Hugging Face's logo

xingxm
/
DesignCoder

Text Generation
Transformers
Safetensors
designcoder
ui-generation
front-end
html
css
javascript
code-generation
full-sft
Model card Files
xet
 Community
xingxm commited on
Commit
f66ede7
·
verified ·
1 Parent(s): f2efa2e

Add designcoder_qwen3.5_4b_muon_bs32_step1900 (base Qwen3.5-4B, Muon, lr1e-5, global bs32, 2 epochs, step 1900)

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. designcoder_qwen3.5_4b_muon_bs32_step1900/all_results.json +8 -0
  3. designcoder_qwen3.5_4b_muon_bs32_step1900/chat_template.jinja +154 -0
  4. designcoder_qwen3.5_4b_muon_bs32_step1900/config.json +113 -0
  5. designcoder_qwen3.5_4b_muon_bs32_step1900/generation_config.json +10 -0
  6. designcoder_qwen3.5_4b_muon_bs32_step1900/model.safetensors +3 -0
  7. designcoder_qwen3.5_4b_muon_bs32_step1900/processor_config.json +60 -0
  8. designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer.json +3 -0
  9. designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer_config.json +34 -0
  10. designcoder_qwen3.5_4b_muon_bs32_step1900/train_results.json +8 -0
  11. designcoder_qwen3.5_4b_muon_bs32_step1900/trainer_log.jsonl +191 -0
  12. designcoder_qwen3.5_4b_muon_bs32_step1900/trainer_state.json +1373 -0
  13. designcoder_qwen3.5_4b_muon_bs32_step1900/training_loss.png +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
designcoder_qwen3.5_4b_muon_bs32_step1900/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 4.673658376419279e+19,
4
+ "train_loss": 0.35662912569547955,
5
+ "train_runtime": 27630.2175,
6
+ "train_samples_per_second": 2.2,
7
+ "train_steps_per_second": 0.069
8
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
designcoder_qwen3.5_4b_muon_bs32_step1900/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "hidden_size": 2560,
8
+ "image_token_id": 248056,
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248044,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "attn_output_gate": true,
15
+ "bos_token_id": null,
16
+ "dtype": "bfloat16",
17
+ "eos_token_id": 248044,
18
+ "full_attention_interval": 4,
19
+ "head_dim": 256,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 2560,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 9216,
24
+ "layer_types": [
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "full_attention"
57
+ ],
58
+ "linear_conv_kernel_dim": 4,
59
+ "linear_key_head_dim": 128,
60
+ "linear_num_key_heads": 16,
61
+ "linear_num_value_heads": 32,
62
+ "linear_value_head_dim": 128,
63
+ "mamba_ssm_dtype": "float32",
64
+ "max_position_embeddings": 262144,
65
+ "mlp_only_layers": [],
66
+ "model_type": "qwen3_5_text",
67
+ "mtp_num_hidden_layers": 1,
68
+ "mtp_use_dedicated_embeddings": false,
69
+ "num_attention_heads": 16,
70
+ "num_hidden_layers": 32,
71
+ "num_key_value_heads": 4,
72
+ "pad_token_id": null,
73
+ "partial_rotary_factor": 0.25,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_parameters": {
76
+ "mrope_interleaved": true,
77
+ "mrope_section": [
78
+ 11,
79
+ 11,
80
+ 10
81
+ ],
82
+ "partial_rotary_factor": 0.25,
83
+ "rope_theta": 10000000,
84
+ "rope_type": "default"
85
+ },
86
+ "tie_word_embeddings": true,
87
+ "use_cache": false,
88
+ "vocab_size": 248320
89
+ },
90
+ "tie_word_embeddings": true,
91
+ "transformers_version": "5.8.0",
92
+ "use_cache": false,
93
+ "video_token_id": 248057,
94
+ "vision_config": {
95
+ "deepstack_visual_indexes": [],
96
+ "depth": 24,
97
+ "dtype": "bfloat16",
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 1024,
100
+ "in_channels": 3,
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 4096,
103
+ "model_type": "qwen3_5_vision",
104
+ "num_heads": 16,
105
+ "num_position_embeddings": 2304,
106
+ "out_hidden_size": 2560,
107
+ "patch_size": 16,
108
+ "spatial_merge_size": 2,
109
+ "temporal_patch_size": 2
110
+ },
111
+ "vision_end_token_id": 248054,
112
+ "vision_start_token_id": 248053
113
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248044
6
+ ],
7
+ "pad_token_id": 248044,
8
+ "transformers_version": "5.8.0",
9
+ "use_cache": true
10
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbf490dd24f3680665a313e0fa7c7c9855de87f90eddf675826c1d2a60c983e
3
+ size 9078620536
designcoder_qwen3.5_4b_muon_bs32_step1900/processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "padding_side": "right",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 4.673658376419279e+19,
4
+ "train_loss": 0.35662912569547955,
5
+ "train_runtime": 27630.2175,
6
+ "train_samples_per_second": 2.2,
7
+ "train_steps_per_second": 0.069
8
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/trainer_log.jsonl ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1900, "loss": 0.5649280548095703, "lr": 4.7368421052631585e-07, "epoch": 0.010526315789473684, "percentage": 0.53, "elapsed_time": "0:05:47", "remaining_time": "18:14:02"}
2
+ {"current_steps": 20, "total_steps": 1900, "loss": 0.5708909034729004, "lr": 1.0000000000000002e-06, "epoch": 0.021052631578947368, "percentage": 1.05, "elapsed_time": "0:08:08", "remaining_time": "12:45:21"}
3
+ {"current_steps": 30, "total_steps": 1900, "loss": 0.5748211860656738, "lr": 1.5263157894736844e-06, "epoch": 0.031578947368421054, "percentage": 1.58, "elapsed_time": "0:10:27", "remaining_time": "10:51:49"}
4
+ {"current_steps": 40, "total_steps": 1900, "loss": 0.557589054107666, "lr": 2.0526315789473687e-06, "epoch": 0.042105263157894736, "percentage": 2.11, "elapsed_time": "0:12:47", "remaining_time": "9:55:08"}
5
+ {"current_steps": 50, "total_steps": 1900, "loss": 0.5640667915344239, "lr": 2.578947368421053e-06, "epoch": 0.05263157894736842, "percentage": 2.63, "elapsed_time": "0:15:07", "remaining_time": "9:19:53"}
6
+ {"current_steps": 60, "total_steps": 1900, "loss": 0.5634438514709472, "lr": 3.1052631578947372e-06, "epoch": 0.06315789473684211, "percentage": 3.16, "elapsed_time": "0:17:30", "remaining_time": "8:56:42"}
7
+ {"current_steps": 70, "total_steps": 1900, "loss": 0.5504179000854492, "lr": 3.6315789473684217e-06, "epoch": 0.07368421052631578, "percentage": 3.68, "elapsed_time": "0:19:52", "remaining_time": "8:39:22"}
8
+ {"current_steps": 80, "total_steps": 1900, "loss": 0.5407459735870361, "lr": 4.157894736842106e-06, "epoch": 0.08421052631578947, "percentage": 4.21, "elapsed_time": "0:22:16", "remaining_time": "8:26:52"}
9
+ {"current_steps": 90, "total_steps": 1900, "loss": 0.5427546977996827, "lr": 4.68421052631579e-06, "epoch": 0.09473684210526316, "percentage": 4.74, "elapsed_time": "0:24:39", "remaining_time": "8:16:00"}
10
+ {"current_steps": 100, "total_steps": 1900, "loss": 0.5267032146453857, "lr": 5.210526315789474e-06, "epoch": 0.10526315789473684, "percentage": 5.26, "elapsed_time": "0:27:01", "remaining_time": "8:06:21"}
11
+ {"current_steps": 110, "total_steps": 1900, "loss": 0.5212538719177247, "lr": 5.736842105263158e-06, "epoch": 0.11578947368421053, "percentage": 5.79, "elapsed_time": "0:29:22", "remaining_time": "7:58:06"}
12
+ {"current_steps": 120, "total_steps": 1900, "loss": 0.5108362197875976, "lr": 6.263157894736842e-06, "epoch": 0.12631578947368421, "percentage": 6.32, "elapsed_time": "0:31:45", "remaining_time": "7:51:09"}
13
+ {"current_steps": 130, "total_steps": 1900, "loss": 0.49319658279418943, "lr": 6.789473684210527e-06, "epoch": 0.1368421052631579, "percentage": 6.84, "elapsed_time": "0:34:06", "remaining_time": "7:44:20"}
14
+ {"current_steps": 140, "total_steps": 1900, "loss": 0.48811187744140627, "lr": 7.315789473684212e-06, "epoch": 0.14736842105263157, "percentage": 7.37, "elapsed_time": "0:36:26", "remaining_time": "7:38:07"}
15
+ {"current_steps": 150, "total_steps": 1900, "loss": 0.47876510620117185, "lr": 7.842105263157895e-06, "epoch": 0.15789473684210525, "percentage": 7.89, "elapsed_time": "0:38:47", "remaining_time": "7:32:30"}
16
+ {"current_steps": 160, "total_steps": 1900, "loss": 0.47615752220153806, "lr": 8.36842105263158e-06, "epoch": 0.16842105263157894, "percentage": 8.42, "elapsed_time": "0:41:07", "remaining_time": "7:27:14"}
17
+ {"current_steps": 170, "total_steps": 1900, "loss": 0.4617812156677246, "lr": 8.894736842105264e-06, "epoch": 0.17894736842105263, "percentage": 8.95, "elapsed_time": "0:43:29", "remaining_time": "7:22:31"}
18
+ {"current_steps": 180, "total_steps": 1900, "loss": 0.462778377532959, "lr": 9.421052631578949e-06, "epoch": 0.18947368421052632, "percentage": 9.47, "elapsed_time": "0:45:52", "remaining_time": "7:18:20"}
19
+ {"current_steps": 190, "total_steps": 1900, "loss": 0.44389495849609373, "lr": 9.947368421052632e-06, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:48:15", "remaining_time": "7:14:15"}
20
+ {"current_steps": 200, "total_steps": 1900, "loss": 0.42847065925598143, "lr": 9.999316524962347e-06, "epoch": 0.21052631578947367, "percentage": 10.53, "elapsed_time": "0:50:37", "remaining_time": "7:10:20"}
21
+ {"current_steps": 210, "total_steps": 1900, "loss": 0.433226203918457, "lr": 9.99695413509548e-06, "epoch": 0.22105263157894736, "percentage": 11.05, "elapsed_time": "0:52:56", "remaining_time": "7:06:03"}
22
+ {"current_steps": 220, "total_steps": 1900, "loss": 0.4245753288269043, "lr": 9.992905189592214e-06, "epoch": 0.23157894736842105, "percentage": 11.58, "elapsed_time": "0:55:18", "remaining_time": "7:02:19"}
23
+ {"current_steps": 230, "total_steps": 1900, "loss": 0.42034215927124025, "lr": 9.987171055039409e-06, "epoch": 0.24210526315789474, "percentage": 12.11, "elapsed_time": "0:57:40", "remaining_time": "6:58:46"}
24
+ {"current_steps": 240, "total_steps": 1900, "loss": 0.41213269233703614, "lr": 9.979753666803427e-06, "epoch": 0.25263157894736843, "percentage": 12.63, "elapsed_time": "1:00:02", "remaining_time": "6:55:16"}
25
+ {"current_steps": 250, "total_steps": 1900, "loss": 0.40923295021057127, "lr": 9.970655528376914e-06, "epoch": 0.2631578947368421, "percentage": 13.16, "elapsed_time": "1:02:23", "remaining_time": "6:51:46"}
26
+ {"current_steps": 260, "total_steps": 1900, "loss": 0.4008836269378662, "lr": 9.959879710533835e-06, "epoch": 0.2736842105263158, "percentage": 13.68, "elapsed_time": "1:04:42", "remaining_time": "6:48:11"}
