,
2724
+ "learning_rate": 1.3110868702895676e-05,
2725
+ "loss": 1.0829,
2726
+ "step": 37200
2727
+ },
2728
+ {
2729
+ "epoch": 14.795715985719953,
2730
+ "grad_norm": 4.7005791664123535,
2731
+ "learning_rate": 1.3011701705672353e-05,
2732
+ "loss": 1.0003,
2733
+ "step": 37300
2734
+ },
2735
+ {
2736
+ "epoch": 14.835382784609282,
2737
+ "grad_norm": 4.253646373748779,
2738
+ "learning_rate": 1.2912534708449028e-05,
2739
+ "loss": 1.0562,
2740
+ "step": 37400
2741
+ },
2742
+ {
2743
+ "epoch": 14.875049583498612,
2744
+ "grad_norm": 4.305023193359375,
2745
+ "learning_rate": 1.2813367711225705e-05,
2746
+ "loss": 1.0712,
2747
+ "step": 37500
2748
+ },
2749
+ {
2750
+ "epoch": 14.914716382387942,
2751
+ "grad_norm": 4.189399719238281,
2752
+ "learning_rate": 1.271420071400238e-05,
2753
+ "loss": 1.0761,
2754
+ "step": 37600
2755
+ },
2756
+ {
2757
+ "epoch": 14.95438318127727,
2758
+ "grad_norm": 3.2512216567993164,
2759
+ "learning_rate": 1.2615033716779057e-05,
2760
+ "loss": 1.0336,
2761
+ "step": 37700
2762
+ },
2763
+ {
2764
+ "epoch": 14.9940499801666,
2765
+ "grad_norm": 3.3554651737213135,
2766
+ "learning_rate": 1.2515866719555732e-05,
2767
+ "loss": 1.0636,
2768
+ "step": 37800
2769
+ },
2770
+ {
2771
+ "epoch": 15.0,
2772
+ "eval_loss": 1.051405906677246,
2773
+ "eval_runtime": 31.6428,
2774
+ "eval_samples_per_second": 47.973,
2775
+ "eval_steps_per_second": 6.005,
2776
+ "step": 37815
2777
+ },
2778
+ {
2779
+ "epoch": 15.033716779055931,
2780
+ "grad_norm": 3.6472902297973633,
2781
+ "learning_rate": 1.241669972233241e-05,
2782
+ "loss": 1.0596,
2783
+ "step": 37900
2784
+ },
2785
+ {
2786
+ "epoch": 15.07338357794526,
2787
+ "grad_norm": 5.338723659515381,
2788
+ "learning_rate": 1.2317532725109085e-05,
2789
+ "loss": 1.0462,
2790
+ "step": 38000
2791
+ },
2792
+ {
2793
+ "epoch": 15.11305037683459,
2794
+ "grad_norm": 4.401419639587402,
2795
+ "learning_rate": 1.221836572788576e-05,
2796
+ "loss": 1.0869,
2797
+ "step": 38100
2798
+ },
2799
+ {
2800
+ "epoch": 15.15271717572392,
2801
+ "grad_norm": 9.426093101501465,
2802
+ "learning_rate": 1.2119198730662435e-05,
2803
+ "loss": 1.0198,
2804
+ "step": 38200
2805
+ },
2806
+ {
2807
+ "epoch": 15.192383974613248,
2808
+ "grad_norm": 3.7169394493103027,
2809
+ "learning_rate": 1.2020031733439112e-05,
2810
+ "loss": 1.1285,
2811
+ "step": 38300
2812
+ },
2813
+ {
2814
+ "epoch": 15.232050773502579,
2815
+ "grad_norm": 3.466498851776123,
2816
+ "learning_rate": 1.1920864736215787e-05,
2817
+ "loss": 1.0125,
2818
+ "step": 38400
2819
+ },
2820
+ {
2821
+ "epoch": 15.271717572391909,
2822
+ "grad_norm": 2.7933382987976074,
2823
+ "learning_rate": 1.1821697738992464e-05,
2824
+ "loss": 1.0545,
2825
+ "step": 38500
2826
+ },
2827
+ {
2828
+ "epoch": 15.311384371281237,
2829
+ "grad_norm": 2.926934003829956,
2830
+ "learning_rate": 1.172253074176914e-05,
2831
+ "loss": 1.1035,
2832
+ "step": 38600
2833
+ },
2834
+ {
2835
+ "epoch": 15.351051170170567,
2836
+ "grad_norm": 3.2757022380828857,
2837
+ "learning_rate": 1.1623363744545816e-05,
2838
+ "loss": 1.0479,
2839
+ "step": 38700
2840
+ },
2841
+ {
2842
+ "epoch": 15.390717969059898,
2843
+ "grad_norm": 4.160761833190918,
2844
+ "learning_rate": 1.1524196747322492e-05,
2845
+ "loss": 1.064,
2846
+ "step": 38800
2847
+ },
2848
+ {
2849
