Hugging Face's logo

VoCuc
/
AMiD

Model card Files
xet
 Community
VoCuc commited on
Commit
e80d90c
·
verified ·
1 Parent(s): 9311a14

Upload folder using huggingface_hub

Browse files
Files changed (26) hide show
  1. .gitattributes +2 -0
  2. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/added_tokens.json +24 -0
  3. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/chat_template.jinja +54 -0
  4. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/config.json +56 -0
  5. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/generation_config.json +6 -0
  6. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/merges.txt +0 -0
  7. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/pytorch_model.bin +3 -0
  8. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/special_tokens_map.json +25 -0
  9. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer.json +3 -0
  10. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer_config.json +207 -0
  11. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/vocab.json +0 -0
  12. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/added_tokens.json +24 -0
  13. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/chat_template.jinja +54 -0
  14. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/config.json +56 -0
  15. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/generation_config.json +6 -0
  16. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/merges.txt +0 -0
  17. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/pytorch_model.bin +3 -0
  18. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/special_tokens_map.json +25 -0
  19. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer.json +3 -0
  20. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer_config.json +207 -0
  21. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/vocab.json +0 -0
  22. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/eval/1/answers.jsonl +0 -0
  23. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/eval/2/answers.jsonl +0 -0
  24. qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/log.txt +351 -0
  25. qwen2.5-1.5B-Instruct#amid/ab_pr_0.5_0.5_4_1e-4/args.json +1 -0
  26. qwen2.5-1.5B-Instruct#amid/ab_pr_0.5_0.5_4_1e-4/log.txt +3 -0
.gitattributes CHANGED
@@ -37,3 +37,5 @@ llama3.2-3B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/2492/tokenizer.json filter=lfs d
37
  llama3.2-3B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  llama3.2-3B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  qwen2.5-0.5B\#amid/ab_pr_0.5_0.5_8_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
37
  llama3.2-3B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  llama3.2-3B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  qwen2.5-0.5B\#amid/ab_pr_0.5_0.5_8_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ qwen2.5-0.5B\#amid/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ qwen2.5-0.5B\#amid/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "is_model_parallel": false,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention"
39
+ ],
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 24,
42
+ "model_type": "qwen2",
43
+ "num_attention_heads": 14,
44
+ "num_hidden_layers": 24,
45
+ "num_key_value_heads": 2,
46
+ "rms_norm_eps": 1e-06,
47
+ "rope_scaling": null,
48
+ "rope_theta": 1000000.0,
49
+ "sliding_window": null,
50
+ "tie_word_embeddings": true,
51
+ "transformers_version": "4.57.3",
52
+ "use_cache": true,
53
+ "use_mrope": false,
54
+ "use_sliding_window": false,
55
+ "vocab_size": 151936
56
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.57.3"
6
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71070a2f09c77d61248d763a90eb5c47d2058acfac1f6a0b0ebe448b6086934b
3
+ size 988104917
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/4984/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "is_model_parallel": false,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention"
39
+ ],
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 24,
42
+ "model_type": "qwen2",
43
+ "num_attention_heads": 14,
44
+ "num_hidden_layers": 24,
45
+ "num_key_value_heads": 2,
46
+ "rms_norm_eps": 1e-06,
47
+ "rope_scaling": null,
48
+ "rope_theta": 1000000.0,
49
+ "sliding_window": null,
50
+ "tie_word_embeddings": true,
51
+ "transformers_version": "4.57.3",
52
+ "use_cache": true,
53
+ "use_mrope": false,
54
+ "use_sliding_window": false,
55
+ "vocab_size": 151936
56
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.57.3"
6
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74a401c2304a1963fd9dd51bfcd119209aad41b440c2a645cbe449816337de1
3
+ size 988104917
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/7476/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/eval/1/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/eval/2/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-0.5B#amid/ab_pr_0.5_0.5_8_1e-4/log.txt CHANGED
@@ -404,3 +404,354 @@ train | epoch 1 | Iter: 3950/ 7476 | global iter: 3950/ 7476 | loss: 0.1
404
  train | epoch 1 | Iter: 3960/ 7476 | global iter: 3960/ 7476 | loss: 0.1117 | ds_loss: 0.1117 | lr: 4.5397e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.111
405
  train | epoch 1 | Iter: 3970/ 7476 | global iter: 3970/ 7476 | loss: 0.1150 | ds_loss: 0.1150 | lr: 4.5188e-05 | scale: 1.0000 | micro time: 0.340 | step time: 5.782
406
  train | epoch 1 | Iter: 3980/ 7476 | global iter: 3980/ 7476 | loss: 0.1105 | ds_loss: 0.1105 | lr: 4.4979e-05 | scale: 1.0000 | micro time: 0.345 | step time: 1.714
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
404
  train | epoch 1 | Iter: 3960/ 7476 | global iter: 3960/ 7476 | loss: 0.1117 | ds_loss: 0.1117 | lr: 4.5397e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.111
405
  train | epoch 1 | Iter: 3970/ 7476 | global iter: 3970/ 7476 | loss: 0.1150 | ds_loss: 0.1150 | lr: 4.5188e-05 | scale: 1.0000 | micro time: 0.340 | step time: 5.782
406
  train | epoch 1 | Iter: 3980/ 7476 | global iter: 3980/ 7476 | loss: 0.1105 | ds_loss: 0.1105 | lr: 4.4979e-05 | scale: 1.0000 | micro time: 0.345 | step time: 1.714
407
+ train | epoch 1 | Iter: 3990/ 7476 | global iter: 3990/ 7476 | loss: 0.1154 | ds_loss: 0.1154 | lr: 4.4770e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.074
408
+ train | epoch 1 | Iter: 4000/ 7476 | global iter: 4000/ 7476 | loss: 0.1130 | ds_loss: 0.1130 | lr: 4.4562e-05 | scale: 1.0000 | micro time: 13.792 | step time: 4.422
409
+ train | epoch 1 | Iter: 4010/ 7476 | global iter: 4010/ 7476 | loss: 0.1145 | ds_loss: 0.1145 | lr: 4.4353e-05 | scale: 1.0000 | micro time: 13.896 | step time: 4.507
410
+ train | epoch 1 | Iter: 4020/ 7476 | global iter: 4020/ 7476 | loss: 0.1152 | ds_loss: 0.1152 | lr: 4.4145e-05 | scale: 1.0000 | micro time: 14.269 | step time: 3.107
411
+ train | epoch 1 | Iter: 4030/ 7476 | global iter: 4030/ 7476 | loss: 0.1132 | ds_loss: 0.1132 | lr: 4.3936e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.747
412
+ train | epoch 1 | Iter: 4040/ 7476 | global iter: 4040/ 7476 | loss: 0.1042 | ds_loss: 0.1042 | lr: 4.3728e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
413
+ train | epoch 1 | Iter: 4050/ 7476 | global iter: 4050/ 7476 | loss: 0.1132 | ds_loss: 0.1132 | lr: 4.3520e-05 | scale: 1.0000 | micro time: 13.916 | step time: 4.463
414
+ train | epoch 1 | Iter: 4060/ 7476 | global iter: 4060/ 7476 | loss: 0.1151 | ds_loss: 0.1151 | lr: 4.3312e-05 | scale: 1.0000 | micro time: 14.087 | step time: 4.449
415
+ train | epoch 1 | Iter: 4070/ 7476 | global iter: 4070/ 7476 | loss: 0.1162 | ds_loss: 0.1162 | lr: 4.3104e-05 | scale: 1.0000 | micro time: 13.845 | step time: 5.791
416
+ train | epoch 1 | Iter: 4080/ 7476 | global iter: 4080/ 7476 | loss: 0.1069 | ds_loss: 0.1069 | lr: 4.2896e-05 | scale: 1.0000 | micro time: 0.338 | step time: 3.057
417
+ train | epoch 1 | Iter: 4090/ 7476 | global iter: 4090/ 7476 | loss: 0.1084 | ds_loss: 0.1084 | lr: 4.2688e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.508
418
+ train | epoch 1 | Iter: 4100/ 7476 | global iter: 4100/ 7476 | loss: 0.1053 | ds_loss: 0.1053 | lr: 4.2481e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
419
+ train | epoch 1 | Iter: 4110/ 7476 | global iter: 4110/ 7476 | loss: 0.1115 | ds_loss: 0.1115 | lr: 4.2273e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.045
420
+ train | epoch 1 | Iter: 4120/ 7476 | global iter: 4120/ 7476 | loss: 0.1097 | ds_loss: 0.1097 | lr: 4.2066e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
421