27
+ {"current_steps": 270, "total_steps": 1900, "loss": 0.3953698635101318, "lr": 9.947429850293025e-06, "epoch": 0.28421052631578947, "percentage": 14.21, "elapsed_time": "1:07:03", "remaining_time": "6:44:48"}
28
+ {"current_steps": 280, "total_steps": 1900, "loss": 0.3896397352218628, "lr": 9.933310149690643e-06, "epoch": 0.29473684210526313, "percentage": 14.74, "elapsed_time": "1:09:25", "remaining_time": "6:41:39"}
29
+ {"current_steps": 290, "total_steps": 1900, "loss": 0.3975999355316162, "lr": 9.917525374361913e-06, "epoch": 0.30526315789473685, "percentage": 15.26, "elapsed_time": "1:11:46", "remaining_time": "6:38:26"}
30
+ {"current_steps": 300, "total_steps": 1900, "loss": 0.38664898872375486, "lr": 9.90008085193264e-06, "epoch": 0.3157894736842105, "percentage": 15.79, "elapsed_time": "1:14:09", "remaining_time": "6:35:31"}
31
+ {"current_steps": 310, "total_steps": 1900, "loss": 0.3833960771560669, "lr": 9.880982470221052e-06, "epoch": 0.3263157894736842, "percentage": 16.32, "elapsed_time": "1:16:33", "remaining_time": "6:32:37"}
32
+ {"current_steps": 320, "total_steps": 1900, "loss": 0.3799261569976807, "lr": 9.860236675250553e-06, "epoch": 0.3368421052631579, "percentage": 16.84, "elapsed_time": "1:18:56", "remaining_time": "6:29:45"}
33
+ {"current_steps": 330, "total_steps": 1900, "loss": 0.38280887603759767, "lr": 9.837850469074094e-06, "epoch": 0.3473684210526316, "percentage": 17.37, "elapsed_time": "1:21:18", "remaining_time": "6:26:48"}
34
+ {"current_steps": 340, "total_steps": 1900, "loss": 0.381818962097168, "lr": 9.813831407410856e-06, "epoch": 0.35789473684210527, "percentage": 17.89, "elapsed_time": "1:23:41", "remaining_time": "6:23:59"}
35
+ {"current_steps": 350, "total_steps": 1900, "loss": 0.3756396770477295, "lr": 9.78818759709607e-06, "epoch": 0.3684210526315789, "percentage": 18.42, "elapsed_time": "1:26:03", "remaining_time": "6:21:05"}
36
+ {"current_steps": 360, "total_steps": 1900, "loss": 0.3703409194946289, "lr": 9.760927693344823e-06, "epoch": 0.37894736842105264, "percentage": 18.95, "elapsed_time": "1:28:26", "remaining_time": "6:18:18"}
37
+ {"current_steps": 370, "total_steps": 1900, "loss": 0.3752593517303467, "lr": 9.732060896830782e-06, "epoch": 0.3894736842105263, "percentage": 19.47, "elapsed_time": "1:30:46", "remaining_time": "6:15:21"}
38
+ {"current_steps": 380, "total_steps": 1900, "loss": 0.36957530975341796, "lr": 9.701596950580807e-06, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "1:33:10", "remaining_time": "6:12:41"}
39
+ {"current_steps": 390, "total_steps": 1900, "loss": 0.370784592628479, "lr": 9.669546136686524e-06, "epoch": 0.4105263157894737, "percentage": 20.53, "elapsed_time": "1:35:31", "remaining_time": "6:09:51"}
40
+ {"current_steps": 400, "total_steps": 1900, "loss": 0.36154358386993407, "lr": 9.635919272833938e-06, "epoch": 0.42105263157894735, "percentage": 21.05, "elapsed_time": "1:37:54", "remaining_time": "6:07:10"}
41
+ {"current_steps": 410, "total_steps": 1900, "loss": 0.36916418075561525, "lr": 9.60072770865229e-06, "epoch": 0.43157894736842106, "percentage": 21.58, "elapsed_time": "1:41:58", "remaining_time": "6:10:33"}
42
+ {"current_steps": 420, "total_steps": 1900, "loss": 0.3586670160293579, "lr": 9.563983321883364e-06, "epoch": 0.4421052631578947, "percentage": 22.11, "elapsed_time": "1:44:17", "remaining_time": "6:07:31"}
43
+ {"current_steps": 430, "total_steps": 1900, "loss": 0.36408448219299316, "lr": 9.525698514372552e-06, "epoch": 0.45263157894736844, "percentage": 22.63, "elapsed_time": "1:46:43", "remaining_time": "6:04:51"}
44
+ {"current_steps": 440, "total_steps": 1900, "loss": 0.3616478681564331, "lr": 9.485886207883022e-06, "epoch": 0.4631578947368421, "percentage": 23.16, "elapsed_time": "1:49:05", "remaining_time": "6:02:00"}
45
+ {"current_steps": 450, "total_steps": 1900, "loss": 0.3540584325790405, "lr": 9.444559839734409e-06, "epoch": 0.47368421052631576, "percentage": 23.68, "elapsed_time": "1:51:25", "remaining_time": "5:59:03"}
46
+ {"current_steps": 460, "total_steps": 1900, "loss": 0.3628517150878906, "lr": 9.401733358267488e-06, "epoch": 0.4842105263157895, "percentage": 24.21, "elapsed_time": "1:53:48", "remaining_time": "5:56:16"}
47
+ {"current_steps": 470, "total_steps": 1900, "loss": 0.3611913204193115, "lr": 9.357421218136387e-06, "epoch": 0.49473684210526314, "percentage": 24.74, "elapsed_time": "1:56:11", "remaining_time": "5:53:30"}
48
+ {"current_steps": 480, "total_steps": 1900, "loss": 0.3575719118118286, "lr": 9.311638375429893e-06, "epoch": 0.5052631578947369, "percentage": 25.26, "elapsed_time": "1:58:34", "remaining_time": "5:50:46"}
49
+ {"current_steps": 490, "total_steps": 1900, "loss": 0.35195198059082033, "lr": 9.264400282623516e-06, "epoch": 0.5157894736842106, "percentage": 25.79, "elapsed_time": "2:00:57", "remaining_time": "5:48:03"}
50
+ {"current_steps": 500, "total_steps": 1900, "loss": 0.3550046682357788, "lr": 9.215722883364033e-06, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "2:03:20", "remaining_time": "5:45:20"}
51
+ {"current_steps": 510, "total_steps": 1900, "loss": 0.35266599655151365, "lr": 9.16562260708823e-06, "epoch": 0.5368421052631579, "percentage": 26.84, "elapsed_time": "2:05:41", "remaining_time": "5:42:34"}
52
+ {"current_steps": 520, "total_steps": 1900, "loss": 0.35182890892028806, "lr": 9.114116363477694e-06, "epoch": 0.5473684210526316, "percentage": 27.37, "elapsed_time": "2:08:01", "remaining_time": "5:39:44"}
53
+ {"current_steps": 530, "total_steps": 1900, "loss": 0.3465148448944092, "lr": 9.061221536751517e-06, "epoch": 0.5578947368421052, "percentage": 27.89, "elapsed_time": "2:10:24", "remaining_time": "5:37:04"}
54
+ {"current_steps": 540, "total_steps": 1900, "loss": 0.3488567352294922, "lr": 9.006955979798828e-06, "epoch": 0.5684210526315789, "percentage": 28.42, "elapsed_time": "2:12:44", "remaining_time": "5:34:18"}
55
+ {"current_steps": 550, "total_steps": 1900, "loss": 0.34726202487945557, "lr": 8.95133800815314e-06, "epoch": 0.5789473684210527, "percentage": 28.95, "elapsed_time": "2:15:03", "remaining_time": "5:31:31"}
56
+ {"current_steps": 560, "total_steps": 1900, "loss": 0.3462839603424072, "lr": 8.894386393810563e-06, "epoch": 0.5894736842105263, "percentage": 29.47, "elapsed_time": "2:17:26", "remaining_time": "5:28:52"}
57
+ {"current_steps": 570, "total_steps": 1900, "loss": 0.3476074695587158, "lr": 8.836120358893926e-06, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "2:19:48", "remaining_time": "5:26:13"}
58
+ {"current_steps": 580, "total_steps": 1900, "loss": 0.34909305572509763, "lr": 8.776559569165001e-06, "epoch": 0.6105263157894737, "percentage": 30.53, "elapsed_time": "2:22:09", "remaining_time": "5:23:31"}
59
+ {"current_steps": 590, "total_steps": 1900, "loss": 0.3453603029251099, "lr": 8.715724127386971e-06, "epoch": 0.6210526315789474, "percentage": 31.05, "elapsed_time": "2:24:29", "remaining_time": "5:20:49"}
60
+ {"current_steps": 600, "total_steps": 1900, "loss": 0.34458560943603517, "lr": 8.653634566539421e-06, "epoch": 0.631578947368421, "percentage": 31.58, "elapsed_time": "2:26:49", "remaining_time": "5:18:06"}
61
+ {"current_steps": 610, "total_steps": 1900, "loss": 0.34335694313049314, "lr": 8.590311842888101e-06, "epoch": 0.6421052631578947, "percentage": 32.11, "elapsed_time": "2:29:10", "remaining_time": "5:15:28"}
62
+ {"current_steps": 620, "total_steps": 1900, "loss": 0.3478172063827515, "lr": 8.525777328911846e-06, "epoch": 0.6526315789473685, "percentage": 32.63, "elapsed_time": "2:31:34", "remaining_time": "5:12:55"}
63
+ {"current_steps": 630, "total_steps": 1900, "loss": 0.3395395040512085, "lr": 8.460052806089e-06, "epoch": 0.6631578947368421, "percentage": 33.16, "elapsed_time": "2:33:55", "remaining_time": "5:10:18"}
64
+ {"current_steps": 640, "total_steps": 1900, "loss": 0.343241024017334, "lr": 8.39316045754581e-06, "epoch": 0.6736842105263158, "percentage": 33.68, "elapsed_time": "2:36:18", "remaining_time": "5:07:43"}
65
+ {"current_steps": 650, "total_steps": 1900, "loss": 0.3414290904998779, "lr": 8.325122860569241e-06, "epoch": 0.6842105263157895, "percentage": 34.21, "elapsed_time": "2:38:41", "remaining_time": "5:05:10"}
66
+ {"current_steps": 660, "total_steps": 1900, "loss": 0.3469081401824951, "lr": 8.255962978986772e-06, "epoch": 0.6947368421052632, "percentage": 34.74, "elapsed_time": "2:41:00", "remaining_time": "5:02:30"}
67
+ {"current_steps": 670, "total_steps": 1900, "loss": 0.34221587181091306, "lr": 8.18570415541571e-06, "epoch": 0.7052631578947368, "percentage": 35.26, "elapsed_time": "2:43:26", "remaining_time": "5:00:02"}
68
+ {"current_steps": 680, "total_steps": 1900, "loss": 0.33984344005584716, "lr": 8.11437010338468e-06, "epoch": 0.7157894736842105, "percentage": 35.79, "elapsed_time": "2:45:46", "remaining_time": "4:57:24"}
69
+ {"current_steps": 690, "total_steps": 1900, "loss": 0.34598817825317385, "lr": 8.041984899329898e-06, "epoch": 0.7263157894736842, "percentage": 36.32, "elapsed_time": "2:48:07", "remaining_time": "4:54:49"}
70
+ {"current_steps": 700, "total_steps": 1900, "loss": 0.34098362922668457, "lr": 7.968572974468982e-06, "epoch": 0.7368421052631579, "percentage": 36.84, "elapsed_time": "2:50:28", "remaining_time": "4:52:14"}
71
+ {"current_steps": 710, "total_steps": 1900, "loss": 0.3334647655487061, "lr": 7.894159106554997e-06, "epoch": 0.7473684210526316, "percentage": 37.37, "elapsed_time": "2:52:51", "remaining_time": "4:49:42"}
72
+ {"current_steps": 720, "total_steps": 1900, "loss": 0.33434553146362306, "lr": 7.81876841151356e-06, "epoch": 0.7578947368421053, "percentage": 37.89, "elapsed_time": "2:55:13", "remaining_time": "4:47:10"}
73
+ {"current_steps": 730, "total_steps": 1900, "loss": 0.33247191905975343, "lr": 7.742426334965788e-06, "epoch": 0.7684210526315789, "percentage": 38.42, "elapsed_time": "2:57:36", "remaining_time": "4:44:39"}
74
+ {"current_steps": 740, "total_steps": 1900, "loss": 0.33722877502441406, "lr": 7.66515864363997e-06, "epoch": 0.7789473684210526, "percentage": 38.95, "elapsed_time": "2:59:57", "remaining_time": "4:42:05"}
