liswei commited on
Commit
4f08481
1 Parent(s): df98541

Training in progress, step 4000

Browse files
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liswei/OpenELM-1_1B-zh-base",
3
+ "activation_fn_name": "swish",
4
+ "architectures": [
5
+ "OpenELMForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_openelm.OpenELMConfig",
9
+ "AutoModel": "modeling_openelm.OpenELMForCausalLM",
10
+ "AutoModelForCausalLM": "apple/OpenELM-1_1B--modeling_openelm.OpenELMForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "eos_token_id": 2,
14
+ "ffn_dim_divisor": 256,
15
+ "ffn_multipliers": [
16
+ 0.5,
17
+ 0.63,
18
+ 0.76,
19
+ 0.89,
20
+ 1.02,
21
+ 1.15,
22
+ 1.28,
23
+ 1.41,
24
+ 1.54,
25
+ 1.67,
26
+ 1.8,
27
+ 1.93,
28
+ 2.06,
29
+ 2.19,
30
+ 2.31,
31
+ 2.44,
32
+ 2.57,
33
+ 2.7,
34
+ 2.83,
35
+ 2.96,
36
+ 3.09,
37
+ 3.22,
38
+ 3.35,
39
+ 3.48,
40
+ 3.61,
41
+ 3.74,
42
+ 3.87,
43
+ 4.0
44
+ ],
45
+ "ffn_with_glu": true,
46
+ "head_dim": 64,
47
+ "initializer_range": 0.02,
48
+ "max_context_length": 2048,
49
+ "model_dim": 2048,
50
+ "model_type": "openelm",
51
+ "normalization_layer_name": "rms_norm",
52
+ "normalize_qk_projections": true,
53
+ "num_gqa_groups": 4,
54
+ "num_kv_heads": [
55
+ 4,
56
+ 4,
57
+ 4,
58
+ 5,
59
+ 5,
60
+ 5,
61
+ 5,
62
+ 5,
63
+ 5,
64
+ 5,
65
+ 6,
66
+ 6,
67
+ 6,
68
+ 6,
69
+ 6,
70
+ 6,
71
+ 6,
72
+ 6,
73
+ 7,
74
+ 7,
75
+ 7,
76
+ 7,
77
+ 7,
78
+ 7,
79
+ 8,
80
+ 8,
81
+ 8,
82
+ 8
83
+ ],
84
+ "num_query_heads": [
85
+ 16,
86
+ 16,
87
+ 16,
88
+ 20,
89
+ 20,
90
+ 20,
91
+ 20,
92
+ 20,
93
+ 20,
94
+ 20,
95
+ 24,
96
+ 24,
97
+ 24,
98
+ 24,
99
+ 24,
100
+ 24,
101
+ 24,
102
+ 24,
103
+ 28,
104
+ 28,
105
+ 28,
106
+ 28,
107
+ 28,
108
+ 28,
109
+ 32,
110
+ 32,
111
+ 32,
112
+ 32
113
+ ],
114
+ "num_transformer_layers": 28,
115
+ "qkv_multipliers": [
116
+ 0.5,
117
+ 1.0
118
+ ],
119
+ "rope_freq_constant": 10000,
120
+ "rope_max_length": 4096,
121
+ "share_input_output_layers": true,
122
+ "torch_dtype": "float32",
123
+ "transformers_version": "4.41.1",
124
+ "use_cache": false,
125
+ "vocab_size": 61758
126
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7a678ef3fb9ee841dffb63788e78c47f94ee4a15d54202f106836c28618d72
3
+ size 4563369024
runs/May27_23-45-48_n0qbsictr1716813819608-jbj64/events.out.tfevents.1716824772.n0qbsictr1716813819608-jbj64.1320.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7865b55dfbf9fe183affb4d81da62b667ed5fefbd451e39e5fed59f86c7c75
3
+ size 90452
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489162c61bf22fed27ac6d11033cb270715cb83b4de4409569e7858c6c56b844
3
+ size 966919
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 13550, "loss": 15.7032, "learning_rate": 7.380073800738008e-07, "epoch": 0.0007380073800738007, "percentage": 0.07, "elapsed_time": "0:03:35", "remaining_time": "3 days, 9:12:16"}
2
+ {"current_steps": 20, "total_steps": 13550, "loss": 12.3986, "learning_rate": 1.4760147601476015e-06, "epoch": 0.0014760147601476014, "percentage": 0.15, "elapsed_time": "0:07:10", "remaining_time": "3 days, 8:54:40"}
3
+ {"current_steps": 30, "total_steps": 13550, "loss": 10.8644, "learning_rate": 2.2140221402214023e-06, "epoch": 0.002214022140221402, "percentage": 0.22, "elapsed_time": "0:10:45", "remaining_time": "3 days, 8:46:36"}
4
+ {"current_steps": 40, "total_steps": 13550, "loss": 10.0464, "learning_rate": 2.952029520295203e-06, "epoch": 0.002952029520295203, "percentage": 0.3, "elapsed_time": "0:14:19", "remaining_time": "3 days, 8:39:47"}
5
+ {"current_steps": 50, "total_steps": 13550, "loss": 9.8267, "learning_rate": 3.690036900369004e-06, "epoch": 0.0036900369003690036, "percentage": 0.37, "elapsed_time": "0:17:54", "remaining_time": "3 days, 8:35:52"}
6
+ {"current_steps": 60, "total_steps": 13550, "loss": 9.6732, "learning_rate": 4.428044280442805e-06, "epoch": 0.004428044280442804, "percentage": 0.44, "elapsed_time": "0:21:29", "remaining_time": "3 days, 8:31:36"}
7
+ {"current_steps": 70, "total_steps": 13550, "loss": 9.6283, "learning_rate": 5.166051660516605e-06, "epoch": 0.0051660516605166054, "percentage": 0.52, "elapsed_time": "0:25:04", "remaining_time": "3 days, 8:28:46"}
8
+ {"current_steps": 80, "total_steps": 13550, "loss": 9.4751, "learning_rate": 5.904059040590406e-06, "epoch": 0.005904059040590406, "percentage": 0.59, "elapsed_time": "0:28:39", "remaining_time": "3 days, 8:26:10"}
9
+ {"current_steps": 90, "total_steps": 13550, "loss": 9.3959, "learning_rate": 6.642066420664207e-06, "epoch": 0.006642066420664207, "percentage": 0.66, "elapsed_time": "0:32:15", "remaining_time": "3 days, 8:24:54"}
10
+ {"current_steps": 100, "total_steps": 13550, "loss": 9.3828, "learning_rate": 7.380073800738008e-06, "epoch": 0.007380073800738007, "percentage": 0.74, "elapsed_time": "0:35:51", "remaining_time": "3 days, 8:22:22"}
11
+ {"current_steps": 110, "total_steps": 13550, "loss": 9.2352, "learning_rate": 8.118081180811808e-06, "epoch": 0.008118081180811807, "percentage": 0.81, "elapsed_time": "0:39:26", "remaining_time": "3 days, 8:19:07"}
12
+ {"current_steps": 120, "total_steps": 13550, "loss": 9.1436, "learning_rate": 8.85608856088561e-06, "epoch": 0.008856088560885609, "percentage": 0.89, "elapsed_time": "0:43:01", "remaining_time": "3 days, 8:15:57"}
13
+ {"current_steps": 130, "total_steps": 13550, "loss": 8.8854, "learning_rate": 9.59409594095941e-06, "epoch": 0.00959409594095941, "percentage": 0.96, "elapsed_time": "0:46:37", "remaining_time": "3 days, 8:12:36"}
14
+ {"current_steps": 140, "total_steps": 13550, "loss": 8.703, "learning_rate": 1.033210332103321e-05, "epoch": 0.010332103321033211, "percentage": 1.03, "elapsed_time": "0:50:12", "remaining_time": "3 days, 8:09:48"}
15
+ {"current_steps": 150, "total_steps": 13550, "loss": 8.5243, "learning_rate": 1.1070110701107012e-05, "epoch": 0.01107011070110701, "percentage": 1.11, "elapsed_time": "0:53:48", "remaining_time": "3 days, 8:06:49"}
16
+ {"current_steps": 160, "total_steps": 13550, "loss": 8.232, "learning_rate": 1.1808118081180812e-05, "epoch": 0.011808118081180811, "percentage": 1.18, "elapsed_time": "0:57:24", "remaining_time": "3 days, 8:04:03"}
17
+ {"current_steps": 170, "total_steps": 13550, "loss": 8.0453, "learning_rate": 1.2546125461254612e-05, "epoch": 0.012546125461254613, "percentage": 1.25, "elapsed_time": "1:00:59", "remaining_time": "3 days, 8:00:40"}
18
+ {"current_steps": 180, "total_steps": 13550, "loss": 7.9445, "learning_rate": 1.3284132841328414e-05, "epoch": 0.013284132841328414, "percentage": 1.33, "elapsed_time": "1:04:35", "remaining_time": "3 days, 7:57:38"}
19
+ {"current_steps": 190, "total_steps": 13550, "loss": 7.9335, "learning_rate": 1.4022140221402214e-05, "epoch": 0.014022140221402213, "percentage": 1.4, "elapsed_time": "1:08:10", "remaining_time": "3 days, 7:54:15"}
20
+ {"current_steps": 200, "total_steps": 13550, "loss": 7.7923, "learning_rate": 1.4760147601476015e-05, "epoch": 0.014760147601476014, "percentage": 1.48, "elapsed_time": "1:11:46", "remaining_time": "3 days, 7:51:07"}
21
+ {"current_steps": 210, "total_steps": 13550, "loss": 7.763, "learning_rate": 1.5498154981549817e-05, "epoch": 0.015498154981549815, "percentage": 1.55, "elapsed_time": "1:15:22", "remaining_time": "3 days, 7:48:10"}
22
+ {"current_steps": 220, "total_steps": 13550, "loss": 7.7702, "learning_rate": 1.6236162361623615e-05, "epoch": 0.016236162361623615, "percentage": 1.62, "elapsed_time": "1:18:58", "remaining_time": "3 days, 7:44:57"}
23
+ {"current_steps": 230, "total_steps": 13550, "loss": 7.76, "learning_rate": 1.6974169741697417e-05, "epoch": 0.016974169741697416, "percentage": 1.7, "elapsed_time": "1:22:34", "remaining_time": "3 days, 7:41:51"}
24
+ {"current_steps": 240, "total_steps": 13550, "loss": 7.6101, "learning_rate": 1.771217712177122e-05, "epoch": 0.017712177121771217, "percentage": 1.77, "elapsed_time": "1:26:09", "remaining_time": "3 days, 7:38:22"}
25
+ {"current_steps": 250, "total_steps": 13550, "loss": 7.5669, "learning_rate": 1.845018450184502e-05, "epoch": 0.01845018450184502, "percentage": 1.85, "elapsed_time": "1:29:45", "remaining_time": "3 days, 7:35:27"}
26
+ {"current_steps": 260, "total_steps": 13550, "loss": 7.3905, "learning_rate": 1.918819188191882e-05, "epoch": 0.01918819188191882, "percentage": 1.92, "elapsed_time": "1:33:21", "remaining_time": "3 days, 7:32:16"}
27
+ {"current_steps": 270, "total_steps": 13550, "loss": 7.3472, "learning_rate": 1.992619926199262e-05, "epoch": 0.01992619926199262, "percentage": 1.99, "elapsed_time": "1:36:57", "remaining_time": "3 days, 7:29:13"}
28
+ {"current_steps": 280, "total_steps": 13550, "loss": 7.2426, "learning_rate": 2.066420664206642e-05, "epoch": 0.020664206642066422, "percentage": 2.07, "elapsed_time": "1:40:34", "remaining_time": "3 days, 7:26:30"}
29
+ {"current_steps": 290, "total_steps": 13550, "loss": 7.0541, "learning_rate": 2.140221402214022e-05, "epoch": 0.021402214022140223, "percentage": 2.14, "elapsed_time": "1:44:10", "remaining_time": "3 days, 7:23:21"}
30
+ {"current_steps": 300, "total_steps": 13550, "loss": 7.0113, "learning_rate": 2.2140221402214025e-05, "epoch": 0.02214022140221402, "percentage": 2.21, "elapsed_time": "1:47:46", "remaining_time": "3 days, 7:20:11"}
31
+ {"current_steps": 310, "total_steps": 13550, "loss": 6.8661, "learning_rate": 2.2878228782287826e-05, "epoch": 0.022878228782287822, "percentage": 2.29, "elapsed_time": "1:51:22", "remaining_time": "3 days, 7:17:00"}
32
+ {"current_steps": 320, "total_steps": 13550, "loss": 7.0323, "learning_rate": 2.3616236162361624e-05, "epoch": 0.023616236162361623, "percentage": 2.36, "elapsed_time": "1:54:58", "remaining_time": "3 days, 7:13:49"}
33
+ {"current_steps": 330, "total_steps": 13550, "loss": 6.8865, "learning_rate": 2.4354243542435426e-05, "epoch": 0.024354243542435424, "percentage": 2.44, "elapsed_time": "1:58:34", "remaining_time": "3 days, 7:10:29"}
34
+ {"current_steps": 340, "total_steps": 13550, "loss": 6.7982, "learning_rate": 2.5092250922509224e-05, "epoch": 0.025092250922509225, "percentage": 2.51, "elapsed_time": "2:02:10", "remaining_time": "3 days, 7:07:08"}
35
+ {"current_steps": 350, "total_steps": 13550, "loss": 6.79, "learning_rate": 2.5830258302583026e-05, "epoch": 0.025830258302583026, "percentage": 2.58, "elapsed_time": "2:05:47", "remaining_time": "3 days, 7:04:08"}
36
+ {"current_steps": 360, "total_steps": 13550, "loss": 6.7459, "learning_rate": 2.6568265682656828e-05, "epoch": 0.026568265682656828, "percentage": 2.66, "elapsed_time": "2:09:23", "remaining_time": "3 days, 7:00:59"}
37
+ {"current_steps": 370, "total_steps": 13550, "loss": 6.637, "learning_rate": 2.730627306273063e-05, "epoch": 0.02730627306273063, "percentage": 2.73, "elapsed_time": "2:12:59", "remaining_time": "3 days, 6:57:31"}
38
+ {"current_steps": 380, "total_steps": 13550, "loss": 6.5645, "learning_rate": 2.8044280442804427e-05, "epoch": 0.028044280442804426, "percentage": 2.8, "elapsed_time": "2:16:36", "remaining_time": "3 days, 6:54:18"}
39
+ {"current_steps": 390, "total_steps": 13550, "loss": 6.4398, "learning_rate": 2.878228782287823e-05, "epoch": 0.028782287822878228, "percentage": 2.88, "elapsed_time": "2:20:12", "remaining_time": "3 days, 6:51:04"}
40
+ {"current_steps": 400, "total_steps": 13550, "loss": 6.4774, "learning_rate": 2.952029520295203e-05, "epoch": 0.02952029520295203, "percentage": 2.95, "elapsed_time": "2:23:48", "remaining_time": "3 days, 6:47:41"}
41