+ "epoch": 15.430384767949226,
2850
+ "grad_norm": 3.412480592727661,
2851
+ "learning_rate": 1.1425029750099167e-05,
2852
+ "loss": 0.9485,
2853
+ "step": 38900
2854
+ },
2855
+ {
2856
+ "epoch": 15.470051566838556,
2857
+ "grad_norm": 3.1907808780670166,
2858
+ "learning_rate": 1.1325862752875844e-05,
2859
+ "loss": 1.0605,
2860
+ "step": 39000
2861
+ },
2862
+ {
2863
+ "epoch": 15.509718365727887,
2864
+ "grad_norm": 4.184901714324951,
2865
+ "learning_rate": 1.1226695755652519e-05,
2866
+ "loss": 1.0551,
2867
+ "step": 39100
2868
+ },
2869
+ {
2870
+ "epoch": 15.549385164617215,
2871
+ "grad_norm": 4.784205436706543,
2872
+ "learning_rate": 1.1127528758429196e-05,
2873
+ "loss": 0.9941,
2874
+ "step": 39200
2875
+ },
2876
+ {
2877
+ "epoch": 15.589051963506545,
2878
+ "grad_norm": 4.00923490524292,
2879
+ "learning_rate": 1.1028361761205871e-05,
2880
+ "loss": 1.076,
2881
+ "step": 39300
2882
+ },
2883
+ {
2884
+ "epoch": 15.628718762395875,
2885
+ "grad_norm": 4.559725284576416,
2886
+ "learning_rate": 1.0929194763982548e-05,
2887
+ "loss": 0.9979,
2888
+ "step": 39400
2889
+ },
2890
+ {
2891
+ "epoch": 15.668385561285204,
2892
+ "grad_norm": 3.8985109329223633,
2893
+ "learning_rate": 1.0830027766759223e-05,
2894
+ "loss": 1.0397,
2895
+ "step": 39500
2896
+ },
2897
+ {
2898
+ "epoch": 15.708052360174534,
2899
+ "grad_norm": 3.3521323204040527,
2900
+ "learning_rate": 1.0730860769535899e-05,
2901
+ "loss": 1.006,
2902
+ "step": 39600
2903
+ },
2904
+ {
2905
+ "epoch": 15.747719159063864,
2906
+ "grad_norm": 3.2745351791381836,
2907
+ "learning_rate": 1.0631693772312574e-05,
2908
+ "loss": 1.0642,
2909
+ "step": 39700
2910
+ },
2911
+ {
2912
+ "epoch": 15.787385957953193,
2913
+ "grad_norm": 3.955242156982422,
2914
+ "learning_rate": 1.053252677508925e-05,
2915
+ "loss": 1.0455,
2916
+ "step": 39800
2917
+ },
2918
+ {
2919
+ "epoch": 15.827052756842523,
2920
+ "grad_norm": 3.2223598957061768,
2921
+ "learning_rate": 1.0433359777865926e-05,
2922
+ "loss": 1.0675,
2923
+ "step": 39900
2924
+ },
2925
+ {
2926
+ "epoch": 15.866719555731853,
2927
+ "grad_norm": 4.809605121612549,
2928
+ "learning_rate": 1.0334192780642603e-05,
2929
+ "loss": 1.0992,
2930
+ "step": 40000
2931
+ },
2932
+ {
2933
+ "epoch": 15.906386354621182,
2934
+ "grad_norm": 2.6435019969940186,
2935
+ "learning_rate": 1.0235025783419278e-05,
2936
+ "loss": 0.9905,
2937
+ "step": 40100
2938
+ },
2939
+ {
2940
+ "epoch": 15.946053153510512,
2941
+ "grad_norm": 6.68290376663208,
2942
+ "learning_rate": 1.0135858786195955e-05,
2943
+ "loss": 1.0951,
2944
+ "step": 40200
2945
+ },
2946
+ {
2947
+ "epoch": 15.985719952399842,
2948
+ "grad_norm": 2.6426591873168945,
2949
+ "learning_rate": 1.003669178897263e-05,
2950
+ "loss": 1.073,
2951
+ "step": 40300
2952
+ },
2953
+ {
2954
+ "epoch": 16.0,
2955
+ "eval_loss": 1.039953351020813,
2956
+ "eval_runtime": 31.6995,
2957
+ "eval_samples_per_second": 47.887,
2958
+ "eval_steps_per_second": 5.994,
2959
+ "step": 40336
2960
+ },
2961
+ {
2962
+ "epoch": 16.025386751289172,
2963
+ "grad_norm": 3.456146001815796,
2964
+ "learning_rate": 9.937524791749306e-06,
2965
+ "loss": 1.0191,
2966
+ "step": 40400
2967
+ },
2968
+ {
2969
+ "epoch": 16.0650535501785,
2970
+ "grad_norm": 5.939918518066406,
2971
+ "learning_rate": 9.838357794525983e-06,
2972
+ "loss": 1.0433,
2973
