xingxm commited on
Commit
e9a50bc
·
verified ·
1 Parent(s): f66ede7

Add designcoder_qwen3.5_9b_adamw_bs16_step3800 (base Qwen3.5-9B, AdamW, lr2e-5, global bs16, 2 epochs, step 3800)

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
 
 
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
37
+ designcoder_qwen3.5_9b_adamw_bs16_step3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
designcoder_qwen3.5_9b_adamw_bs16_step3800/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 1.76068140990464e+16,
4
+ "train_loss": 0.24053681511628,
5
+ "train_runtime": 74474.5181,
6
+ "train_samples_per_second": 0.816,
7
+ "train_steps_per_second": 0.051
8
+ }
designcoder_qwen3.5_9b_adamw_bs16_step3800/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_9b_adamw_bs16_step3800/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": 4096,
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": 4096,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 12288,
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": false,
87
+ "use_cache": false,
88
+ "vocab_size": 248320
89
+ },
90
+ "tie_word_embeddings": false,
91
+ "transformers_version": "5.8.0",
92
+ "use_cache": false,
93
+ "video_token_id": 248057,
94
+ "vision_config": {
95
+ "deepstack_visual_indexes": [],
96
+ "depth": 27,
97
+ "dtype": "bfloat16",
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 1152,
100
+ "in_channels": 3,
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 4304,
103
+ "model_type": "qwen3_5_vision",
104
+ "num_heads": 16,
105
+ "num_position_embeddings": 2304,
106
+ "out_hidden_size": 4096,
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_9b_adamw_bs16_step3800/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_9b_adamw_bs16_step3800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463d5ce8f032bea2ce44e420f46dcead777158bc46990a89d6f8c37aaff0295a
3
+ size 18819722392
designcoder_qwen3.5_9b_adamw_bs16_step3800/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_9b_adamw_bs16_step3800/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_9b_adamw_bs16_step3800/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_9b_adamw_bs16_step3800/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 1.76068140990464e+16,
4
+ "train_loss": 0.24053681511628,
5
+ "train_runtime": 74474.5181,
6
+ "train_samples_per_second": 0.816,
7
+ "train_steps_per_second": 0.051
8
+ }
designcoder_qwen3.5_9b_adamw_bs16_step3800/trainer_log.jsonl ADDED
@@ -0,0 +1,381 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3800, "loss": 0.5256161212921142, "lr": 4.7368421052631585e-07, "epoch": 0.005263157894736842, "percentage": 0.26, "elapsed_time": "0:03:43", "remaining_time": "23:34:42"}
2
+ {"current_steps": 20, "total_steps": 3800, "loss": 0.5117449760437012, "lr": 1.0000000000000002e-06, "epoch": 0.010526315789473684, "percentage": 0.53, "elapsed_time": "0:06:56", "remaining_time": "21:52:18"}
3
+ {"current_steps": 30, "total_steps": 3800, "loss": 0.47916154861450194, "lr": 1.5263157894736844e-06, "epoch": 0.015789473684210527, "percentage": 0.79, "elapsed_time": "0:10:10", "remaining_time": "21:17:49"}
4
+ {"current_steps": 40, "total_steps": 3800, "loss": 0.4465330123901367, "lr": 2.0526315789473687e-06, "epoch": 0.021052631578947368, "percentage": 1.05, "elapsed_time": "0:13:23", "remaining_time": "20:58:08"}