75
+ {"current_steps": 750, "total_steps": 1900, "loss": 0.34308178424835206, "lr": 7.58699141667488e-06, "epoch": 0.7894736842105263, "percentage": 39.47, "elapsed_time": "3:02:21", "remaining_time": "4:39:37"}
76
+ {"current_steps": 760, "total_steps": 1900, "loss": 0.3383188247680664, "lr": 7.507951036817618e-06, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "3:04:45", "remaining_time": "4:37:08"}
77
+ {"current_steps": 770, "total_steps": 1900, "loss": 0.34044275283813474, "lr": 7.428064181518997e-06, "epoch": 0.8105263157894737, "percentage": 40.53, "elapsed_time": "3:07:07", "remaining_time": "4:34:36"}
78
+ {"current_steps": 780, "total_steps": 1900, "loss": 0.33629164695739744, "lr": 7.347357813929455e-06, "epoch": 0.8210526315789474, "percentage": 41.05, "elapsed_time": "3:09:30", "remaining_time": "4:32:07"}
79
+ {"current_steps": 790, "total_steps": 1900, "loss": 0.3386510372161865, "lr": 7.2658591737985405e-06, "epoch": 0.8315789473684211, "percentage": 41.58, "elapsed_time": "3:11:52", "remaining_time": "4:29:35"}
80
+ {"current_steps": 800, "total_steps": 1900, "loss": 0.33289337158203125, "lr": 7.183595768281044e-06, "epoch": 0.8421052631578947, "percentage": 42.11, "elapsed_time": "3:14:16", "remaining_time": "4:27:08"}
81
+ {"current_steps": 810, "total_steps": 1900, "loss": 0.3377974510192871, "lr": 7.100595362652872e-06, "epoch": 0.8526315789473684, "percentage": 42.63, "elapsed_time": "3:18:20", "remaining_time": "4:26:54"}
82
+ {"current_steps": 820, "total_steps": 1900, "loss": 0.3373216390609741, "lr": 7.016885970939798e-06, "epoch": 0.8631578947368421, "percentage": 43.16, "elapsed_time": "3:20:40", "remaining_time": "4:24:17"}
83
+ {"current_steps": 830, "total_steps": 1900, "loss": 0.33392086029052737, "lr": 6.932495846462262e-06, "epoch": 0.8736842105263158, "percentage": 43.68, "elapsed_time": "3:23:03", "remaining_time": "4:21:46"}
84
+ {"current_steps": 840, "total_steps": 1900, "loss": 0.3390925168991089, "lr": 6.847453472299408e-06, "epoch": 0.8842105263157894, "percentage": 44.21, "elapsed_time": "3:25:24", "remaining_time": "4:19:12"}
85
+ {"current_steps": 850, "total_steps": 1900, "loss": 0.3334352016448975, "lr": 6.761787551675559e-06, "epoch": 0.8947368421052632, "percentage": 44.74, "elapsed_time": "3:27:46", "remaining_time": "4:16:39"}
86
+ {"current_steps": 860, "total_steps": 1900, "loss": 0.33690924644470216, "lr": 6.675526998272405e-06, "epoch": 0.9052631578947369, "percentage": 45.26, "elapsed_time": "3:30:10", "remaining_time": "4:14:10"}
87
+ {"current_steps": 870, "total_steps": 1900, "loss": 0.3396608352661133, "lr": 6.588700926470145e-06, "epoch": 0.9157894736842105, "percentage": 45.79, "elapsed_time": "3:32:32", "remaining_time": "4:11:37"}
88
+ {"current_steps": 880, "total_steps": 1900, "loss": 0.3291656017303467, "lr": 6.501338641520906e-06, "epoch": 0.9263157894736842, "percentage": 46.32, "elapsed_time": "3:34:53", "remaining_time": "4:09:05"}
89
+ {"current_steps": 890, "total_steps": 1900, "loss": 0.33728480339050293, "lr": 6.413469629657724e-06, "epoch": 0.9368421052631579, "percentage": 46.84, "elapsed_time": "3:37:17", "remaining_time": "4:06:34"}
90
+ {"current_steps": 900, "total_steps": 1900, "loss": 0.333527660369873, "lr": 6.325123548142442e-06, "epoch": 0.9473684210526315, "percentage": 47.37, "elapsed_time": "3:39:37", "remaining_time": "4:04:01"}
91
+ {"current_steps": 910, "total_steps": 1900, "loss": 0.32869296073913573, "lr": 6.2363302152559004e-06, "epoch": 0.9578947368421052, "percentage": 47.89, "elapsed_time": "3:41:57", "remaining_time": "4:01:27"}
92
+ {"current_steps": 920, "total_steps": 1900, "loss": 0.33417134284973143, "lr": 6.147119600233758e-06, "epoch": 0.968421052631579, "percentage": 48.42, "elapsed_time": "3:44:18", "remaining_time": "3:58:56"}
93
+ {"current_steps": 930, "total_steps": 1900, "loss": 0.33371286392211913, "lr": 6.0575218131513795e-06, "epoch": 0.9789473684210527, "percentage": 48.95, "elapsed_time": "3:46:41", "remaining_time": "3:56:26"}
94
+ {"current_steps": 940, "total_steps": 1900, "loss": 0.33172919750213625, "lr": 5.967567094761173e-06, "epoch": 0.9894736842105263, "percentage": 49.47, "elapsed_time": "3:49:00", "remaining_time": "3:53:52"}
95
+ {"current_steps": 950, "total_steps": 1900, "loss": 0.3245907545089722, "lr": 5.8772858062858414e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "3:51:22", "remaining_time": "3:51:22"}
96
+ {"current_steps": 960, "total_steps": 1900, "loss": 0.3322077751159668, "lr": 5.786708419170955e-06, "epoch": 1.0105263157894737, "percentage": 50.53, "elapsed_time": "3:53:44", "remaining_time": "3:48:52"}
97
+ {"current_steps": 970, "total_steps": 1900, "loss": 0.32666444778442383, "lr": 5.695865504800328e-06, "epoch": 1.0210526315789474, "percentage": 51.05, "elapsed_time": "3:56:05", "remaining_time": "3:46:21"}
98
+ {"current_steps": 980, "total_steps": 1900, "loss": 0.3285836219787598, "lr": 5.604787724177666e-06, "epoch": 1.0315789473684212, "percentage": 51.58, "elapsed_time": "3:58:28", "remaining_time": "3:43:52"}
99
+ {"current_steps": 990, "total_steps": 1900, "loss": 0.32537705898284913, "lr": 5.513505817577966e-06, "epoch": 1.0421052631578946, "percentage": 52.11, "elapsed_time": "4:00:53", "remaining_time": "3:41:25"}
100
+ {"current_steps": 1000, "total_steps": 1900, "loss": 0.3251340389251709, "lr": 5.422050594172161e-06, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "4:03:14", "remaining_time": "3:38:55"}
101
+ {"current_steps": 1010, "total_steps": 1900, "loss": 0.3211204051971436, "lr": 5.3304529216284974e-06, "epoch": 1.063157894736842, "percentage": 53.16, "elapsed_time": "4:05:34", "remaining_time": "3:36:23"}
102
+ {"current_steps": 1020, "total_steps": 1900, "loss": 0.3239119052886963, "lr": 5.2387437156942e-06, "epoch": 1.0736842105263158, "percentage": 53.68, "elapsed_time": "4:07:58", "remaining_time": "3:33:56"}
103
+ {"current_steps": 1030, "total_steps": 1900, "loss": 0.3276015281677246, "lr": 5.146953929760873e-06, "epoch": 1.0842105263157895, "percentage": 54.21, "elapsed_time": "4:10:20", "remaining_time": "3:31:26"}
104
+ {"current_steps": 1040, "total_steps": 1900, "loss": 0.3195406436920166, "lr": 5.055114544417219e-06, "epoch": 1.0947368421052632, "percentage": 54.74, "elapsed_time": "4:12:43", "remaining_time": "3:28:59"}
105
+ {"current_steps": 1050, "total_steps": 1900, "loss": 0.3270190477371216, "lr": 4.963256556992573e-06, "epoch": 1.1052631578947367, "percentage": 55.26, "elapsed_time": "4:15:04", "remaining_time": "3:26:29"}
106
+ {"current_steps": 1060, "total_steps": 1900, "loss": 0.3211397171020508, "lr": 4.871410971094783e-06, "epoch": 1.1157894736842104, "percentage": 55.79, "elapsed_time": "4:17:26", "remaining_time": "3:24:00"}
107
+ {"current_steps": 1070, "total_steps": 1900, "loss": 0.3231573343276978, "lr": 4.779608786145974e-06, "epoch": 1.1263157894736842, "percentage": 56.32, "elapsed_time": "4:19:50", "remaining_time": "3:21:33"}
108
+ {"current_steps": 1080, "total_steps": 1900, "loss": 0.32362775802612304, "lr": 4.687880986919725e-06, "epoch": 1.1368421052631579, "percentage": 56.84, "elapsed_time": "4:22:10", "remaining_time": "3:19:03"}
109
+ {"current_steps": 1090, "total_steps": 1900, "loss": 0.3258507251739502, "lr": 4.596258533083189e-06, "epoch": 1.1473684210526316, "percentage": 57.37, "elapsed_time": "4:24:31", "remaining_time": "3:16:34"}
110
+ {"current_steps": 1100, "total_steps": 1900, "loss": 0.3234171628952026, "lr": 4.504772348747687e-06, "epoch": 1.1578947368421053, "percentage": 57.89, "elapsed_time": "4:26:52", "remaining_time": "3:14:05"}
111
+ {"current_steps": 1110, "total_steps": 1900, "loss": 0.32814559936523435, "lr": 4.4134533120313015e-06, "epoch": 1.168421052631579, "percentage": 58.42, "elapsed_time": "4:29:15", "remaining_time": "3:11:37"}
112
+ {"current_steps": 1120, "total_steps": 1900, "loss": 0.32781333923339845, "lr": 4.322332244637e-06, "epoch": 1.1789473684210527, "percentage": 58.95, "elapsed_time": "4:31:34", "remaining_time": "3:09:07"}
113
+ {"current_steps": 1130, "total_steps": 1900, "loss": 0.32119724750518797, "lr": 4.231439901449788e-06, "epoch": 1.1894736842105262, "percentage": 59.47, "elapsed_time": "4:33:54", "remaining_time": "3:06:38"}
114
+ {"current_steps": 1140, "total_steps": 1900, "loss": 0.3235795497894287, "lr": 4.140806960156426e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "4:36:14", "remaining_time": "3:04:09"}
115
+ {"current_steps": 1150, "total_steps": 1900, "loss": 0.32244420051574707, "lr": 4.050464010891191e-06, "epoch": 1.2105263157894737, "percentage": 60.53, "elapsed_time": "4:38:35", "remaining_time": "3:01:41"}
116
+ {"current_steps": 1160, "total_steps": 1900, "loss": 0.32084407806396487, "lr": 3.960441545911205e-06, "epoch": 1.2210526315789474, "percentage": 61.05, "elapsed_time": "4:40:58", "remaining_time": "2:59:14"}
117
+ {"current_steps": 1170, "total_steps": 1900, "loss": 0.32793939113616943, "lr": 3.870769949304771e-06, "epoch": 1.231578947368421, "percentage": 61.58, "elapsed_time": "4:43:19", "remaining_time": "2:56:46"}
118
+ {"current_steps": 1180, "total_steps": 1900, "loss": 0.32079472541809084, "lr": 3.7814794867362563e-06, "epoch": 1.2421052631578948, "percentage": 62.11, "elapsed_time": "4:45:42", "remaining_time": "2:54:19"}
119
+ {"current_steps": 1190, "total_steps": 1900, "loss": 0.32700533866882325, "lr": 3.6926002952309015e-06, "epoch": 1.2526315789473683, "percentage": 62.63, "elapsed_time": "4:48:02", "remaining_time": "2:51:51"}
120
+ {"current_steps": 1200, "total_steps": 1900, "loss": 0.323567795753479, "lr": 3.6041623730030908e-06, "epoch": 1.263157894736842, "percentage": 63.16, "elapsed_time": "4:50:23", "remaining_time": "2:49:23"}
121
+ {"current_steps": 1210, "total_steps": 1900, "loss": 0.3220393419265747, "lr": 3.5161955693314353e-06, "epoch": 1.2736842105263158, "percentage": 63.68, "elapsed_time": "4:54:20", "remaining_time": "2:47:50"}
122