+ train | epoch 1 | Iter: 4130/ 7476 | global iter: 4130/ 7476 | loss: 0.1151 | ds_loss: 0.1151 | lr: 4.1859e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.693
422
+ train | epoch 1 | Iter: 4140/ 7476 | global iter: 4140/ 7476 | loss: 0.1189 | ds_loss: 0.1189 | lr: 4.1652e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.097
423
+ train | epoch 1 | Iter: 4150/ 7476 | global iter: 4150/ 7476 | loss: 0.1025 | ds_loss: 0.1025 | lr: 4.1445e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
424
+ train | epoch 1 | Iter: 4160/ 7476 | global iter: 4160/ 7476 | loss: 0.1150 | ds_loss: 0.1150 | lr: 4.1238e-05 | scale: 1.0000 | micro time: 0.341 | step time: 5.866
425
+ train | epoch 1 | Iter: 4170/ 7476 | global iter: 4170/ 7476 | loss: 0.1128 | ds_loss: 0.1128 | lr: 4.1032e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.101
426
+ train | epoch 1 | Iter: 4180/ 7476 | global iter: 4180/ 7476 | loss: 0.1077 | ds_loss: 0.1077 | lr: 4.0826e-05 | scale: 1.0000 | micro time: 0.346 | step time: 0.342
427
+ train | epoch 1 | Iter: 4190/ 7476 | global iter: 4190/ 7476 | loss: 0.1122 | ds_loss: 0.1122 | lr: 4.0619e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
428
+ train | epoch 1 | Iter: 4200/ 7476 | global iter: 4200/ 7476 | loss: 0.1086 | ds_loss: 0.1086 | lr: 4.0413e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.737
429
+ train | epoch 1 | Iter: 4210/ 7476 | global iter: 4210/ 7476 | loss: 0.1120 | ds_loss: 0.1120 | lr: 4.0207e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.068
430
+ train | epoch 1 | Iter: 4220/ 7476 | global iter: 4220/ 7476 | loss: 0.1083 | ds_loss: 0.1083 | lr: 4.0002e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.752
431
+ train | epoch 1 | Iter: 4230/ 7476 | global iter: 4230/ 7476 | loss: 0.1099 | ds_loss: 0.1099 | lr: 3.9796e-05 | scale: 1.0000 | micro time: 0.342 | step time: 3.078
432
+ train | epoch 1 | Iter: 4240/ 7476 | global iter: 4240/ 7476 | loss: 0.1223 | ds_loss: 0.1223 | lr: 3.9591e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.721
433
+ train | epoch 1 | Iter: 4250/ 7476 | global iter: 4250/ 7476 | loss: 0.1174 | ds_loss: 0.1174 | lr: 3.9386e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.690
434
+ train | epoch 1 | Iter: 4260/ 7476 | global iter: 4260/ 7476 | loss: 0.1185 | ds_loss: 0.1185 | lr: 3.9181e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.075
435
+ train | epoch 1 | Iter: 4270/ 7476 | global iter: 4270/ 7476 | loss: 0.1095 | ds_loss: 0.1095 | lr: 3.8976e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
436
+ train | epoch 1 | Iter: 4280/ 7476 | global iter: 4280/ 7476 | loss: 0.1114 | ds_loss: 0.1114 | lr: 3.8771e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.701
437
+ train | epoch 1 | Iter: 4290/ 7476 | global iter: 4290/ 7476 | loss: 0.1083 | ds_loss: 0.1083 | lr: 3.8567e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.691
438
+ train | epoch 1 | Iter: 4300/ 7476 | global iter: 4300/ 7476 | loss: 0.1086 | ds_loss: 0.1086 | lr: 3.8363e-05 | scale: 1.0000 | micro time: 0.339 | step time: 5.796
439
+ train | epoch 1 | Iter: 4310/ 7476 | global iter: 4310/ 7476 | loss: 0.1106 | ds_loss: 0.1106 | lr: 3.8159e-05 | scale: 1.0000 | micro time: 13.975 | step time: 4.448
440
+ train | epoch 1 | Iter: 4320/ 7476 | global iter: 4320/ 7476 | loss: 0.1140 | ds_loss: 0.1140 | lr: 3.7955e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.478
441
+ train | epoch 1 | Iter: 4330/ 7476 | global iter: 4330/ 7476 | loss: 0.1178 | ds_loss: 0.1178 | lr: 3.7752e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.701
442
+ train | epoch 1 | Iter: 4340/ 7476 | global iter: 4340/ 7476 | loss: 0.1101 | ds_loss: 0.1101 | lr: 3.7548e-05 | scale: 1.0000 | micro time: 0.342 | step time: 5.864
443
+ train | epoch 1 | Iter: 4350/ 7476 | global iter: 4350/ 7476 | loss: 0.1124 | ds_loss: 0.1124 | lr: 3.7345e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.703
444
+ train | epoch 1 | Iter: 4360/ 7476 | global iter: 4360/ 7476 | loss: 0.1075 | ds_loss: 0.1075 | lr: 3.7142e-05 | scale: 1.0000 | micro time: 0.341 | step time: 3.151
445
+ train | epoch 1 | Iter: 4370/ 7476 | global iter: 4370/ 7476 | loss: 0.1132 | ds_loss: 0.1132 | lr: 3.6940e-05 | scale: 1.0000 | micro time: 0.345 | step time: 4.458
446
+ train | epoch 1 | Iter: 4380/ 7476 | global iter: 4380/ 7476 | loss: 0.1157 | ds_loss: 0.1157 | lr: 3.6737e-05 | scale: 1.0000 | micro time: 14.107 | step time: 4.447
447
+ train | epoch 1 | Iter: 4390/ 7476 | global iter: 4390/ 7476 | loss: 0.1094 | ds_loss: 0.1094 | lr: 3.6535e-05 | scale: 1.0000 | micro time: 0.344 | step time: 5.850
448
+ train | epoch 1 | Iter: 4400/ 7476 | global iter: 4400/ 7476 | loss: 0.1082 | ds_loss: 0.1082 | lr: 3.6333e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
449
+ train | epoch 1 | Iter: 4410/ 7476 | global iter: 4410/ 7476 | loss: 0.1143 | ds_loss: 0.1143 | lr: 3.6131e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.456
450
+ train | epoch 1 | Iter: 4420/ 7476 | global iter: 4420/ 7476 | loss: 0.1073 | ds_loss: 0.1073 | lr: 3.5930e-05 | scale: 1.0000 | micro time: 0.338 | step time: 1.698
451
+ train | epoch 1 | Iter: 4430/ 7476 | global iter: 4430/ 7476 | loss: 0.1087 | ds_loss: 0.1087 | lr: 3.5729e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.691
452
+ train | epoch 1 | Iter: 4440/ 7476 | global iter: 4440/ 7476 | loss: 0.1102 | ds_loss: 0.1102 | lr: 3.5528e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.721
453
+ train | epoch 1 | Iter: 4450/ 7476 | global iter: 4450/ 7476 | loss: 0.1122 | ds_loss: 0.1122 | lr: 3.5327e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.724
454
+ train | epoch 1 | Iter: 4460/ 7476 | global iter: 4460/ 7476 | loss: 0.1122 | ds_loss: 0.1122 | lr: 3.5127e-05 | scale: 1.0000 | micro time: 14.385 | step time: 3.137
455
+ train | epoch 1 | Iter: 4470/ 7476 | global iter: 4470/ 7476 | loss: 0.1150 | ds_loss: 0.1150 | lr: 3.4926e-05 | scale: 1.0000 | micro time: 0.341 | step time: 0.340
456
+ train | epoch 1 | Iter: 4480/ 7476 | global iter: 4480/ 7476 | loss: 0.1063 | ds_loss: 0.1063 | lr: 3.4726e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.056
457
+ train | epoch 1 | Iter: 4490/ 7476 | global iter: 4490/ 7476 | loss: 0.1035 | ds_loss: 0.1035 | lr: 3.4527e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.038
458
+ train | epoch 1 | Iter: 4500/ 7476 | global iter: 4500/ 7476 | loss: 0.1221 | ds_loss: 0.1221 | lr: 3.4327e-05 | scale: 1.0000 | micro time: 0.338 | step time: 3.101
459
+ train | epoch 1 | Iter: 4510/ 7476 | global iter: 4510/ 7476 | loss: 0.1134 | ds_loss: 0.1134 | lr: 3.4128e-05 | scale: 1.0000 | micro time: 0.338 | step time: 0.339
460
+ train | epoch 1 | Iter: 4520/ 7476 | global iter: 4520/ 7476 | loss: 0.1165 | ds_loss: 0.1165 | lr: 3.3930e-05 | scale: 1.0000 | micro time: 14.295 | step time: 1.735
461
+ train | epoch 1 | Iter: 4530/ 7476 | global iter: 4530/ 7476 | loss: 0.1131 | ds_loss: 0.1131 | lr: 3.3731e-05 | scale: 1.0000 | micro time: 0.342 | step time: 4.418
462
+ train | epoch 1 | Iter: 4540/ 7476 | global iter: 4540/ 7476 | loss: 0.1099 | ds_loss: 0.1099 | lr: 3.3533e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.682
463
+ train | epoch 1 | Iter: 4550/ 7476 | global iter: 4550/ 7476 | loss: 0.1069 | ds_loss: 0.1069 | lr: 3.3335e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.089
464
+ train | epoch 1 | Iter: 4560/ 7476 | global iter: 4560/ 7476 | loss: 0.1124 | ds_loss: 0.1124 | lr: 3.3137e-05 | scale: 1.0000 | micro time: 14.360 | step time: 1.742
465
+ train | epoch 1 | Iter: 4570/ 7476 | global iter: 4570/ 7476 | loss: 0.1096 | ds_loss: 0.1096 | lr: 3.2940e-05 | scale: 1.0000 | micro time: 0.344 | step time: 4.400
466
+ train | epoch 1 | Iter: 4580/ 7476 | global iter: 4580/ 7476 | loss: 0.1070 | ds_loss: 0.1070 | lr: 3.2743e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.680
467
+ train | epoch 1 | Iter: 4590/ 7476 | global iter: 4590/ 7476 | loss: 0.1088 | ds_loss: 0.1088 | lr: 3.2546e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.104
468
+ train | epoch 1 | Iter: 4600/ 7476 | global iter: 4600/ 7476 | loss: 0.1010 | ds_loss: 0.1010 | lr: 3.2350e-05 | scale: 1.0000 | micro time: 13.690 | step time: 1.676
469
+ train | epoch 1 | Iter: 4610/ 7476 | global iter: 4610/ 7476 | loss: 0.1052 | ds_loss: 0.1052 | lr: 3.2153e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
470
+ train | epoch 1 | Iter: 4620/ 7476 | global iter: 4620/ 7476 | loss: 0.1024 | ds_loss: 0.1024 | lr: 3.1958e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.076