5
+ {"current_steps": 50, "total_steps": 3800, "loss": 0.42493352890014646, "lr": 2.578947368421053e-06, "epoch": 0.02631578947368421, "percentage": 1.32, "elapsed_time": "0:16:33", "remaining_time": "20:41:55"}
6
+ {"current_steps": 60, "total_steps": 3800, "loss": 0.39734339714050293, "lr": 3.1052631578947372e-06, "epoch": 0.031578947368421054, "percentage": 1.58, "elapsed_time": "0:19:46", "remaining_time": "20:32:30"}
7
+ {"current_steps": 70, "total_steps": 3800, "loss": 0.3773430109024048, "lr": 3.6315789473684217e-06, "epoch": 0.03684210526315789, "percentage": 1.84, "elapsed_time": "0:22:57", "remaining_time": "20:23:42"}
8
+ {"current_steps": 80, "total_steps": 3800, "loss": 0.37105565071105956, "lr": 4.157894736842106e-06, "epoch": 0.042105263157894736, "percentage": 2.11, "elapsed_time": "0:26:11", "remaining_time": "20:17:41"}
9
+ {"current_steps": 90, "total_steps": 3800, "loss": 0.36675457954406737, "lr": 4.68421052631579e-06, "epoch": 0.04736842105263158, "percentage": 2.37, "elapsed_time": "0:29:24", "remaining_time": "20:12:16"}
10
+ {"current_steps": 100, "total_steps": 3800, "loss": 0.3579871654510498, "lr": 5.210526315789474e-06, "epoch": 0.05263157894736842, "percentage": 2.63, "elapsed_time": "0:32:36", "remaining_time": "20:06:16"}
11
+ {"current_steps": 110, "total_steps": 3800, "loss": 0.35358657836914065, "lr": 5.736842105263158e-06, "epoch": 0.05789473684210526, "percentage": 2.89, "elapsed_time": "0:35:50", "remaining_time": "20:02:19"}
12
+ {"current_steps": 120, "total_steps": 3800, "loss": 0.3630886793136597, "lr": 6.263157894736842e-06, "epoch": 0.06315789473684211, "percentage": 3.16, "elapsed_time": "0:39:03", "remaining_time": "19:57:45"}
13
+ {"current_steps": 130, "total_steps": 3800, "loss": 0.3483468532562256, "lr": 6.789473684210527e-06, "epoch": 0.06842105263157895, "percentage": 3.42, "elapsed_time": "0:42:17", "remaining_time": "19:53:47"}
14
+ {"current_steps": 140, "total_steps": 3800, "loss": 0.335282039642334, "lr": 7.315789473684212e-06, "epoch": 0.07368421052631578, "percentage": 3.68, "elapsed_time": "0:45:30", "remaining_time": "19:49:44"}
15
+ {"current_steps": 150, "total_steps": 3800, "loss": 0.3350475311279297, "lr": 7.842105263157895e-06, "epoch": 0.07894736842105263, "percentage": 3.95, "elapsed_time": "0:48:43", "remaining_time": "19:45:49"}
16
+ {"current_steps": 160, "total_steps": 3800, "loss": 0.33222599029541017, "lr": 8.36842105263158e-06, "epoch": 0.08421052631578947, "percentage": 4.21, "elapsed_time": "0:52:00", "remaining_time": "19:43:20"}
17
+ {"current_steps": 170, "total_steps": 3800, "loss": 0.3343937873840332, "lr": 8.894736842105264e-06, "epoch": 0.08947368421052632, "percentage": 4.47, "elapsed_time": "0:55:17", "remaining_time": "19:40:28"}
18
+ {"current_steps": 180, "total_steps": 3800, "loss": 0.3304591178894043, "lr": 9.421052631578949e-06, "epoch": 0.09473684210526316, "percentage": 4.74, "elapsed_time": "0:58:30", "remaining_time": "19:36:42"}
19
+ {"current_steps": 190, "total_steps": 3800, "loss": 0.3218997001647949, "lr": 9.947368421052632e-06, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "1:01:43", "remaining_time": "19:32:48"}
20