+ {"current_steps": 1220, "total_steps": 1900, "loss": 0.32195496559143066, "lr": 3.4287295744841588e-06, "epoch": 1.2842105263157895, "percentage": 64.21, "elapsed_time": "4:56:43", "remaining_time": "2:45:23"}
123
+ {"current_steps": 1230, "total_steps": 1900, "loss": 0.32832560539245603, "lr": 3.3417939096981154e-06, "epoch": 1.2947368421052632, "percentage": 64.74, "elapsed_time": "4:59:03", "remaining_time": "2:42:54"}
124
+ {"current_steps": 1240, "total_steps": 1900, "loss": 0.32657656669616697, "lr": 3.2554179172149027e-06, "epoch": 1.305263157894737, "percentage": 65.26, "elapsed_time": "5:01:25", "remaining_time": "2:40:25"}
125
+ {"current_steps": 1250, "total_steps": 1900, "loss": 0.32687838077545167, "lr": 3.169630750377337e-06, "epoch": 1.3157894736842106, "percentage": 65.79, "elapsed_time": "5:03:49", "remaining_time": "2:37:59"}
126
+ {"current_steps": 1260, "total_steps": 1900, "loss": 0.3185723781585693, "lr": 3.084461363789739e-06, "epoch": 1.3263157894736843, "percentage": 66.32, "elapsed_time": "5:06:09", "remaining_time": "2:35:30"}
127
+ {"current_steps": 1270, "total_steps": 1900, "loss": 0.321709418296814, "lr": 2.9999385035452477e-06, "epoch": 1.3368421052631578, "percentage": 66.84, "elapsed_time": "5:08:33", "remaining_time": "2:33:03"}
128
+ {"current_steps": 1280, "total_steps": 1900, "loss": 0.3230076551437378, "lr": 2.9160906975235493e-06, "epoch": 1.3473684210526315, "percentage": 67.37, "elapsed_time": "5:10:54", "remaining_time": "2:30:35"}
129
+ {"current_steps": 1290, "total_steps": 1900, "loss": 0.3239234209060669, "lr": 2.8329462457622263e-06, "epoch": 1.3578947368421053, "percentage": 67.89, "elapsed_time": "5:13:15", "remaining_time": "2:28:07"}
130
+ {"current_steps": 1300, "total_steps": 1900, "loss": 0.3209430694580078, "lr": 2.750533210905042e-06, "epoch": 1.368421052631579, "percentage": 68.42, "elapsed_time": "5:15:37", "remaining_time": "2:25:40"}
131
+ {"current_steps": 1310, "total_steps": 1900, "loss": 0.32194013595581056, "lr": 2.6688794087302993e-06, "epoch": 1.3789473684210527, "percentage": 68.95, "elapsed_time": "5:18:01", "remaining_time": "2:23:13"}
132
+ {"current_steps": 1320, "total_steps": 1900, "loss": 0.3310521125793457, "lr": 2.588012398762578e-06, "epoch": 1.3894736842105262, "percentage": 69.47, "elapsed_time": "5:20:22", "remaining_time": "2:20:46"}
133
+ {"current_steps": 1330, "total_steps": 1900, "loss": 0.32281064987182617, "lr": 2.507959474970918e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "5:22:45", "remaining_time": "2:18:19"}
134
+ {"current_steps": 1340, "total_steps": 1900, "loss": 0.32929823398590086, "lr": 2.4287476565566525e-06, "epoch": 1.4105263157894736, "percentage": 70.53, "elapsed_time": "5:25:06", "remaining_time": "2:15:52"}
135
+ {"current_steps": 1350, "total_steps": 1900, "loss": 0.32490930557250974, "lr": 2.3504036788339763e-06, "epoch": 1.4210526315789473, "percentage": 71.05, "elapsed_time": "5:27:30", "remaining_time": "2:13:25"}
136
+ {"current_steps": 1360, "total_steps": 1900, "loss": 0.31843137741088867, "lr": 2.2729539842063275e-06, "epoch": 1.431578947368421, "percentage": 71.58, "elapsed_time": "5:29:51", "remaining_time": "2:10:58"}
137
+ {"current_steps": 1370, "total_steps": 1900, "loss": 0.3216635465621948, "lr": 2.1964247132416373e-06, "epoch": 1.4421052631578948, "percentage": 72.11, "elapsed_time": "5:32:13", "remaining_time": "2:08:31"}
138
+ {"current_steps": 1380, "total_steps": 1900, "loss": 0.320039176940918, "lr": 2.1208416958494472e-06, "epoch": 1.4526315789473685, "percentage": 72.63, "elapsed_time": "5:34:36", "remaining_time": "2:06:05"}
139
+ {"current_steps": 1390, "total_steps": 1900, "loss": 0.3187244415283203, "lr": 2.0462304425628836e-06, "epoch": 1.4631578947368422, "percentage": 73.16, "elapsed_time": "5:36:58", "remaining_time": "2:03:38"}
140
+ {"current_steps": 1400, "total_steps": 1900, "loss": 0.3253413200378418, "lr": 1.9726161359284283e-06, "epoch": 1.4736842105263157, "percentage": 73.68, "elapsed_time": "5:39:20", "remaining_time": "2:01:11"}
141
+ {"current_steps": 1410, "total_steps": 1900, "loss": 0.3248704433441162, "lr": 1.900023622006385e-06, "epoch": 1.4842105263157894, "percentage": 74.21, "elapsed_time": "5:41:41", "remaining_time": "1:58:44"}
142
+ {"current_steps": 1420, "total_steps": 1900, "loss": 0.324160099029541, "lr": 1.8284774019849176e-06, "epoch": 1.4947368421052631, "percentage": 74.74, "elapsed_time": "5:44:00", "remaining_time": "1:56:17"}
143
+ {"current_steps": 1430, "total_steps": 1900, "loss": 0.3209646940231323, "lr": 1.7580016239104924e-06, "epoch": 1.5052631578947369, "percentage": 75.26, "elapsed_time": "5:46:21", "remaining_time": "1:53:50"}
144
+ {"current_steps": 1440, "total_steps": 1900, "loss": 0.32266716957092284, "lr": 1.688620074537506e-06, "epoch": 1.5157894736842106, "percentage": 75.79, "elapsed_time": "5:48:42", "remaining_time": "1:51:23"}
145
+ {"current_steps": 1450, "total_steps": 1900, "loss": 0.31873378753662107, "lr": 1.6203561712998561e-06, "epoch": 1.526315789473684, "percentage": 76.32, "elapsed_time": "5:51:06", "remaining_time": "1:48:57"}
146
+ {"current_steps": 1460, "total_steps": 1900, "loss": 0.32254483699798586, "lr": 1.5532329544071712e-06, "epoch": 1.5368421052631578, "percentage": 76.84, "elapsed_time": "5:53:28", "remaining_time": "1:46:31"}
147
+ {"current_steps": 1470, "total_steps": 1900, "loss": 0.31874861717224123, "lr": 1.4872730790683488e-06, "epoch": 1.5473684210526315, "percentage": 77.37, "elapsed_time": "5:55:50", "remaining_time": "1:44:05"}
148
+ {"current_steps": 1480, "total_steps": 1900, "loss": 0.3291239500045776, "lr": 1.4224988078450453e-06, "epoch": 1.5578947368421052, "percentage": 77.89, "elapsed_time": "5:58:12", "remaining_time": "1:41:39"}
149
+ {"current_steps": 1490, "total_steps": 1900, "loss": 0.3205441951751709, "lr": 1.35893200313769e-06, "epoch": 1.568421052631579, "percentage": 78.42, "elapsed_time": "6:00:33", "remaining_time": "1:39:12"}
150
+ {"current_steps": 1500, "total_steps": 1900, "loss": 0.32458648681640623, "lr": 1.2965941198065568e-06, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "6:02:58", "remaining_time": "1:36:47"}
151
+ {"current_steps": 1510, "total_steps": 1900, "loss": 0.32656116485595704, "lr": 1.2355061979303922e-06, "epoch": 1.5894736842105264, "percentage": 79.47, "elapsed_time": "6:05:21", "remaining_time": "1:34:21"}
152
+ {"current_steps": 1520, "total_steps": 1900, "loss": 0.32614789009094236, "lr": 1.1756888557050356e-06, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "6:07:43", "remaining_time": "1:31:55"}
153
+ {"current_steps": 1530, "total_steps": 1900, "loss": 0.32253460884094237, "lr": 1.1171622824844324e-06, "epoch": 1.6105263157894738, "percentage": 80.53, "elapsed_time": "6:10:05", "remaining_time": "1:29:30"}
154
+ {"current_steps": 1540, "total_steps": 1900, "loss": 0.3218738317489624, "lr": 1.0599462319663906e-06, "epoch": 1.6210526315789475, "percentage": 81.05, "elapsed_time": "6:12:28", "remaining_time": "1:27:04"}
155
+ {"current_steps": 1550, "total_steps": 1900, "loss": 0.3189677715301514, "lr": 1.0040600155253766e-06, "epoch": 1.631578947368421, "percentage": 81.58, "elapsed_time": "6:14:50", "remaining_time": "1:24:38"}
156
+ {"current_steps": 1560, "total_steps": 1900, "loss": 0.3237604141235352, "lr": 9.495224956946031e-07, "epoch": 1.6421052631578947, "percentage": 82.11, "elapsed_time": "6:17:11", "remaining_time": "1:22:12"}
157
+ {"current_steps": 1570, "total_steps": 1900, "loss": 0.3268871307373047, "lr": 8.963520797996078e-07, "epoch": 1.6526315789473685, "percentage": 82.63, "elapsed_time": "6:19:33", "remaining_time": "1:19:46"}
158
+ {"current_steps": 1580, "total_steps": 1900, "loss": 0.32371490001678466, "lr": 8.44566713745476e-07, "epoch": 1.663157894736842, "percentage": 83.16, "elapsed_time": "6:21:57", "remaining_time": "1:17:21"}
159
+ {"current_steps": 1590, "total_steps": 1900, "loss": 0.3219043016433716, "lr": 7.941838759597931e-07, "epoch": 1.6736842105263157, "percentage": 83.68, "elapsed_time": "6:24:19", "remaining_time": "1:14:55"}
160
+ {"current_steps": 1600, "total_steps": 1900, "loss": 0.3194981575012207, "lr": 7.452205714933864e-07, "epoch": 1.6842105263157894, "percentage": 84.21, "elapsed_time": "6:26:39", "remaining_time": "1:12:29"}
161
+ {"current_steps": 1610, "total_steps": 1900, "loss": 0.3213656425476074, "lr": 6.976933262808322e-07, "epoch": 1.694736842105263, "percentage": 84.74, "elapsed_time": "6:30:33", "remaining_time": "1:10:20"}
162
+ {"current_steps": 1620, "total_steps": 1900, "loss": 0.3243042230606079, "lr": 6.516181815626809e-07, "epoch": 1.7052631578947368, "percentage": 85.26, "elapsed_time": "6:32:55", "remaining_time": "1:07:54"}
163
+ {"current_steps": 1630, "total_steps": 1900, "loss": 0.32139909267425537, "lr": 6.070106884712668e-07, "epoch": 1.7157894736842105, "percentage": 85.79, "elapsed_time": "6:35:19", "remaining_time": "1:05:28"}
164
+ {"current_steps": 1640, "total_steps": 1900, "loss": 0.3254119873046875, "lr": 5.63885902781941e-07, "epoch": 1.7263157894736842, "percentage": 86.32, "elapsed_time": "6:37:40", "remaining_time": "1:03:02"}
165
+ {"current_steps": 1650, "total_steps": 1900, "loss": 0.3192205667495728, "lr": 5.222583798314962e-07, "epoch": 1.736842105263158, "percentage": 86.84, "elapsed_time": "6:40:00", "remaining_time": "1:00:36"}
166
+ {"current_steps": 1660, "total_steps": 1900, "loss": 0.3214584827423096, "lr": 4.821421696054957e-07, "epoch": 1.7473684210526317, "percentage": 87.37, "elapsed_time": "6:42:20", "remaining_time": "0:58:10"}
167
+ {"current_steps": 1670, "total_steps": 1900, "loss": 0.32129769325256347, "lr": 4.435508119961701e-07, "epoch": 1.7578947368421054, "percentage": 87.89, "elapsed_time": "6:44:42", "remaining_time": "0:55:44"}
168
+ {"current_steps": 1680, "total_steps": 1900, "loss": 0.32092599868774413, "lr": 4.06497332232475e-07, "epoch": 1.768421052631579, "percentage": 88.42, "elapsed_time": "6:47:03", "remaining_time": "0:53:18"}
169
+ {"current_steps": 1690, "total_steps": 1900, "loss": 0.32193360328674314, "lr": 3.709942364838598e-07, "epoch": 1.7789473684210526, "percentage": 88.95, "elapsed_time": "6:49:24", "remaining_time": "0:50:52"}