471
+ train | epoch 1 | Iter: 4630/ 7476 | global iter: 4630/ 7476 | loss: 0.1059 | ds_loss: 0.1059 | lr: 3.1762e-05 | scale: 1.0000 | micro time: 14.611 | step time: 4.507
472
+ train | epoch 1 | Iter: 4640/ 7476 | global iter: 4640/ 7476 | loss: 0.1072 | ds_loss: 0.1072 | lr: 3.1567e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
473
+ train | epoch 1 | Iter: 4650/ 7476 | global iter: 4650/ 7476 | loss: 0.1006 | ds_loss: 0.1006 | lr: 3.1372e-05 | scale: 1.0000 | micro time: 0.343 | step time: 1.713
474
+ train | epoch 1 | Iter: 4660/ 7476 | global iter: 4660/ 7476 | loss: 0.1201 | ds_loss: 0.1201 | lr: 3.1178e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.083
475
+ train | epoch 1 | Iter: 4670/ 7476 | global iter: 4670/ 7476 | loss: 0.1095 | ds_loss: 0.1095 | lr: 3.0983e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.411
476
+ train | epoch 1 | Iter: 4680/ 7476 | global iter: 4680/ 7476 | loss: 0.1069 | ds_loss: 0.1069 | lr: 3.0790e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.726
477
+ train | epoch 1 | Iter: 4690/ 7476 | global iter: 4690/ 7476 | loss: 0.1137 | ds_loss: 0.1137 | lr: 3.0596e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.692
478
+ train | epoch 1 | Iter: 4700/ 7476 | global iter: 4700/ 7476 | loss: 0.1095 | ds_loss: 0.1095 | lr: 3.0403e-05 | scale: 1.0000 | micro time: 13.849 | step time: 3.037
479
+ train | epoch 1 | Iter: 4710/ 7476 | global iter: 4710/ 7476 | loss: 0.1048 | ds_loss: 0.1048 | lr: 3.0210e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
480
+ train | epoch 1 | Iter: 4720/ 7476 | global iter: 4720/ 7476 | loss: 0.1033 | ds_loss: 0.1033 | lr: 3.0018e-05 | scale: 1.0000 | micro time: 14.343 | step time: 1.740
481
+ train | epoch 1 | Iter: 4730/ 7476 | global iter: 4730/ 7476 | loss: 0.0984 | ds_loss: 0.0984 | lr: 2.9826e-05 | scale: 1.0000 | micro time: 0.338 | step time: 0.339
482
+ train | epoch 1 | Iter: 4740/ 7476 | global iter: 4740/ 7476 | loss: 0.1015 | ds_loss: 0.1015 | lr: 2.9634e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.706
483
+ train | epoch 1 | Iter: 4750/ 7476 | global iter: 4750/ 7476 | loss: 0.1129 | ds_loss: 0.1129 | lr: 2.9442e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.102
484
+ train | epoch 1 | Iter: 4760/ 7476 | global iter: 4760/ 7476 | loss: 0.1030 | ds_loss: 0.1030 | lr: 2.9251e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.739
485
+ train | epoch 1 | Iter: 4770/ 7476 | global iter: 4770/ 7476 | loss: 0.1160 | ds_loss: 0.1160 | lr: 2.9061e-05 | scale: 1.0000 | micro time: 13.823 | step time: 3.086
486
+ train | epoch 1 | Iter: 4780/ 7476 | global iter: 4780/ 7476 | loss: 0.1030 | ds_loss: 0.1030 | lr: 2.8870e-05 | scale: 1.0000 | micro time: 14.400 | step time: 3.141
487
+ train | epoch 1 | Iter: 4790/ 7476 | global iter: 4790/ 7476 | loss: 0.1094 | ds_loss: 0.1094 | lr: 2.8681e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.028
488
+ train | epoch 1 | Iter: 4800/ 7476 | global iter: 4800/ 7476 | loss: 0.0999 | ds_loss: 0.0999 | lr: 2.8491e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.681
489
+ train | epoch 1 | Iter: 4810/ 7476 | global iter: 4810/ 7476 | loss: 0.1029 | ds_loss: 0.1029 | lr: 2.8302e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.682
490
+ train | epoch 1 | Iter: 4820/ 7476 | global iter: 4820/ 7476 | loss: 0.1078 | ds_loss: 0.1078 | lr: 2.8113e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.696
491
+ train | epoch 1 | Iter: 4830/ 7476 | global iter: 4830/ 7476 | loss: 0.1069 | ds_loss: 0.1069 | lr: 2.7925e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
492
+ train | epoch 1 | Iter: 4840/ 7476 | global iter: 4840/ 7476 | loss: 0.0989 | ds_loss: 0.0989 | lr: 2.7737e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
493
+ train | epoch 1 | Iter: 4850/ 7476 | global iter: 4850/ 7476 | loss: 0.1078 | ds_loss: 0.1078 | lr: 2.7549e-05 | scale: 1.0000 | micro time: 0.342 | step time: 4.420
494
+ train | epoch 1 | Iter: 4860/ 7476 | global iter: 4860/ 7476 | loss: 0.0997 | ds_loss: 0.0997 | lr: 2.7362e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
495
+ train | epoch 1 | Iter: 4870/ 7476 | global iter: 4870/ 7476 | loss: 0.1053 | ds_loss: 0.1053 | lr: 2.7175e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
496
+ train | epoch 1 | Iter: 4880/ 7476 | global iter: 4880/ 7476 | loss: 0.1190 | ds_loss: 0.1190 | lr: 2.6989e-05 | scale: 1.0000 | micro time: 14.477 | step time: 8.569
497
+ train | epoch 1 | Iter: 4890/ 7476 | global iter: 4890/ 7476 | loss: 0.1109 | ds_loss: 0.1109 | lr: 2.6803e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
498
+ train | epoch 1 | Iter: 4900/ 7476 | global iter: 4900/ 7476 | loss: 0.1142 | ds_loss: 0.1142 | lr: 2.6617e-05 | scale: 1.0000 | micro time: 14.250 | step time: 4.460
499
+ train | epoch 1 | Iter: 4910/ 7476 | global iter: 4910/ 7476 | loss: 0.1059 | ds_loss: 0.1059 | lr: 2.6432e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.742
500
+ train | epoch 1 | Iter: 4920/ 7476 | global iter: 4920/ 7476 | loss: 0.1074 | ds_loss: 0.1074 | lr: 2.6247e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.103
501
+ train | epoch 1 | Iter: 4930/ 7476 | global iter: 4930/ 7476 | loss: 0.1036 | ds_loss: 0.1036 | lr: 2.6063e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.133
502
+ train | epoch 1 | Iter: 4940/ 7476 | global iter: 4940/ 7476 | loss: 0.0968 | ds_loss: 0.0968 | lr: 2.5879e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.693
503
+ train | epoch 1 | Iter: 4950/ 7476 | global iter: 4950/ 7476 | loss: 0.1136 | ds_loss: 0.1136 | lr: 2.5696e-05 | scale: 1.0000 | micro time: 0.342 | step time: 1.727
504
+ train | epoch 1 | Iter: 4960/ 7476 | global iter: 4960/ 7476 | loss: 0.1099 | ds_loss: 0.1099 | lr: 2.5513e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.110
505
+ train | epoch 1 | Iter: 4970/ 7476 | global iter: 4970/ 7476 | loss: 0.1070 | ds_loss: 0.1070 | lr: 2.5330e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
506
+ train | epoch 1 | Iter: 4980/ 7476 | global iter: 4980/ 7476 | loss: 0.1100 | ds_loss: 0.1100 | lr: 2.5148e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.512
507
+ dev | avg_loss: 2.90625 | {'exact_match': 0.0, 'rougeL': 11.0961} | threshold: 0.1
508
+ train | epoch 2 | Iter: 4990/ 7476 | global iter: 4990/ 7476 | loss: 0.1064 | ds_loss: 0.1064 | lr: 2.4966e-05 | scale: 1.0000 | micro time: 0.341 | step time: 0.328
509
+ train | epoch 2 | Iter: 5000/ 7476 | global iter: 5000/ 7476 | loss: 0.0985 | ds_loss: 0.0985 | lr: 2.4785e-05 | scale: 1.0000 | micro time: 13.989 | step time: 4.469
510
+ train | epoch 2 | Iter: 5010/ 7476 | global iter: 5010/ 7476 | loss: 0.1009 | ds_loss: 0.1009 | lr: 2.4604e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.688
511
+ train | epoch 2 | Iter: 5020/ 7476 | global iter: 5020/ 7476 | loss: 0.0927 | ds_loss: 0.0927 | lr: 2.4423e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
512
+ train | epoch 2 | Iter: 5030/ 7476 | global iter: 5030/ 7476 | loss: 0.0963 | ds_loss: 0.0963 | lr: 2.4244e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.715
513
+ train | epoch 2 | Iter: 5040/ 7476 | global iter: 5040/ 7476 | loss: 0.0898 | ds_loss: 0.0898 | lr: 2.4064e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
514
+ train | epoch 2 | Iter: 5050/ 7476 | global iter: 5050/ 7476 | loss: 0.0940 | ds_loss: 0.0940 | lr: 2.3885e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.694
515
+ train | epoch 2 | Iter: 5060/ 7476 | global iter: 5060/ 7476 | loss: 0.0907 | ds_loss: 0.0907 | lr: 2.3706e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.103
516
+ train | epoch 2 | Iter: 5070/ 7476 | global iter: 5070/ 7476 | loss: 0.0903 | ds_loss: 0.0903 | lr: 2.3528e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
517
+ train | epoch 2 | Iter: 5080/ 7476 | global iter: 5080/ 7476 | loss: 0.0876 | ds_loss: 0.0876 | lr: 2.3351e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.702
518
+ train | epoch 2 | Iter: 5090/ 7476 | global iter: 5090/ 7476 | loss: 0.0858 | ds_loss: 0.0858 | lr: 2.3174e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
519
+ train | epoch 2 | Iter: 5100/ 7476 | global iter: 5100/ 7476 | loss: 0.0968 | ds_loss: 0.0968 | lr: 2.2997e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
520
+ train | epoch 2 | Iter: 5110/ 7476 | global iter: 5110/ 7476 | loss: 0.0892 | ds_loss: 0.0892 | lr: 2.2821e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.723
521