+ {"current_steps": 410, "total_steps": 13550, "loss": 6.3106, "learning_rate": 3.0258302583025832e-05, "epoch": 0.03025830258302583, "percentage": 3.03, "elapsed_time": "2:27:24", "remaining_time": "3 days, 6:44:27"}
42
+ {"current_steps": 420, "total_steps": 13550, "loss": 6.3172, "learning_rate": 3.0996309963099634e-05, "epoch": 0.03099630996309963, "percentage": 3.1, "elapsed_time": "2:31:01", "remaining_time": "3 days, 6:41:14"}
43
+ {"current_steps": 430, "total_steps": 13550, "loss": 6.1359, "learning_rate": 3.173431734317343e-05, "epoch": 0.03173431734317343, "percentage": 3.17, "elapsed_time": "2:34:37", "remaining_time": "3 days, 6:38:00"}
44
+ {"current_steps": 440, "total_steps": 13550, "loss": 6.2412, "learning_rate": 3.247232472324723e-05, "epoch": 0.03247232472324723, "percentage": 3.25, "elapsed_time": "2:38:13", "remaining_time": "3 days, 6:34:27"}
45
+ {"current_steps": 450, "total_steps": 13550, "loss": 6.2192, "learning_rate": 3.3210332103321035e-05, "epoch": 0.033210332103321034, "percentage": 3.32, "elapsed_time": "2:41:50", "remaining_time": "3 days, 6:31:09"}
46
+ {"current_steps": 460, "total_steps": 13550, "loss": 6.1654, "learning_rate": 3.3948339483394833e-05, "epoch": 0.03394833948339483, "percentage": 3.39, "elapsed_time": "2:45:26", "remaining_time": "3 days, 6:27:51"}
47
+ {"current_steps": 470, "total_steps": 13550, "loss": 6.0669, "learning_rate": 3.468634686346864e-05, "epoch": 0.03468634686346864, "percentage": 3.47, "elapsed_time": "2:49:02", "remaining_time": "3 days, 6:24:17"}
48
+ {"current_steps": 480, "total_steps": 13550, "loss": 6.0332, "learning_rate": 3.542435424354244e-05, "epoch": 0.035424354243542434, "percentage": 3.54, "elapsed_time": "2:52:38", "remaining_time": "3 days, 6:21:00"}
49
+ {"current_steps": 490, "total_steps": 13550, "loss": 5.9708, "learning_rate": 3.6162361623616235e-05, "epoch": 0.03616236162361624, "percentage": 3.62, "elapsed_time": "2:56:15", "remaining_time": "3 days, 6:17:36"}
50
+ {"current_steps": 500, "total_steps": 13550, "loss": 5.76, "learning_rate": 3.690036900369004e-05, "epoch": 0.03690036900369004, "percentage": 3.69, "elapsed_time": "2:59:51", "remaining_time": "3 days, 6:14:23"}
51
+ {"current_steps": 510, "total_steps": 13550, "loss": 5.9036, "learning_rate": 3.763837638376384e-05, "epoch": 0.037638376383763834, "percentage": 3.76, "elapsed_time": "3:03:28", "remaining_time": "3 days, 6:11:01"}
52
+ {"current_steps": 520, "total_steps": 13550, "loss": 5.808, "learning_rate": 3.837638376383764e-05, "epoch": 0.03837638376383764, "percentage": 3.84, "elapsed_time": "3:07:04", "remaining_time": "3 days, 6:07:34"}
53
+ {"current_steps": 530, "total_steps": 13550, "loss": 5.7391, "learning_rate": 3.911439114391144e-05, "epoch": 0.03911439114391144, "percentage": 3.91, "elapsed_time": "3:10:40", "remaining_time": "3 days, 6:04:19"}
54
+ {"current_steps": 540, "total_steps": 13550, "loss": 5.7045, "learning_rate": 3.985239852398524e-05, "epoch": 0.03985239852398524, "percentage": 3.99, "elapsed_time": "3:14:17", "remaining_time": "3 days, 6:00:52"}
55
+ {"current_steps": 550, "total_steps": 13550, "loss": 5.6956, "learning_rate": 4.0590405904059045e-05, "epoch": 0.04059040590405904, "percentage": 4.06, "elapsed_time": "3:17:53", "remaining_time": "3 days, 5:57:32"}
56
+ {"current_steps": 560, "total_steps": 13550, "loss": 5.6103, "learning_rate": 4.132841328413284e-05, "epoch": 0.041328413284132844, "percentage": 4.13, "elapsed_time": "3:21:29", "remaining_time": "3 days, 5:54:04"}
57
+ {"current_steps": 570, "total_steps": 13550, "loss": 5.4107, "learning_rate": 4.206642066420665e-05, "epoch": 0.04206642066420664, "percentage": 4.21, "elapsed_time": "3:25:06", "remaining_time": "3 days, 5:50:34"}
58
+ {"current_steps": 580, "total_steps": 13550, "loss": 5.4208, "learning_rate": 4.280442804428044e-05, "epoch": 0.042804428044280446, "percentage": 4.28, "elapsed_time": "3:28:42", "remaining_time": "3 days, 5:47:01"}
59
+ {"current_steps": 590, "total_steps": 13550, "loss": 5.4217, "learning_rate": 4.3542435424354244e-05, "epoch": 0.043542435424354244, "percentage": 4.35, "elapsed_time": "3:32:18", "remaining_time": "3 days, 5:43:38"}
60
+ {"current_steps": 600, "total_steps": 13550, "loss": 5.3994, "learning_rate": 4.428044280442805e-05, "epoch": 0.04428044280442804, "percentage": 4.43, "elapsed_time": "3:35:54", "remaining_time": "3 days, 5:40:04"}
61
+ {"current_steps": 610, "total_steps": 13550, "loss": 5.3605, "learning_rate": 4.501845018450185e-05, "epoch": 0.045018450184501846, "percentage": 4.5, "elapsed_time": "3:39:31", "remaining_time": "3 days, 5:36:41"}
62
+ {"current_steps": 620, "total_steps": 13550, "loss": 5.1682, "learning_rate": 4.575645756457565e-05, "epoch": 0.045756457564575644, "percentage": 4.58, "elapsed_time": "3:43:07", "remaining_time": "3 days, 5:33:14"}
63
+ {"current_steps": 630, "total_steps": 13550, "loss": 5.1585, "learning_rate": 4.6494464944649444e-05, "epoch": 0.04649446494464945, "percentage": 4.65, "elapsed_time": "3:46:43", "remaining_time": "3 days, 5:29:48"}
64
+ {"current_steps": 640, "total_steps": 13550, "loss": 5.2147, "learning_rate": 4.723247232472325e-05, "epoch": 0.047232472324723246, "percentage": 4.72, "elapsed_time": "3:50:19", "remaining_time": "3 days, 5:26:11"}
65
+ {"current_steps": 650, "total_steps": 13550, "loss": 5.0839, "learning_rate": 4.797047970479705e-05, "epoch": 0.04797047970479705, "percentage": 4.8, "elapsed_time": "3:53:55", "remaining_time": "3 days, 5:22:35"}
66
+ {"current_steps": 660, "total_steps": 13550, "loss": 5.1216, "learning_rate": 4.870848708487085e-05, "epoch": 0.04870848708487085, "percentage": 4.87, "elapsed_time": "3:57:31", "remaining_time": "3 days, 5:19:04"}
67
+ {"current_steps": 670, "total_steps": 13550, "loss": 4.9789, "learning_rate": 4.944649446494466e-05, "epoch": 0.04944649446494465, "percentage": 4.94, "elapsed_time": "4:01:08", "remaining_time": "3 days, 5:15:33"}
68
+ {"current_steps": 680, "total_steps": 13550, "loss": 4.9611, "learning_rate": 5.018450184501845e-05, "epoch": 0.05018450184501845, "percentage": 5.02, "elapsed_time": "4:04:44", "remaining_time": "3 days, 5:12:10"}
69
+ {"current_steps": 690, "total_steps": 13550, "loss": 4.8993, "learning_rate": 5.0922509225092254e-05, "epoch": 0.05092250922509225, "percentage": 5.09, "elapsed_time": "4:08:20", "remaining_time": "3 days, 5:08:39"}
70
+ {"current_steps": 700, "total_steps": 13550, "loss": 4.8083, "learning_rate": 5.166051660516605e-05, "epoch": 0.05166051660516605, "percentage": 5.17, "elapsed_time": "4:11:57", "remaining_time": "3 days, 5:05:10"}
71
+ {"current_steps": 710, "total_steps": 13550, "loss": 4.828, "learning_rate": 5.239852398523986e-05, "epoch": 0.05239852398523985, "percentage": 5.24, "elapsed_time": "4:15:33", "remaining_time": "3 days, 5:01:45"}
72
+ {"current_steps": 720, "total_steps": 13550, "loss": 4.7838, "learning_rate": 5.3136531365313655e-05, "epoch": 0.053136531365313655, "percentage": 5.31, "elapsed_time": "4:19:10", "remaining_time": "3 days, 4:58:19"}
73
+ {"current_steps": 730, "total_steps": 13550, "loss": 4.6931, "learning_rate": 5.387453874538746e-05, "epoch": 0.05387453874538745, "percentage": 5.39, "elapsed_time": "4:22:46", "remaining_time": "3 days, 4:54:51"}
74
+ {"current_steps": 740, "total_steps": 13550, "loss": 4.7027, "learning_rate": 5.461254612546126e-05, "epoch": 0.05461254612546126, "percentage": 5.46, "elapsed_time": "4:26:23", "remaining_time": "3 days, 4:51:25"}
75
+ {"current_steps": 750, "total_steps": 13550, "loss": 4.7452, "learning_rate": 5.535055350553506e-05, "epoch": 0.055350553505535055, "percentage": 5.54, "elapsed_time": "4:29:59", "remaining_time": "3 days, 4:47:59"}
76
+ {"current_steps": 760, "total_steps": 13550, "loss": 4.7062, "learning_rate": 5.6088560885608855e-05, "epoch": 0.05608856088560885, "percentage": 5.61, "elapsed_time": "4:33:36", "remaining_time": "3 days, 4:44:29"}
77
+ {"current_steps": 770, "total_steps": 13550, "loss": 4.6142, "learning_rate": 5.682656826568265e-05, "epoch": 0.05682656826568266, "percentage": 5.68, "elapsed_time": "4:37:12", "remaining_time": "3 days, 4:41:00"}
78
+ {"current_steps": 780, "total_steps": 13550, "loss": 4.4524, "learning_rate": 5.756457564575646e-05, "epoch": 0.057564575645756455, "percentage": 5.76, "elapsed_time": "4:40:48", "remaining_time": "3 days, 4:37:27"}
79
+ {"current_steps": 790, "total_steps": 13550, "loss": 4.5299, "learning_rate": 5.830258302583026e-05, "epoch": 0.05830258302583026, "percentage": 5.83, "elapsed_time": "4:44:25", "remaining_time": "3 days, 4:34:00"}
80
+ {"current_steps": 800, "total_steps": 13550, "loss": 4.4703, "learning_rate": 5.904059040590406e-05, "epoch": 0.05904059040590406, "percentage": 5.9, "elapsed_time": "4:48:01", "remaining_time": "3 days, 4:30:31"}
81
+ {"current_steps": 810, "total_steps": 13550, "loss": 4.463, "learning_rate": 5.9778597785977866e-05, "epoch": 0.05977859778597786, "percentage": 5.98, "elapsed_time": "4:51:38", "remaining_time": "3 days, 4:27:04"}
82
+ {"current_steps": 820, "total_steps": 13550, "loss": 4.4363, "learning_rate": 6.0516605166051664e-05, "epoch": 0.06051660516605166, "percentage": 6.05, "elapsed_time": "4:55:14", "remaining_time": "3 days, 4:23:32"}
83
+ {"current_steps": 830, "total_steps": 13550, "loss": 4.4099, "learning_rate": 6.125461254612547e-05, "epoch": 0.061254612546125464, "percentage": 6.13, "elapsed_time": "4:58:51", "remaining_time": "3 days, 4:20:01"}
84
+ {"current_steps": 840, "total_steps": 13550, "loss": 4.4153, "learning_rate": 6.199261992619927e-05, "epoch": 0.06199261992619926, "percentage": 6.2, "elapsed_time": "5:02:27", "remaining_time": "3 days, 4:16:28"}
85
+ {"current_steps": 850, "total_steps": 13550, "loss": 4.4721, "learning_rate": 6.273062730627307e-05, "epoch": 0.06273062730627306, "percentage": 6.27, "elapsed_time": "5:06:04", "remaining_time": "3 days, 4:13:02"}
86
+ {"current_steps": 860, "total_steps": 13550, "loss": 4.3287, "learning_rate": 6.346863468634686e-05, "epoch": 0.06346863468634686, "percentage": 6.35, "elapsed_time": "5:09:40", "remaining_time": "3 days, 4:09:23"}
87
+ {"current_steps": 870, "total_steps": 13550, "loss": 4.3766, "learning_rate": 6.420664206642066e-05, "epoch": 0.06420664206642067, "percentage": 6.42, "elapsed_time": "5:13:15", "remaining_time": "3 days, 4:05:44"}
88
+ {"current_steps": 880, "total_steps": 13550, "loss": 4.2412, "learning_rate": 6.494464944649446e-05, "epoch": 0.06494464944649446, "percentage": 6.49, "elapsed_time": "5:16:52", "remaining_time": "3 days, 4:02:13"}
89
+ {"current_steps": 890, "total_steps": 13550, "loss": 4.1558, "learning_rate": 6.568265682656827e-05, "epoch": 0.06568265682656826, "percentage": 6.57, "elapsed_time": "5:20:28", "remaining_time": "3 days, 3:58:41"}
90
+ {"current_steps": 900, "total_steps": 13550, "loss": 4.2074, "learning_rate": 6.642066420664207e-05, "epoch": 0.06642066420664207, "percentage": 6.64, "elapsed_time": "5:24:04", "remaining_time": "3 days, 3:55:06"}
91
+ {"current_steps": 910, "total_steps": 13550, "loss": 4.258, "learning_rate": 6.715867158671587e-05, "epoch": 0.06715867158671587, "percentage": 6.72, "elapsed_time": "5:27:40", "remaining_time": "3 days, 3:51:32"}
92
+ {"current_steps": 920, "total_steps": 13550, "loss": 4.1444, "learning_rate": 6.789667896678967e-05, "epoch": 0.06789667896678966, "percentage": 6.79, "elapsed_time": "5:31:17", "remaining_time": "3 days, 3:48:03"}
93