+ {"current_steps": 200, "total_steps": 3800, "loss": 0.3258413076400757, "lr": 1.0473684210526316e-05, "epoch": 0.10526315789473684, "percentage": 5.26, "elapsed_time": "1:04:55", "remaining_time": "19:28:41"}
21
+ {"current_steps": 210, "total_steps": 3800, "loss": 0.3291585445404053, "lr": 1.1000000000000001e-05, "epoch": 0.11052631578947368, "percentage": 5.53, "elapsed_time": "1:08:07", "remaining_time": "19:24:40"}
22
+ {"current_steps": 220, "total_steps": 3800, "loss": 0.31838207244873046, "lr": 1.1526315789473685e-05, "epoch": 0.11578947368421053, "percentage": 5.79, "elapsed_time": "1:11:22", "remaining_time": "19:21:24"}
23
+ {"current_steps": 230, "total_steps": 3800, "loss": 0.31834683418273924, "lr": 1.2052631578947369e-05, "epoch": 0.12105263157894737, "percentage": 6.05, "elapsed_time": "1:14:37", "remaining_time": "19:18:11"}
24
+ {"current_steps": 240, "total_steps": 3800, "loss": 0.3187001943588257, "lr": 1.2578947368421052e-05, "epoch": 0.12631578947368421, "percentage": 6.32, "elapsed_time": "1:17:51", "remaining_time": "19:14:51"}
25
+ {"current_steps": 250, "total_steps": 3800, "loss": 0.31230387687683103, "lr": 1.310526315789474e-05, "epoch": 0.13157894736842105, "percentage": 6.58, "elapsed_time": "1:21:05", "remaining_time": "19:11:28"}
26
+ {"current_steps": 260, "total_steps": 3800, "loss": 0.3076712846755981, "lr": 1.3631578947368423e-05, "epoch": 0.1368421052631579, "percentage": 6.84, "elapsed_time": "1:24:18", "remaining_time": "19:07:57"}
27
+ {"current_steps": 270, "total_steps": 3800, "loss": 0.3154590606689453, "lr": 1.4157894736842107e-05, "epoch": 0.14210526315789473, "percentage": 7.11, "elapsed_time": "1:27:31", "remaining_time": "19:04:21"}
28
+ {"current_steps": 280, "total_steps": 3800, "loss": 0.30873308181762693, "lr": 1.468421052631579e-05, "epoch": 0.14736842105263157, "percentage": 7.37, "elapsed_time": "1:30:44", "remaining_time": "19:00:39"}
29
+ {"current_steps": 290, "total_steps": 3800, "loss": 0.3070851802825928, "lr": 1.5210526315789476e-05, "epoch": 0.15263157894736842, "percentage": 7.63, "elapsed_time": "1:33:56", "remaining_time": "18:57:02"}
30
+ {"current_steps": 300, "total_steps": 3800, "loss": 0.31069626808166506, "lr": 1.573684210526316e-05, "epoch": 0.15789473684210525, "percentage": 7.89, "elapsed_time": "1:37:09", "remaining_time": "18:53:32"}
31
+ {"current_steps": 310, "total_steps": 3800, "loss": 0.3106666088104248, "lr": 1.6263157894736843e-05, "epoch": 0.1631578947368421, "percentage": 8.16, "elapsed_time": "1:40:22", "remaining_time": "18:50:06"}
32
+ {"current_steps": 320, "total_steps": 3800, "loss": 0.3167429447174072, "lr": 1.6789473684210526e-05, "epoch": 0.16842105263157894, "percentage": 8.42, "elapsed_time": "1:43:35", "remaining_time": "18:46:36"}
33
+ {"current_steps": 330, "total_steps": 3800, "loss": 0.31033878326416015, "lr": 1.7315789473684213e-05, "epoch": 0.1736842105263158, "percentage": 8.68, "elapsed_time": "1:46:48", "remaining_time": "18:43:04"}
34
+ {"current_steps": 340, "total_steps": 3800, "loss": 0.3044872760772705, "lr": 1.7842105263157897e-05, "epoch": 0.17894736842105263, "percentage": 8.95, "elapsed_time": "1:50:01", "remaining_time": "18:39:35"}
35