+ train | epoch 2 | Iter: 5120/ 7476 | global iter: 5120/ 7476 | loss: 0.0918 | ds_loss: 0.0918 | lr: 2.2645e-05 | scale: 1.0000 | micro time: 13.815 | step time: 1.687
522
+ train | epoch 2 | Iter: 5130/ 7476 | global iter: 5130/ 7476 | loss: 0.0893 | ds_loss: 0.0893 | lr: 2.2470e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
523
+ train | epoch 2 | Iter: 5140/ 7476 | global iter: 5140/ 7476 | loss: 0.0939 | ds_loss: 0.0939 | lr: 2.2295e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.130
524
+ train | epoch 2 | Iter: 5150/ 7476 | global iter: 5150/ 7476 | loss: 0.0857 | ds_loss: 0.0857 | lr: 2.2121e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
525
+ train | epoch 2 | Iter: 5160/ 7476 | global iter: 5160/ 7476 | loss: 0.0938 | ds_loss: 0.0938 | lr: 2.1947e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.079
526
+ train | epoch 2 | Iter: 5170/ 7476 | global iter: 5170/ 7476 | loss: 0.0891 | ds_loss: 0.0891 | lr: 2.1774e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.072
527
+ train | epoch 2 | Iter: 5180/ 7476 | global iter: 5180/ 7476 | loss: 0.0887 | ds_loss: 0.0887 | lr: 2.1601e-05 | scale: 1.0000 | micro time: 14.126 | step time: 1.718
528
+ train | epoch 2 | Iter: 5190/ 7476 | global iter: 5190/ 7476 | loss: 0.0930 | ds_loss: 0.0930 | lr: 2.1429e-05 | scale: 1.0000 | micro time: 14.099 | step time: 3.094
529
+ train | epoch 2 | Iter: 5200/ 7476 | global iter: 5200/ 7476 | loss: 0.1012 | ds_loss: 0.1012 | lr: 2.1257e-05 | scale: 1.0000 | micro time: 13.875 | step time: 4.444
530
+ train | epoch 2 | Iter: 5210/ 7476 | global iter: 5210/ 7476 | loss: 0.0967 | ds_loss: 0.0967 | lr: 2.1085e-05 | scale: 1.0000 | micro time: 0.343 | step time: 4.461
531
+ train | epoch 2 | Iter: 5220/ 7476 | global iter: 5220/ 7476 | loss: 0.0942 | ds_loss: 0.0942 | lr: 2.0915e-05 | scale: 1.0000 | micro time: 0.343 | step time: 1.689
532
+ train | epoch 2 | Iter: 5230/ 7476 | global iter: 5230/ 7476 | loss: 0.0899 | ds_loss: 0.0899 | lr: 2.0744e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.718
533
+ train | epoch 2 | Iter: 5240/ 7476 | global iter: 5240/ 7476 | loss: 0.0906 | ds_loss: 0.0906 | lr: 2.0575e-05 | scale: 1.0000 | micro time: 0.343 | step time: 1.700
534
+ train | epoch 2 | Iter: 5250/ 7476 | global iter: 5250/ 7476 | loss: 0.0958 | ds_loss: 0.0958 | lr: 2.0406e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.478
535
+ train | epoch 2 | Iter: 5260/ 7476 | global iter: 5260/ 7476 | loss: 0.0883 | ds_loss: 0.0883 | lr: 2.0237e-05 | scale: 1.0000 | micro time: 14.004 | step time: 3.132
536
+ train | epoch 2 | Iter: 5270/ 7476 | global iter: 5270/ 7476 | loss: 0.0922 | ds_loss: 0.0922 | lr: 2.0069e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.068
537
+ train | epoch 2 | Iter: 5280/ 7476 | global iter: 5280/ 7476 | loss: 0.0901 | ds_loss: 0.0901 | lr: 1.9901e-05 | scale: 1.0000 | micro time: 0.344 | step time: 1.705
538
+ train | epoch 2 | Iter: 5290/ 7476 | global iter: 5290/ 7476 | loss: 0.0905 | ds_loss: 0.0905 | lr: 1.9734e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
539
+ train | epoch 2 | Iter: 5300/ 7476 | global iter: 5300/ 7476 | loss: 0.0942 | ds_loss: 0.0942 | lr: 1.9567e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.706
540
+ train | epoch 2 | Iter: 5310/ 7476 | global iter: 5310/ 7476 | loss: 0.0968 | ds_loss: 0.0968 | lr: 1.9401e-05 | scale: 1.0000 | micro time: 0.340 | step time: 4.501
541
+ train | epoch 2 | Iter: 5320/ 7476 | global iter: 5320/ 7476 | loss: 0.0864 | ds_loss: 0.0864 | lr: 1.9236e-05 | scale: 1.0000 | micro time: 0.339 | step time: 3.103
542
+ train | epoch 2 | Iter: 5330/ 7476 | global iter: 5330/ 7476 | loss: 0.0833 | ds_loss: 0.0833 | lr: 1.9071e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.720
543
+ train | epoch 2 | Iter: 5340/ 7476 | global iter: 5340/ 7476 | loss: 0.0851 | ds_loss: 0.0851 | lr: 1.8907e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.730
544
+ train | epoch 2 | Iter: 5350/ 7476 | global iter: 5350/ 7476 | loss: 0.0993 | ds_loss: 0.0993 | lr: 1.8743e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.494
545
+ train | epoch 2 | Iter: 5360/ 7476 | global iter: 5360/ 7476 | loss: 0.0879 | ds_loss: 0.0879 | lr: 1.8580e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
546
+ train | epoch 2 | Iter: 5370/ 7476 | global iter: 5370/ 7476 | loss: 0.0837 | ds_loss: 0.0837 | lr: 1.8417e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.737
547
+ train | epoch 2 | Iter: 5380/ 7476 | global iter: 5380/ 7476 | loss: 0.0950 | ds_loss: 0.0950 | lr: 1.8255e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
548
+ train | epoch 2 | Iter: 5390/ 7476 | global iter: 5390/ 7476 | loss: 0.0931 | ds_loss: 0.0931 | lr: 1.8093e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.730
549
+ train | epoch 2 | Iter: 5400/ 7476 | global iter: 5400/ 7476 | loss: 0.0977 | ds_loss: 0.0977 | lr: 1.7932e-05 | scale: 1.0000 | micro time: 13.946 | step time: 3.067
550
+ train | epoch 2 | Iter: 5410/ 7476 | global iter: 5410/ 7476 | loss: 0.0967 | ds_loss: 0.0967 | lr: 1.7772e-05 | scale: 1.0000 | micro time: 0.341 | step time: 1.742
551
+ train | epoch 2 | Iter: 5420/ 7476 | global iter: 5420/ 7476 | loss: 0.0936 | ds_loss: 0.0936 | lr: 1.7612e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.069
552
+ train | epoch 2 | Iter: 5430/ 7476 | global iter: 5430/ 7476 | loss: 0.0881 | ds_loss: 0.0881 | lr: 1.7452e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
553
+ train | epoch 2 | Iter: 5440/ 7476 | global iter: 5440/ 7476 | loss: 0.0916 | ds_loss: 0.0916 | lr: 1.7294e-05 | scale: 1.0000 | micro time: 0.350 | step time: 0.341
554
+ train | epoch 2 | Iter: 5450/ 7476 | global iter: 5450/ 7476 | loss: 0.0769 | ds_loss: 0.0769 | lr: 1.7135e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.701
555
+ train | epoch 2 | Iter: 5460/ 7476 | global iter: 5460/ 7476 | loss: 0.0899 | ds_loss: 0.0899 | lr: 1.6978e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.704
556
+ train | epoch 2 | Iter: 5470/ 7476 | global iter: 5470/ 7476 | loss: 0.0918 | ds_loss: 0.0918 | lr: 1.6821e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.702
557
+ train | epoch 2 | Iter: 5480/ 7476 | global iter: 5480/ 7476 | loss: 0.0946 | ds_loss: 0.0946 | lr: 1.6664e-05 | scale: 1.0000 | micro time: 0.342 | step time: 3.069
558
+ train | epoch 2 | Iter: 5490/ 7476 | global iter: 5490/ 7476 | loss: 0.0788 | ds_loss: 0.0788 | lr: 1.6509e-05 | scale: 1.0000 | micro time: 0.344 | step time: 1.737
559
+ train | epoch 2 | Iter: 5500/ 7476 | global iter: 5500/ 7476 | loss: 0.0976 | ds_loss: 0.0976 | lr: 1.6353e-05 | scale: 1.0000 | micro time: 0.349 | step time: 1.723
560
+ train | epoch 2 | Iter: 5510/ 7476 | global iter: 5510/ 7476 | loss: 0.0843 | ds_loss: 0.0843 | lr: 1.6199e-05 | scale: 1.0000 | micro time: 0.345 | step time: 3.066
561
+ train | epoch 2 | Iter: 5520/ 7476 | global iter: 5520/ 7476 | loss: 0.0927 | ds_loss: 0.0927 | lr: 1.6045e-05 | scale: 1.0000 | micro time: 0.339 | step time: 4.413
562
+ train | epoch 2 | Iter: 5530/ 7476 | global iter: 5530/ 7476 | loss: 0.0887 | ds_loss: 0.0887 | lr: 1.5891e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
563
+ train | epoch 2 | Iter: 5540/ 7476 | global iter: 5540/ 7476 | loss: 0.0901 | ds_loss: 0.0901 | lr: 1.5738e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
564
+ train | epoch 2 | Iter: 5550/ 7476 | global iter: 5550/ 7476 | loss: 0.0859 | ds_loss: 0.0859 | lr: 1.5586e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
565
+ train | epoch 2 | Iter: 5560/ 7476 | global iter: 5560/ 7476 | loss: 0.0929 | ds_loss: 0.0929 | lr: 1.5434e-05 | scale: 1.0000 | micro time: 0.342 | step time: 0.340
566
+ train | epoch 2 | Iter: 5570/ 7476 | global iter: 5570/ 7476 | loss: 0.0858 | ds_loss: 0.0858 | lr: 1.5283e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.723
567
+ train | epoch 2 | Iter: 5580/ 7476 | global iter: 5580/ 7476 | loss: 0.0880 | ds_loss: 0.0880 | lr: 1.5133e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.703
568
+ train | epoch 2 | Iter: 5590/ 7476 | global iter: 5590/ 7476 | loss: 0.0869 | ds_loss: 0.0869 | lr: 1.4983e-05 | scale: 1.0000 | micro time: 0.340 | step time: 3.089
569
+ train | epoch 2 | Iter: 5600/ 7476 | global iter: 5600/ 7476 | loss: 0.0905 | ds_loss: 0.0905 | lr: 1.4834e-05 | scale: 1.0000 | micro time: 0.338 | step time: 3.102
570
+ train | epoch 2 | Iter: 5610/ 7476 | global iter: 5610/ 7476 | loss: 0.0927 | ds_loss: 0.0927 | lr: 1.4686e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
571