+ "step": 40500
2974
+ },
2975
+ {
2976
+ "epoch": 16.10472034906783,
2977
+ "grad_norm": 3.538282871246338,
2978
+ "learning_rate": 9.739190797302658e-06,
2979
+ "loss": 1.0295,
2980
+ "step": 40600
2981
+ },
2982
+ {
2983
+ "epoch": 16.14438714795716,
2984
+ "grad_norm": 4.2307844161987305,
2985
+ "learning_rate": 9.640023800079335e-06,
2986
+ "loss": 1.0371,
2987
+ "step": 40700
2988
+ },
2989
+ {
2990
+ "epoch": 16.18405394684649,
2991
+ "grad_norm": 4.40711784362793,
2992
+ "learning_rate": 9.54085680285601e-06,
2993
+ "loss": 1.0236,
2994
+ "step": 40800
2995
+ },
2996
+ {
2997
+ "epoch": 16.223720745735818,
2998
+ "grad_norm": 3.8492507934570312,
2999
+ "learning_rate": 9.441689805632687e-06,
3000
+ "loss": 1.0628,
3001
+ "step": 40900
3002
+ },
3003
+ {
3004
+ "epoch": 16.26338754462515,
3005
+ "grad_norm": 4.397724628448486,
3006
+ "learning_rate": 9.342522808409362e-06,
3007
+ "loss": 1.0072,
3008
+ "step": 41000
3009
+ },
3010
+ {
3011
+ "epoch": 16.30305434351448,
3012
+ "grad_norm": 3.3145904541015625,
3013
+ "learning_rate": 9.243355811186037e-06,
3014
+ "loss": 1.045,
3015
+ "step": 41100
3016
+ },
3017
+ {
3018
+ "epoch": 16.342721142403807,
3019
+ "grad_norm": 5.359413146972656,
3020
+ "learning_rate": 9.144188813962713e-06,
3021
+ "loss": 1.0299,
3022
+ "step": 41200
3023
+ },
3024
+ {
3025
+ "epoch": 16.38238794129314,
3026
+ "grad_norm": 3.4849679470062256,
3027
+ "learning_rate": 9.04502181673939e-06,
3028
+ "loss": 1.012,
3029
+ "step": 41300
3030
+ },
3031
+ {
3032
+ "epoch": 16.422054740182467,
3033
+ "grad_norm": 2.9378600120544434,
3034
+ "learning_rate": 8.945854819516065e-06,
3035
+ "loss": 1.0269,
3036
+ "step": 41400
3037
+ },
3038
+ {
3039
+ "epoch": 16.461721539071796,
3040
+ "grad_norm": 3.024475574493408,
3041
+ "learning_rate": 8.846687822292742e-06,
3042
+ "loss": 1.0373,
3043
+ "step": 41500
3044
+ },
3045
+ {
3046
+ "epoch": 16.501388337961128,
3047
+ "grad_norm": 3.2381701469421387,
3048
+ "learning_rate": 8.747520825069417e-06,
3049
+ "loss": 0.9888,
3050
+ "step": 41600
3051
+ },
3052
+ {
3053
+ "epoch": 16.541055136850456,
3054
+ "grad_norm": 3.816202163696289,
3055
+ "learning_rate": 8.648353827846094e-06,
3056
+ "loss": 0.9384,
3057
+ "step": 41700
3058
+ },
3059
+ {
3060
+ "epoch": 16.580721935739785,
3061
+ "grad_norm": 4.290541648864746,
3062
+ "learning_rate": 8.54918683062277e-06,
3063
+ "loss": 1.0653,
3064
+ "step": 41800
3065
+ },
3066
+ {
3067
+ "epoch": 16.620388734629117,
3068
+ "grad_norm": 4.712522029876709,
3069
+ "learning_rate": 8.450019833399444e-06,
3070
+ "loss": 0.9951,
3071
+ "step": 41900
3072
+ },
3073
+ {
3074
+ "epoch": 16.660055533518445,
3075
+ "grad_norm": 3.3500611782073975,
3076
+ "learning_rate": 8.350852836176121e-06,
3077
+ "loss": 1.0356,
3078
+ "step": 42000
3079
+ },
3080
+ {
3081
+ "epoch": 16.699722332407774,
3082
+ "grad_norm": 3.6570308208465576,
3083
+ "learning_rate": 8.251685838952797e-06,
3084
+ "loss": 1.0205,
3085
+ "step": 42100
3086
+ },
3087
+ {
3088
+ "epoch": 16.739389131297106,
3089
+ "grad_norm": 3.4734184741973877,
3090
+ "learning_rate": 8.152518841729474e-06,
3091
+ "loss": 1.037,
3092
+ "step": 42200
3093
+ },
3094
+ {
3095
+ "epoch": 16.779055930186434,
3096
+ "grad_norm": 3.528817653656006,
3097
+ "learning_rate": 8.053351844506149e-06,
3098
+ "loss": 0.9402,