170
+ {"current_steps": 1700, "total_steps": 1900, "loss": 0.3206108570098877, "lr": 3.370535076392256e-07, "epoch": 1.7894736842105263, "percentage": 89.47, "elapsed_time": "6:51:45", "remaining_time": "0:48:26"}
171
+ {"current_steps": 1710, "total_steps": 1900, "loss": 0.3236824035644531, "lr": 3.046866012624999e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "6:54:09", "remaining_time": "0:46:01"}
172
+ {"current_steps": 1720, "total_steps": 1900, "loss": 0.32245032787322997, "lr": 2.73904441726191e-07, "epoch": 1.8105263157894735, "percentage": 90.53, "elapsed_time": "6:56:29", "remaining_time": "0:43:35"}
173
+ {"current_steps": 1730, "total_steps": 1900, "loss": 0.32442536354064944, "lr": 2.447174185242324e-07, "epoch": 1.8210526315789473, "percentage": 91.05, "elapsed_time": "6:58:51", "remaining_time": "0:41:09"}
174
+ {"current_steps": 1740, "total_steps": 1900, "loss": 0.33084514141082766, "lr": 2.1713538276535052e-07, "epoch": 1.831578947368421, "percentage": 91.58, "elapsed_time": "7:01:13", "remaining_time": "0:38:43"}
175
+ {"current_steps": 1750, "total_steps": 1900, "loss": 0.31865687370300294, "lr": 1.9116764384815467e-07, "epoch": 1.8421052631578947, "percentage": 92.11, "elapsed_time": "7:03:33", "remaining_time": "0:36:18"}
176
+ {"current_steps": 1760, "total_steps": 1900, "loss": 0.32346787452697756, "lr": 1.6682296631905626e-07, "epoch": 1.8526315789473684, "percentage": 92.63, "elapsed_time": "7:05:53", "remaining_time": "0:33:52"}
177
+ {"current_steps": 1770, "total_steps": 1900, "loss": 0.32239809036254885, "lr": 1.441095669140896e-07, "epoch": 1.8631578947368421, "percentage": 93.16, "elapsed_time": "7:08:14", "remaining_time": "0:31:27"}
178
+ {"current_steps": 1780, "total_steps": 1900, "loss": 0.3282062768936157, "lr": 1.2303511178562544e-07, "epoch": 1.8736842105263158, "percentage": 93.68, "elapsed_time": "7:10:36", "remaining_time": "0:29:01"}
179
+ {"current_steps": 1790, "total_steps": 1900, "loss": 0.32117500305175783, "lr": 1.0360671391491606e-07, "epoch": 1.8842105263157896, "percentage": 94.21, "elapsed_time": "7:12:57", "remaining_time": "0:26:36"}
180
+ {"current_steps": 1800, "total_steps": 1900, "loss": 0.3236595869064331, "lr": 8.583093071134473e-08, "epoch": 1.8947368421052633, "percentage": 94.74, "elapsed_time": "7:15:17", "remaining_time": "0:24:10"}
181
+ {"current_steps": 1810, "total_steps": 1900, "loss": 0.3243385076522827, "lr": 6.971376179919109e-08, "epoch": 1.905263157894737, "percentage": 95.26, "elapsed_time": "7:17:38", "remaining_time": "0:21:45"}
182
+ {"current_steps": 1820, "total_steps": 1900, "loss": 0.32702107429504396, "lr": 5.526064699265754e-08, "epoch": 1.9157894736842105, "percentage": 95.79, "elapsed_time": "7:19:59", "remaining_time": "0:19:20"}
183
+ {"current_steps": 1830, "total_steps": 1900, "loss": 0.32095746994018554, "lr": 4.247646445984077e-08, "epoch": 1.9263157894736842, "percentage": 96.32, "elapsed_time": "7:22:21", "remaining_time": "0:16:55"}
184
+ {"current_steps": 1840, "total_steps": 1900, "loss": 0.32458717823028566, "lr": 3.136552907626711e-08, "epoch": 1.936842105263158, "percentage": 96.84, "elapsed_time": "7:24:43", "remaining_time": "0:14:30"}
185
+ {"current_steps": 1850, "total_steps": 1900, "loss": 0.3225292682647705, "lr": 2.193159096855191e-08, "epoch": 1.9473684210526314, "percentage": 97.37, "elapsed_time": "7:27:03", "remaining_time": "0:12:04"}
186
+ {"current_steps": 1860, "total_steps": 1900, "loss": 0.3201985597610474, "lr": 1.4177834248668144e-08, "epoch": 1.9578947368421051, "percentage": 97.89, "elapsed_time": "7:29:25", "remaining_time": "0:09:39"}
187
+ {"current_steps": 1870, "total_steps": 1900, "loss": 0.32071843147277834, "lr": 8.106875939254966e-09, "epoch": 1.9684210526315788, "percentage": 98.42, "elapsed_time": "7:31:46", "remaining_time": "0:07:14"}
188
+ {"current_steps": 1880, "total_steps": 1900, "loss": 0.32130463123321534, "lr": 3.7207650903298143e-09, "epoch": 1.9789473684210526, "percentage": 98.95, "elapsed_time": "7:34:09", "remaining_time": "0:04:49"}
189
+ {"current_steps": 1890, "total_steps": 1900, "loss": 0.3224200963973999, "lr": 1.0209820876977416e-09, "epoch": 1.9894736842105263, "percentage": 99.47, "elapsed_time": "7:36:31", "remaining_time": "0:02:24"}
190
+ {"current_steps": 1900, "total_steps": 1900, "loss": 0.32581171989440916, "lr": 8.438153299428209e-12, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:38:55", "remaining_time": "0:00:00"}
191
+ {"current_steps": 1900, "total_steps": 1900, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:40:30", "remaining_time": "0:00:00"}
designcoder_qwen3.5_4b_muon_bs32_step1900/trainer_state.json ADDED
@@ -0,0 +1,1373 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1900,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.010526315789473684,
14
+ "grad_norm": 2.4375,
15
+ "learning_rate": 4.7368421052631585e-07,
16
+ "loss": 0.5649280548095703,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.021052631578947368,
21
+ "grad_norm": 2.5,
22
+ "learning_rate": 1.0000000000000002e-06,
23
+ "loss": 0.5708909034729004,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.031578947368421054,
28
+ "grad_norm": 2.40625,
29
+ "learning_rate": 1.5263157894736844e-06,
30
+ "loss": 0.5748211860656738,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.042105263157894736,
35
+ "grad_norm": 2.03125,
36
+ "learning_rate": 2.0526315789473687e-06,
37
+ "loss": 0.557589054107666,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.05263157894736842,
42
+ "grad_norm": 1.875,
43
+ "learning_rate": 2.578947368421053e-06,
44
+ "loss": 0.5640667915344239,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.06315789473684211,
49
+ "grad_norm": 1.5,
50
+ "learning_rate": 3.1052631578947372e-06,
51
+ "loss": 0.5634438514709472,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.07368421052631578,
56
+ "grad_norm": 1.1953125,
57
+ "learning_rate": 3.6315789473684217e-06,
58
+ "loss": 0.5504179000854492,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.08421052631578947,
63
+ "grad_norm": 1.1171875,
64
+ "learning_rate": 4.157894736842106e-06,
65
+ "loss": 0.5407459735870361,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.09473684210526316,
70
+ "grad_norm": 0.9453125,
71
+ "learning_rate": 4.68421052631579e-06,
72
+ "loss": 0.5427546977996827,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.10526315789473684,
77
+ "grad_norm": 0.875,
78
+ "learning_rate": 5.210526315789474e-06,
79
+ "loss": 0.5267032146453857,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.11578947368421053,
84
+ "grad_norm": 0.765625,
85
+ "learning_rate": 5.736842105263158e-06,
86
+ "loss": 0.5212538719177247,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.12631578947368421,
91
+ "grad_norm": 0.75390625,
92
+ "learning_rate": 6.263157894736842e-06,
93
+ "loss": 0.5108362197875976,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.1368421052631579,
98
+ "grad_norm": 0.69140625,
99
+ "learning_rate": 6.789473684210527e-06,
100
+ "loss": 0.49319658279418943,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.14736842105263157,
105
+ "grad_norm": 0.63671875,
106
+ "learning_rate": 7.315789473684212e-06,
107
+ "loss": 0.48811187744140627,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.15789473684210525,
112
+ "grad_norm": 0.6328125,
113
+ "learning_rate": 7.842105263157895e-06,
114
+ "loss": 0.47876510620117185,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.16842105263157894,
119
+ "grad_norm": 0.58203125,
120
+ "learning_rate": 8.36842105263158e-06,
121
+ "loss": 0.47615752220153806,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.17894736842105263,
126
+ "grad_norm": 0.578125,
127
+ "learning_rate": 8.894736842105264e-06,
128
+ "loss": 0.4617812156677246,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.18947368421052632,
133
+ "grad_norm": 0.58984375,
134
+ "learning_rate": 9.421052631578949e-06,
135
+ "loss": 0.462778377532959,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.2,
140
+ "grad_norm": 0.5390625,
141
+ "learning_rate": 9.947368421052632e-06,
142
+ "loss": 0.44389495849609373,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.21052631578947367,
147
+ "grad_norm": 0.55078125,
148
+ "learning_rate": 9.999316524962347e-06,
149
+ "loss": 0.42847065925598143,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.22105263157894736,
154
+ "grad_norm": 0.51953125,
155
+ "learning_rate": 9.99695413509548e-06,
156
+ "loss": 0.433226203918457,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.23157894736842105,
161
+ "grad_norm": 0.7109375,
162
+ "learning_rate": 9.992905189592214e-06,
163
+ "loss": 0.4245753288269043,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.24210526315789474,
168
+ "grad_norm": 0.51171875,
169
+ "learning_rate": 9.987171055039409e-06,
170
+ "loss": 0.42034215927124025,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.25263157894736843,
175
+ "grad_norm": 0.55078125,
176
+ "learning_rate": 9.979753666803427e-06,
177
+ "loss": 0.41213269233703614,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.2631578947368421,
182
+ "grad_norm": 0.51171875,
183
+ "learning_rate": 9.970655528376914e-06,
184
+ "loss": 0.40923295021057127,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.2736842105263158,
189
+ "grad_norm": 0.578125,
190
+ "learning_rate": 9.959879710533835e-06,
191
+ "loss": 0.4008836269378662,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.28421052631578947,
196
+ "grad_norm": 0.5546875,
197
+ "learning_rate": 9.947429850293025e-06,
198
+ "loss": 0.3953698635101318,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.29473684210526313,
203
+ "grad_norm": 0.50390625,
204
+ "learning_rate": 9.933310149690643e-06,
205
+ "loss": 0.3896397352218628,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.30526315789473685,
210
+ "grad_norm": 0.56640625,
211
+ "learning_rate": 9.917525374361913e-06,
212
+ "loss": 0.3975999355316162,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.3157894736842105,