+ train | epoch 2 | Iter: 5620/ 7476 | global iter: 5620/ 7476 | loss: 0.0947 | ds_loss: 0.0947 | lr: 1.4538e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.713
572
+ train | epoch 2 | Iter: 5630/ 7476 | global iter: 5630/ 7476 | loss: 0.0907 | ds_loss: 0.0907 | lr: 1.4390e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.700
573
+ train | epoch 2 | Iter: 5640/ 7476 | global iter: 5640/ 7476 | loss: 0.0863 | ds_loss: 0.0863 | lr: 1.4244e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
574
+ train | epoch 2 | Iter: 5650/ 7476 | global iter: 5650/ 7476 | loss: 0.0892 | ds_loss: 0.0892 | lr: 1.4098e-05 | scale: 1.0000 | micro time: 14.004 | step time: 3.074
575
+ train | epoch 2 | Iter: 5660/ 7476 | global iter: 5660/ 7476 | loss: 0.0871 | ds_loss: 0.0871 | lr: 1.3952e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
576
+ train | epoch 2 | Iter: 5670/ 7476 | global iter: 5670/ 7476 | loss: 0.0890 | ds_loss: 0.0890 | lr: 1.3807e-05 | scale: 1.0000 | micro time: 0.338 | step time: 1.703
577
+ train | epoch 2 | Iter: 5680/ 7476 | global iter: 5680/ 7476 | loss: 0.0864 | ds_loss: 0.0864 | lr: 1.3663e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
578
+ train | epoch 2 | Iter: 5690/ 7476 | global iter: 5690/ 7476 | loss: 0.0897 | ds_loss: 0.0897 | lr: 1.3520e-05 | scale: 1.0000 | micro time: 13.955 | step time: 4.422
579
+ train | epoch 2 | Iter: 5700/ 7476 | global iter: 5700/ 7476 | loss: 0.0865 | ds_loss: 0.0865 | lr: 1.3377e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.701
580
+ train | epoch 2 | Iter: 5710/ 7476 | global iter: 5710/ 7476 | loss: 0.0768 | ds_loss: 0.0768 | lr: 1.3235e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
581
+ train | epoch 2 | Iter: 5720/ 7476 | global iter: 5720/ 7476 | loss: 0.0885 | ds_loss: 0.0885 | lr: 1.3093e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
582
+ train | epoch 2 | Iter: 5730/ 7476 | global iter: 5730/ 7476 | loss: 0.0903 | ds_loss: 0.0903 | lr: 1.2952e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.696
583
+ train | epoch 2 | Iter: 5740/ 7476 | global iter: 5740/ 7476 | loss: 0.0888 | ds_loss: 0.0888 | lr: 1.2812e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.725
584
+ train | epoch 2 | Iter: 5750/ 7476 | global iter: 5750/ 7476 | loss: 0.0890 | ds_loss: 0.0890 | lr: 1.2673e-05 | scale: 1.0000 | micro time: 0.340 | step time: 1.718
585
+ train | epoch 2 | Iter: 5760/ 7476 | global iter: 5760/ 7476 | loss: 0.0862 | ds_loss: 0.0862 | lr: 1.2534e-05 | scale: 1.0000 | micro time: 13.791 | step time: 3.070
586
+ train | epoch 2 | Iter: 5770/ 7476 | global iter: 5770/ 7476 | loss: 0.0943 | ds_loss: 0.0943 | lr: 1.2395e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
587
+ train | epoch 2 | Iter: 5780/ 7476 | global iter: 5780/ 7476 | loss: 0.0860 | ds_loss: 0.0860 | lr: 1.2258e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
588
+ train | epoch 2 | Iter: 5790/ 7476 | global iter: 5790/ 7476 | loss: 0.1034 | ds_loss: 0.1034 | lr: 1.2121e-05 | scale: 1.0000 | micro time: 0.344 | step time: 3.036
589
+ train | epoch 2 | Iter: 5800/ 7476 | global iter: 5800/ 7476 | loss: 0.0927 | ds_loss: 0.0927 | lr: 1.1985e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
590
+ train | epoch 2 | Iter: 5810/ 7476 | global iter: 5810/ 7476 | loss: 0.0926 | ds_loss: 0.0926 | lr: 1.1849e-05 | scale: 1.0000 | micro time: 13.797 | step time: 3.080
591
+ train | epoch 2 | Iter: 5820/ 7476 | global iter: 5820/ 7476 | loss: 0.0903 | ds_loss: 0.0903 | lr: 1.1714e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.693
592
+ train | epoch 2 | Iter: 5830/ 7476 | global iter: 5830/ 7476 | loss: 0.0837 | ds_loss: 0.0837 | lr: 1.1580e-05 | scale: 1.0000 | micro time: 0.344 | step time: 0.340
593
+ train | epoch 2 | Iter: 5840/ 7476 | global iter: 5840/ 7476 | loss: 0.0958 | ds_loss: 0.0958 | lr: 1.1446e-05 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
594
+ train | epoch 2 | Iter: 5850/ 7476 | global iter: 5850/ 7476 | loss: 0.0913 | ds_loss: 0.0913 | lr: 1.1314e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.712
595
+ train | epoch 2 | Iter: 5860/ 7476 | global iter: 5860/ 7476 | loss: 0.0939 | ds_loss: 0.0939 | lr: 1.1181e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
596
+ train | epoch 2 | Iter: 5870/ 7476 | global iter: 5870/ 7476 | loss: 0.0899 | ds_loss: 0.0899 | lr: 1.1050e-05 | scale: 1.0000 | micro time: 14.351 | step time: 1.741
597
+ train | epoch 2 | Iter: 5880/ 7476 | global iter: 5880/ 7476 | loss: 0.0959 | ds_loss: 0.0959 | lr: 1.0919e-05 | scale: 1.0000 | micro time: 0.339 | step time: 1.692
598
+ train | epoch 2 | Iter: 5890/ 7476 | global iter: 5890/ 7476 | loss: 0.0936 | ds_loss: 0.0936 | lr: 1.0789e-05 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
599
+ train | epoch 2 | Iter: 5900/ 7476 | global iter: 5900/ 7476 | loss: 0.0932 | ds_loss: 0.0932 | lr: 1.0660e-05 | scale: 1.0000 | micro time: 0.344 | step time: 1.686
600
+ train | epoch 2 | Iter: 5910/ 7476 | global iter: 5910/ 7476 | loss: 0.0850 | ds_loss: 0.0850 | lr: 1.0531e-05 | scale: 1.0000 | micro time: 0.345 | step time: 1.704
601
+ train | epoch 2 | Iter: 5920/ 7476 | global iter: 5920/ 7476 | loss: 0.0877 | ds_loss: 0.0877 | lr: 1.0403e-05 | scale: 1.0000 | micro time: 14.015 | step time: 1.707
602
+ train | epoch 2 | Iter: 5930/ 7476 | global iter: 5930/ 7476 | loss: 0.0890 | ds_loss: 0.0890 | lr: 1.0276e-05 | scale: 1.0000 | micro time: 0.338 | step time: 1.715
603
+ train | epoch 2 | Iter: 5940/ 7476 | global iter: 5940/ 7476 | loss: 0.0874 | ds_loss: 0.0874 | lr: 1.0149e-05 | scale: 1.0000 | micro time: 14.008 | step time: 3.072
604
+ train | epoch 2 | Iter: 5950/ 7476 | global iter: 5950/ 7476 | loss: 0.0868 | ds_loss: 0.0868 | lr: 1.0023e-05 | scale: 1.0000 | micro time: 0.338 | step time: 1.710
605
+ train | epoch 2 | Iter: 5960/ 7476 | global iter: 5960/ 7476 | loss: 0.0870 | ds_loss: 0.0870 | lr: 9.8978e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
606
+ train | epoch 2 | Iter: 5970/ 7476 | global iter: 5970/ 7476 | loss: 0.0825 | ds_loss: 0.0825 | lr: 9.7733e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.684
607
+ train | epoch 2 | Iter: 5980/ 7476 | global iter: 5980/ 7476 | loss: 0.0791 | ds_loss: 0.0791 | lr: 9.6495e-06 | scale: 1.0000 | micro time: 0.341 | step time: 1.706
608
+ train | epoch 2 | Iter: 5990/ 7476 | global iter: 5990/ 7476 | loss: 0.0841 | ds_loss: 0.0841 | lr: 9.5264e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.708
609
+ train | epoch 2 | Iter: 6000/ 7476 | global iter: 6000/ 7476 | loss: 0.0898 | ds_loss: 0.0898 | lr: 9.4040e-06 | scale: 1.0000 | micro time: 14.412 | step time: 3.142
610
+ train | epoch 2 | Iter: 6010/ 7476 | global iter: 6010/ 7476 | loss: 0.0846 | ds_loss: 0.0846 | lr: 9.2824e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
611
+ train | epoch 2 | Iter: 6020/ 7476 | global iter: 6020/ 7476 | loss: 0.0932 | ds_loss: 0.0932 | lr: 9.1615e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.708
612
+ train | epoch 2 | Iter: 6030/ 7476 | global iter: 6030/ 7476 | loss: 0.0885 | ds_loss: 0.0885 | lr: 9.0413e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
613
+ train | epoch 2 | Iter: 6040/ 7476 | global iter: 6040/ 7476 | loss: 0.0903 | ds_loss: 0.0903 | lr: 8.9218e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
614
+ train | epoch 2 | Iter: 6050/ 7476 | global iter: 6050/ 7476 | loss: 0.0915 | ds_loss: 0.0915 | lr: 8.8030e-06 | scale: 1.0000 | micro time: 0.339 | step time: 3.115
615
+ train | epoch 2 | Iter: 6060/ 7476 | global iter: 6060/ 7476 | loss: 0.0862 | ds_loss: 0.0862 | lr: 8.6850e-06 | scale: 1.0000 | micro time: 0.344 | step time: 5.909
616
+ train | epoch 2 | Iter: 6070/ 7476 | global iter: 6070/ 7476 | loss: 0.0885 | ds_loss: 0.0885 | lr: 8.5677e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.682
617
+ train | epoch 2 | Iter: 6080/ 7476 | global iter: 6080/ 7476 | loss: 0.0890 | ds_loss: 0.0890 | lr: 8.4512e-06 | scale: 1.0000 | micro time: 0.339 | step time: 4.445
618
+ train | epoch 2 | Iter: 6090/ 7476 | global iter: 6090/ 7476 | loss: 0.0923 | ds_loss: 0.0923 | lr: 8.3353e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.735
619
+ train | epoch 2 | Iter: 6100/ 7476 | global iter: 6100/ 7476 | loss: 0.0784 | ds_loss: 0.0784 | lr: 8.2202e-06 | scale: 1.0000 | micro time: 0.342 | step time: 0.340
620
+ train | epoch 2 | Iter: 6110/ 7476 | global iter: 6110/ 7476 | loss: 0.0839 | ds_loss: 0.0839 | lr: 8.1059e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
621