3099
+ "step": 42300
3100
+ },
3101
+ {
3102
+ "epoch": 16.818722729075763,
3103
+ "grad_norm": 4.3084025382995605,
3104
+ "learning_rate": 7.954184847282826e-06,
3105
+ "loss": 1.0702,
3106
+ "step": 42400
3107
+ },
3108
+ {
3109
+ "epoch": 16.858389527965095,
3110
+ "grad_norm": 3.520242214202881,
3111
+ "learning_rate": 7.855017850059501e-06,
3112
+ "loss": 1.0474,
3113
+ "step": 42500
3114
+ },
3115
+ {
3116
+ "epoch": 16.898056326854423,
3117
+ "grad_norm": 4.44198751449585,
3118
+ "learning_rate": 7.755850852836176e-06,
3119
+ "loss": 1.0506,
3120
+ "step": 42600
3121
+ },
3122
+ {
3123
+ "epoch": 16.93772312574375,
3124
+ "grad_norm": 2.8113813400268555,
3125
+ "learning_rate": 7.656683855612852e-06,
3126
+ "loss": 1.0167,
3127
+ "step": 42700
3128
+ },
3129
+ {
3130
+ "epoch": 16.977389924633083,
3131
+ "grad_norm": 3.3131535053253174,
3132
+ "learning_rate": 7.5575168583895284e-06,
3133
+ "loss": 1.0077,
3134
+ "step": 42800
3135
+ },
3136
+ {
3137
+ "epoch": 17.0,
3138
+ "eval_loss": 1.0288244485855103,
3139
+ "eval_runtime": 31.6731,
3140
+ "eval_samples_per_second": 47.927,
3141
+ "eval_steps_per_second": 5.999,
3142
+ "step": 42857
3143
+ },
3144
+ {
3145
+ "epoch": 17.017056723522412,
3146
+ "grad_norm": 5.444199562072754,
3147
+ "learning_rate": 7.4583498611662045e-06,
3148
+ "loss": 0.9996,
3149
+ "step": 42900
3150
+ },
3151
+ {
3152
+ "epoch": 17.05672352241174,
3153
+ "grad_norm": 4.1272783279418945,
3154
+ "learning_rate": 7.359182863942881e-06,
3155
+ "loss": 1.0256,
3156
+ "step": 43000
3157
+ },
3158
+ {
3159
+ "epoch": 17.096390321301072,
3160
+ "grad_norm": 4.819570064544678,
3161
+ "learning_rate": 7.260015866719557e-06,
3162
+ "loss": 1.0325,
3163
+ "step": 43100
3164
+ },
3165
+ {
3166
+ "epoch": 17.1360571201904,
3167
+ "grad_norm": 4.795453071594238,
3168
+ "learning_rate": 7.160848869496233e-06,
3169
+ "loss": 0.9845,
3170
+ "step": 43200
3171
+ },
3172
+ {
3173
+ "epoch": 17.17572391907973,
3174
+ "grad_norm": 5.2741827964782715,
3175
+ "learning_rate": 7.061681872272907e-06,
3176
+ "loss": 1.0406,
3177
+ "step": 43300
3178
+ },
3179
+ {
3180
+ "epoch": 17.21539071796906,
3181
+ "grad_norm": 5.457202911376953,
3182
+ "learning_rate": 6.962514875049583e-06,
3183
+ "loss": 1.0704,
3184
+ "step": 43400
3185
+ },
3186
+ {
3187
+ "epoch": 17.25505751685839,
3188
+ "grad_norm": 6.256078243255615,
3189
+ "learning_rate": 6.863347877826259e-06,
3190
+ "loss": 1.0182,
3191
+ "step": 43500
3192
+ },
3193
+ {
3194
+ "epoch": 17.294724315747718,
3195
+ "grad_norm": 3.9407060146331787,
3196
+ "learning_rate": 6.7641808806029355e-06,
3197
+ "loss": 0.9889,
3198
+ "step": 43600
3199
+ },
3200
+ {
3201
+ "epoch": 17.33439111463705,
3202
+ "grad_norm": 3.250436782836914,
3203
+ "learning_rate": 6.6650138833796116e-06,
3204
+ "loss": 1.0079,
3205
+ "step": 43700
3206
+ },
3207
+ {
3208
+ "epoch": 17.37405791352638,
3209
+ "grad_norm": 2.7779972553253174,
3210
+ "learning_rate": 6.565846886156288e-06,
3211
+ "loss": 1.0134,
3212
+ "step": 43800
3213
+ },
3214
+ {
3215
+ "epoch": 17.413724712415707,
3216
+ "grad_norm": 4.296668529510498,
3217
+ "learning_rate": 6.466679888932964e-06,
3218
+ "loss": 0.9585,
3219
+ "step": 43900
3220
+ },
3221
+ {
3222
+ "epoch": 17.45339151130504,
3223
+ "grad_norm": 3.737541437149048,
3224
+ "learning_rate": 6.36751289170964e-06,