+ {"current_steps": 350, "total_steps": 3800, "loss": 0.3083398103713989, "lr": 1.836842105263158e-05, "epoch": 0.18421052631578946, "percentage": 9.21, "elapsed_time": "1:53:15", "remaining_time": "18:36:22"}
36
+ {"current_steps": 360, "total_steps": 3800, "loss": 0.31491541862487793, "lr": 1.8894736842105264e-05, "epoch": 0.18947368421052632, "percentage": 9.47, "elapsed_time": "1:56:27", "remaining_time": "18:32:52"}
37
+ {"current_steps": 370, "total_steps": 3800, "loss": 0.305939245223999, "lr": 1.9421052631578948e-05, "epoch": 0.19473684210526315, "percentage": 9.74, "elapsed_time": "1:59:41", "remaining_time": "18:29:36"}
38
+ {"current_steps": 380, "total_steps": 3800, "loss": 0.3013646125793457, "lr": 1.994736842105263e-05, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "2:02:54", "remaining_time": "18:26:10"}
39
+ {"current_steps": 390, "total_steps": 3800, "loss": 0.30339813232421875, "lr": 1.9999658256641746e-05, "epoch": 0.20526315789473684, "percentage": 10.26, "elapsed_time": "2:06:07", "remaining_time": "18:22:43"}
40
+ {"current_steps": 400, "total_steps": 3800, "loss": 0.2942552089691162, "lr": 1.9998476951563914e-05, "epoch": 0.21052631578947367, "percentage": 10.53, "elapsed_time": "2:09:21", "remaining_time": "18:19:30"}
41
+ {"current_steps": 410, "total_steps": 3800, "loss": 0.30738029479980467, "lr": 1.999645196536862e-05, "epoch": 0.21578947368421053, "percentage": 10.79, "elapsed_time": "2:14:06", "remaining_time": "18:28:50"}
42
+ {"current_steps": 420, "total_steps": 3800, "loss": 0.3012552738189697, "lr": 1.9993583468926155e-05, "epoch": 0.22105263157894736, "percentage": 11.05, "elapsed_time": "2:17:18", "remaining_time": "18:24:58"}
43
+ {"current_steps": 430, "total_steps": 3800, "loss": 0.2997457027435303, "lr": 1.9989871704283007e-05, "epoch": 0.22631578947368422, "percentage": 11.32, "elapsed_time": "2:20:32", "remaining_time": "18:21:25"}
44
+ {"current_steps": 440, "total_steps": 3800, "loss": 0.30234060287475584, "lr": 1.9985316984641456e-05, "epoch": 0.23157894736842105, "percentage": 11.58, "elapsed_time": "2:23:44", "remaining_time": "18:17:40"}
45
+ {"current_steps": 450, "total_steps": 3800, "loss": 0.29965386390686033, "lr": 1.9979919694333134e-05, "epoch": 0.23684210526315788, "percentage": 11.84, "elapsed_time": "2:26:59", "remaining_time": "18:14:16"}
46
+ {"current_steps": 460, "total_steps": 3800, "loss": 0.29823567867279055, "lr": 1.9973680288786593e-05, "epoch": 0.24210526315789474, "percentage": 12.11, "elapsed_time": "2:30:12", "remaining_time": "18:10:41"}
47
+ {"current_steps": 470, "total_steps": 3800, "loss": 0.2968828916549683, "lr": 1.996659929448889e-05, "epoch": 0.24736842105263157, "percentage": 12.37, "elapsed_time": "2:33:25", "remaining_time": "18:07:02"}
48
+ {"current_steps": 480, "total_steps": 3800, "loss": 0.29349508285522463, "lr": 1.995867730894114e-05, "epoch": 0.25263157894736843, "percentage": 12.63, "elapsed_time": "2:36:40", "remaining_time": "18:03:38"}
49
+ {"current_steps": 490, "total_steps": 3800, "loss": 0.29422550201416015, "lr": 1.9949915000608117e-05, "epoch": 0.2578947368421053, "percentage": 12.89, "elapsed_time": "2:39:52", "remaining_time": "17:59:59"}
50