+ train | epoch 2 | Iter: 6120/ 7476 | global iter: 6120/ 7476 | loss: 0.0900 | ds_loss: 0.0900 | lr: 7.9923e-06 | scale: 1.0000 | micro time: 0.338 | step time: 1.719
622
+ train | epoch 2 | Iter: 6130/ 7476 | global iter: 6130/ 7476 | loss: 0.0814 | ds_loss: 0.0814 | lr: 7.8794e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
623
+ train | epoch 2 | Iter: 6140/ 7476 | global iter: 6140/ 7476 | loss: 0.0823 | ds_loss: 0.0823 | lr: 7.7673e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
624
+ train | epoch 2 | Iter: 6150/ 7476 | global iter: 6150/ 7476 | loss: 0.0900 | ds_loss: 0.0900 | lr: 7.6559e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
625
+ train | epoch 2 | Iter: 6160/ 7476 | global iter: 6160/ 7476 | loss: 0.0901 | ds_loss: 0.0901 | lr: 7.5453e-06 | scale: 1.0000 | micro time: 0.340 | step time: 1.711
626
+ train | epoch 2 | Iter: 6170/ 7476 | global iter: 6170/ 7476 | loss: 0.0885 | ds_loss: 0.0885 | lr: 7.4354e-06 | scale: 1.0000 | micro time: 14.179 | step time: 3.114
627
+ train | epoch 2 | Iter: 6180/ 7476 | global iter: 6180/ 7476 | loss: 0.0912 | ds_loss: 0.0912 | lr: 7.3263e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
628
+ train | epoch 2 | Iter: 6190/ 7476 | global iter: 6190/ 7476 | loss: 0.0950 | ds_loss: 0.0950 | lr: 7.2179e-06 | scale: 1.0000 | micro time: 0.339 | step time: 3.124
629
+ train | epoch 2 | Iter: 6200/ 7476 | global iter: 6200/ 7476 | loss: 0.0835 | ds_loss: 0.0835 | lr: 7.1103e-06 | scale: 1.0000 | micro time: 0.338 | step time: 1.715
630
+ train | epoch 2 | Iter: 6210/ 7476 | global iter: 6210/ 7476 | loss: 0.0928 | ds_loss: 0.0928 | lr: 7.0035e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
631
+ train | epoch 2 | Iter: 6220/ 7476 | global iter: 6220/ 7476 | loss: 0.0875 | ds_loss: 0.0875 | lr: 6.8974e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
632
+ train | epoch 2 | Iter: 6230/ 7476 | global iter: 6230/ 7476 | loss: 0.0897 | ds_loss: 0.0897 | lr: 6.7920e-06 | scale: 1.0000 | micro time: 0.340 | step time: 1.742
633
+ train | epoch 2 | Iter: 6240/ 7476 | global iter: 6240/ 7476 | loss: 0.0887 | ds_loss: 0.0887 | lr: 6.6875e-06 | scale: 1.0000 | micro time: 14.159 | step time: 1.721
634
+ train | epoch 2 | Iter: 6250/ 7476 | global iter: 6250/ 7476 | loss: 0.0827 | ds_loss: 0.0827 | lr: 6.5837e-06 | scale: 1.0000 | micro time: 14.435 | step time: 3.121
635
+ train | epoch 2 | Iter: 6260/ 7476 | global iter: 6260/ 7476 | loss: 0.1005 | ds_loss: 0.1005 | lr: 6.4806e-06 | scale: 1.0000 | micro time: 0.340 | step time: 4.477
636
+ train | epoch 2 | Iter: 6270/ 7476 | global iter: 6270/ 7476 | loss: 0.0880 | ds_loss: 0.0880 | lr: 6.3784e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.742
637
+ train | epoch 2 | Iter: 6280/ 7476 | global iter: 6280/ 7476 | loss: 0.0870 | ds_loss: 0.0870 | lr: 6.2769e-06 | scale: 1.0000 | micro time: 0.342 | step time: 0.340
638
+ train | epoch 2 | Iter: 6290/ 7476 | global iter: 6290/ 7476 | loss: 0.0821 | ds_loss: 0.0821 | lr: 6.1761e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
639
+ train | epoch 2 | Iter: 6300/ 7476 | global iter: 6300/ 7476 | loss: 0.0821 | ds_loss: 0.0821 | lr: 6.0762e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
640
+ train | epoch 2 | Iter: 6310/ 7476 | global iter: 6310/ 7476 | loss: 0.0861 | ds_loss: 0.0861 | lr: 5.9770e-06 | scale: 1.0000 | micro time: 0.338 | step time: 1.700
641
+ train | epoch 2 | Iter: 6320/ 7476 | global iter: 6320/ 7476 | loss: 0.0915 | ds_loss: 0.0915 | lr: 5.8786e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.717
642
+ train | epoch 2 | Iter: 6330/ 7476 | global iter: 6330/ 7476 | loss: 0.0910 | ds_loss: 0.0910 | lr: 5.7810e-06 | scale: 1.0000 | micro time: 0.341 | step time: 1.711
643
+ train | epoch 2 | Iter: 6340/ 7476 | global iter: 6340/ 7476 | loss: 0.0790 | ds_loss: 0.0790 | lr: 5.6842e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
644
+ train | epoch 2 | Iter: 6350/ 7476 | global iter: 6350/ 7476 | loss: 0.0877 | ds_loss: 0.0877 | lr: 5.5881e-06 | scale: 1.0000 | micro time: 0.341 | step time: 1.744
645
+ train | epoch 2 | Iter: 6360/ 7476 | global iter: 6360/ 7476 | loss: 0.0916 | ds_loss: 0.0916 | lr: 5.4929e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
646
+ train | epoch 2 | Iter: 6370/ 7476 | global iter: 6370/ 7476 | loss: 0.0858 | ds_loss: 0.0858 | lr: 5.3984e-06 | scale: 1.0000 | micro time: 0.338 | step time: 0.340
647
+ train | epoch 2 | Iter: 6380/ 7476 | global iter: 6380/ 7476 | loss: 0.0823 | ds_loss: 0.0823 | lr: 5.3047e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
648
+ train | epoch 2 | Iter: 6390/ 7476 | global iter: 6390/ 7476 | loss: 0.0842 | ds_loss: 0.0842 | lr: 5.2118e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.723
649
+ train | epoch 2 | Iter: 6400/ 7476 | global iter: 6400/ 7476 | loss: 0.0866 | ds_loss: 0.0866 | lr: 5.1197e-06 | scale: 1.0000 | micro time: 0.341 | step time: 0.340
650
+ train | epoch 2 | Iter: 6410/ 7476 | global iter: 6410/ 7476 | loss: 0.0977 | ds_loss: 0.0977 | lr: 5.0284e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.718
651
+ train | epoch 2 | Iter: 6420/ 7476 | global iter: 6420/ 7476 | loss: 0.0911 | ds_loss: 0.0911 | lr: 4.9379e-06 | scale: 1.0000 | micro time: 13.987 | step time: 4.584
652
+ train | epoch 2 | Iter: 6430/ 7476 | global iter: 6430/ 7476 | loss: 0.0913 | ds_loss: 0.0913 | lr: 4.8482e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
653
+ train | epoch 2 | Iter: 6440/ 7476 | global iter: 6440/ 7476 | loss: 0.0877 | ds_loss: 0.0877 | lr: 4.7592e-06 | scale: 1.0000 | micro time: 0.338 | step time: 0.340
654
+ train | epoch 2 | Iter: 6450/ 7476 | global iter: 6450/ 7476 | loss: 0.0872 | ds_loss: 0.0872 | lr: 4.6711e-06 | scale: 1.0000 | micro time: 0.339 | step time: 3.095
655
+ train | epoch 2 | Iter: 6460/ 7476 | global iter: 6460/ 7476 | loss: 0.0887 | ds_loss: 0.0887 | lr: 4.5838e-06 | scale: 1.0000 | micro time: 0.340 | step time: 3.126
656
+ train | epoch 2 | Iter: 6470/ 7476 | global iter: 6470/ 7476 | loss: 0.0899 | ds_loss: 0.0899 | lr: 4.4973e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.714
657
+ train | epoch 2 | Iter: 6480/ 7476 | global iter: 6480/ 7476 | loss: 0.0837 | ds_loss: 0.0837 | lr: 4.4116e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.714
658
+ train | epoch 2 | Iter: 6490/ 7476 | global iter: 6490/ 7476 | loss: 0.0883 | ds_loss: 0.0883 | lr: 4.3267e-06 | scale: 1.0000 | micro time: 0.338 | step time: 3.108
659
+ train | epoch 2 | Iter: 6500/ 7476 | global iter: 6500/ 7476 | loss: 0.0869 | ds_loss: 0.0869 | lr: 4.2426e-06 | scale: 1.0000 | micro time: 0.343 | step time: 1.689
660
+ train | epoch 2 | Iter: 6510/ 7476 | global iter: 6510/ 7476 | loss: 0.0935 | ds_loss: 0.0935 | lr: 4.1593e-06 | scale: 1.0000 | micro time: 0.343 | step time: 1.715
661
+ train | epoch 2 | Iter: 6520/ 7476 | global iter: 6520/ 7476 | loss: 0.0887 | ds_loss: 0.0887 | lr: 4.0768e-06 | scale: 1.0000 | micro time: 0.340 | step time: 1.709
662
+ train | epoch 2 | Iter: 6530/ 7476 | global iter: 6530/ 7476 | loss: 0.0818 | ds_loss: 0.0818 | lr: 3.9951e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
663
+ train | epoch 2 | Iter: 6540/ 7476 | global iter: 6540/ 7476 | loss: 0.0930 | ds_loss: 0.0930 | lr: 3.9143e-06 | scale: 1.0000 | micro time: 14.041 | step time: 3.077
664
+ train | epoch 2 | Iter: 6550/ 7476 | global iter: 6550/ 7476 | loss: 0.0827 | ds_loss: 0.0827 | lr: 3.8342e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
665
+ train | epoch 2 | Iter: 6560/ 7476 | global iter: 6560/ 7476 | loss: 0.0859 | ds_loss: 0.0859 | lr: 3.7550e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.696
666
+ train | epoch 2 | Iter: 6570/ 7476 | global iter: 6570/ 7476 | loss: 0.0805 | ds_loss: 0.0805 | lr: 3.6766e-06 | scale: 1.0000 | micro time: 0.342 | step time: 0.342
667
+ train | epoch 2 | Iter: 6580/ 7476 | global iter: 6580/ 7476 | loss: 0.0858 | ds_loss: 0.0858 | lr: 3.5990e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.717
668
+ train | epoch 2 | Iter: 6590/ 7476 | global iter: 6590/ 7476 | loss: 0.0913 | ds_loss: 0.0913 | lr: 3.5222e-06 | scale: 1.0000 | micro time: 0.341 | step time: 3.080
669
+ train | epoch 2 | Iter: 6600/ 7476 | global iter: 6600/ 7476 | loss: 0.0849 | ds_loss: 0.0849 | lr: 3.4463e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
670
+ train | epoch 2 | Iter: 6610/ 7476 | global iter: 6610/ 7476 | loss: 0.0903 | ds_loss: 0.0903 | lr: 3.3712e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
671