+ {"current_steps": 930, "total_steps": 13550, "loss": 4.1201, "learning_rate": 6.863468634686348e-05, "epoch": 0.06863468634686347, "percentage": 6.86, "elapsed_time": "5:34:53", "remaining_time": "3 days, 3:44:29"}
94
+ {"current_steps": 940, "total_steps": 13550, "loss": 4.1113, "learning_rate": 6.937269372693728e-05, "epoch": 0.06937269372693727, "percentage": 6.94, "elapsed_time": "5:38:30", "remaining_time": "3 days, 3:40:57"}
95
+ {"current_steps": 950, "total_steps": 13550, "loss": 4.0805, "learning_rate": 7.011070110701108e-05, "epoch": 0.07011070110701106, "percentage": 7.01, "elapsed_time": "5:42:06", "remaining_time": "3 days, 3:37:29"}
96
+ {"current_steps": 960, "total_steps": 13550, "loss": 4.0324, "learning_rate": 7.084870848708487e-05, "epoch": 0.07084870848708487, "percentage": 7.08, "elapsed_time": "5:45:43", "remaining_time": "3 days, 3:33:57"}
97
+ {"current_steps": 970, "total_steps": 13550, "loss": 4.0455, "learning_rate": 7.158671586715867e-05, "epoch": 0.07158671586715867, "percentage": 7.16, "elapsed_time": "5:49:19", "remaining_time": "3 days, 3:30:27"}
98
+ {"current_steps": 980, "total_steps": 13550, "loss": 4.0044, "learning_rate": 7.232472324723247e-05, "epoch": 0.07232472324723248, "percentage": 7.23, "elapsed_time": "5:52:55", "remaining_time": "3 days, 3:26:50"}
99
+ {"current_steps": 990, "total_steps": 13550, "loss": 4.0215, "learning_rate": 7.306273062730628e-05, "epoch": 0.07306273062730627, "percentage": 7.31, "elapsed_time": "5:56:32", "remaining_time": "3 days, 3:23:20"}
100
+ {"current_steps": 1000, "total_steps": 13550, "loss": 4.0744, "learning_rate": 7.380073800738008e-05, "epoch": 0.07380073800738007, "percentage": 7.38, "elapsed_time": "6:00:08", "remaining_time": "3 days, 3:19:43"}
101
+ {"current_steps": 1010, "total_steps": 13550, "loss": 3.9955, "learning_rate": 7.453874538745388e-05, "epoch": 0.07453874538745388, "percentage": 7.45, "elapsed_time": "6:03:44", "remaining_time": "3 days, 3:16:10"}
102
+ {"current_steps": 1020, "total_steps": 13550, "loss": 3.9916, "learning_rate": 7.527675276752768e-05, "epoch": 0.07527675276752767, "percentage": 7.53, "elapsed_time": "6:07:20", "remaining_time": "3 days, 3:12:36"}
103
+ {"current_steps": 1030, "total_steps": 13550, "loss": 3.9025, "learning_rate": 7.601476014760149e-05, "epoch": 0.07601476014760147, "percentage": 7.6, "elapsed_time": "6:10:57", "remaining_time": "3 days, 3:09:04"}
104
+ {"current_steps": 1040, "total_steps": 13550, "loss": 3.9822, "learning_rate": 7.675276752767529e-05, "epoch": 0.07675276752767528, "percentage": 7.68, "elapsed_time": "6:14:33", "remaining_time": "3 days, 3:05:31"}
105
+ {"current_steps": 1050, "total_steps": 13550, "loss": 3.8762, "learning_rate": 7.749077490774908e-05, "epoch": 0.07749077490774908, "percentage": 7.75, "elapsed_time": "6:18:10", "remaining_time": "3 days, 3:01:59"}
106
+ {"current_steps": 1060, "total_steps": 13550, "loss": 3.7911, "learning_rate": 7.822878228782288e-05, "epoch": 0.07822878228782287, "percentage": 7.82, "elapsed_time": "6:21:46", "remaining_time": "3 days, 2:58:27"}
107
+ {"current_steps": 1070, "total_steps": 13550, "loss": 3.8972, "learning_rate": 7.896678966789668e-05, "epoch": 0.07896678966789668, "percentage": 7.9, "elapsed_time": "6:25:22", "remaining_time": "3 days, 2:54:52"}
108
+ {"current_steps": 1080, "total_steps": 13550, "loss": 3.7901, "learning_rate": 7.970479704797048e-05, "epoch": 0.07970479704797048, "percentage": 7.97, "elapsed_time": "6:28:59", "remaining_time": "3 days, 2:51:22"}
109
+ {"current_steps": 1090, "total_steps": 13550, "loss": 3.9768, "learning_rate": 8.044280442804428e-05, "epoch": 0.08044280442804429, "percentage": 8.04, "elapsed_time": "6:32:35", "remaining_time": "3 days, 2:47:49"}
110
+ {"current_steps": 1100, "total_steps": 13550, "loss": 3.7534, "learning_rate": 8.118081180811809e-05, "epoch": 0.08118081180811808, "percentage": 8.12, "elapsed_time": "6:36:12", "remaining_time": "3 days, 2:44:17"}
111
+ {"current_steps": 1110, "total_steps": 13550, "loss": 3.7609, "learning_rate": 8.191881918819189e-05, "epoch": 0.08191881918819188, "percentage": 8.19, "elapsed_time": "6:39:48", "remaining_time": "3 days, 2:40:47"}
112
+ {"current_steps": 1120, "total_steps": 13550, "loss": 3.8031, "learning_rate": 8.265682656826569e-05, "epoch": 0.08265682656826569, "percentage": 8.27, "elapsed_time": "6:43:24", "remaining_time": "3 days, 2:37:11"}
113
+ {"current_steps": 1130, "total_steps": 13550, "loss": 3.8526, "learning_rate": 8.339483394833948e-05, "epoch": 0.08339483394833948, "percentage": 8.34, "elapsed_time": "6:47:01", "remaining_time": "3 days, 2:33:39"}
114
+ {"current_steps": 1140, "total_steps": 13550, "loss": 3.7551, "learning_rate": 8.41328413284133e-05, "epoch": 0.08413284132841328, "percentage": 8.41, "elapsed_time": "6:50:37", "remaining_time": "3 days, 2:30:05"}
115
+ {"current_steps": 1150, "total_steps": 13550, "loss": 3.834, "learning_rate": 8.48708487084871e-05, "epoch": 0.08487084870848709, "percentage": 8.49, "elapsed_time": "6:54:13", "remaining_time": "3 days, 2:26:28"}
116
+ {"current_steps": 1160, "total_steps": 13550, "loss": 3.7804, "learning_rate": 8.560885608856088e-05, "epoch": 0.08560885608856089, "percentage": 8.56, "elapsed_time": "6:57:50", "remaining_time": "3 days, 2:22:55"}
117
+ {"current_steps": 1170, "total_steps": 13550, "loss": 3.8757, "learning_rate": 8.634686346863469e-05, "epoch": 0.08634686346863468, "percentage": 8.63, "elapsed_time": "7:01:26", "remaining_time": "3 days, 2:19:23"}
118
+ {"current_steps": 1180, "total_steps": 13550, "loss": 3.7513, "learning_rate": 8.708487084870849e-05, "epoch": 0.08708487084870849, "percentage": 8.71, "elapsed_time": "7:05:02", "remaining_time": "3 days, 2:15:48"}
119
+ {"current_steps": 1190, "total_steps": 13550, "loss": 3.7555, "learning_rate": 8.782287822878229e-05, "epoch": 0.08782287822878229, "percentage": 8.78, "elapsed_time": "7:08:39", "remaining_time": "3 days, 2:12:19"}
120
+ {"current_steps": 1200, "total_steps": 13550, "loss": 3.834, "learning_rate": 8.85608856088561e-05, "epoch": 0.08856088560885608, "percentage": 8.86, "elapsed_time": "7:12:15", "remaining_time": "3 days, 2:08:42"}
121
+ {"current_steps": 1210, "total_steps": 13550, "loss": 3.6299, "learning_rate": 8.92988929889299e-05, "epoch": 0.08929889298892989, "percentage": 8.93, "elapsed_time": "7:15:51", "remaining_time": "3 days, 2:05:05"}
122
+ {"current_steps": 1220, "total_steps": 13550, "loss": 3.7695, "learning_rate": 9.00369003690037e-05, "epoch": 0.09003690036900369, "percentage": 9.0, "elapsed_time": "7:19:27", "remaining_time": "3 days, 2:01:28"}
123
+ {"current_steps": 1230, "total_steps": 13550, "loss": 3.7346, "learning_rate": 9.077490774907749e-05, "epoch": 0.0907749077490775, "percentage": 9.08, "elapsed_time": "7:23:04", "remaining_time": "3 days, 1:57:53"}
124
+ {"current_steps": 1240, "total_steps": 13550, "loss": 3.7646, "learning_rate": 9.15129151291513e-05, "epoch": 0.09151291512915129, "percentage": 9.15, "elapsed_time": "7:26:40", "remaining_time": "3 days, 1:54:17"}
125
+ {"current_steps": 1250, "total_steps": 13550, "loss": 3.6518, "learning_rate": 9.22509225092251e-05, "epoch": 0.09225092250922509, "percentage": 9.23, "elapsed_time": "7:30:16", "remaining_time": "3 days, 1:50:43"}
126
+ {"current_steps": 1260, "total_steps": 13550, "loss": 3.6702, "learning_rate": 9.298892988929889e-05, "epoch": 0.0929889298892989, "percentage": 9.3, "elapsed_time": "7:33:53", "remaining_time": "3 days, 1:47:13"}
127
+ {"current_steps": 1270, "total_steps": 13550, "loss": 3.6757, "learning_rate": 9.37269372693727e-05, "epoch": 0.09372693726937269, "percentage": 9.37, "elapsed_time": "7:37:29", "remaining_time": "3 days, 1:43:38"}
128
+ {"current_steps": 1280, "total_steps": 13550, "loss": 3.8173, "learning_rate": 9.44649446494465e-05, "epoch": 0.09446494464944649, "percentage": 9.45, "elapsed_time": "7:41:05", "remaining_time": "3 days, 1:40:01"}
129
+ {"current_steps": 1290, "total_steps": 13550, "loss": 3.6719, "learning_rate": 9.52029520295203e-05, "epoch": 0.0952029520295203, "percentage": 9.52, "elapsed_time": "7:44:41", "remaining_time": "3 days, 1:36:26"}
130
+ {"current_steps": 1300, "total_steps": 13550, "loss": 3.6447, "learning_rate": 9.59409594095941e-05, "epoch": 0.0959409594095941, "percentage": 9.59, "elapsed_time": "7:48:18", "remaining_time": "3 days, 1:32:54"}
131
+ {"current_steps": 1310, "total_steps": 13550, "loss": 3.6681, "learning_rate": 9.66789667896679e-05, "epoch": 0.09667896678966789, "percentage": 9.67, "elapsed_time": "7:51:54", "remaining_time": "3 days, 1:29:20"}
132
+ {"current_steps": 1320, "total_steps": 13550, "loss": 3.6526, "learning_rate": 9.74169741697417e-05, "epoch": 0.0974169741697417, "percentage": 9.74, "elapsed_time": "7:55:31", "remaining_time": "3 days, 1:25:46"}
133
+ {"current_steps": 1330, "total_steps": 13550, "loss": 3.6717, "learning_rate": 9.81549815498155e-05, "epoch": 0.0981549815498155, "percentage": 9.82, "elapsed_time": "7:59:08", "remaining_time": "3 days, 1:22:16"}
134
+ {"current_steps": 1340, "total_steps": 13550, "loss": 3.5892, "learning_rate": 9.889298892988931e-05, "epoch": 0.0988929889298893, "percentage": 9.89, "elapsed_time": "8:02:44", "remaining_time": "3 days, 1:18:41"}
135
+ {"current_steps": 1350, "total_steps": 13550, "loss": 3.6615, "learning_rate": 9.963099630996311e-05, "epoch": 0.0996309963099631, "percentage": 9.96, "elapsed_time": "8:06:20", "remaining_time": "3 days, 1:15:07"}
136
+ {"current_steps": 1360, "total_steps": 13550, "loss": 3.5785, "learning_rate": 9.999995852216369e-05, "epoch": 0.1003690036900369, "percentage": 10.04, "elapsed_time": "8:09:57", "remaining_time": "3 days, 1:11:33"}
137
+ {"current_steps": 1370, "total_steps": 13550, "loss": 3.625, "learning_rate": 9.999962669988607e-05, "epoch": 0.1011070110701107, "percentage": 10.11, "elapsed_time": "8:13:33", "remaining_time": "3 days, 1:07:59"}
138
+ {"current_steps": 1380, "total_steps": 13550, "loss": 3.6656, "learning_rate": 9.999896305753297e-05, "epoch": 0.1018450184501845, "percentage": 10.18, "elapsed_time": "8:17:10", "remaining_time": "3 days, 1:04:27"}
139
+ {"current_steps": 1390, "total_steps": 13550, "loss": 3.5761, "learning_rate": 9.999796759950864e-05, "epoch": 0.1025830258302583, "percentage": 10.26, "elapsed_time": "8:20:46", "remaining_time": "3 days, 1:00:52"}
140
+ {"current_steps": 1400, "total_steps": 13550, "loss": 3.5234, "learning_rate": 9.999664033241933e-05, "epoch": 0.1033210332103321, "percentage": 10.33, "elapsed_time": "8:24:23", "remaining_time": "3 days, 0:57:20"}
141
+ {"current_steps": 1410, "total_steps": 13550, "loss": 3.5132, "learning_rate": 9.99949812650734e-05, "epoch": 0.10405904059040591, "percentage": 10.41, "elapsed_time": "8:27:59", "remaining_time": "3 days, 0:53:43"}
142
+ {"current_steps": 1420, "total_steps": 13550, "loss": 3.5173, "learning_rate": 9.999299040848121e-05, "epoch": 0.1047970479704797, "percentage": 10.48, "elapsed_time": "8:31:35", "remaining_time": "3 days, 0:50:08"}
143
+ {"current_steps": 1430, "total_steps": 13550, "loss": 3.5605, "learning_rate": 9.999066777585495e-05, "epoch": 0.1055350553505535, "percentage": 10.55, "elapsed_time": "8:35:12", "remaining_time": "3 days, 0:46:35"}
144
+ {"current_steps": 1440, "total_steps": 13550, "loss": 3.5839, "learning_rate": 9.998801338260865e-05, "epoch": 0.10627306273062731, "percentage": 10.63, "elapsed_time": "8:38:48", "remaining_time": "3 days, 0:43:00"}
145