3225
+ "loss": 1.0307,
3226
+ "step": 44000
3227
+ },
3228
+ {
3229
+ "epoch": 17.493058310194368,
3230
+ "grad_norm": 5.0776848793029785,
3231
+ "learning_rate": 6.268345894486314e-06,
3232
+ "loss": 1.0395,
3233
+ "step": 44100
3234
+ },
3235
+ {
3236
+ "epoch": 17.532725109083696,
3237
+ "grad_norm": 6.334095001220703,
3238
+ "learning_rate": 6.169178897262991e-06,
3239
+ "loss": 0.9772,
3240
+ "step": 44200
3241
+ },
3242
+ {
3243
+ "epoch": 17.572391907973028,
3244
+ "grad_norm": 5.443525314331055,
3245
+ "learning_rate": 6.070011900039667e-06,
3246
+ "loss": 0.9264,
3247
+ "step": 44300
3248
+ },
3249
+ {
3250
+ "epoch": 17.612058706862356,
3251
+ "grad_norm": 4.61970853805542,
3252
+ "learning_rate": 5.970844902816343e-06,
3253
+ "loss": 1.0307,
3254
+ "step": 44400
3255
+ },
3256
+ {
3257
+ "epoch": 17.651725505751685,
3258
+ "grad_norm": 3.089509963989258,
3259
+ "learning_rate": 5.8716779055930195e-06,
3260
+ "loss": 0.9633,
3261
+ "step": 44500
3262
+ },
3263
+ {
3264
+ "epoch": 17.691392304641017,
3265
+ "grad_norm": 4.635293006896973,
3266
+ "learning_rate": 5.7725109083696955e-06,
3267
+ "loss": 1.0537,
3268
+ "step": 44600
3269
+ },
3270
+ {
3271
+ "epoch": 17.731059103530345,
3272
+ "grad_norm": 3.052475929260254,
3273
+ "learning_rate": 5.673343911146371e-06,
3274
+ "loss": 0.9983,
3275
+ "step": 44700
3276
+ },
3277
+ {
3278
+ "epoch": 17.770725902419674,
3279
+ "grad_norm": 3.9765052795410156,
3280
+ "learning_rate": 5.574176913923047e-06,
3281
+ "loss": 1.0687,
3282
+ "step": 44800
3283
+ },
3284
+ {
3285
+ "epoch": 17.810392701309006,
3286
+ "grad_norm": 4.3488030433654785,
3287
+ "learning_rate": 5.475009916699723e-06,
3288
+ "loss": 1.012,
3289
+ "step": 44900
3290
+ },
3291
+ {
3292
+ "epoch": 17.850059500198334,
3293
+ "grad_norm": 3.6032917499542236,
3294
+ "learning_rate": 5.375842919476398e-06,
3295
+ "loss": 0.9933,
3296
+ "step": 45000
3297
+ },
3298
+ {
3299
+ "epoch": 17.889726299087663,
3300
+ "grad_norm": 3.2621772289276123,
3301
+ "learning_rate": 5.276675922253074e-06,
3302
+ "loss": 0.9657,
3303
+ "step": 45100
3304
+ },
3305
+ {
3306
+ "epoch": 17.929393097976995,
3307
+ "grad_norm": 3.9976959228515625,
3308
+ "learning_rate": 5.17750892502975e-06,
3309
+ "loss": 0.9799,
3310
+ "step": 45200
3311
+ },
3312
+ {
3313
+ "epoch": 17.969059896866323,
3314
+ "grad_norm": 4.725791931152344,
3315
+ "learning_rate": 5.0783419278064265e-06,
3316
+ "loss": 1.043,
3317
+ "step": 45300
3318
+ },
3319
+ {
3320
+ "epoch": 18.0,
3321
+ "eval_loss": 1.0184741020202637,
3322
+ "eval_runtime": 31.6571,
3323
+ "eval_samples_per_second": 47.951,
3324
+ "eval_steps_per_second": 6.002,
3325
+ "step": 45378
3326
+ },
3327
+ {
3328
+ "epoch": 18.00872669575565,
3329
+ "grad_norm": 3.418588876724243,
3330
+ "learning_rate": 4.979174930583102e-06,
3331
+ "loss": 0.9965,
3332
+ "step": 45400
3333
+ },
3334
+ {
3335
+ "epoch": 18.048393494644984,
3336
+ "grad_norm": 4.835160255432129,
3337
+ "learning_rate": 4.880007933359778e-06,
3338
+ "loss": 0.9789,
3339
+ "step": 45500
3340
+ },
3341
+ {
3342
+ "epoch": 18.088060293534312,
3343
+ "grad_norm": 4.275815486907959,
3344
+ "learning_rate": 4.780840936136454e-06,
3345
+ "loss": 1.0233,
3346
+ "step": 45600
3347
+ },
3348
+ {
3349
+ "epoch": 18.12772709242364,
3350