217
+ "grad_norm": 0.54296875,
218
+ "learning_rate": 9.90008085193264e-06,
219
+ "loss": 0.38664898872375486,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.3263157894736842,
224
+ "grad_norm": 0.57421875,
225
+ "learning_rate": 9.880982470221052e-06,
226
+ "loss": 0.3833960771560669,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.3368421052631579,
231
+ "grad_norm": 0.55078125,
232
+ "learning_rate": 9.860236675250553e-06,
233
+ "loss": 0.3799261569976807,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.3473684210526316,
238
+ "grad_norm": 0.5234375,
239
+ "learning_rate": 9.837850469074094e-06,
240
+ "loss": 0.38280887603759767,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.35789473684210527,
245
+ "grad_norm": 0.578125,
246
+ "learning_rate": 9.813831407410856e-06,
247
+ "loss": 0.381818962097168,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.3684210526315789,
252
+ "grad_norm": 0.55078125,
253
+ "learning_rate": 9.78818759709607e-06,
254
+ "loss": 0.3756396770477295,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.37894736842105264,
259
+ "grad_norm": 0.578125,
260
+ "learning_rate": 9.760927693344823e-06,
261
+ "loss": 0.3703409194946289,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.3894736842105263,
266
+ "grad_norm": 0.5625,
267
+ "learning_rate": 9.732060896830782e-06,
268
+ "loss": 0.3752593517303467,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.4,
273
+ "grad_norm": 0.56640625,
274
+ "learning_rate": 9.701596950580807e-06,
275
+ "loss": 0.36957530975341796,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.4105263157894737,
280
+ "grad_norm": 0.5859375,
281
+ "learning_rate": 9.669546136686524e-06,
282
+ "loss": 0.370784592628479,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.42105263157894735,
287
+ "grad_norm": 0.53125,
288
+ "learning_rate": 9.635919272833938e-06,
289
+ "loss": 0.36154358386993407,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.43157894736842106,
294
+ "grad_norm": 0.55078125,
295
+ "learning_rate": 9.60072770865229e-06,
296
+ "loss": 0.36916418075561525,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.4421052631578947,
301
+ "grad_norm": 0.54296875,
302
+ "learning_rate": 9.563983321883364e-06,
303
+ "loss": 0.3586670160293579,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.45263157894736844,
308
+ "grad_norm": 0.55078125,
309
+ "learning_rate": 9.525698514372552e-06,
310
+ "loss": 0.36408448219299316,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.4631578947368421,
315
+ "grad_norm": 0.578125,
316
+ "learning_rate": 9.485886207883022e-06,
317
+ "loss": 0.3616478681564331,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.47368421052631576,
322
+ "grad_norm": 0.55078125,
323
+ "learning_rate": 9.444559839734409e-06,
324
+ "loss": 0.3540584325790405,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.4842105263157895,
329
+ "grad_norm": 0.515625,
330
+ "learning_rate": 9.401733358267488e-06,
331
+ "loss": 0.3628517150878906,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.49473684210526314,
336
+ "grad_norm": 0.56640625,
337
+ "learning_rate": 9.357421218136387e-06,
338
+ "loss": 0.3611913204193115,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.5052631578947369,
343
+ "grad_norm": 0.55859375,
344
+ "learning_rate": 9.311638375429893e-06,
345
+ "loss": 0.3575719118118286,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.5157894736842106,
350
+ "grad_norm": 0.55859375,
351
+ "learning_rate": 9.264400282623516e-06,
352
+ "loss": 0.35195198059082033,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.5263157894736842,
357
+ "grad_norm": 0.55078125,
358
+ "learning_rate": 9.215722883364033e-06,
359
+ "loss": 0.3550046682357788,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.5368421052631579,
364
+ "grad_norm": 0.54296875,
365
+ "learning_rate": 9.16562260708823e-06,
366
+ "loss": 0.35266599655151365,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.5473684210526316,
371
+ "grad_norm": 0.56640625,
372
+ "learning_rate": 9.114116363477694e-06,
373
+ "loss": 0.35182890892028806,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.5578947368421052,
378
+ "grad_norm": 0.546875,
379
+ "learning_rate": 9.061221536751517e-06,
380
+ "loss": 0.3465148448944092,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.5684210526315789,
385
+ "grad_norm": 0.60546875,
386
+ "learning_rate": 9.006955979798828e-06,
387
+ "loss": 0.3488567352294922,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.5789473684210527,
392
+ "grad_norm": 0.55078125,
393
+ "learning_rate": 8.95133800815314e-06,
394
+ "loss": 0.34726202487945557,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.5894736842105263,
399
+ "grad_norm": 0.51953125,
400
+ "learning_rate": 8.894386393810563e-06,
401
+ "loss": 0.3462839603424072,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.6,
406
+ "grad_norm": 0.53125,
407
+ "learning_rate": 8.836120358893926e-06,
408
+ "loss": 0.3476074695587158,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.6105263157894737,
413
+ "grad_norm": 0.56640625,
414
+ "learning_rate": 8.776559569165001e-06,
415
+ "loss": 0.34909305572509763,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.6210526315789474,
420
+ "grad_norm": 0.52734375,
421
+ "learning_rate": 8.715724127386971e-06,
422
+ "loss": 0.3453603029251099,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.631578947368421,
427
+ "grad_norm": 0.55859375,
428
+ "learning_rate": 8.653634566539421e-06,
429
+ "loss": 0.34458560943603517,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.6421052631578947,
434
+ "grad_norm": 0.546875,
435
+ "learning_rate": 8.590311842888101e-06,
436
+ "loss": 0.34335694313049314,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.6526315789473685,
441
+ "grad_norm": 0.53125,
442
+ "learning_rate": 8.525777328911846e-06,
443
+ "loss": 0.3478172063827515,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.6631578947368421,
448
+ "grad_norm": 0.55078125,
449
+ "learning_rate": 8.460052806089e-06,
450
+ "loss": 0.3395395040512085,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.6736842105263158,
455
+ "grad_norm": 0.56640625,
456
+ "learning_rate": 8.39316045754581e-06,
457
+ "loss": 0.343241024017334,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.6842105263157895,
462
+ "grad_norm": 0.55078125,
463
+ "learning_rate": 8.325122860569241e-06,
464
+ "loss": 0.3414290904998779,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.6947368421052632,
469
+ "grad_norm": 0.56640625,
470
+ "learning_rate": 8.255962978986772e-06,
471
+ "loss": 0.3469081401824951,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.7052631578947368,
476
+ "grad_norm": 0.59375,
477
+ "learning_rate": 8.18570415541571e-06,
478
+ "loss": 0.34221587181091306,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.7157894736842105,
483
+ "grad_norm": 0.52734375,
484
+ "learning_rate": 8.11437010338468e-06,
485
+ "loss": 0.33984344005584716,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.7263157894736842,
490
+ "grad_norm": 0.5390625,
491
+ "learning_rate": 8.041984899329898e-06,
492
+ "loss": 0.34598817825317385,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.7368421052631579,
497
+ "grad_norm": 0.5390625,
498
+ "learning_rate": 7.968572974468982e-06,
499
+ "loss": 0.34098362922668457,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.7473684210526316,
504
+ "grad_norm": 0.546875,
505
+ "learning_rate": 7.894159106554997e-06,
506
+ "loss": 0.3334647655487061,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.7578947368421053,
511
+ "grad_norm": 0.61328125,
512
+ "learning_rate": 7.81876841151356e-06,
513
+ "loss": 0.33434553146362306,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.7684210526315789,
518
+ "grad_norm": 0.62890625,
519
+ "learning_rate": 7.742426334965788e-06,
520
+ "loss": 0.33247191905975343,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.7789473684210526,
525
+ "grad_norm": 0.53515625,
526
+ "learning_rate": 7.66515864363997e-06,
527
+ "loss": 0.33722877502441406,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.7894736842105263,
532
+ "grad_norm": 0.546875,
533
+ "learning_rate": 7.58699141667488e-06,
534
+ "loss": 0.34308178424835206,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.8,
539
+ "grad_norm": 0.54296875,
540
+ "learning_rate": 7.507951036817618e-06,
541
+ "loss": 0.3383188247680664,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.8105263157894737,
546
+ "grad_norm": 0.54296875,
547
+ "learning_rate": 7.428064181518997e-06,
548
+ "loss": 0.34044275283813474,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.8210526315789474,
553
+ "grad_norm": 0.55078125,
554
+ "learning_rate": 7.347357813929455e-06,
555
+ "loss": 0.33629164695739744,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.8315789473684211,
560
+ "grad_norm": 0.56640625,
561
+ "learning_rate": 7.2658591737985405e-06,
562
+ "loss": 0.3386510372161865,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.8421052631578947,
567
+ "grad_norm": 0.55859375,
568
+ "learning_rate": 7.183595768281044e-06,
569
+ "loss": 0.33289337158203125,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.8526315789473684,
574
+ "grad_norm": 0.5625,
575
+ "learning_rate": 7.100595362652872e-06,
576
+ "loss": 0.3377974510192871,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.8631578947368421,
581
+ "grad_norm": 0.546875,
582
+ "learning_rate": 7.016885970939798e-06,
583
+ "loss": 0.3373216390609741,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.8736842105263158,
588
+ "grad_norm": 0.59765625,
589
+ "learning_rate": 6.932495846462262e-06,
590
+ "loss": 0.33392086029052737,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.8842105263157894,
595
+ "grad_norm": 0.61328125,
596
+ "learning_rate": 6.847453472299408e-06,
597
+ "loss": 0.3390925168991089,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.8947368421052632,
602
+ "grad_norm": 0.55078125,
603
+ "learning_rate": 6.761787551675559e-06,
604