+ {"current_steps": 1450, "total_steps": 13550, "loss": 3.5685, "learning_rate": 9.99850272463581e-05, "epoch": 0.1070110701107011, "percentage": 10.7, "elapsed_time": "8:42:24", "remaining_time": "3 days, 0:39:24"}
146
+ {"current_steps": 1460, "total_steps": 13550, "loss": 3.5476, "learning_rate": 9.99817093869206e-05, "epoch": 0.1077490774907749, "percentage": 10.77, "elapsed_time": "8:46:00", "remaining_time": "3 days, 0:35:49"}
147
+ {"current_steps": 1470, "total_steps": 13550, "loss": 3.4777, "learning_rate": 9.997805982631499e-05, "epoch": 0.10848708487084871, "percentage": 10.85, "elapsed_time": "8:49:37", "remaining_time": "3 days, 0:32:17"}
148
+ {"current_steps": 1480, "total_steps": 13550, "loss": 3.5084, "learning_rate": 9.99740785887614e-05, "epoch": 0.10922509225092251, "percentage": 10.92, "elapsed_time": "8:53:13", "remaining_time": "3 days, 0:28:43"}
149
+ {"current_steps": 1490, "total_steps": 13550, "loss": 3.5741, "learning_rate": 9.99697657006811e-05, "epoch": 0.1099630996309963, "percentage": 11.0, "elapsed_time": "8:56:50", "remaining_time": "3 days, 0:25:07"}
150
+ {"current_steps": 1500, "total_steps": 13550, "loss": 3.5083, "learning_rate": 9.996512119069636e-05, "epoch": 0.11070110701107011, "percentage": 11.07, "elapsed_time": "9:00:26", "remaining_time": "3 days, 0:21:30"}
151
+ {"current_steps": 1510, "total_steps": 13550, "loss": 3.365, "learning_rate": 9.996014508963028e-05, "epoch": 0.11143911439114391, "percentage": 11.14, "elapsed_time": "9:04:02", "remaining_time": "3 days, 0:17:55"}
152
+ {"current_steps": 1520, "total_steps": 13550, "loss": 3.5233, "learning_rate": 9.995483743050648e-05, "epoch": 0.1121771217712177, "percentage": 11.22, "elapsed_time": "9:07:38", "remaining_time": "3 days, 0:14:18"}
153
+ {"current_steps": 1530, "total_steps": 13550, "loss": 3.5548, "learning_rate": 9.994919824854898e-05, "epoch": 0.11291512915129151, "percentage": 11.29, "elapsed_time": "9:11:15", "remaining_time": "3 days, 0:10:45"}
154
+ {"current_steps": 1540, "total_steps": 13550, "loss": 3.4293, "learning_rate": 9.994322758118196e-05, "epoch": 0.11365313653136531, "percentage": 11.37, "elapsed_time": "9:14:51", "remaining_time": "3 days, 0:07:09"}
155
+ {"current_steps": 1550, "total_steps": 13550, "loss": 3.4583, "learning_rate": 9.993692546802941e-05, "epoch": 0.11439114391143912, "percentage": 11.44, "elapsed_time": "9:18:28", "remaining_time": "3 days, 0:03:38"}
156
+ {"current_steps": 1560, "total_steps": 13550, "loss": 3.4349, "learning_rate": 9.993029195091505e-05, "epoch": 0.11512915129151291, "percentage": 11.51, "elapsed_time": "9:22:04", "remaining_time": "3 days, 0:00:05"}
157
+ {"current_steps": 1570, "total_steps": 13550, "loss": 3.4496, "learning_rate": 9.992332707386188e-05, "epoch": 0.11586715867158671, "percentage": 11.59, "elapsed_time": "9:25:41", "remaining_time": "2 days, 23:56:31"}
158
+ {"current_steps": 1580, "total_steps": 13550, "loss": 3.517, "learning_rate": 9.991603088309194e-05, "epoch": 0.11660516605166052, "percentage": 11.66, "elapsed_time": "9:29:17", "remaining_time": "2 days, 23:52:57"}
159
+ {"current_steps": 1590, "total_steps": 13550, "loss": 3.4505, "learning_rate": 9.990840342702606e-05, "epoch": 0.11734317343173432, "percentage": 11.73, "elapsed_time": "9:32:54", "remaining_time": "2 days, 23:49:23"}
160
+ {"current_steps": 1600, "total_steps": 13550, "loss": 3.5077, "learning_rate": 9.990044475628347e-05, "epoch": 0.11808118081180811, "percentage": 11.81, "elapsed_time": "9:36:30", "remaining_time": "2 days, 23:45:51"}
161
+ {"current_steps": 1610, "total_steps": 13550, "loss": 3.4272, "learning_rate": 9.989215492368151e-05, "epoch": 0.11881918819188192, "percentage": 11.88, "elapsed_time": "9:40:07", "remaining_time": "2 days, 23:42:17"}
162
+ {"current_steps": 1620, "total_steps": 13550, "loss": 3.3559, "learning_rate": 9.988353398423527e-05, "epoch": 0.11955719557195572, "percentage": 11.96, "elapsed_time": "9:43:43", "remaining_time": "2 days, 23:38:41"}
163
+ {"current_steps": 1630, "total_steps": 13550, "loss": 3.4108, "learning_rate": 9.987458199515713e-05, "epoch": 0.12029520295202951, "percentage": 12.03, "elapsed_time": "9:47:20", "remaining_time": "2 days, 23:35:07"}
164
+ {"current_steps": 1640, "total_steps": 13550, "loss": 3.4688, "learning_rate": 9.98652990158566e-05, "epoch": 0.12103321033210332, "percentage": 12.1, "elapsed_time": "9:50:56", "remaining_time": "2 days, 23:31:32"}
165
+ {"current_steps": 1650, "total_steps": 13550, "loss": 3.4611, "learning_rate": 9.985568510793967e-05, "epoch": 0.12177121771217712, "percentage": 12.18, "elapsed_time": "9:54:33", "remaining_time": "2 days, 23:27:58"}
166
+ {"current_steps": 1660, "total_steps": 13550, "loss": 3.4669, "learning_rate": 9.984574033520857e-05, "epoch": 0.12250922509225093, "percentage": 12.25, "elapsed_time": "9:58:09", "remaining_time": "2 days, 23:24:24"}
167
+ {"current_steps": 1670, "total_steps": 13550, "loss": 3.4798, "learning_rate": 9.983546476366132e-05, "epoch": 0.12324723247232472, "percentage": 12.32, "elapsed_time": "10:01:45", "remaining_time": "2 days, 23:20:48"}
168
+ {"current_steps": 1680, "total_steps": 13550, "loss": 3.3932, "learning_rate": 9.982485846149125e-05, "epoch": 0.12398523985239852, "percentage": 12.4, "elapsed_time": "10:05:21", "remaining_time": "2 days, 23:17:12"}
169
+ {"current_steps": 1690, "total_steps": 13550, "loss": 3.3856, "learning_rate": 9.981392149908652e-05, "epoch": 0.12472324723247233, "percentage": 12.47, "elapsed_time": "10:08:58", "remaining_time": "2 days, 23:13:36"}
170
+ {"current_steps": 1700, "total_steps": 13550, "loss": 3.455, "learning_rate": 9.98026539490298e-05, "epoch": 0.12546125461254612, "percentage": 12.55, "elapsed_time": "10:12:34", "remaining_time": "2 days, 23:10:03"}
171
+ {"current_steps": 1710, "total_steps": 13550, "loss": 3.4001, "learning_rate": 9.979105588609762e-05, "epoch": 0.12619926199261994, "percentage": 12.62, "elapsed_time": "10:16:11", "remaining_time": "2 days, 23:06:26"}
172
+ {"current_steps": 1720, "total_steps": 13550, "loss": 3.4277, "learning_rate": 9.977912738725994e-05, "epoch": 0.12693726937269373, "percentage": 12.69, "elapsed_time": "10:19:47", "remaining_time": "2 days, 23:02:52"}
173
+ {"current_steps": 1730, "total_steps": 13550, "loss": 3.4075, "learning_rate": 9.976686853167967e-05, "epoch": 0.12767527675276752, "percentage": 12.77, "elapsed_time": "10:23:23", "remaining_time": "2 days, 22:59:15"}
174
+ {"current_steps": 1740, "total_steps": 13550, "loss": 3.4226, "learning_rate": 9.975427940071211e-05, "epoch": 0.12841328413284134, "percentage": 12.84, "elapsed_time": "10:26:59", "remaining_time": "2 days, 22:55:39"}
175
+ {"current_steps": 1750, "total_steps": 13550, "loss": 3.4306, "learning_rate": 9.97413600779044e-05, "epoch": 0.12915129151291513, "percentage": 12.92, "elapsed_time": "10:30:35", "remaining_time": "2 days, 22:52:02"}
176
+ {"current_steps": 1760, "total_steps": 13550, "loss": 3.3937, "learning_rate": 9.9728110648995e-05, "epoch": 0.12988929889298892, "percentage": 12.99, "elapsed_time": "10:34:12", "remaining_time": "2 days, 22:48:29"}
177
+ {"current_steps": 1770, "total_steps": 13550, "loss": 3.3822, "learning_rate": 9.971453120191309e-05, "epoch": 0.13062730627306274, "percentage": 13.06, "elapsed_time": "10:37:48", "remaining_time": "2 days, 22:44:53"}
178
+ {"current_steps": 1780, "total_steps": 13550, "loss": 3.3824, "learning_rate": 9.970062182677801e-05, "epoch": 0.13136531365313653, "percentage": 13.14, "elapsed_time": "10:41:25", "remaining_time": "2 days, 22:41:17"}
179
+ {"current_steps": 1790, "total_steps": 13550, "loss": 3.4047, "learning_rate": 9.968638261589866e-05, "epoch": 0.13210332103321032, "percentage": 13.21, "elapsed_time": "10:45:01", "remaining_time": "2 days, 22:37:41"}
180
+ {"current_steps": 1800, "total_steps": 13550, "loss": 3.3903, "learning_rate": 9.967181366377285e-05, "epoch": 0.13284132841328414, "percentage": 13.28, "elapsed_time": "10:48:37", "remaining_time": "2 days, 22:34:06"}
181
+ {"current_steps": 1810, "total_steps": 13550, "loss": 3.3911, "learning_rate": 9.965691506708672e-05, "epoch": 0.13357933579335793, "percentage": 13.36, "elapsed_time": "10:52:14", "remaining_time": "2 days, 22:30:31"}
182
+ {"current_steps": 1820, "total_steps": 13550, "loss": 3.3861, "learning_rate": 9.964168692471408e-05, "epoch": 0.13431734317343175, "percentage": 13.43, "elapsed_time": "10:55:50", "remaining_time": "2 days, 22:26:56"}
183
+ {"current_steps": 1830, "total_steps": 13550, "loss": 3.4424, "learning_rate": 9.962612933771576e-05, "epoch": 0.13505535055350554, "percentage": 13.51, "elapsed_time": "10:59:27", "remaining_time": "2 days, 22:23:21"}
184
+ {"current_steps": 1840, "total_steps": 13550, "loss": 3.3459, "learning_rate": 9.961024240933892e-05, "epoch": 0.13579335793357933, "percentage": 13.58, "elapsed_time": "11:03:03", "remaining_time": "2 days, 22:19:47"}
185
+ {"current_steps": 1850, "total_steps": 13550, "loss": 3.3327, "learning_rate": 9.959402624501636e-05, "epoch": 0.13653136531365315, "percentage": 13.65, "elapsed_time": "11:06:39", "remaining_time": "2 days, 22:16:10"}
186
+ {"current_steps": 1860, "total_steps": 13550, "loss": 3.4398, "learning_rate": 9.957748095236589e-05, "epoch": 0.13726937269372694, "percentage": 13.73, "elapsed_time": "11:10:16", "remaining_time": "2 days, 22:12:35"}
187
+ {"current_steps": 1870, "total_steps": 13550, "loss": 3.3513, "learning_rate": 9.956060664118951e-05, "epoch": 0.13800738007380073, "percentage": 13.8, "elapsed_time": "11:13:52", "remaining_time": "2 days, 22:08:59"}
188
+ {"current_steps": 1880, "total_steps": 13550, "loss": 3.304, "learning_rate": 9.954340342347279e-05, "epoch": 0.13874538745387455, "percentage": 13.87, "elapsed_time": "11:17:28", "remaining_time": "2 days, 22:05:23"}
189
+ {"current_steps": 1890, "total_steps": 13550, "loss": 3.3155, "learning_rate": 9.952587141338403e-05, "epoch": 0.13948339483394834, "percentage": 13.95, "elapsed_time": "11:21:05", "remaining_time": "2 days, 22:01:50"}
190
+ {"current_steps": 1900, "total_steps": 13550, "loss": 3.3803, "learning_rate": 9.950801072727356e-05, "epoch": 0.14022140221402213, "percentage": 14.02, "elapsed_time": "11:24:41", "remaining_time": "2 days, 21:58:15"}
191
+ {"current_steps": 1910, "total_steps": 13550, "loss": 3.4219, "learning_rate": 9.948982148367292e-05, "epoch": 0.14095940959409595, "percentage": 14.1, "elapsed_time": "11:28:18", "remaining_time": "2 days, 21:54:42"}
192
+ {"current_steps": 1920, "total_steps": 13550, "loss": 3.301, "learning_rate": 9.947130380329418e-05, "epoch": 0.14169741697416974, "percentage": 14.17, "elapsed_time": "11:31:54", "remaining_time": "2 days, 21:51:06"}
193
+ {"current_steps": 1930, "total_steps": 13550, "loss": 3.3666, "learning_rate": 9.945245780902899e-05, "epoch": 0.14243542435424356, "percentage": 14.24, "elapsed_time": "11:35:31", "remaining_time": "2 days, 21:47:32"}
194
+ {"current_steps": 1940, "total_steps": 13550, "loss": 3.2862, "learning_rate": 9.943328362594788e-05, "epoch": 0.14317343173431735, "percentage": 14.32, "elapsed_time": "11:39:07", "remaining_time": "2 days, 21:43:56"}
195
+ {"current_steps": 1950, "total_steps": 13550, "loss": 3.3112, "learning_rate": 9.941378138129938e-05, "epoch": 0.14391143911439114, "percentage": 14.39, "elapsed_time": "11:42:44", "remaining_time": "2 days, 21:40:24"}
196
+ {"current_steps": 1960, "total_steps": 13550, "loss": 3.3539, "learning_rate": 9.939395120450916e-05, "epoch": 0.14464944649446496, "percentage": 14.46, "elapsed_time": "11:46:20", "remaining_time": "2 days, 21:36:49"}