+ {"current_steps": 500, "total_steps": 3800, "loss": 0.29750072956085205, "lr": 1.9940313108861838e-05, "epoch": 0.2631578947368421, "percentage": 13.16, "elapsed_time": "2:43:06", "remaining_time": "17:56:32"}
51
+ {"current_steps": 510, "total_steps": 3800, "loss": 0.29425339698791503, "lr": 1.9929872443919184e-05, "epoch": 0.26842105263157895, "percentage": 13.42, "elapsed_time": "2:46:17", "remaining_time": "17:52:42"}
52
+ {"current_steps": 520, "total_steps": 3800, "loss": 0.28567793369293215, "lr": 1.9918593886773517e-05, "epoch": 0.2736842105263158, "percentage": 13.68, "elapsed_time": "2:49:30", "remaining_time": "17:49:10"}
53
+ {"current_steps": 530, "total_steps": 3800, "loss": 0.286260986328125, "lr": 1.9906478389120353e-05, "epoch": 0.2789473684210526, "percentage": 13.95, "elapsed_time": "2:52:42", "remaining_time": "17:45:35"}
54
+ {"current_steps": 540, "total_steps": 3800, "loss": 0.289249062538147, "lr": 1.9893526973277058e-05, "epoch": 0.28421052631578947, "percentage": 14.21, "elapsed_time": "2:55:55", "remaining_time": "17:42:03"}
55
+ {"current_steps": 550, "total_steps": 3800, "loss": 0.2874547004699707, "lr": 1.9879740732096578e-05, "epoch": 0.2894736842105263, "percentage": 14.47, "elapsed_time": "2:59:09", "remaining_time": "17:38:42"}
56
+ {"current_steps": 560, "total_steps": 3800, "loss": 0.2794506072998047, "lr": 1.9865120828875226e-05, "epoch": 0.29473684210526313, "percentage": 14.74, "elapsed_time": "3:02:21", "remaining_time": "17:35:04"}
57
+ {"current_steps": 570, "total_steps": 3800, "loss": 0.2895684242248535, "lr": 1.984966849725452e-05, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "3:05:36", "remaining_time": "17:31:45"}
58
+ {"current_steps": 580, "total_steps": 3800, "loss": 0.29196949005126954, "lr": 1.9833385041117084e-05, "epoch": 0.30526315789473685, "percentage": 15.26, "elapsed_time": "3:08:47", "remaining_time": "17:28:05"}
59
+ {"current_steps": 590, "total_steps": 3800, "loss": 0.28489394187927247, "lr": 1.9816271834476642e-05, "epoch": 0.3105263157894737, "percentage": 15.53, "elapsed_time": "3:12:01", "remaining_time": "17:24:43"}
60
+ {"current_steps": 600, "total_steps": 3800, "loss": 0.28308355808258057, "lr": 1.979833032136205e-05, "epoch": 0.3157894736842105, "percentage": 15.79, "elapsed_time": "3:15:15", "remaining_time": "17:21:24"}
61
+ {"current_steps": 610, "total_steps": 3800, "loss": 0.2814664840698242, "lr": 1.9779562015695472e-05, "epoch": 0.32105263157894737, "percentage": 16.05, "elapsed_time": "3:18:30", "remaining_time": "17:18:03"}
62
+ {"current_steps": 620, "total_steps": 3800, "loss": 0.2858001470565796, "lr": 1.975996850116462e-05, "epoch": 0.3263157894736842, "percentage": 16.32, "elapsed_time": "3:21:44", "remaining_time": "17:14:46"}
63
+ {"current_steps": 630, "total_steps": 3800, "loss": 0.28349668979644777, "lr": 1.9739551431089127e-05, "epoch": 0.33157894736842103, "percentage": 16.58, "elapsed_time": "3:25:00", "remaining_time": "17:11:32"}
64
+ {"current_steps": 640, "total_steps": 3800, "loss": 0.2791487216949463, "lr": 1.9718312528281032e-05, "epoch": 0.3368421052631579, "percentage": 16.84, "elapsed_time": "3:28:15", "remaining_time": "17:08:15"}
65
+ {"current_steps": 650, "total_steps": 3800, "loss": 0.281187629699707, "lr": 1.969625358489942e-05, "epoch": 0.34210526315789475, "percentage": 17.11, "elapsed_time": "3:31:33", "remaining_time": "17:05:12"}