+ "loss": 0.3334352016448975,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.9052631578947369,
609
+ "grad_norm": 0.52734375,
610
+ "learning_rate": 6.675526998272405e-06,
611
+ "loss": 0.33690924644470216,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.9157894736842105,
616
+ "grad_norm": 0.5625,
617
+ "learning_rate": 6.588700926470145e-06,
618
+ "loss": 0.3396608352661133,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.9263157894736842,
623
+ "grad_norm": 0.546875,
624
+ "learning_rate": 6.501338641520906e-06,
625
+ "loss": 0.3291656017303467,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.9368421052631579,
630
+ "grad_norm": 0.578125,
631
+ "learning_rate": 6.413469629657724e-06,
632
+ "loss": 0.33728480339050293,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.9473684210526315,
637
+ "grad_norm": 0.52734375,
638
+ "learning_rate": 6.325123548142442e-06,
639
+ "loss": 0.333527660369873,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.9578947368421052,
644
+ "grad_norm": 0.55859375,
645
+ "learning_rate": 6.2363302152559004e-06,
646
+ "loss": 0.32869296073913573,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.968421052631579,
651
+ "grad_norm": 0.55078125,
652
+ "learning_rate": 6.147119600233758e-06,
653
+ "loss": 0.33417134284973143,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.9789473684210527,
658
+ "grad_norm": 0.55078125,
659
+ "learning_rate": 6.0575218131513795e-06,
660
+ "loss": 0.33371286392211913,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.9894736842105263,
665
+ "grad_norm": 0.5859375,
666
+ "learning_rate": 5.967567094761173e-06,
667
+ "loss": 0.33172919750213625,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.0,
672
+ "grad_norm": 0.5546875,
673
+ "learning_rate": 5.8772858062858414e-06,
674
+ "loss": 0.3245907545089722,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.0105263157894737,
679
+ "grad_norm": 0.61328125,
680
+ "learning_rate": 5.786708419170955e-06,
681
+ "loss": 0.3322077751159668,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.0210526315789474,
686
+ "grad_norm": 0.5703125,
687
+ "learning_rate": 5.695865504800328e-06,
688
+ "loss": 0.32666444778442383,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.0315789473684212,
693
+ "grad_norm": 0.5546875,
694
+ "learning_rate": 5.604787724177666e-06,
695
+ "loss": 0.3285836219787598,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.0421052631578946,
700
+ "grad_norm": 0.5390625,
701
+ "learning_rate": 5.513505817577966e-06,
702
+ "loss": 0.32537705898284913,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 1.0526315789473684,
707
+ "grad_norm": 0.55078125,
708
+ "learning_rate": 5.422050594172161e-06,
709
+ "loss": 0.3251340389251709,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 1.063157894736842,
714
+ "grad_norm": 0.56640625,
715
+ "learning_rate": 5.3304529216284974e-06,
716
+ "loss": 0.3211204051971436,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 1.0736842105263158,
721
+ "grad_norm": 0.5625,
722
+ "learning_rate": 5.2387437156942e-06,
723
+ "loss": 0.3239119052886963,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 1.0842105263157895,
728
+ "grad_norm": 0.56640625,
729
+ "learning_rate": 5.146953929760873e-06,
730
+ "loss": 0.3276015281677246,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 1.0947368421052632,
735
+ "grad_norm": 0.578125,
736
+ "learning_rate": 5.055114544417219e-06,
737
+ "loss": 0.3195406436920166,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 1.1052631578947367,
742
+ "grad_norm": 0.578125,
743
+ "learning_rate": 4.963256556992573e-06,
744
+ "loss": 0.3270190477371216,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 1.1157894736842104,
749
+ "grad_norm": 0.546875,
750
+ "learning_rate": 4.871410971094783e-06,
751
+ "loss": 0.3211397171020508,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 1.1263157894736842,
756
+ "grad_norm": 0.66015625,
757
+ "learning_rate": 4.779608786145974e-06,
758
+ "loss": 0.3231573343276978,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 1.1368421052631579,
763
+ "grad_norm": 0.5390625,
764
+ "learning_rate": 4.687880986919725e-06,
765
+ "loss": 0.32362775802612304,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 1.1473684210526316,
770
+ "grad_norm": 0.55859375,
771
+ "learning_rate": 4.596258533083189e-06,
772
+ "loss": 0.3258507251739502,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 1.1578947368421053,
777
+ "grad_norm": 0.546875,
778
+ "learning_rate": 4.504772348747687e-06,
779
+ "loss": 0.3234171628952026,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 1.168421052631579,
784
+ "grad_norm": 0.578125,
785
+ "learning_rate": 4.4134533120313015e-06,
786
+ "loss": 0.32814559936523435,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 1.1789473684210527,
791
+ "grad_norm": 0.59765625,
792
+ "learning_rate": 4.322332244637e-06,
793
+ "loss": 0.32781333923339845,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 1.1894736842105262,
798
+ "grad_norm": 0.578125,
799
+ "learning_rate": 4.231439901449788e-06,
800
+ "loss": 0.32119724750518797,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 1.2,
805
+ "grad_norm": 0.5859375,
806
+ "learning_rate": 4.140806960156426e-06,
807
+ "loss": 0.3235795497894287,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 1.2105263157894737,
812
+ "grad_norm": 0.55859375,
813
+ "learning_rate": 4.050464010891191e-06,
814
+ "loss": 0.32244420051574707,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 1.2210526315789474,
819
+ "grad_norm": 0.57421875,
820
+ "learning_rate": 3.960441545911205e-06,
821
+ "loss": 0.32084407806396487,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 1.231578947368421,
826
+ "grad_norm": 0.55859375,
827
+ "learning_rate": 3.870769949304771e-06,
828
+ "loss": 0.32793939113616943,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 1.2421052631578948,
833
+ "grad_norm": 0.5390625,
834
+ "learning_rate": 3.7814794867362563e-06,
835
+ "loss": 0.32079472541809084,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 1.2526315789473683,
840
+ "grad_norm": 0.53125,
841
+ "learning_rate": 3.6926002952309015e-06,
842
+ "loss": 0.32700533866882325,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 1.263157894736842,
847
+ "grad_norm": 0.55859375,
848
+ "learning_rate": 3.6041623730030908e-06,
849
+ "loss": 0.323567795753479,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 1.2736842105263158,
854
+ "grad_norm": 0.546875,
855
+ "learning_rate": 3.5161955693314353e-06,
856
+ "loss": 0.3220393419265747,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 1.2842105263157895,
861
+ "grad_norm": 0.55859375,
862
+ "learning_rate": 3.4287295744841588e-06,
863
+ "loss": 0.32195496559143066,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 1.2947368421052632,
868
+ "grad_norm": 0.59375,
869
+ "learning_rate": 3.3417939096981154e-06,
870
+ "loss": 0.32832560539245603,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 1.305263157894737,
875
+ "grad_norm": 0.59375,
876
+ "learning_rate": 3.2554179172149027e-06,
877
+ "loss": 0.32657656669616697,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 1.3157894736842106,
882
+ "grad_norm": 0.578125,
883
+ "learning_rate": 3.169630750377337e-06,
884
+ "loss": 0.32687838077545167,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 1.3263157894736843,
889
+ "grad_norm": 0.5703125,
890
+ "learning_rate": 3.084461363789739e-06,
891
+ "loss": 0.3185723781585693,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 1.3368421052631578,
896
+ "grad_norm": 0.58203125,
897
+ "learning_rate": 2.9999385035452477e-06,
898
+ "loss": 0.321709418296814,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 1.3473684210526315,
903
+ "grad_norm": 0.546875,
904
+ "learning_rate": 2.9160906975235493e-06,
905
+ "loss": 0.3230076551437378,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 1.3578947368421053,
910
+ "grad_norm": 0.61328125,
911
+ "learning_rate": 2.8329462457622263e-06,
912
+ "loss": 0.3239234209060669,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 1.368421052631579,
917
+ "grad_norm": 0.53515625,
918
+ "learning_rate": 2.750533210905042e-06,
919
+ "loss": 0.3209430694580078,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 1.3789473684210527,
924
+ "grad_norm": 0.546875,
925
+ "learning_rate": 2.6688794087302993e-06,
926
+ "loss": 0.32194013595581056,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 1.3894736842105262,
931
+ "grad_norm": 0.6171875,
932
+ "learning_rate": 2.588012398762578e-06,
933
+ "loss": 0.3310521125793457,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 1.4,
938
+ "grad_norm": 0.546875,
939
+ "learning_rate": 2.507959474970918e-06,
940
+ "loss": 0.32281064987182617,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 1.4105263157894736,
945
+ "grad_norm": 0.60546875,
946
+ "learning_rate": 2.4287476565566525e-06,
947
+ "loss": 0.32929823398590086,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 1.4210526315789473,
952
+ "grad_norm": 0.57421875,
953
+ "learning_rate": 2.3504036788339763e-06,
954
+ "loss": 0.32490930557250974,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 1.431578947368421,
959
+ "grad_norm": 0.53515625,
960
+ "learning_rate": 2.2729539842063275e-06,
961
+ "loss": 0.31843137741088867,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 1.4421052631578948,
966
+ "grad_norm": 0.56640625,
967
+ "learning_rate": 2.1964247132416373e-06,
968
+ "loss": 0.3216635465621948,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 1.4526315789473685,
973
+ "grad_norm": 0.54296875,
974
+ "learning_rate": 2.1208416958494472e-06,
975
+ "loss": 0.320039176940918,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 1.4631578947368422,
980
+ "grad_norm": 0.5703125,
981
+ "learning_rate": 2.0462304425628836e-06,
982
+ "loss": 0.3187244415283203,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 1.4736842105263157,
987
+ "grad_norm": 0.546875,
988
+ "learning_rate": 1.9726161359284283e-06,
989
+ "loss": 0.3253413200378418,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 1.4842105263157894,
994
+ "grad_norm": 0.58203125,