197
+ {"current_steps": 1970, "total_steps": 13550, "loss": 3.3722, "learning_rate": 9.937379322717924e-05, "epoch": 0.14538745387453875, "percentage": 14.54, "elapsed_time": "11:49:57", "remaining_time": "2 days, 21:33:13"}
198
+ {"current_steps": 1980, "total_steps": 13550, "loss": 3.3329, "learning_rate": 9.935330758308705e-05, "epoch": 0.14612546125461254, "percentage": 14.61, "elapsed_time": "11:53:33", "remaining_time": "2 days, 21:29:37"}
199
+ {"current_steps": 1990, "total_steps": 13550, "loss": 3.2807, "learning_rate": 9.933249440818455e-05, "epoch": 0.14686346863468636, "percentage": 14.69, "elapsed_time": "11:57:09", "remaining_time": "2 days, 21:26:02"}
200
+ {"current_steps": 2000, "total_steps": 13550, "loss": 3.2662, "learning_rate": 9.931135384059736e-05, "epoch": 0.14760147601476015, "percentage": 14.76, "elapsed_time": "12:00:46", "remaining_time": "2 days, 21:22:26"}
201
+ {"current_steps": 2010, "total_steps": 13550, "loss": 3.2942, "learning_rate": 9.928988602062384e-05, "epoch": 0.14833948339483394, "percentage": 14.83, "elapsed_time": "12:04:22", "remaining_time": "2 days, 21:18:50"}
202
+ {"current_steps": 2020, "total_steps": 13550, "loss": 3.2639, "learning_rate": 9.926809109073412e-05, "epoch": 0.14907749077490776, "percentage": 14.91, "elapsed_time": "12:07:59", "remaining_time": "2 days, 21:15:16"}
203
+ {"current_steps": 2030, "total_steps": 13550, "loss": 3.3648, "learning_rate": 9.924596919556917e-05, "epoch": 0.14981549815498155, "percentage": 14.98, "elapsed_time": "12:11:35", "remaining_time": "2 days, 21:11:40"}
204
+ {"current_steps": 2040, "total_steps": 13550, "loss": 3.3417, "learning_rate": 9.922352048193986e-05, "epoch": 0.15055350553505534, "percentage": 15.06, "elapsed_time": "12:15:11", "remaining_time": "2 days, 21:08:03"}
205
+ {"current_steps": 2050, "total_steps": 13550, "loss": 3.3304, "learning_rate": 9.920074509882602e-05, "epoch": 0.15129151291512916, "percentage": 15.13, "elapsed_time": "12:18:48", "remaining_time": "2 days, 21:04:29"}
206
+ {"current_steps": 2060, "total_steps": 13550, "loss": 3.2585, "learning_rate": 9.917764319737533e-05, "epoch": 0.15202952029520295, "percentage": 15.2, "elapsed_time": "12:22:24", "remaining_time": "2 days, 21:00:54"}
207
+ {"current_steps": 2070, "total_steps": 13550, "loss": 3.2753, "learning_rate": 9.915421493090243e-05, "epoch": 0.15276752767527677, "percentage": 15.28, "elapsed_time": "12:26:01", "remaining_time": "2 days, 20:57:21"}
208
+ {"current_steps": 2080, "total_steps": 13550, "loss": 3.2683, "learning_rate": 9.913046045488786e-05, "epoch": 0.15350553505535056, "percentage": 15.35, "elapsed_time": "12:29:37", "remaining_time": "2 days, 20:53:46"}
209
+ {"current_steps": 2090, "total_steps": 13550, "loss": 3.2676, "learning_rate": 9.910637992697707e-05, "epoch": 0.15424354243542435, "percentage": 15.42, "elapsed_time": "12:33:14", "remaining_time": "2 days, 20:50:12"}
210
+ {"current_steps": 2100, "total_steps": 13550, "loss": 3.2941, "learning_rate": 9.908197350697926e-05, "epoch": 0.15498154981549817, "percentage": 15.5, "elapsed_time": "12:36:51", "remaining_time": "2 days, 20:46:38"}
211
+ {"current_steps": 2110, "total_steps": 13550, "loss": 3.3365, "learning_rate": 9.905724135686648e-05, "epoch": 0.15571955719557196, "percentage": 15.57, "elapsed_time": "12:40:27", "remaining_time": "2 days, 20:43:04"}
212
+ {"current_steps": 2120, "total_steps": 13550, "loss": 3.2594, "learning_rate": 9.903218364077243e-05, "epoch": 0.15645756457564575, "percentage": 15.65, "elapsed_time": "12:44:04", "remaining_time": "2 days, 20:39:31"}
213
+ {"current_steps": 2130, "total_steps": 13550, "loss": 3.3316, "learning_rate": 9.900680052499138e-05, "epoch": 0.15719557195571957, "percentage": 15.72, "elapsed_time": "12:47:40", "remaining_time": "2 days, 20:35:54"}
214
+ {"current_steps": 2140, "total_steps": 13550, "loss": 3.3196, "learning_rate": 9.898109217797717e-05, "epoch": 0.15793357933579336, "percentage": 15.79, "elapsed_time": "12:51:17", "remaining_time": "2 days, 20:32:21"}
215
+ {"current_steps": 2150, "total_steps": 13550, "loss": 3.3116, "learning_rate": 9.895505877034198e-05, "epoch": 0.15867158671586715, "percentage": 15.87, "elapsed_time": "12:54:53", "remaining_time": "2 days, 20:28:46"}
216
+ {"current_steps": 2160, "total_steps": 13550, "loss": 3.3119, "learning_rate": 9.892870047485526e-05, "epoch": 0.15940959409594097, "percentage": 15.94, "elapsed_time": "12:58:30", "remaining_time": "2 days, 20:25:10"}
217
+ {"current_steps": 2170, "total_steps": 13550, "loss": 3.2727, "learning_rate": 9.89020174664425e-05, "epoch": 0.16014760147601476, "percentage": 16.01, "elapsed_time": "13:02:06", "remaining_time": "2 days, 20:21:35"}
218
+ {"current_steps": 2180, "total_steps": 13550, "loss": 3.3661, "learning_rate": 9.887500992218421e-05, "epoch": 0.16088560885608857, "percentage": 16.09, "elapsed_time": "13:05:43", "remaining_time": "2 days, 20:18:01"}
219
+ {"current_steps": 2190, "total_steps": 13550, "loss": 3.3215, "learning_rate": 9.884767802131465e-05, "epoch": 0.16162361623616237, "percentage": 16.16, "elapsed_time": "13:09:20", "remaining_time": "2 days, 20:14:26"}
220
+ {"current_steps": 2200, "total_steps": 13550, "loss": 3.2374, "learning_rate": 9.882002194522064e-05, "epoch": 0.16236162361623616, "percentage": 16.24, "elapsed_time": "13:12:56", "remaining_time": "2 days, 20:10:50"}
221
+ {"current_steps": 2210, "total_steps": 13550, "loss": 3.2342, "learning_rate": 9.879204187744036e-05, "epoch": 0.16309963099630997, "percentage": 16.31, "elapsed_time": "13:16:33", "remaining_time": "2 days, 20:07:16"}
222
+ {"current_steps": 2220, "total_steps": 13550, "loss": 3.3181, "learning_rate": 9.876373800366215e-05, "epoch": 0.16383763837638377, "percentage": 16.38, "elapsed_time": "13:20:09", "remaining_time": "2 days, 20:03:39"}
223
+ {"current_steps": 2230, "total_steps": 13550, "loss": 3.3758, "learning_rate": 9.87351105117233e-05, "epoch": 0.16457564575645756, "percentage": 16.46, "elapsed_time": "13:23:45", "remaining_time": "2 days, 20:00:03"}
224
+ {"current_steps": 2240, "total_steps": 13550, "loss": 3.3542, "learning_rate": 9.870615959160875e-05, "epoch": 0.16531365313653137, "percentage": 16.53, "elapsed_time": "13:27:21", "remaining_time": "2 days, 19:56:27"}
225
+ {"current_steps": 2250, "total_steps": 13550, "loss": 3.2135, "learning_rate": 9.867688543544988e-05, "epoch": 0.16605166051660517, "percentage": 16.61, "elapsed_time": "13:30:57", "remaining_time": "2 days, 19:52:50"}
226
+ {"current_steps": 2260, "total_steps": 13550, "loss": 3.294, "learning_rate": 9.86472882375232e-05, "epoch": 0.16678966789667896, "percentage": 16.68, "elapsed_time": "13:34:34", "remaining_time": "2 days, 19:49:15"}
227
+ {"current_steps": 2270, "total_steps": 13550, "loss": 3.1992, "learning_rate": 9.861736819424902e-05, "epoch": 0.16752767527675277, "percentage": 16.75, "elapsed_time": "13:38:10", "remaining_time": "2 days, 19:45:39"}
228
+ {"current_steps": 2280, "total_steps": 13550, "loss": 3.2167, "learning_rate": 9.85871255041903e-05, "epoch": 0.16826568265682657, "percentage": 16.83, "elapsed_time": "13:41:46", "remaining_time": "2 days, 19:42:03"}
229
+ {"current_steps": 2290, "total_steps": 13550, "loss": 3.2945, "learning_rate": 9.855656036805114e-05, "epoch": 0.16900369003690036, "percentage": 16.9, "elapsed_time": "13:45:23", "remaining_time": "2 days, 19:38:26"}
230
+ {"current_steps": 2300, "total_steps": 13550, "loss": 3.2865, "learning_rate": 9.852567298867557e-05, "epoch": 0.16974169741697417, "percentage": 16.97, "elapsed_time": "13:48:59", "remaining_time": "2 days, 19:34:51"}
231
+ {"current_steps": 2310, "total_steps": 13550, "loss": 3.2188, "learning_rate": 9.84944635710462e-05, "epoch": 0.17047970479704797, "percentage": 17.05, "elapsed_time": "13:52:36", "remaining_time": "2 days, 19:31:16"}
232
+ {"current_steps": 2320, "total_steps": 13550, "loss": 3.2896, "learning_rate": 9.846293232228274e-05, "epoch": 0.17121771217712178, "percentage": 17.12, "elapsed_time": "13:56:12", "remaining_time": "2 days, 19:27:40"}
233
+ {"current_steps": 2330, "total_steps": 13550, "loss": 3.1705, "learning_rate": 9.843107945164086e-05, "epoch": 0.17195571955719557, "percentage": 17.2, "elapsed_time": "13:59:48", "remaining_time": "2 days, 19:24:04"}
234
+ {"current_steps": 2340, "total_steps": 13550, "loss": 3.2288, "learning_rate": 9.83989051705105e-05, "epoch": 0.17269372693726937, "percentage": 17.27, "elapsed_time": "14:03:25", "remaining_time": "2 days, 19:20:28"}
235
+ {"current_steps": 2350, "total_steps": 13550, "loss": 3.2441, "learning_rate": 9.836640969241475e-05, "epoch": 0.17343173431734318, "percentage": 17.34, "elapsed_time": "14:07:01", "remaining_time": "2 days, 19:16:52"}
236
+ {"current_steps": 2360, "total_steps": 13550, "loss": 3.2246, "learning_rate": 9.833359323300826e-05, "epoch": 0.17416974169741697, "percentage": 17.42, "elapsed_time": "14:10:37", "remaining_time": "2 days, 19:13:16"}
237
+ {"current_steps": 2370, "total_steps": 13550, "loss": 3.2008, "learning_rate": 9.830045601007584e-05, "epoch": 0.17490774907749077, "percentage": 17.49, "elapsed_time": "14:14:14", "remaining_time": "2 days, 19:09:41"}
238
+ {"current_steps": 2380, "total_steps": 13550, "loss": 3.3275, "learning_rate": 9.826699824353106e-05, "epoch": 0.17564575645756458, "percentage": 17.56, "elapsed_time": "14:17:50", "remaining_time": "2 days, 19:06:05"}
239
+ {"current_steps": 2390, "total_steps": 13550, "loss": 3.2064, "learning_rate": 9.823322015541474e-05, "epoch": 0.17638376383763837, "percentage": 17.64, "elapsed_time": "14:21:26", "remaining_time": "2 days, 19:02:30"}
240
+ {"current_steps": 2400, "total_steps": 13550, "loss": 3.1643, "learning_rate": 9.819912196989351e-05, "epoch": 0.17712177121771217, "percentage": 17.71, "elapsed_time": "14:25:03", "remaining_time": "2 days, 18:58:55"}
241
+ {"current_steps": 2410, "total_steps": 13550, "loss": 3.1848, "learning_rate": 9.816470391325832e-05, "epoch": 0.17785977859778598, "percentage": 17.79, "elapsed_time": "14:28:39", "remaining_time": "2 days, 18:55:18"}
242
+ {"current_steps": 2420, "total_steps": 13550, "loss": 3.2719, "learning_rate": 9.81299662139229e-05, "epoch": 0.17859778597785977, "percentage": 17.86, "elapsed_time": "14:32:16", "remaining_time": "2 days, 18:51:43"}
243
+ {"current_steps": 2430, "total_steps": 13550, "loss": 3.2619, "learning_rate": 9.809490910242229e-05, "epoch": 0.1793357933579336, "percentage": 17.93, "elapsed_time": "14:35:52", "remaining_time": "2 days, 18:48:07"}
244
+ {"current_steps": 2440, "total_steps": 13550, "loss": 3.243, "learning_rate": 9.805953281141131e-05, "epoch": 0.18007380073800738, "percentage": 18.01, "elapsed_time": "14:39:28", "remaining_time": "2 days, 18:44:31"}
245
+ {"current_steps": 2450, "total_steps": 13550, "loss": 3.2284, "learning_rate": 9.802383757566301e-05, "epoch": 0.18081180811808117, "percentage": 18.08, "elapsed_time": "14:43:05", "remaining_time": "2 days, 18:40:56"}
246
+ {"current_steps": 2460, "total_steps": 13550, "loss": 3.2043, "learning_rate": 9.798782363206702e-05, "epoch": 0.181549815498155, "percentage": 18.15, "elapsed_time": "14:46:41", "remaining_time": "2 days, 18:37:20"}
247
+ {"current_steps": 2470, "total_steps": 13550, "loss": 3.2683, "learning_rate": 9.795149121962815e-05, "epoch": 0.18228782287822878, "percentage": 18.23, "elapsed_time": "14:50:18", "remaining_time": "2 days, 18:33:46"}