66
+ {"current_steps": 660, "total_steps": 3800, "loss": 0.28690199851989745, "lr": 1.9673376462299186e-05, "epoch": 0.3473684210526316, "percentage": 17.37, "elapsed_time": "3:34:46", "remaining_time": "17:01:48"}
67
+ {"current_steps": 670, "total_steps": 3800, "loss": 0.2867712497711182, "lr": 1.9649683090873966e-05, "epoch": 0.3526315789473684, "percentage": 17.63, "elapsed_time": "3:38:01", "remaining_time": "16:58:32"}
68
+ {"current_steps": 680, "total_steps": 3800, "loss": 0.2830781936645508, "lr": 1.9625175469893274e-05, "epoch": 0.35789473684210527, "percentage": 17.89, "elapsed_time": "3:41:17", "remaining_time": "16:55:21"}
69
+ {"current_steps": 690, "total_steps": 3800, "loss": 0.2801445484161377, "lr": 1.9599855667333775e-05, "epoch": 0.3631578947368421, "percentage": 18.16, "elapsed_time": "3:44:31", "remaining_time": "16:51:58"}
70
+ {"current_steps": 700, "total_steps": 3800, "loss": 0.2798027038574219, "lr": 1.95737258197048e-05, "epoch": 0.3684210526315789, "percentage": 18.42, "elapsed_time": "3:47:45", "remaining_time": "16:48:38"}
71
+ {"current_steps": 710, "total_steps": 3800, "loss": 0.27515039443969724, "lr": 1.9546788131868066e-05, "epoch": 0.3736842105263158, "percentage": 18.68, "elapsed_time": "3:51:00", "remaining_time": "16:45:24"}
72
+ {"current_steps": 720, "total_steps": 3800, "loss": 0.27915568351745607, "lr": 1.9519044876851625e-05, "epoch": 0.37894736842105264, "percentage": 18.95, "elapsed_time": "3:54:14", "remaining_time": "16:42:01"}
73
+ {"current_steps": 730, "total_steps": 3800, "loss": 0.2834479331970215, "lr": 1.9490498395658065e-05, "epoch": 0.38421052631578945, "percentage": 19.21, "elapsed_time": "3:57:25", "remaining_time": "16:38:31"}
74
+ {"current_steps": 740, "total_steps": 3800, "loss": 0.27811641693115235, "lr": 1.9461151097066966e-05, "epoch": 0.3894736842105263, "percentage": 19.47, "elapsed_time": "4:00:39", "remaining_time": "16:35:08"}
75
+ {"current_steps": 750, "total_steps": 3800, "loss": 0.27672529220581055, "lr": 1.9431005457431654e-05, "epoch": 0.39473684210526316, "percentage": 19.74, "elapsed_time": "4:03:53", "remaining_time": "16:31:50"}
76
+ {"current_steps": 760, "total_steps": 3800, "loss": 0.27708661556243896, "lr": 1.9400064020470248e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "4:07:09", "remaining_time": "16:28:37"}
77
+ {"current_steps": 770, "total_steps": 3800, "loss": 0.2778616428375244, "lr": 1.9368329397051005e-05, "epoch": 0.4052631578947368, "percentage": 20.26, "elapsed_time": "4:10:20", "remaining_time": "16:25:07"}
78
+ {"current_steps": 780, "total_steps": 3800, "loss": 0.2797053575515747, "lr": 1.9335804264972018e-05, "epoch": 0.4105263157894737, "percentage": 20.53, "elapsed_time": "4:13:34", "remaining_time": "16:21:49"}
79
+ {"current_steps": 790, "total_steps": 3800, "loss": 0.2725248098373413, "lr": 1.930249136873527e-05, "epoch": 0.41578947368421054, "percentage": 20.79, "elapsed_time": "4:16:47", "remaining_time": "16:18:25"}
80
+ {"current_steps": 800, "total_steps": 3800, "loss": 0.2721980571746826, "lr": 1.9268393519315037e-05, "epoch": 0.42105263157894735, "percentage": 21.05, "elapsed_time": "4:20:02", "remaining_time": "16:15:09"}