+ "grad_norm": 4.429009914398193,
3351
+ "learning_rate": 4.68167393891313e-06,
3352
+ "loss": 1.0487,
3353
+ "step": 45700
3354
+ },
3355
+ {
3356
+ "epoch": 18.167393891312972,
3357
+ "grad_norm": 4.390066146850586,
3358
+ "learning_rate": 4.582506941689805e-06,
3359
+ "loss": 0.968,
3360
+ "step": 45800
3361
+ },
3362
+ {
3363
+ "epoch": 18.2070606902023,
3364
+ "grad_norm": 3.265092372894287,
3365
+ "learning_rate": 4.483339944466481e-06,
3366
+ "loss": 1.0171,
3367
+ "step": 45900
3368
+ },
3369
+ {
3370
+ "epoch": 18.24672748909163,
3371
+ "grad_norm": 4.843317031860352,
3372
+ "learning_rate": 4.3841729472431574e-06,
3373
+ "loss": 1.0204,
3374
+ "step": 46000
3375
+ },
3376
+ {
3377
+ "epoch": 18.28639428798096,
3378
+ "grad_norm": 4.457988262176514,
3379
+ "learning_rate": 4.2850059500198335e-06,
3380
+ "loss": 1.0246,
3381
+ "step": 46100
3382
+ },
3383
+ {
3384
+ "epoch": 18.32606108687029,
3385
+ "grad_norm": 3.9527127742767334,
3386
+ "learning_rate": 4.18583895279651e-06,
3387
+ "loss": 0.9241,
3388
+ "step": 46200
3389
+ },
3390
+ {
3391
+ "epoch": 18.36572788575962,
3392
+ "grad_norm": 3.7694692611694336,
3393
+ "learning_rate": 4.086671955573186e-06,
3394
+ "loss": 1.0318,
3395
+ "step": 46300
3396
+ },
3397
+ {
3398
+ "epoch": 18.40539468464895,
3399
+ "grad_norm": 5.390737533569336,
3400
+ "learning_rate": 3.987504958349862e-06,
3401
+ "loss": 0.9938,
3402
+ "step": 46400
3403
+ },
3404
+ {
3405
+ "epoch": 18.44506148353828,
3406
+ "grad_norm": 3.8084776401519775,
3407
+ "learning_rate": 3.888337961126538e-06,
3408
+ "loss": 0.9652,
3409
+ "step": 46500
3410
+ },
3411
+ {
3412
+ "epoch": 18.484728282427607,
3413
+ "grad_norm": 3.5767834186553955,
3414
+ "learning_rate": 3.789170963903213e-06,
3415
+ "loss": 0.9582,
3416
+ "step": 46600
3417
+ },
3418
+ {
3419
+ "epoch": 18.52439508131694,
3420
+ "grad_norm": 3.4777605533599854,
3421
+ "learning_rate": 3.6900039666798892e-06,
3422
+ "loss": 0.9981,
3423
+ "step": 46700
3424
+ },
3425
+ {
3426
+ "epoch": 18.564061880206268,
3427
+ "grad_norm": 4.1490092277526855,
3428
+ "learning_rate": 3.5908369694565653e-06,
3429
+ "loss": 0.9607,
3430
+ "step": 46800
3431
+ },
3432
+ {
3433
+ "epoch": 18.603728679095596,
3434
+ "grad_norm": 4.089176654815674,
3435
+ "learning_rate": 3.4916699722332406e-06,
3436
+ "loss": 1.0168,
3437
+ "step": 46900
3438
+ },
3439
+ {
3440
+ "epoch": 18.643395477984928,
3441
+ "grad_norm": 3.9602725505828857,
3442
+ "learning_rate": 3.3925029750099167e-06,
3443
+ "loss": 0.9785,
3444
+ "step": 47000
3445
+ },
3446
+ {
3447
+ "epoch": 18.683062276874256,
3448
+ "grad_norm": 4.800217628479004,
3449
+ "learning_rate": 3.2933359777865927e-06,
3450
+ "loss": 1.0514,
3451
+ "step": 47100
3452
+ },
3453
+ {
3454
+ "epoch": 18.722729075763585,
3455
+ "grad_norm": 4.848387718200684,
3456
+ "learning_rate": 3.194168980563269e-06,
3457
+ "loss": 0.9798,
3458
+ "step": 47200
3459
+ },
3460
+ {
3461
+ "epoch": 18.762395874652917,
3462
+ "grad_norm": 3.5444610118865967,
3463
+ "learning_rate": 3.0950019833399445e-06,
3464
+ "loss": 1.0602,
3465
+ "step": 47300
3466
+ },
3467
+ {
3468
+ "epoch": 18.802062673542245,
3469
+ "grad_norm": 3.4162533283233643,
3470
+ "learning_rate": 2.9958349861166206e-06,
3471
+ "loss": 0.9881,
3472
+ "step": 47400
3473
+ },
3474
+ {
3475
+ "epoch": 18.841729472431574,
3476