248
+ {"current_steps": 2480, "total_steps": 13550, "loss": 3.1977, "learning_rate": 9.791484057946465e-05, "epoch": 0.18302583025830257, "percentage": 18.3, "elapsed_time": "14:53:55", "remaining_time": "2 days, 18:30:12"}
249
+ {"current_steps": 2490, "total_steps": 13550, "loss": 3.2263, "learning_rate": 9.787787195480672e-05, "epoch": 0.1837638376383764, "percentage": 18.38, "elapsed_time": "14:57:31", "remaining_time": "2 days, 18:26:35"}
250
+ {"current_steps": 2500, "total_steps": 13550, "loss": 3.1628, "learning_rate": 9.784058559099483e-05, "epoch": 0.18450184501845018, "percentage": 18.45, "elapsed_time": "15:01:07", "remaining_time": "2 days, 18:22:58"}
251
+ {"current_steps": 2510, "total_steps": 13550, "loss": 3.1828, "learning_rate": 9.78029817354781e-05, "epoch": 0.18523985239852397, "percentage": 18.52, "elapsed_time": "15:04:44", "remaining_time": "2 days, 18:19:23"}
252
+ {"current_steps": 2520, "total_steps": 13550, "loss": 3.2248, "learning_rate": 9.776506063781269e-05, "epoch": 0.1859778597785978, "percentage": 18.6, "elapsed_time": "15:08:20", "remaining_time": "2 days, 18:15:47"}
253
+ {"current_steps": 2530, "total_steps": 13550, "loss": 3.2495, "learning_rate": 9.772682254966008e-05, "epoch": 0.18671586715867158, "percentage": 18.67, "elapsed_time": "15:11:56", "remaining_time": "2 days, 18:12:11"}
254
+ {"current_steps": 2540, "total_steps": 13550, "loss": 3.1979, "learning_rate": 9.76882677247855e-05, "epoch": 0.18745387453874537, "percentage": 18.75, "elapsed_time": "15:15:33", "remaining_time": "2 days, 18:08:38"}
255
+ {"current_steps": 2550, "total_steps": 13550, "loss": 3.1714, "learning_rate": 9.764939641905615e-05, "epoch": 0.1881918819188192, "percentage": 18.82, "elapsed_time": "15:19:10", "remaining_time": "2 days, 18:05:04"}
256
+ {"current_steps": 2560, "total_steps": 13550, "loss": 3.154, "learning_rate": 9.761020889043954e-05, "epoch": 0.18892988929889298, "percentage": 18.89, "elapsed_time": "15:22:47", "remaining_time": "2 days, 18:01:28"}
257
+ {"current_steps": 2570, "total_steps": 13550, "loss": 3.2036, "learning_rate": 9.75707053990018e-05, "epoch": 0.1896678966789668, "percentage": 18.97, "elapsed_time": "15:26:23", "remaining_time": "2 days, 17:57:54"}
258
+ {"current_steps": 2580, "total_steps": 13550, "loss": 3.2392, "learning_rate": 9.75308862069059e-05, "epoch": 0.1904059040590406, "percentage": 19.04, "elapsed_time": "15:29:59", "remaining_time": "2 days, 17:54:18"}
259
+ {"current_steps": 2590, "total_steps": 13550, "loss": 3.2528, "learning_rate": 9.749075157840996e-05, "epoch": 0.19114391143911438, "percentage": 19.11, "elapsed_time": "15:33:36", "remaining_time": "2 days, 17:50:44"}
260
+ {"current_steps": 2600, "total_steps": 13550, "loss": 3.2256, "learning_rate": 9.74503017798655e-05, "epoch": 0.1918819188191882, "percentage": 19.19, "elapsed_time": "15:37:13", "remaining_time": "2 days, 17:47:07"}
261
+ {"current_steps": 2610, "total_steps": 13550, "loss": 3.2183, "learning_rate": 9.74095370797156e-05, "epoch": 0.192619926199262, "percentage": 19.26, "elapsed_time": "15:40:49", "remaining_time": "2 days, 17:43:32"}
262
+ {"current_steps": 2620, "total_steps": 13550, "loss": 3.2418, "learning_rate": 9.736845774849321e-05, "epoch": 0.19335793357933578, "percentage": 19.34, "elapsed_time": "15:44:25", "remaining_time": "2 days, 17:39:56"}
263
+ {"current_steps": 2630, "total_steps": 13550, "loss": 3.191, "learning_rate": 9.732706405881931e-05, "epoch": 0.1940959409594096, "percentage": 19.41, "elapsed_time": "15:48:02", "remaining_time": "2 days, 17:36:20"}
264
+ {"current_steps": 2640, "total_steps": 13550, "loss": 3.1968, "learning_rate": 9.728535628540109e-05, "epoch": 0.1948339483394834, "percentage": 19.48, "elapsed_time": "15:51:38", "remaining_time": "2 days, 17:32:45"}
265
+ {"current_steps": 2650, "total_steps": 13550, "loss": 3.2596, "learning_rate": 9.724333470503013e-05, "epoch": 0.19557195571955718, "percentage": 19.56, "elapsed_time": "15:55:15", "remaining_time": "2 days, 17:29:11"}
266
+ {"current_steps": 2660, "total_steps": 13550, "loss": 3.1729, "learning_rate": 9.720099959658062e-05, "epoch": 0.196309963099631, "percentage": 19.63, "elapsed_time": "15:58:52", "remaining_time": "2 days, 17:25:35"}
267
+ {"current_steps": 2670, "total_steps": 13550, "loss": 3.2604, "learning_rate": 9.715835124100742e-05, "epoch": 0.1970479704797048, "percentage": 19.7, "elapsed_time": "16:02:28", "remaining_time": "2 days, 17:21:59"}
268
+ {"current_steps": 2680, "total_steps": 13550, "loss": 3.2194, "learning_rate": 9.711538992134426e-05, "epoch": 0.1977859778597786, "percentage": 19.78, "elapsed_time": "16:06:04", "remaining_time": "2 days, 17:18:22"}
269
+ {"current_steps": 2690, "total_steps": 13550, "loss": 3.1994, "learning_rate": 9.707211592270183e-05, "epoch": 0.1985239852398524, "percentage": 19.85, "elapsed_time": "16:09:41", "remaining_time": "2 days, 17:14:48"}
270
+ {"current_steps": 2700, "total_steps": 13550, "loss": 3.1919, "learning_rate": 9.70285295322659e-05, "epoch": 0.1992619926199262, "percentage": 19.93, "elapsed_time": "16:13:17", "remaining_time": "2 days, 17:11:11"}
271
+ {"current_steps": 2710, "total_steps": 13550, "loss": 3.2464, "learning_rate": 9.698463103929542e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "16:16:53", "remaining_time": "2 days, 17:07:35"}
272
+ {"current_steps": 2720, "total_steps": 13550, "loss": 3.2042, "learning_rate": 9.69404207351206e-05, "epoch": 0.2007380073800738, "percentage": 20.07, "elapsed_time": "16:20:30", "remaining_time": "2 days, 17:04:00"}
273
+ {"current_steps": 2730, "total_steps": 13550, "loss": 3.2012, "learning_rate": 9.689589891314094e-05, "epoch": 0.2014760147601476, "percentage": 20.15, "elapsed_time": "16:24:06", "remaining_time": "2 days, 17:00:23"}
274
+ {"current_steps": 2740, "total_steps": 13550, "loss": 3.2053, "learning_rate": 9.685106586882336e-05, "epoch": 0.2022140221402214, "percentage": 20.22, "elapsed_time": "16:27:43", "remaining_time": "2 days, 16:56:47"}
275
+ {"current_steps": 2750, "total_steps": 13550, "loss": 3.177, "learning_rate": 9.680592189970015e-05, "epoch": 0.2029520295202952, "percentage": 20.3, "elapsed_time": "16:31:19", "remaining_time": "2 days, 16:53:12"}
276
+ {"current_steps": 2760, "total_steps": 13550, "loss": 3.2039, "learning_rate": 9.676046730536704e-05, "epoch": 0.203690036900369, "percentage": 20.37, "elapsed_time": "16:34:56", "remaining_time": "2 days, 16:49:37"}
277
+ {"current_steps": 2770, "total_steps": 13550, "loss": 3.1654, "learning_rate": 9.671470238748124e-05, "epoch": 0.2044280442804428, "percentage": 20.44, "elapsed_time": "16:38:32", "remaining_time": "2 days, 16:46:00"}
278
+ {"current_steps": 2780, "total_steps": 13550, "loss": 3.1978, "learning_rate": 9.666862744975938e-05, "epoch": 0.2051660516605166, "percentage": 20.52, "elapsed_time": "16:42:09", "remaining_time": "2 days, 16:42:26"}
279
+ {"current_steps": 2790, "total_steps": 13550, "loss": 3.2152, "learning_rate": 9.662224279797552e-05, "epoch": 0.2059040590405904, "percentage": 20.59, "elapsed_time": "16:45:45", "remaining_time": "2 days, 16:38:51"}
280
+ {"current_steps": 2800, "total_steps": 13550, "loss": 3.1699, "learning_rate": 9.657554873995913e-05, "epoch": 0.2066420664206642, "percentage": 20.66, "elapsed_time": "16:49:21", "remaining_time": "2 days, 16:35:14"}
281
+ {"current_steps": 2810, "total_steps": 13550, "loss": 3.1766, "learning_rate": 9.652854558559308e-05, "epoch": 0.207380073800738, "percentage": 20.74, "elapsed_time": "16:52:58", "remaining_time": "2 days, 16:31:38"}
282
+ {"current_steps": 2820, "total_steps": 13550, "loss": 3.0935, "learning_rate": 9.648123364681145e-05, "epoch": 0.20811808118081182, "percentage": 20.81, "elapsed_time": "16:56:34", "remaining_time": "2 days, 16:28:03"}
283
+ {"current_steps": 2830, "total_steps": 13550, "loss": 3.1111, "learning_rate": 9.643361323759763e-05, "epoch": 0.2088560885608856, "percentage": 20.89, "elapsed_time": "17:00:11", "remaining_time": "2 days, 16:24:28"}
284
+ {"current_steps": 2840, "total_steps": 13550, "loss": 3.1739, "learning_rate": 9.638568467398215e-05, "epoch": 0.2095940959409594, "percentage": 20.96, "elapsed_time": "17:03:47", "remaining_time": "2 days, 16:20:51"}
285
+ {"current_steps": 2850, "total_steps": 13550, "loss": 3.2064, "learning_rate": 9.633744827404055e-05, "epoch": 0.21033210332103322, "percentage": 21.03, "elapsed_time": "17:07:24", "remaining_time": "2 days, 16:17:15"}
286
+ {"current_steps": 2860, "total_steps": 13550, "loss": 3.2281, "learning_rate": 9.628890435789135e-05, "epoch": 0.211070110701107, "percentage": 21.11, "elapsed_time": "17:11:00", "remaining_time": "2 days, 16:13:40"}
287
+ {"current_steps": 2870, "total_steps": 13550, "loss": 3.113, "learning_rate": 9.624005324769388e-05, "epoch": 0.2118081180811808, "percentage": 21.18, "elapsed_time": "17:14:37", "remaining_time": "2 days, 16:10:04"}
288
+ {"current_steps": 2880, "total_steps": 13550, "loss": 3.1592, "learning_rate": 9.619089526764614e-05, "epoch": 0.21254612546125462, "percentage": 21.25, "elapsed_time": "17:18:13", "remaining_time": "2 days, 16:06:29"}
289
+ {"current_steps": 2890, "total_steps": 13550, "loss": 3.1904, "learning_rate": 9.614143074398264e-05, "epoch": 0.2132841328413284, "percentage": 21.33, "elapsed_time": "17:21:50", "remaining_time": "2 days, 16:02:53"}
290
+ {"current_steps": 2900, "total_steps": 13550, "loss": 3.1156, "learning_rate": 9.609166000497229e-05, "epoch": 0.2140221402214022, "percentage": 21.4, "elapsed_time": "17:25:26", "remaining_time": "2 days, 15:59:18"}
291
+ {"current_steps": 2910, "total_steps": 13550, "loss": 3.1888, "learning_rate": 9.604158338091615e-05, "epoch": 0.21476014760147602, "percentage": 21.48, "elapsed_time": "17:29:03", "remaining_time": "2 days, 15:55:44"}
292
+ {"current_steps": 2920, "total_steps": 13550, "loss": 3.1079, "learning_rate": 9.599120120414531e-05, "epoch": 0.2154981549815498, "percentage": 21.55, "elapsed_time": "17:32:40", "remaining_time": "2 days, 15:52:08"}
293
+ {"current_steps": 2930, "total_steps": 13550, "loss": 3.1147, "learning_rate": 9.594051380901859e-05, "epoch": 0.21623616236162363, "percentage": 21.62, "elapsed_time": "17:36:16", "remaining_time": "2 days, 15:48:34"}
294
+ {"current_steps": 2940, "total_steps": 13550, "loss": 3.1061, "learning_rate": 9.588952153192041e-05, "epoch": 0.21697416974169742, "percentage": 21.7, "elapsed_time": "17:39:53", "remaining_time": "2 days, 15:44:57"}
295
+ {"current_steps": 2950, "total_steps": 13550, "loss": 3.1172, "learning_rate": 9.583822471125854e-05, "epoch": 0.2177121771217712, "percentage": 21.77, "elapsed_time": "17:43:29", "remaining_time": "2 days, 15:41:22"}
296
+ {"current_steps": 2960, "total_steps": 13550, "loss": 3.2186, "learning_rate": 9.578662368746182e-05, "epoch": 0.21845018450184503, "percentage": 21.85, "elapsed_time": "17:47:06", "remaining_time": "2 days, 15:37:47"}
297
+ {"current_steps": 2970, "total_steps": 13550, "loss": 3.1628, "learning_rate": 9.57347188029779e-05, "epoch": 0.21918819188191882, "percentage": 21.92, "elapsed_time": "17:50:42", "remaining_time": "2 days, 15:34:11"}
298
+ {"current_steps": 2980, "total_steps": 13550, "loss": 3.1291, "learning_rate": 9.568251040227101e-05, "epoch": 0.2199261992619926, "percentage": 21.99, "elapsed_time": "17:54:19", "remaining_time": "2 days, 15:30:36"}
299