+ train | epoch 2 | Iter: 6620/ 7476 | global iter: 6620/ 7476 | loss: 0.0771 | ds_loss: 0.0771 | lr: 3.2969e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
672
+ train | epoch 2 | Iter: 6630/ 7476 | global iter: 6630/ 7476 | loss: 0.0868 | ds_loss: 0.0868 | lr: 3.2234e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
673
+ train | epoch 2 | Iter: 6640/ 7476 | global iter: 6640/ 7476 | loss: 0.0878 | ds_loss: 0.0878 | lr: 3.1508e-06 | scale: 1.0000 | micro time: 0.345 | step time: 1.691
674
+ train | epoch 2 | Iter: 6650/ 7476 | global iter: 6650/ 7476 | loss: 0.0865 | ds_loss: 0.0865 | lr: 3.0789e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
675
+ train | epoch 2 | Iter: 6660/ 7476 | global iter: 6660/ 7476 | loss: 0.0937 | ds_loss: 0.0937 | lr: 3.0080e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
676
+ train | epoch 2 | Iter: 6670/ 7476 | global iter: 6670/ 7476 | loss: 0.0797 | ds_loss: 0.0797 | lr: 2.9378e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
677
+ train | epoch 2 | Iter: 6680/ 7476 | global iter: 6680/ 7476 | loss: 0.0860 | ds_loss: 0.0860 | lr: 2.8685e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
678
+ train | epoch 2 | Iter: 6690/ 7476 | global iter: 6690/ 7476 | loss: 0.0922 | ds_loss: 0.0922 | lr: 2.8000e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
679
+ train | epoch 2 | Iter: 6700/ 7476 | global iter: 6700/ 7476 | loss: 0.0949 | ds_loss: 0.0949 | lr: 2.7323e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
680
+ train | epoch 2 | Iter: 6710/ 7476 | global iter: 6710/ 7476 | loss: 0.0871 | ds_loss: 0.0871 | lr: 2.6655e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
681
+ train | epoch 2 | Iter: 6720/ 7476 | global iter: 6720/ 7476 | loss: 0.0799 | ds_loss: 0.0799 | lr: 2.5995e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
682
+ train | epoch 2 | Iter: 6730/ 7476 | global iter: 6730/ 7476 | loss: 0.0893 | ds_loss: 0.0893 | lr: 2.5344e-06 | scale: 1.0000 | micro time: 0.338 | step time: 0.339
683
+ train | epoch 2 | Iter: 6740/ 7476 | global iter: 6740/ 7476 | loss: 0.0861 | ds_loss: 0.0861 | lr: 2.4701e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
684
+ train | epoch 2 | Iter: 6750/ 7476 | global iter: 6750/ 7476 | loss: 0.0905 | ds_loss: 0.0905 | lr: 2.4066e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
685
+ train | epoch 2 | Iter: 6760/ 7476 | global iter: 6760/ 7476 | loss: 0.0953 | ds_loss: 0.0953 | lr: 2.3440e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
686
+ train | epoch 2 | Iter: 6770/ 7476 | global iter: 6770/ 7476 | loss: 0.0907 | ds_loss: 0.0907 | lr: 2.2822e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
687
+ train | epoch 2 | Iter: 6780/ 7476 | global iter: 6780/ 7476 | loss: 0.0868 | ds_loss: 0.0868 | lr: 2.2212e-06 | scale: 1.0000 | micro time: 0.338 | step time: 1.709
688
+ train | epoch 2 | Iter: 6790/ 7476 | global iter: 6790/ 7476 | loss: 0.0856 | ds_loss: 0.0856 | lr: 2.1611e-06 | scale: 1.0000 | micro time: 0.338 | step time: 0.339
689
+ train | epoch 2 | Iter: 6800/ 7476 | global iter: 6800/ 7476 | loss: 0.0863 | ds_loss: 0.0863 | lr: 2.1019e-06 | scale: 1.0000 | micro time: 0.338 | step time: 0.339
690
+ train | epoch 2 | Iter: 6810/ 7476 | global iter: 6810/ 7476 | loss: 0.0869 | ds_loss: 0.0869 | lr: 2.0435e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
691
+ train | epoch 2 | Iter: 6820/ 7476 | global iter: 6820/ 7476 | loss: 0.0888 | ds_loss: 0.0888 | lr: 1.9859e-06 | scale: 1.0000 | micro time: 0.340 | step time: 1.709
692
+ train | epoch 2 | Iter: 6830/ 7476 | global iter: 6830/ 7476 | loss: 0.0857 | ds_loss: 0.0857 | lr: 1.9292e-06 | scale: 1.0000 | micro time: 14.461 | step time: 1.752
693
+ train | epoch 2 | Iter: 6840/ 7476 | global iter: 6840/ 7476 | loss: 0.0848 | ds_loss: 0.0848 | lr: 1.8733e-06 | scale: 1.0000 | micro time: 0.338 | step time: 1.704
694
+ train | epoch 2 | Iter: 6850/ 7476 | global iter: 6850/ 7476 | loss: 0.0853 | ds_loss: 0.0853 | lr: 1.8183e-06 | scale: 1.0000 | micro time: 14.383 | step time: 3.129
695
+ train | epoch 2 | Iter: 6860/ 7476 | global iter: 6860/ 7476 | loss: 0.0885 | ds_loss: 0.0885 | lr: 1.7642e-06 | scale: 1.0000 | micro time: 0.340 | step time: 1.705
696
+ train | epoch 2 | Iter: 6870/ 7476 | global iter: 6870/ 7476 | loss: 0.0884 | ds_loss: 0.0884 | lr: 1.7109e-06 | scale: 1.0000 | micro time: 0.340 | step time: 1.723
697
+ train | epoch 2 | Iter: 6880/ 7476 | global iter: 6880/ 7476 | loss: 0.0894 | ds_loss: 0.0894 | lr: 1.6584e-06 | scale: 1.0000 | micro time: 0.342 | step time: 0.341
698
+ train | epoch 2 | Iter: 6890/ 7476 | global iter: 6890/ 7476 | loss: 0.0882 | ds_loss: 0.0882 | lr: 1.6068e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
699
+ train | epoch 2 | Iter: 6900/ 7476 | global iter: 6900/ 7476 | loss: 0.0862 | ds_loss: 0.0862 | lr: 1.5561e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
700
+ train | epoch 2 | Iter: 6910/ 7476 | global iter: 6910/ 7476 | loss: 0.0819 | ds_loss: 0.0819 | lr: 1.5062e-06 | scale: 1.0000 | micro time: 0.341 | step time: 0.342
701
+ train | epoch 2 | Iter: 6920/ 7476 | global iter: 6920/ 7476 | loss: 0.0841 | ds_loss: 0.0841 | lr: 1.4572e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
702
+ train | epoch 2 | Iter: 6930/ 7476 | global iter: 6930/ 7476 | loss: 0.0804 | ds_loss: 0.0804 | lr: 1.4090e-06 | scale: 1.0000 | micro time: 0.339 | step time: 1.724
703
+ train | epoch 2 | Iter: 6940/ 7476 | global iter: 6940/ 7476 | loss: 0.0966 | ds_loss: 0.0966 | lr: 1.3617e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
704
+ train | epoch 2 | Iter: 6950/ 7476 | global iter: 6950/ 7476 | loss: 0.0897 | ds_loss: 0.0897 | lr: 1.3153e-06 | scale: 1.0000 | micro time: 0.343 | step time: 1.692
705
+ train | epoch 2 | Iter: 6960/ 7476 | global iter: 6960/ 7476 | loss: 0.0817 | ds_loss: 0.0817 | lr: 1.2697e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
706
+ train | epoch 2 | Iter: 6970/ 7476 | global iter: 6970/ 7476 | loss: 0.0825 | ds_loss: 0.0825 | lr: 1.2249e-06 | scale: 1.0000 | micro time: 0.341 | step time: 0.339
707
+ train | epoch 2 | Iter: 6980/ 7476 | global iter: 6980/ 7476 | loss: 0.0876 | ds_loss: 0.0876 | lr: 1.1811e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
708
+ train | epoch 2 | Iter: 6990/ 7476 | global iter: 6990/ 7476 | loss: 0.0828 | ds_loss: 0.0828 | lr: 1.1381e-06 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
709
+ train | epoch 2 | Iter: 7000/ 7476 | global iter: 7000/ 7476 | loss: 0.0833 | ds_loss: 0.0833 | lr: 1.0959e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
710
+ train | epoch 2 | Iter: 7010/ 7476 | global iter: 7010/ 7476 | loss: 0.0800 | ds_loss: 0.0800 | lr: 1.0547e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
711
+ train | epoch 2 | Iter: 7020/ 7476 | global iter: 7020/ 7476 | loss: 0.0937 | ds_loss: 0.0937 | lr: 1.0143e-06 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
712
+ train | epoch 2 | Iter: 7030/ 7476 | global iter: 7030/ 7476 | loss: 0.0933 | ds_loss: 0.0933 | lr: 9.7471e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
713
+ train | epoch 2 | Iter: 7040/ 7476 | global iter: 7040/ 7476 | loss: 0.0871 | ds_loss: 0.0871 | lr: 9.3603e-07 | scale: 1.0000 | micro time: 0.338 | step time: 0.340
714
+ train | epoch 2 | Iter: 7050/ 7476 | global iter: 7050/ 7476 | loss: 0.0797 | ds_loss: 0.0797 | lr: 8.9823e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.339
715
+ train | epoch 2 | Iter: 7060/ 7476 | global iter: 7060/ 7476 | loss: 0.0898 | ds_loss: 0.0898 | lr: 8.6128e-07 | scale: 1.0000 | micro time: 0.338 | step time: 0.340
716
+ train | epoch 2 | Iter: 7070/ 7476 | global iter: 7070/ 7476 | loss: 0.0799 | ds_loss: 0.0799 | lr: 8.2521e-07 | scale: 1.0000 | micro time: 0.567 | step time: 0.361
717
+ train | epoch 2 | Iter: 7080/ 7476 | global iter: 7080/ 7476 | loss: 0.0831 | ds_loss: 0.0831 | lr: 7.9001e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
718
+ train | epoch 2 | Iter: 7090/ 7476 | global iter: 7090/ 7476 | loss: 0.0808 | ds_loss: 0.0808 | lr: 7.5568e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
719
+ train | epoch 2 | Iter: 7100/ 7476 | global iter: 7100/ 7476 | loss: 0.0851 | ds_loss: 0.0851 | lr: 7.2221e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
720
+ train | epoch 2 | Iter: 7110/ 7476 | global iter: 7110/ 7476 | loss: 0.0960 | ds_loss: 0.0960 | lr: 6.8962e-07 | scale: 1.0000 | micro time: 0.340 | step time: 1.719
721
+ train | epoch 2 | Iter: 7120/ 7476 | global iter: 7120/ 7476 | loss: 0.0814 | ds_loss: 0.0814 | lr: 6.5790e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.342