81
+ {"current_steps": 810, "total_steps": 3800, "loss": 0.27883172035217285, "lr": 1.923351359392071e-05, "epoch": 0.4263157894736842, "percentage": 21.32, "elapsed_time": "4:24:48", "remaining_time": "16:17:31"}
82
+ {"current_steps": 820, "total_steps": 3800, "loss": 0.2791574478149414, "lr": 1.919785453575398e-05, "epoch": 0.43157894736842106, "percentage": 21.58, "elapsed_time": "4:28:04", "remaining_time": "16:14:15"}
83
+ {"current_steps": 830, "total_steps": 3800, "loss": 0.2733182907104492, "lr": 1.9161419353760537e-05, "epoch": 0.4368421052631579, "percentage": 21.84, "elapsed_time": "4:31:17", "remaining_time": "16:10:44"}
84
+ {"current_steps": 840, "total_steps": 3800, "loss": 0.2692681312561035, "lr": 1.9124211122376138e-05, "epoch": 0.4421052631578947, "percentage": 22.11, "elapsed_time": "4:34:28", "remaining_time": "16:07:11"}
85
+ {"current_steps": 850, "total_steps": 3800, "loss": 0.27492191791534426, "lr": 1.9086232981267193e-05, "epoch": 0.4473684210526316, "percentage": 22.37, "elapsed_time": "4:37:44", "remaining_time": "16:03:55"}
86
+ {"current_steps": 860, "total_steps": 3800, "loss": 0.2736824035644531, "lr": 1.9047488135065838e-05, "epoch": 0.45263157894736844, "percentage": 22.63, "elapsed_time": "4:40:59", "remaining_time": "16:00:37"}
87
+ {"current_steps": 870, "total_steps": 3800, "loss": 0.26795847415924073, "lr": 1.900797985309952e-05, "epoch": 0.45789473684210524, "percentage": 22.89, "elapsed_time": "4:44:11", "remaining_time": "15:57:07"}
88
+ {"current_steps": 880, "total_steps": 3800, "loss": 0.27838611602783203, "lr": 1.8967711469115125e-05, "epoch": 0.4631578947368421, "percentage": 23.16, "elapsed_time": "4:47:24", "remaining_time": "15:53:41"}
89
+ {"current_steps": 890, "total_steps": 3800, "loss": 0.2694388866424561, "lr": 1.89266863809977e-05, "epoch": 0.46842105263157896, "percentage": 23.42, "elapsed_time": "4:50:37", "remaining_time": "15:50:15"}
90
+ {"current_steps": 900, "total_steps": 3800, "loss": 0.2662887334823608, "lr": 1.8884908050483694e-05, "epoch": 0.47368421052631576, "percentage": 23.68, "elapsed_time": "4:53:49", "remaining_time": "15:46:47"}
91
+ {"current_steps": 910, "total_steps": 3800, "loss": 0.2719233512878418, "lr": 1.884238000286889e-05, "epoch": 0.4789473684210526, "percentage": 23.95, "elapsed_time": "4:57:01", "remaining_time": "15:43:19"}
92
+ {"current_steps": 920, "total_steps": 3800, "loss": 0.27722165584564207, "lr": 1.8799105826710907e-05, "epoch": 0.4842105263157895, "percentage": 24.21, "elapsed_time": "5:00:17", "remaining_time": "15:40:01"}
93
+ {"current_steps": 930, "total_steps": 3800, "loss": 0.27123408317565917, "lr": 1.875508917352643e-05, "epoch": 0.48947368421052634, "percentage": 24.47, "elapsed_time": "5:03:30", "remaining_time": "15:36:37"}
94
+ {"current_steps": 940, "total_steps": 3800, "loss": 0.2743401050567627, "lr": 1.871033375748305e-05, "epoch": 0.49473684210526314, "percentage": 24.74, "elapsed_time": "5:06:43", "remaining_time": "15:33:13"}
95
+ {"current_steps": 950, "total_steps": 3800, "loss": 0.2736999988555908, "lr": 1.8664843355085897e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "5:09:57", "remaining_time": "15:29:52"}
96