+ {"current_steps": 2990, "total_steps": 13550, "loss": 3.1305, "learning_rate": 9.562999883181967e-05, "epoch": 0.22066420664206643, "percentage": 22.07, "elapsed_time": "17:57:55", "remaining_time": "2 days, 15:26:59"}
300
+ {"current_steps": 3000, "total_steps": 13550, "loss": 3.2148, "learning_rate": 9.557718444011431e-05, "epoch": 0.22140221402214022, "percentage": 22.14, "elapsed_time": "18:01:32", "remaining_time": "2 days, 15:23:25"}
301
+ {"current_steps": 3010, "total_steps": 13550, "loss": 3.1322, "learning_rate": 9.552406757765509e-05, "epoch": 0.222140221402214, "percentage": 22.21, "elapsed_time": "18:05:08", "remaining_time": "2 days, 15:19:49"}
302
+ {"current_steps": 3020, "total_steps": 13550, "loss": 3.1822, "learning_rate": 9.547064859694943e-05, "epoch": 0.22287822878228783, "percentage": 22.29, "elapsed_time": "18:08:45", "remaining_time": "2 days, 15:16:13"}
303
+ {"current_steps": 3030, "total_steps": 13550, "loss": 3.1371, "learning_rate": 9.541692785250981e-05, "epoch": 0.22361623616236162, "percentage": 22.36, "elapsed_time": "18:12:21", "remaining_time": "2 days, 15:12:37"}
304
+ {"current_steps": 3040, "total_steps": 13550, "loss": 3.1329, "learning_rate": 9.536290570085131e-05, "epoch": 0.2243542435424354, "percentage": 22.44, "elapsed_time": "18:15:58", "remaining_time": "2 days, 15:09:01"}
305
+ {"current_steps": 3050, "total_steps": 13550, "loss": 3.2538, "learning_rate": 9.530858250048932e-05, "epoch": 0.22509225092250923, "percentage": 22.51, "elapsed_time": "18:19:34", "remaining_time": "2 days, 15:05:25"}
306
+ {"current_steps": 3060, "total_steps": 13550, "loss": 3.2139, "learning_rate": 9.525395861193707e-05, "epoch": 0.22583025830258302, "percentage": 22.58, "elapsed_time": "18:23:10", "remaining_time": "2 days, 15:01:49"}
307
+ {"current_steps": 3070, "total_steps": 13550, "loss": 3.1138, "learning_rate": 9.519903439770332e-05, "epoch": 0.22656826568265684, "percentage": 22.66, "elapsed_time": "18:26:47", "remaining_time": "2 days, 14:58:13"}
308
+ {"current_steps": 3080, "total_steps": 13550, "loss": 3.0872, "learning_rate": 9.514381022228997e-05, "epoch": 0.22730627306273063, "percentage": 22.73, "elapsed_time": "18:30:24", "remaining_time": "2 days, 14:54:38"}
309
+ {"current_steps": 3090, "total_steps": 13550, "loss": 3.167, "learning_rate": 9.50882864521895e-05, "epoch": 0.22804428044280442, "percentage": 22.8, "elapsed_time": "18:34:00", "remaining_time": "2 days, 14:51:03"}
310
+ {"current_steps": 3100, "total_steps": 13550, "loss": 3.15, "learning_rate": 9.503246345588274e-05, "epoch": 0.22878228782287824, "percentage": 22.88, "elapsed_time": "18:37:37", "remaining_time": "2 days, 14:47:28"}
311
+ {"current_steps": 3110, "total_steps": 13550, "loss": 3.1367, "learning_rate": 9.497634160383626e-05, "epoch": 0.22952029520295203, "percentage": 22.95, "elapsed_time": "18:41:13", "remaining_time": "2 days, 14:43:51"}
312
+ {"current_steps": 3120, "total_steps": 13550, "loss": 3.1779, "learning_rate": 9.491992126849997e-05, "epoch": 0.23025830258302582, "percentage": 23.03, "elapsed_time": "18:44:50", "remaining_time": "2 days, 14:40:15"}
313
+ {"current_steps": 3130, "total_steps": 13550, "loss": 3.0789, "learning_rate": 9.486320282430468e-05, "epoch": 0.23099630996309964, "percentage": 23.1, "elapsed_time": "18:48:26", "remaining_time": "2 days, 14:36:40"}
314
+ {"current_steps": 3140, "total_steps": 13550, "loss": 3.1866, "learning_rate": 9.480618664765955e-05, "epoch": 0.23173431734317343, "percentage": 23.17, "elapsed_time": "18:52:03", "remaining_time": "2 days, 14:33:04"}
315
+ {"current_steps": 3150, "total_steps": 13550, "loss": 3.2089, "learning_rate": 9.474887311694968e-05, "epoch": 0.23247232472324722, "percentage": 23.25, "elapsed_time": "18:55:39", "remaining_time": "2 days, 14:29:28"}
316
+ {"current_steps": 3160, "total_steps": 13550, "loss": 3.1159, "learning_rate": 9.469126261253348e-05, "epoch": 0.23321033210332104, "percentage": 23.32, "elapsed_time": "18:59:16", "remaining_time": "2 days, 14:25:53"}
317
+ {"current_steps": 3170, "total_steps": 13550, "loss": 3.124, "learning_rate": 9.463335551674025e-05, "epoch": 0.23394833948339483, "percentage": 23.39, "elapsed_time": "19:02:52", "remaining_time": "2 days, 14:22:17"}
318
+ {"current_steps": 3180, "total_steps": 13550, "loss": 3.103, "learning_rate": 9.45751522138676e-05, "epoch": 0.23468634686346865, "percentage": 23.47, "elapsed_time": "19:06:29", "remaining_time": "2 days, 14:18:41"}
319
+ {"current_steps": 3190, "total_steps": 13550, "loss": 3.1502, "learning_rate": 9.45166530901789e-05, "epoch": 0.23542435424354244, "percentage": 23.54, "elapsed_time": "19:10:05", "remaining_time": "2 days, 14:15:06"}
320
+ {"current_steps": 3200, "total_steps": 13550, "loss": 3.0856, "learning_rate": 9.445785853390073e-05, "epoch": 0.23616236162361623, "percentage": 23.62, "elapsed_time": "19:13:41", "remaining_time": "2 days, 14:11:29"}
321
+ {"current_steps": 3210, "total_steps": 13550, "loss": 3.1143, "learning_rate": 9.439876893522028e-05, "epoch": 0.23690036900369005, "percentage": 23.69, "elapsed_time": "19:17:18", "remaining_time": "2 days, 14:07:53"}
322
+ {"current_steps": 3220, "total_steps": 13550, "loss": 3.1628, "learning_rate": 9.433938468628277e-05, "epoch": 0.23763837638376384, "percentage": 23.76, "elapsed_time": "19:20:54", "remaining_time": "2 days, 14:04:16"}
323
+ {"current_steps": 3230, "total_steps": 13550, "loss": 3.1164, "learning_rate": 9.427970618118888e-05, "epoch": 0.23837638376383763, "percentage": 23.84, "elapsed_time": "19:24:31", "remaining_time": "2 days, 14:00:42"}
324
+ {"current_steps": 3240, "total_steps": 13550, "loss": 3.0361, "learning_rate": 9.421973381599208e-05, "epoch": 0.23911439114391145, "percentage": 23.91, "elapsed_time": "19:28:07", "remaining_time": "2 days, 13:57:06"}
325
+ {"current_steps": 3250, "total_steps": 13550, "loss": 3.1452, "learning_rate": 9.415946798869602e-05, "epoch": 0.23985239852398524, "percentage": 23.99, "elapsed_time": "19:31:44", "remaining_time": "2 days, 13:53:30"}
326
+ {"current_steps": 3260, "total_steps": 13550, "loss": 3.1493, "learning_rate": 9.409890909925193e-05, "epoch": 0.24059040590405903, "percentage": 24.06, "elapsed_time": "19:35:20", "remaining_time": "2 days, 13:49:54"}
327
+ {"current_steps": 3270, "total_steps": 13550, "loss": 3.1315, "learning_rate": 9.40380575495559e-05, "epoch": 0.24132841328413285, "percentage": 24.13, "elapsed_time": "19:38:57", "remaining_time": "2 days, 13:46:18"}
328
+ {"current_steps": 3280, "total_steps": 13550, "loss": 3.1218, "learning_rate": 9.39769137434463e-05, "epoch": 0.24206642066420664, "percentage": 24.21, "elapsed_time": "19:42:33", "remaining_time": "2 days, 13:42:43"}
329
+ {"current_steps": 3290, "total_steps": 13550, "loss": 3.0916, "learning_rate": 9.391547808670096e-05, "epoch": 0.24280442804428043, "percentage": 24.28, "elapsed_time": "19:46:10", "remaining_time": "2 days, 13:39:06"}
330
+ {"current_steps": 3300, "total_steps": 13550, "loss": 3.0469, "learning_rate": 9.385375098703465e-05, "epoch": 0.24354243542435425, "percentage": 24.35, "elapsed_time": "19:49:46", "remaining_time": "2 days, 13:35:30"}
331
+ {"current_steps": 3310, "total_steps": 13550, "loss": 3.068, "learning_rate": 9.379173285409621e-05, "epoch": 0.24428044280442804, "percentage": 24.43, "elapsed_time": "19:53:22", "remaining_time": "2 days, 13:31:54"}
332
+ {"current_steps": 3320, "total_steps": 13550, "loss": 3.1542, "learning_rate": 9.372942409946596e-05, "epoch": 0.24501845018450186, "percentage": 24.5, "elapsed_time": "19:56:59", "remaining_time": "2 days, 13:28:18"}
333
+ {"current_steps": 3330, "total_steps": 13550, "loss": 3.1484, "learning_rate": 9.366682513665293e-05, "epoch": 0.24575645756457565, "percentage": 24.58, "elapsed_time": "20:00:35", "remaining_time": "2 days, 13:24:42"}
334
+ {"current_steps": 3340, "total_steps": 13550, "loss": 3.103, "learning_rate": 9.360393638109201e-05, "epoch": 0.24649446494464944, "percentage": 24.65, "elapsed_time": "20:04:12", "remaining_time": "2 days, 13:21:06"}
335
+ {"current_steps": 3350, "total_steps": 13550, "loss": 3.0701, "learning_rate": 9.354075825014139e-05, "epoch": 0.24723247232472326, "percentage": 24.72, "elapsed_time": "20:07:48", "remaining_time": "2 days, 13:17:30"}
336
+ {"current_steps": 3360, "total_steps": 13550, "loss": 3.1434, "learning_rate": 9.347729116307964e-05, "epoch": 0.24797047970479705, "percentage": 24.8, "elapsed_time": "20:11:24", "remaining_time": "2 days, 13:13:54"}
337
+ {"current_steps": 3370, "total_steps": 13550, "loss": 3.1567, "learning_rate": 9.341353554110297e-05, "epoch": 0.24870848708487084, "percentage": 24.87, "elapsed_time": "20:15:01", "remaining_time": "2 days, 13:10:18"}
338
+ {"current_steps": 3380, "total_steps": 13550, "loss": 3.162, "learning_rate": 9.334949180732245e-05, "epoch": 0.24944649446494466, "percentage": 24.94, "elapsed_time": "20:18:37", "remaining_time": "2 days, 13:06:42"}
339
+ {"current_steps": 3390, "total_steps": 13550, "loss": 3.1532, "learning_rate": 9.328516038676119e-05, "epoch": 0.25018450184501845, "percentage": 25.02, "elapsed_time": "20:22:14", "remaining_time": "2 days, 13:03:06"}
340
+ {"current_steps": 3400, "total_steps": 13550, "loss": 3.1, "learning_rate": 9.322054170635149e-05, "epoch": 0.25092250922509224, "percentage": 25.09, "elapsed_time": "20:25:50", "remaining_time": "2 days, 12:59:29"}
341
+ {"current_steps": 3410, "total_steps": 13550, "loss": 3.0438, "learning_rate": 9.315563619493209e-05, "epoch": 0.25166051660516603, "percentage": 25.17, "elapsed_time": "20:29:27", "remaining_time": "2 days, 12:55:54"}
342
+ {"current_steps": 3420, "total_steps": 13550, "loss": 3.2005, "learning_rate": 9.309044428324522e-05, "epoch": 0.2523985239852399, "percentage": 25.24, "elapsed_time": "20:33:03", "remaining_time": "2 days, 12:52:17"}
343
+ {"current_steps": 3430, "total_steps": 13550, "loss": 3.1035, "learning_rate": 9.302496640393382e-05, "epoch": 0.25313653136531367, "percentage": 25.31, "elapsed_time": "20:36:39", "remaining_time": "2 days, 12:48:41"}
344
+ {"current_steps": 3440, "total_steps": 13550, "loss": 3.1706, "learning_rate": 9.295920299153863e-05, "epoch": 0.25387453874538746, "percentage": 25.39, "elapsed_time": "20:40:15", "remaining_time": "2 days, 12:45:05"}
345
+ {"current_steps": 3450, "total_steps": 13550, "loss": 3.1218, "learning_rate": 9.289315448249531e-05, "epoch": 0.25461254612546125, "percentage": 25.46, "elapsed_time": "20:43:52", "remaining_time": "2 days, 12:41:29"}
346
+ {"current_steps": 3460, "total_steps": 13550, "loss": 3.1231, "learning_rate": 9.282682131513157e-05, "epoch": 0.25535055350553504, "percentage": 25.54, "elapsed_time": "20:47:28", "remaining_time": "2 days, 12:37:52"}
347
+ {"current_steps": 3470, "total_steps": 13550, "loss": 3.1082, "learning_rate": 9.276020392966422e-05, "epoch": 0.25608856088560883, "percentage": 25.61, "elapsed_time": "20:51:05", "remaining_time": "2 days, 12:34:16"}
348
+ {"current_steps": 3480, "total_steps": 13550, "loss": 3.1454, "learning_rate": 9.26933027681963e-05, "epoch": 0.2568265682656827, "percentage": 25.68, "elapsed_time": "20:54:41", "remaining_time": "2 days, 12:30:41"}
349
+ {"current_steps": 3490, "total_steps": 13550, "loss": 3.1334, "learning_rate": 9.262611827471406e-05, "epoch": 0.25756457564575647, "percentage": 25.76, "elapsed_time": "20:58:18", "remaining_time": "2 days, 12:27:05"}
350