+ "grad_norm": 4.719314098358154,
3477
+ "learning_rate": 2.8966679888932967e-06,
3478
+ "loss": 0.9503,
3479
+ "step": 47500
3480
+ },
3481
+ {
3482
+ "epoch": 18.881396271320906,
3483
+ "grad_norm": 5.332608222961426,
3484
+ "learning_rate": 2.7975009916699724e-06,
3485
+ "loss": 1.0245,
3486
+ "step": 47600
3487
+ },
3488
+ {
3489
+ "epoch": 18.921063070210234,
3490
+ "grad_norm": 5.230047702789307,
3491
+ "learning_rate": 2.6983339944466484e-06,
3492
+ "loss": 0.9947,
3493
+ "step": 47700
3494
+ },
3495
+ {
3496
+ "epoch": 18.960729869099563,
3497
+ "grad_norm": 3.1582813262939453,
3498
+ "learning_rate": 2.599166997223324e-06,
3499
+ "loss": 1.0198,
3500
+ "step": 47800
3501
+ },
3502
+ {
3503
+ "epoch": 19.0,
3504
+ "eval_loss": 1.017343521118164,
3505
+ "eval_runtime": 31.7039,
3506
+ "eval_samples_per_second": 47.881,
3507
+ "eval_steps_per_second": 5.993,
3508
+ "step": 47899
3509
+ },
3510
+ {
3511
+ "epoch": 19.000396667988895,
3512
+ "grad_norm": 5.45066499710083,
3513
+ "learning_rate": 2.5e-06,
3514
+ "loss": 0.9753,
3515
+ "step": 47900
3516
+ },
3517
+ {
3518
+ "epoch": 19.040063466878223,
3519
+ "grad_norm": 3.2004072666168213,
3520
+ "learning_rate": 2.400833002776676e-06,
3521
+ "loss": 0.946,
3522
+ "step": 48000
3523
+ },
3524
+ {
3525
+ "epoch": 19.07973026576755,
3526
+ "grad_norm": 3.971540689468384,
3527
+ "learning_rate": 2.301666005553352e-06,
3528
+ "loss": 0.9783,
3529
+ "step": 48100
3530
+ },
3531
+ {
3532
+ "epoch": 19.119397064656884,
3533
+ "grad_norm": 4.348784923553467,
3534
+ "learning_rate": 2.202499008330028e-06,
3535
+ "loss": 0.952,
3536
+ "step": 48200
3537
+ },
3538
+ {
3539
+ "epoch": 19.159063863546212,
3540
+ "grad_norm": 3.7044036388397217,
3541
+ "learning_rate": 2.1033320111067037e-06,
3542
+ "loss": 1.0662,
3543
+ "step": 48300
3544
+ },
3545
+ {
3546
+ "epoch": 19.19873066243554,
3547
+ "grad_norm": 2.662105083465576,
3548
+ "learning_rate": 2.00416501388338e-06,
3549
+ "loss": 0.9647,
3550
+ "step": 48400
3551
+ },
3552
+ {
3553
+ "epoch": 19.238397461324872,
3554
+ "grad_norm": 4.103559494018555,
3555
+ "learning_rate": 1.9049980166600555e-06,
3556
+ "loss": 0.9142,
3557
+ "step": 48500
3558
+ },
3559
+ {
3560
+ "epoch": 19.2780642602142,
3561
+ "grad_norm": 2.8791961669921875,
3562
+ "learning_rate": 1.8058310194367316e-06,
3563
+ "loss": 1.0167,
3564
+ "step": 48600
3565
+ },
3566
+ {
3567
+ "epoch": 19.31773105910353,
3568
+ "grad_norm": 2.689680576324463,
3569
+ "learning_rate": 1.7066640222134072e-06,
3570
+ "loss": 1.0012,
3571
+ "step": 48700
3572
+ },
3573
+ {
3574
+ "epoch": 19.35739785799286,
3575
+ "grad_norm": 3.3067831993103027,
3576
+ "learning_rate": 1.6074970249900833e-06,
3577
+ "loss": 0.967,
3578
+ "step": 48800
3579
+ },
3580
+ {
3581
+ "epoch": 19.39706465688219,
3582
+ "grad_norm": 3.9777708053588867,
3583
+ "learning_rate": 1.5083300277667594e-06,
3584
+ "loss": 0.9081,
3585
+ "step": 48900
3586
+ },
3587
+ {
3588
+ "epoch": 19.43673145577152,
3589
+ "grad_norm": 3.582973003387451,
3590
+ "learning_rate": 1.4091630305434353e-06,
3591
+ "loss": 1.0104,
3592
+ "step": 49000
3593
+ },
3594
+ {
3595
+ "epoch": 19.47639825466085,
3596
+ "grad_norm": 5.202731132507324,
3597
+ "learning_rate": 1.309996033320111e-06,
3598
+ "loss": 0.9648,
3599
+ "step": 49100
3600
+ },
3601
+ {
3602