995
+ "learning_rate": 1.900023622006385e-06,
996
+ "loss": 0.3248704433441162,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 1.4947368421052631,
1001
+ "grad_norm": 0.5546875,
1002
+ "learning_rate": 1.8284774019849176e-06,
1003
+ "loss": 0.324160099029541,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 1.5052631578947369,
1008
+ "grad_norm": 0.6171875,
1009
+ "learning_rate": 1.7580016239104924e-06,
1010
+ "loss": 0.3209646940231323,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 1.5157894736842106,
1015
+ "grad_norm": 0.58984375,
1016
+ "learning_rate": 1.688620074537506e-06,
1017
+ "loss": 0.32266716957092284,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 1.526315789473684,
1022
+ "grad_norm": 0.55859375,
1023
+ "learning_rate": 1.6203561712998561e-06,
1024
+ "loss": 0.31873378753662107,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 1.5368421052631578,
1029
+ "grad_norm": 0.56640625,
1030
+ "learning_rate": 1.5532329544071712e-06,
1031
+ "loss": 0.32254483699798586,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 1.5473684210526315,
1036
+ "grad_norm": 0.5546875,
1037
+ "learning_rate": 1.4872730790683488e-06,
1038
+ "loss": 0.31874861717224123,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 1.5578947368421052,
1043
+ "grad_norm": 0.5390625,
1044
+ "learning_rate": 1.4224988078450453e-06,
1045
+ "loss": 0.3291239500045776,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 1.568421052631579,
1050
+ "grad_norm": 0.5546875,
1051
+ "learning_rate": 1.35893200313769e-06,
1052
+ "loss": 0.3205441951751709,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 1.5789473684210527,
1057
+ "grad_norm": 0.578125,
1058
+ "learning_rate": 1.2965941198065568e-06,
1059
+ "loss": 0.32458648681640623,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 1.5894736842105264,
1064
+ "grad_norm": 0.57421875,
1065
+ "learning_rate": 1.2355061979303922e-06,
1066
+ "loss": 0.32656116485595704,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 1.6,
1071
+ "grad_norm": 0.55859375,
1072
+ "learning_rate": 1.1756888557050356e-06,
1073
+ "loss": 0.32614789009094236,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 1.6105263157894738,
1078
+ "grad_norm": 0.56640625,
1079
+ "learning_rate": 1.1171622824844324e-06,
1080
+ "loss": 0.32253460884094237,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 1.6210526315789475,
1085
+ "grad_norm": 0.578125,
1086
+ "learning_rate": 1.0599462319663906e-06,
1087
+ "loss": 0.3218738317489624,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 1.631578947368421,
1092
+ "grad_norm": 0.5625,
1093
+ "learning_rate": 1.0040600155253766e-06,
1094
+ "loss": 0.3189677715301514,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 1.6421052631578947,
1099
+ "grad_norm": 0.5703125,
1100
+ "learning_rate": 9.495224956946031e-07,
1101
+ "loss": 0.3237604141235352,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 1.6526315789473685,
1106
+ "grad_norm": 0.58203125,
1107
+ "learning_rate": 8.963520797996078e-07,
1108
+ "loss": 0.3268871307373047,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 1.663157894736842,
1113
+ "grad_norm": 0.58203125,
1114
+ "learning_rate": 8.44566713745476e-07,
1115
+ "loss": 0.32371490001678466,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 1.6736842105263157,
1120
+ "grad_norm": 0.5625,
1121
+ "learning_rate": 7.941838759597931e-07,
1122
+ "loss": 0.3219043016433716,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 1.6842105263157894,
1127
+ "grad_norm": 0.58984375,
1128
+ "learning_rate": 7.452205714933864e-07,
1129
+ "loss": 0.3194981575012207,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 1.694736842105263,
1134
+ "grad_norm": 0.5703125,
1135
+ "learning_rate": 6.976933262808322e-07,
1136
+ "loss": 0.3213656425476074,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 1.7052631578947368,
1141
+ "grad_norm": 0.56640625,
1142
+ "learning_rate": 6.516181815626809e-07,
1143
+ "loss": 0.3243042230606079,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 1.7157894736842105,
1148
+ "grad_norm": 0.546875,
1149
+ "learning_rate": 6.070106884712668e-07,
1150
+ "loss": 0.32139909267425537,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 1.7263157894736842,
1155
+ "grad_norm": 0.55859375,
1156
+ "learning_rate": 5.63885902781941e-07,
1157
+ "loss": 0.3254119873046875,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 1.736842105263158,
1162
+ "grad_norm": 0.5703125,
1163
+ "learning_rate": 5.222583798314962e-07,
1164
+ "loss": 0.3192205667495728,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 1.7473684210526317,
1169
+ "grad_norm": 0.5625,
1170
+ "learning_rate": 4.821421696054957e-07,
1171
+ "loss": 0.3214584827423096,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 1.7578947368421054,
1176
+ "grad_norm": 0.5546875,
1177
+ "learning_rate": 4.435508119961701e-07,
1178
+ "loss": 0.32129769325256347,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 1.768421052631579,
1183
+ "grad_norm": 0.53125,
1184
+ "learning_rate": 4.06497332232475e-07,
1185
+ "loss": 0.32092599868774413,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 1.7789473684210526,
1190
+ "grad_norm": 0.578125,
1191
+ "learning_rate": 3.709942364838598e-07,
1192
+ "loss": 0.32193360328674314,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 1.7894736842105263,
1197
+ "grad_norm": 0.5390625,
1198
+ "learning_rate": 3.370535076392256e-07,
1199
+ "loss": 0.3206108570098877,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 1.8,
1204
+ "grad_norm": 0.5625,
1205
+ "learning_rate": 3.046866012624999e-07,
1206
+ "loss": 0.3236824035644531,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 1.8105263157894735,
1211
+ "grad_norm": 0.671875,
1212
+ "learning_rate": 2.73904441726191e-07,
1213
+ "loss": 0.32245032787322997,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 1.8210526315789473,
1218
+ "grad_norm": 0.6015625,
1219
+ "learning_rate": 2.447174185242324e-07,
1220
+ "loss": 0.32442536354064944,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 1.831578947368421,
1225
+ "grad_norm": 0.546875,
1226
+ "learning_rate": 2.1713538276535052e-07,
1227
+ "loss": 0.33084514141082766,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 1.8421052631578947,
1232
+ "grad_norm": 0.546875,
1233
+ "learning_rate": 1.9116764384815467e-07,
1234
+ "loss": 0.31865687370300294,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 1.8526315789473684,
1239
+ "grad_norm": 0.5703125,
1240
+ "learning_rate": 1.6682296631905626e-07,
1241
+ "loss": 0.32346787452697756,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 1.8631578947368421,
1246
+ "grad_norm": 0.5546875,
1247
+ "learning_rate": 1.441095669140896e-07,
1248
+ "loss": 0.32239809036254885,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 1.8736842105263158,
1253
+ "grad_norm": 0.5625,
1254
+ "learning_rate": 1.2303511178562544e-07,
1255
+ "loss": 0.3282062768936157,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 1.8842105263157896,
1260
+ "grad_norm": 0.5859375,
1261
+ "learning_rate": 1.0360671391491606e-07,
1262
+ "loss": 0.32117500305175783,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 1.8947368421052633,
1267
+ "grad_norm": 0.51953125,
1268
+ "learning_rate": 8.583093071134473e-08,
1269
+ "loss": 0.3236595869064331,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 1.905263157894737,
1274
+ "grad_norm": 0.578125,
1275
+ "learning_rate": 6.971376179919109e-08,
1276
+ "loss": 0.3243385076522827,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 1.9157894736842105,
1281
+ "grad_norm": 0.59765625,
1282
+ "learning_rate": 5.526064699265754e-08,
1283
+ "loss": 0.32702107429504396,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 1.9263157894736842,
1288
+ "grad_norm": 0.5703125,
1289
+ "learning_rate": 4.247646445984077e-08,
1290
+ "loss": 0.32095746994018554,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 1.936842105263158,
1295
+ "grad_norm": 0.58203125,
1296
+ "learning_rate": 3.136552907626711e-08,
1297
+ "loss": 0.32458717823028566,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 1.9473684210526314,
1302
+ "grad_norm": 0.546875,
1303
+ "learning_rate": 2.193159096855191e-08,
1304
+ "loss": 0.3225292682647705,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 1.9578947368421051,
1309
+ "grad_norm": 0.546875,
1310
+ "learning_rate": 1.4177834248668144e-08,
1311
+ "loss": 0.3201985597610474,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 1.9684210526315788,
1316
+ "grad_norm": 0.5625,
1317
+ "learning_rate": 8.106875939254966e-09,
1318
+ "loss": 0.32071843147277834,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 1.9789473684210526,
1323
+ "grad_norm": 0.5625,
1324
+ "learning_rate": 3.7207650903298143e-09,
1325
+ "loss": 0.32130463123321534,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 1.9894736842105263,
1330
+ "grad_norm": 0.87890625,
1331
+ "learning_rate": 1.0209820876977416e-09,
1332
+ "loss": 0.3224200963973999,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 2.0,
1337
+ "grad_norm": 0.5546875,
1338
+ "learning_rate": 8.438153299428209e-12,
1339
+ "loss": 0.32581171989440916,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 2.0,
1344
+ "step": 1900,
1345
+ "total_flos": 4.673658376419279e+19,
1346
+ "train_loss": 0.35662912569547955,
1347
+ "train_runtime": 27630.2175,
1348
+ "train_samples_per_second": 2.2,
1349
+ "train_steps_per_second": 0.069
1350
+ }
1351
+ ],
1352
+ "logging_steps": 10,
1353
+ "max_steps": 1900,
1354
+ "num_input_tokens_seen": 0,
1355
+ "num_train_epochs": 2,
1356
+ "save_steps": 400,
1357
+ "stateful_callbacks": {
1358
+ "TrainerControl": {
1359
+ "args": {
1360
+ "should_epoch_stop": false,
1361
+ "should_evaluate": false,
1362
+ "should_log": false,
1363
+ "should_save": true,
1364
+ "should_training_stop": true
1365
+ },
1366
+ "attributes": {}
1367
+ }
1368
+ },
1369
+ "total_flos": 4.673658376419279e+19,
1370
+ "train_batch_size": 1,
1371
+ "trial_name": null,
1372
+ "trial_params": null
1373
+ }
designcoder_qwen3.5_4b_muon_bs32_step1900/training_loss.png ADDED