+ {"current_steps": 3500, "total_steps": 13550, "loss": 3.0149, "learning_rate": 9.25586508950841e-05, "epoch": 0.25830258302583026, "percentage": 25.83, "elapsed_time": "21:01:55", "remaining_time": "2 days, 12:23:30"}
351
+ {"current_steps": 3510, "total_steps": 13550, "loss": 3.1859, "learning_rate": 9.249090107705044e-05, "epoch": 0.25904059040590405, "percentage": 25.9, "elapsed_time": "21:05:31", "remaining_time": "2 days, 12:19:53"}
352
+ {"current_steps": 3520, "total_steps": 13550, "loss": 3.171, "learning_rate": 9.242286927023136e-05, "epoch": 0.25977859778597784, "percentage": 25.98, "elapsed_time": "21:09:07", "remaining_time": "2 days, 12:16:17"}
353
+ {"current_steps": 3530, "total_steps": 13550, "loss": 3.1198, "learning_rate": 9.235455592611665e-05, "epoch": 0.2605166051660517, "percentage": 26.05, "elapsed_time": "21:12:44", "remaining_time": "2 days, 12:12:41"}
354
+ {"current_steps": 3540, "total_steps": 13550, "loss": 3.0841, "learning_rate": 9.22859614980645e-05, "epoch": 0.2612546125461255, "percentage": 26.13, "elapsed_time": "21:16:20", "remaining_time": "2 days, 12:09:05"}
355
+ {"current_steps": 3550, "total_steps": 13550, "loss": 3.13, "learning_rate": 9.221708644129843e-05, "epoch": 0.26199261992619927, "percentage": 26.2, "elapsed_time": "21:19:57", "remaining_time": "2 days, 12:05:29"}
356
+ {"current_steps": 3560, "total_steps": 13550, "loss": 3.0718, "learning_rate": 9.214793121290442e-05, "epoch": 0.26273062730627306, "percentage": 26.27, "elapsed_time": "21:23:33", "remaining_time": "2 days, 12:01:54"}
357
+ {"current_steps": 3570, "total_steps": 13550, "loss": 3.1159, "learning_rate": 9.207849627182772e-05, "epoch": 0.26346863468634685, "percentage": 26.35, "elapsed_time": "21:27:10", "remaining_time": "2 days, 11:58:19"}
358
+ {"current_steps": 3580, "total_steps": 13550, "loss": 3.1932, "learning_rate": 9.200878207886993e-05, "epoch": 0.26420664206642064, "percentage": 26.42, "elapsed_time": "21:30:47", "remaining_time": "2 days, 11:54:43"}
359
+ {"current_steps": 3590, "total_steps": 13550, "loss": 3.0973, "learning_rate": 9.19387890966859e-05, "epoch": 0.2649446494464945, "percentage": 26.49, "elapsed_time": "21:34:23", "remaining_time": "2 days, 11:51:06"}
360
+ {"current_steps": 3600, "total_steps": 13550, "loss": 3.1466, "learning_rate": 9.186851778978062e-05, "epoch": 0.2656826568265683, "percentage": 26.57, "elapsed_time": "21:37:59", "remaining_time": "2 days, 11:47:31"}
361
+ {"current_steps": 3610, "total_steps": 13550, "loss": 3.0424, "learning_rate": 9.179796862450618e-05, "epoch": 0.26642066420664207, "percentage": 26.64, "elapsed_time": "21:41:36", "remaining_time": "2 days, 11:43:54"}
362
+ {"current_steps": 3620, "total_steps": 13550, "loss": 3.0505, "learning_rate": 9.172714206905866e-05, "epoch": 0.26715867158671586, "percentage": 26.72, "elapsed_time": "21:45:12", "remaining_time": "2 days, 11:40:18"}
363
+ {"current_steps": 3630, "total_steps": 13550, "loss": 3.1561, "learning_rate": 9.165603859347502e-05, "epoch": 0.26789667896678965, "percentage": 26.79, "elapsed_time": "21:48:49", "remaining_time": "2 days, 11:36:43"}
364
+ {"current_steps": 3640, "total_steps": 13550, "loss": 3.0778, "learning_rate": 9.158465866963002e-05, "epoch": 0.2686346863468635, "percentage": 26.86, "elapsed_time": "21:52:25", "remaining_time": "2 days, 11:33:06"}
365
+ {"current_steps": 3650, "total_steps": 13550, "loss": 3.0517, "learning_rate": 9.151300277123301e-05, "epoch": 0.2693726937269373, "percentage": 26.94, "elapsed_time": "21:56:01", "remaining_time": "2 days, 11:29:30"}
366
+ {"current_steps": 3660, "total_steps": 13550, "loss": 2.979, "learning_rate": 9.144107137382484e-05, "epoch": 0.2701107011070111, "percentage": 27.01, "elapsed_time": "21:59:38", "remaining_time": "2 days, 11:25:53"}
367
+ {"current_steps": 3670, "total_steps": 13550, "loss": 3.0661, "learning_rate": 9.136886495477475e-05, "epoch": 0.27084870848708487, "percentage": 27.08, "elapsed_time": "22:03:14", "remaining_time": "2 days, 11:22:18"}
368
+ {"current_steps": 3680, "total_steps": 13550, "loss": 3.0624, "learning_rate": 9.129638399327706e-05, "epoch": 0.27158671586715866, "percentage": 27.16, "elapsed_time": "22:06:51", "remaining_time": "2 days, 11:18:43"}
369
+ {"current_steps": 3690, "total_steps": 13550, "loss": 3.0344, "learning_rate": 9.122362897034817e-05, "epoch": 0.27232472324723245, "percentage": 27.23, "elapsed_time": "22:10:27", "remaining_time": "2 days, 11:15:06"}
370
+ {"current_steps": 3700, "total_steps": 13550, "loss": 3.0374, "learning_rate": 9.115060036882318e-05, "epoch": 0.2730627306273063, "percentage": 27.31, "elapsed_time": "22:14:04", "remaining_time": "2 days, 11:11:30"}
371
+ {"current_steps": 3710, "total_steps": 13550, "loss": 3.0823, "learning_rate": 9.107729867335288e-05, "epoch": 0.2738007380073801, "percentage": 27.38, "elapsed_time": "22:17:40", "remaining_time": "2 days, 11:07:53"}
372
+ {"current_steps": 3720, "total_steps": 13550, "loss": 3.0558, "learning_rate": 9.100372437040034e-05, "epoch": 0.2745387453874539, "percentage": 27.45, "elapsed_time": "22:21:16", "remaining_time": "2 days, 11:04:17"}
373
+ {"current_steps": 3730, "total_steps": 13550, "loss": 3.0836, "learning_rate": 9.092987794823786e-05, "epoch": 0.27527675276752767, "percentage": 27.53, "elapsed_time": "22:24:53", "remaining_time": "2 days, 11:00:42"}
374
+ {"current_steps": 3740, "total_steps": 13550, "loss": 3.1079, "learning_rate": 9.085575989694357e-05, "epoch": 0.27601476014760146, "percentage": 27.6, "elapsed_time": "22:28:29", "remaining_time": "2 days, 10:57:05"}
375
+ {"current_steps": 3750, "total_steps": 13550, "loss": 3.0775, "learning_rate": 9.078137070839832e-05, "epoch": 0.2767527675276753, "percentage": 27.68, "elapsed_time": "22:32:05", "remaining_time": "2 days, 10:53:29"}
376
+ {"current_steps": 3760, "total_steps": 13550, "loss": 3.0756, "learning_rate": 9.070671087628229e-05, "epoch": 0.2774907749077491, "percentage": 27.75, "elapsed_time": "22:35:42", "remaining_time": "2 days, 10:49:53"}
377
+ {"current_steps": 3770, "total_steps": 13550, "loss": 3.0615, "learning_rate": 9.063178089607183e-05, "epoch": 0.2782287822878229, "percentage": 27.82, "elapsed_time": "22:39:19", "remaining_time": "2 days, 10:46:17"}
378
+ {"current_steps": 3780, "total_steps": 13550, "loss": 3.0594, "learning_rate": 9.055658126503605e-05, "epoch": 0.2789667896678967, "percentage": 27.9, "elapsed_time": "22:42:55", "remaining_time": "2 days, 10:42:42"}
379
+ {"current_steps": 3790, "total_steps": 13550, "loss": 3.097, "learning_rate": 9.048111248223368e-05, "epoch": 0.27970479704797047, "percentage": 27.97, "elapsed_time": "22:46:31", "remaining_time": "2 days, 10:39:05"}
380
+ {"current_steps": 3800, "total_steps": 13550, "loss": 3.0303, "learning_rate": 9.040537504850954e-05, "epoch": 0.28044280442804426, "percentage": 28.04, "elapsed_time": "22:50:07", "remaining_time": "2 days, 10:35:28"}
381
+ {"current_steps": 3810, "total_steps": 13550, "loss": 3.063, "learning_rate": 9.032936946649144e-05, "epoch": 0.2811808118081181, "percentage": 28.12, "elapsed_time": "22:53:44", "remaining_time": "2 days, 10:31:52"}
382
+ {"current_steps": 3820, "total_steps": 13550, "loss": 3.0853, "learning_rate": 9.02530962405867e-05, "epoch": 0.2819188191881919, "percentage": 28.19, "elapsed_time": "22:57:21", "remaining_time": "2 days, 10:28:16"}
383
+ {"current_steps": 3830, "total_steps": 13550, "loss": 3.1374, "learning_rate": 9.017655587697885e-05, "epoch": 0.2826568265682657, "percentage": 28.27, "elapsed_time": "23:00:57", "remaining_time": "2 days, 10:24:40"}
384
+ {"current_steps": 3840, "total_steps": 13550, "loss": 3.064, "learning_rate": 9.009974888362424e-05, "epoch": 0.2833948339483395, "percentage": 28.34, "elapsed_time": "23:04:33", "remaining_time": "2 days, 10:21:03"}
385
+ {"current_steps": 3850, "total_steps": 13550, "loss": 3.0662, "learning_rate": 9.002267577024876e-05, "epoch": 0.28413284132841327, "percentage": 28.41, "elapsed_time": "23:08:09", "remaining_time": "2 days, 10:17:27"}
386
+ {"current_steps": 3860, "total_steps": 13550, "loss": 3.0999, "learning_rate": 8.994533704834435e-05, "epoch": 0.2848708487084871, "percentage": 28.49, "elapsed_time": "23:11:46", "remaining_time": "2 days, 10:13:51"}
387
+ {"current_steps": 3870, "total_steps": 13550, "loss": 3.0496, "learning_rate": 8.986773323116563e-05, "epoch": 0.2856088560885609, "percentage": 28.56, "elapsed_time": "23:15:22", "remaining_time": "2 days, 10:10:14"}
388
+ {"current_steps": 3880, "total_steps": 13550, "loss": 3.0549, "learning_rate": 8.978986483372655e-05, "epoch": 0.2863468634686347, "percentage": 28.63, "elapsed_time": "23:18:59", "remaining_time": "2 days, 10:06:38"}
389
+ {"current_steps": 3890, "total_steps": 13550, "loss": 3.085, "learning_rate": 8.971173237279692e-05, "epoch": 0.2870848708487085, "percentage": 28.71, "elapsed_time": "23:22:35", "remaining_time": "2 days, 10:03:01"}
390
+ {"current_steps": 3900, "total_steps": 13550, "loss": 3.0659, "learning_rate": 8.963333636689898e-05, "epoch": 0.2878228782287823, "percentage": 28.78, "elapsed_time": "23:26:11", "remaining_time": "2 days, 9:59:25"}
391
+ {"current_steps": 3910, "total_steps": 13550, "loss": 3.0963, "learning_rate": 8.9554677336304e-05, "epoch": 0.28856088560885607, "percentage": 28.86, "elapsed_time": "23:29:47", "remaining_time": "2 days, 9:55:49"}
392
+ {"current_steps": 3920, "total_steps": 13550, "loss": 3.0503, "learning_rate": 8.947575580302878e-05, "epoch": 0.2892988929889299, "percentage": 28.93, "elapsed_time": "23:33:24", "remaining_time": "2 days, 9:52:12"}
393
+ {"current_steps": 3930, "total_steps": 13550, "loss": 3.1322, "learning_rate": 8.939657229083222e-05, "epoch": 0.2900369003690037, "percentage": 29.0, "elapsed_time": "23:37:00", "remaining_time": "2 days, 9:48:36"}
394
+ {"current_steps": 3940, "total_steps": 13550, "loss": 3.0947, "learning_rate": 8.931712732521183e-05, "epoch": 0.2907749077490775, "percentage": 29.08, "elapsed_time": "23:40:37", "remaining_time": "2 days, 9:45:01"}
395
+ {"current_steps": 3950, "total_steps": 13550, "loss": 3.0379, "learning_rate": 8.92374214334002e-05, "epoch": 0.2915129151291513, "percentage": 29.15, "elapsed_time": "23:44:13", "remaining_time": "2 days, 9:41:25"}
396
+ {"current_steps": 3960, "total_steps": 13550, "loss": 3.0636, "learning_rate": 8.915745514436161e-05, "epoch": 0.2922509225092251, "percentage": 29.23, "elapsed_time": "23:47:50", "remaining_time": "2 days, 9:37:48"}
397
+ {"current_steps": 3970, "total_steps": 13550, "loss": 3.0737, "learning_rate": 8.907722898878844e-05, "epoch": 0.29298892988929887, "percentage": 29.3, "elapsed_time": "23:51:26", "remaining_time": "2 days, 9:34:12"}
398
+ {"current_steps": 3980, "total_steps": 13550, "loss": 3.0743, "learning_rate": 8.899674349909759e-05, "epoch": 0.2937269372693727, "percentage": 29.37, "elapsed_time": "23:55:02", "remaining_time": "2 days, 9:30:36"}
399
+ {"current_steps": 3990, "total_steps": 13550, "loss": 3.0711, "learning_rate": 8.891599920942713e-05, "epoch": 0.2944649446494465, "percentage": 29.45, "elapsed_time": "23:58:38", "remaining_time": "2 days, 9:26:59"}
400
+ {"current_steps": 4000, "total_steps": 13550, "loss": 3.0302, "learning_rate": 8.883499665563253e-05, "epoch": 0.2952029520295203, "percentage": 29.52, "elapsed_time": "1 day, 0:02:15", "remaining_time": "2 days, 9:23:23"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a753d14e4ced7fa659beaf1a59013b7f3855c465d5f64bb8ce332727deec5ff1
3
+ size 6520