+ "epoch": 19.51606505355018,
3603
+ "grad_norm": 3.264211893081665,
3604
+ "learning_rate": 1.210829036096787e-06,
3605
+ "loss": 0.9599,
3606
+ "step": 49200
3607
+ },
3608
+ {
3609
+ "epoch": 19.555731852439507,
3610
+ "grad_norm": 4.432053565979004,
3611
+ "learning_rate": 1.111662038873463e-06,
3612
+ "loss": 0.9935,
3613
+ "step": 49300
3614
+ },
3615
+ {
3616
+ "epoch": 19.59539865132884,
3617
+ "grad_norm": 3.386671781539917,
3618
+ "learning_rate": 1.0124950416501388e-06,
3619
+ "loss": 1.002,
3620
+ "step": 49400
3621
+ },
3622
+ {
3623
+ "epoch": 19.635065450218168,
3624
+ "grad_norm": 4.273075103759766,
3625
+ "learning_rate": 9.133280444268148e-07,
3626
+ "loss": 1.0225,
3627
+ "step": 49500
3628
+ },
3629
+ {
3630
+ "epoch": 19.674732249107496,
3631
+ "grad_norm": 3.5673136711120605,
3632
+ "learning_rate": 8.141610472034907e-07,
3633
+ "loss": 1.0149,
3634
+ "step": 49600
3635
+ },
3636
+ {
3637
+ "epoch": 19.714399047996828,
3638
+ "grad_norm": 3.68278431892395,
3639
+ "learning_rate": 7.149940499801666e-07,
3640
+ "loss": 0.996,
3641
+ "step": 49700
3642
+ },
3643
+ {
3644
+ "epoch": 19.754065846886157,
3645
+ "grad_norm": 4.8836870193481445,
3646
+ "learning_rate": 6.158270527568425e-07,
3647
+ "loss": 1.0097,
3648
+ "step": 49800
3649
+ },
3650
+ {
3651
+ "epoch": 19.793732645775485,
3652
+ "grad_norm": 3.579880475997925,
3653
+ "learning_rate": 5.166600555335184e-07,
3654
+ "loss": 0.9482,
3655
+ "step": 49900
3656
+ },
3657
+ {
3658
+ "epoch": 19.833399444664817,
3659
+ "grad_norm": 2.7329444885253906,
3660
+ "learning_rate": 4.174930583101944e-07,
3661
+ "loss": 1.0365,
3662
+ "step": 50000
3663
+ },
3664
+ {
3665
+ "epoch": 19.873066243554145,
3666
+ "grad_norm": 5.478430271148682,
3667
+ "learning_rate": 3.1832606108687035e-07,
3668
+ "loss": 1.0543,
3669
+ "step": 50100
3670
+ },
3671
+ {
3672
+ "epoch": 19.912733042443474,
3673
+ "grad_norm": 3.1377158164978027,
3674
+ "learning_rate": 2.191590638635462e-07,
3675
+ "loss": 0.9637,
3676
+ "step": 50200
3677
+ },
3678
+ {
3679
+ "epoch": 19.952399841332806,
3680
+ "grad_norm": 3.789954662322998,
3681
+ "learning_rate": 1.1999206664022213e-07,
3682
+ "loss": 0.9847,
3683
+ "step": 50300
3684
+ },
3685
+ {
3686
+ "epoch": 19.992066640222134,
3687
+ "grad_norm": 4.29661226272583,
3688
+ "learning_rate": 2.0825069416898058e-08,
3689
+ "loss": 1.0306,
3690
+ "step": 50400
3691
+ },
3692
+ {
3693
+ "epoch": 20.0,
3694
+ "eval_loss": 1.0158944129943848,
3695
+ "eval_runtime": 31.6451,
3696
+ "eval_samples_per_second": 47.97,
3697
+ "eval_steps_per_second": 6.004,
3698
+ "step": 50420
3699
+ }
3700
+ ],
3701
+ "logging_steps": 100,
3702
+ "max_steps": 50420,
3703
+ "num_input_tokens_seen": 0,
3704
+ "num_train_epochs": 20,
3705
+ "save_steps": 500,
3706
+ "stateful_callbacks": {
3707
+ "TrainerControl": {
3708
+ "args": {
3709
+ "should_epoch_stop": false,
3710
+ "should_evaluate": false,
3711
+ "should_log": false,
3712
+ "should_save": true,
3713
+ "should_training_stop": true
3714
+ },
3715
+ "attributes": {}
3716
+ }
3717
+ },
3718
+ "total_flos": 6.902420484390912e+16,
3719
+ "train_batch_size": 8,
3720
+ "trial_name": null,
3721
+ "trial_params": null
3722
+ }
checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75188bd643b1477939c9a6819e9a5ad3a7a388c5c13a37c2fcbd210bd1b5fc26
3
+ size 5496