722
+ train | epoch 2 | Iter: 7130/ 7476 | global iter: 7130/ 7476 | loss: 0.0855 | ds_loss: 0.0855 | lr: 6.2705e-07 | scale: 1.0000 | micro time: 0.342 | step time: 0.340
723
+ train | epoch 2 | Iter: 7140/ 7476 | global iter: 7140/ 7476 | loss: 0.0873 | ds_loss: 0.0873 | lr: 5.9708e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
724
+ train | epoch 2 | Iter: 7150/ 7476 | global iter: 7150/ 7476 | loss: 0.0853 | ds_loss: 0.0853 | lr: 5.6797e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
725
+ train | epoch 2 | Iter: 7160/ 7476 | global iter: 7160/ 7476 | loss: 0.0824 | ds_loss: 0.0824 | lr: 5.3975e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
726
+ train | epoch 2 | Iter: 7170/ 7476 | global iter: 7170/ 7476 | loss: 0.0871 | ds_loss: 0.0871 | lr: 5.1239e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.339
727
+ train | epoch 2 | Iter: 7180/ 7476 | global iter: 7180/ 7476 | loss: 0.0810 | ds_loss: 0.0810 | lr: 4.8591e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
728
+ train | epoch 2 | Iter: 7190/ 7476 | global iter: 7190/ 7476 | loss: 0.0878 | ds_loss: 0.0878 | lr: 4.6031e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
729
+ train | epoch 2 | Iter: 7200/ 7476 | global iter: 7200/ 7476 | loss: 0.0859 | ds_loss: 0.0859 | lr: 4.3558e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
730
+ train | epoch 2 | Iter: 7210/ 7476 | global iter: 7210/ 7476 | loss: 0.0898 | ds_loss: 0.0898 | lr: 4.1173e-07 | scale: 1.0000 | micro time: 0.346 | step time: 0.342
731
+ train | epoch 2 | Iter: 7220/ 7476 | global iter: 7220/ 7476 | loss: 0.0837 | ds_loss: 0.0837 | lr: 3.8875e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.364
732
+ train | epoch 2 | Iter: 7230/ 7476 | global iter: 7230/ 7476 | loss: 0.0863 | ds_loss: 0.0863 | lr: 3.6666e-07 | scale: 1.0000 | micro time: 0.340 | step time: 1.703
733
+ train | epoch 2 | Iter: 7240/ 7476 | global iter: 7240/ 7476 | loss: 0.0873 | ds_loss: 0.0873 | lr: 3.4543e-07 | scale: 1.0000 | micro time: 0.350 | step time: 1.718
734
+ train | epoch 2 | Iter: 7250/ 7476 | global iter: 7250/ 7476 | loss: 0.0897 | ds_loss: 0.0897 | lr: 3.2509e-07 | scale: 1.0000 | micro time: 0.352 | step time: 0.342
735
+ train | epoch 2 | Iter: 7260/ 7476 | global iter: 7260/ 7476 | loss: 0.0835 | ds_loss: 0.0835 | lr: 3.0563e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.343
736
+ train | epoch 2 | Iter: 7270/ 7476 | global iter: 7270/ 7476 | loss: 0.0865 | ds_loss: 0.0865 | lr: 2.8704e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.342
737
+ train | epoch 2 | Iter: 7280/ 7476 | global iter: 7280/ 7476 | loss: 0.0836 | ds_loss: 0.0836 | lr: 2.6933e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
738
+ train | epoch 2 | Iter: 7290/ 7476 | global iter: 7290/ 7476 | loss: 0.0786 | ds_loss: 0.0786 | lr: 2.5250e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
739
+ train | epoch 2 | Iter: 7300/ 7476 | global iter: 7300/ 7476 | loss: 0.0870 | ds_loss: 0.0870 | lr: 2.3655e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
740
+ train | epoch 2 | Iter: 7310/ 7476 | global iter: 7310/ 7476 | loss: 0.0913 | ds_loss: 0.0913 | lr: 2.2148e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.342
741
+ train | epoch 2 | Iter: 7320/ 7476 | global iter: 7320/ 7476 | loss: 0.0826 | ds_loss: 0.0826 | lr: 2.0729e-07 | scale: 1.0000 | micro time: 0.343 | step time: 1.691
742
+ train | epoch 2 | Iter: 7330/ 7476 | global iter: 7330/ 7476 | loss: 0.0814 | ds_loss: 0.0814 | lr: 1.9398e-07 | scale: 1.0000 | micro time: 0.339 | step time: 1.720
743
+ train | epoch 2 | Iter: 7340/ 7476 | global iter: 7340/ 7476 | loss: 0.0940 | ds_loss: 0.0940 | lr: 1.8155e-07 | scale: 1.0000 | micro time: 0.345 | step time: 0.341
744
+ train | epoch 2 | Iter: 7350/ 7476 | global iter: 7350/ 7476 | loss: 0.0907 | ds_loss: 0.0907 | lr: 1.7000e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
745
+ train | epoch 2 | Iter: 7360/ 7476 | global iter: 7360/ 7476 | loss: 0.0896 | ds_loss: 0.0896 | lr: 1.5933e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
746
+ train | epoch 2 | Iter: 7370/ 7476 | global iter: 7370/ 7476 | loss: 0.0854 | ds_loss: 0.0854 | lr: 1.4955e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.340
747
+ train | epoch 2 | Iter: 7380/ 7476 | global iter: 7380/ 7476 | loss: 0.0865 | ds_loss: 0.0865 | lr: 1.4064e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.341
748
+ train | epoch 2 | Iter: 7390/ 7476 | global iter: 7390/ 7476 | loss: 0.0832 | ds_loss: 0.0832 | lr: 1.3261e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
749
+ train | epoch 2 | Iter: 7400/ 7476 | global iter: 7400/ 7476 | loss: 0.0845 | ds_loss: 0.0845 | lr: 1.2547e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
750
+ train | epoch 2 | Iter: 7410/ 7476 | global iter: 7410/ 7476 | loss: 0.0820 | ds_loss: 0.0820 | lr: 1.1921e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.340
751
+ train | epoch 2 | Iter: 7420/ 7476 | global iter: 7420/ 7476 | loss: 0.0975 | ds_loss: 0.0975 | lr: 1.1383e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.340
752
+ train | epoch 2 | Iter: 7430/ 7476 | global iter: 7430/ 7476 | loss: 0.0896 | ds_loss: 0.0896 | lr: 1.0933e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.339
753
+ train | epoch 2 | Iter: 7440/ 7476 | global iter: 7440/ 7476 | loss: 0.0867 | ds_loss: 0.0867 | lr: 1.0572e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.340
754
+ train | epoch 2 | Iter: 7450/ 7476 | global iter: 7450/ 7476 | loss: 0.0893 | ds_loss: 0.0893 | lr: 1.0298e-07 | scale: 1.0000 | micro time: 0.340 | step time: 0.340
755
+ train | epoch 2 | Iter: 7460/ 7476 | global iter: 7460/ 7476 | loss: 0.0863 | ds_loss: 0.0863 | lr: 1.0113e-07 | scale: 1.0000 | micro time: 0.339 | step time: 0.341
756
+ train | epoch 2 | Iter: 7470/ 7476 | global iter: 7470/ 7476 | loss: 0.0886 | ds_loss: 0.0886 | lr: 1.0016e-07 | scale: 1.0000 | micro time: 0.341 | step time: 0.340
757
+ dev | avg_loss: 2.890625 | {'exact_match': 0.0, 'rougeL': 11.0517} | threshold: 0.1
qwen2.5-1.5B-Instruct#amid/ab_pr_0.5_0.5_4_1e-4/args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_path": "Qwen/Qwen2.5-1.5B-Instruct", "ckpt_name": "qwen2.5-1.5B-Instruct", "model_type": "gpt2", "teacher_model_type": null, "n_gpu": 4, "n_nodes": 1, "teacher_model_path": "Qwen/Qwen2.5-14B-Instruct", "teacher_ckpt_name": "qwen2.5-14B-Instruct", "teacher_model_fp16": true, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "type": "adaptive-amid", "do_train": true, "do_valid": true, "do_eval": false, "base_path": ".", "load": null, "save": "./results/qwen2.5-1.5B-Instruct#amid/ab_pr_0.5_0.5_4_1e-4", "log_interval": 10, "mid_log_num": -1, "save_interval": -1, "eval_interval": -1, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "data_dir": "./processed_data/ultraInteract/Qwen/Qwen2.5-14B-Instruct/", "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": -1, "dev_ratio": 1, "gen_num": -1, "data_names": null, "prompt_type": null, "num_workers": 4, "max_prompt_length": 512, "min_prompt_length": 128, "json_data": false, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": true, "only_prompt": false, "batch_size": 4, "eval_batch_size": 16, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 1024, "seed": 10, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": 3, "training_epochs": 10000, "gradient_accumulation_steps": 2, "gradient_checkpointing": false, "attn_dtype": null, "lr": 0.0001, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": 1.0, "warmup_iters": 0, "lr_decay_iters": null, "lr_decay_style": "cosine", "scheduler_name": "constant_trm", "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": true, "gen_top_p": 1.0, "gen_num_beams": 1, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "top_k": 0, "top_p": 1.0, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 1.0, "peft": "lora", "peft_lora_r": 16, "peft_lora_alpha": 128, "peft_lora_dropout": 0.05, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "deepspeed": true, "deepspeed_config": "./configs/deepspeed/ds_config_zero1_bf16.json", "deepscale": false, "deepscale_config": null, "ab_alpha": 0.5, "ab_beta": 0.5, "amid_div_name": "ab", "amid_div_order": "pr", "amid_alpha": 0.5, "amid_lam": 0.5, "rank": 0, "world_size": 4}
qwen2.5-1.5B-Instruct#amid/ab_pr_0.5_0.5_4_1e-4/log.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+
2
+
3
+ ============================== EXP at 2026-05-12 04:50:57 ==============================