+ {"current_steps": 960, "total_steps": 3800, "loss": 0.2695770740509033, "lr": 1.8618621804858942e-05, "epoch": 0.5052631578947369, "percentage": 25.26, "elapsed_time": "5:13:10", "remaining_time": "15:26:29"}
97
+ {"current_steps": 970, "total_steps": 3800, "loss": 0.2674164533615112, "lr": 1.8571673007021124e-05, "epoch": 0.5105263157894737, "percentage": 25.53, "elapsed_time": "5:16:25", "remaining_time": "15:23:11"}
98
+ {"current_steps": 980, "total_steps": 3800, "loss": 0.2656900644302368, "lr": 1.8524000923157236e-05, "epoch": 0.5157894736842106, "percentage": 25.79, "elapsed_time": "5:19:38", "remaining_time": "15:19:48"}
99
+ {"current_steps": 990, "total_steps": 3800, "loss": 0.2646545648574829, "lr": 1.847560957588364e-05, "epoch": 0.5210526315789473, "percentage": 26.05, "elapsed_time": "5:22:52", "remaining_time": "15:16:25"}
100
+ {"current_steps": 1000, "total_steps": 3800, "loss": 0.2751678228378296, "lr": 1.8426503048508837e-05, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "5:26:06", "remaining_time": "15:13:07"}
101
+ {"current_steps": 1010, "total_steps": 3800, "loss": 0.2681708335876465, "lr": 1.8376685484688917e-05, "epoch": 0.531578947368421, "percentage": 26.58, "elapsed_time": "5:29:21", "remaining_time": "15:09:47"}
102
+ {"current_steps": 1020, "total_steps": 3800, "loss": 0.2672728538513184, "lr": 1.8326161088077905e-05, "epoch": 0.5368421052631579, "percentage": 26.84, "elapsed_time": "5:32:33", "remaining_time": "15:06:21"}
103
+ {"current_steps": 1030, "total_steps": 3800, "loss": 0.2671975135803223, "lr": 1.8274934121973063e-05, "epoch": 0.5421052631578948, "percentage": 27.11, "elapsed_time": "5:35:45", "remaining_time": "15:02:58"}
104
+ {"current_steps": 1040, "total_steps": 3800, "loss": 0.26558561325073243, "lr": 1.8223008908955142e-05, "epoch": 0.5473684210526316, "percentage": 27.37, "elapsed_time": "5:38:57", "remaining_time": "14:59:33"}
105
+ {"current_steps": 1050, "total_steps": 3800, "loss": 0.26291708946228026, "lr": 1.817038983052364e-05, "epoch": 0.5526315789473685, "percentage": 27.63, "elapsed_time": "5:42:10", "remaining_time": "14:56:10"}
106
+ {"current_steps": 1060, "total_steps": 3800, "loss": 0.26275482177734377, "lr": 1.811708132672708e-05, "epoch": 0.5578947368421052, "percentage": 27.89, "elapsed_time": "5:45:25", "remaining_time": "14:52:53"}
107
+ {"current_steps": 1070, "total_steps": 3800, "loss": 0.26116185188293456, "lr": 1.806308789578838e-05, "epoch": 0.5631578947368421, "percentage": 28.16, "elapsed_time": "5:48:37", "remaining_time": "14:49:28"}
108
+ {"current_steps": 1080, "total_steps": 3800, "loss": 0.26714067459106444, "lr": 1.800841409372525e-05, "epoch": 0.5684210526315789, "percentage": 28.42, "elapsed_time": "5:51:49", "remaining_time": "14:46:04"}
109
+ {"current_steps": 1090, "total_steps": 3800, "loss": 0.2601884126663208, "lr": 1.7953064533965786e-05, "epoch": 0.5736842105263158, "percentage": 28.68, "elapsed_time": "5:55:00", "remaining_time": "14:42:38"}
110
+ {"current_steps": 1100, "total_steps": 3800, "loss": 0.2656057834625244, "lr": 1.789704388695916e-05, "epoch": 0.5789473684210527, "percentage": 28.95, "elapsed_time": "5:58:13", "remaining_time": "14:39:16"}
111
+ {"current_steps": 1110, "total_steps": 3800, "loss": 0.26111807823181155, "lr": 1.784035687978153e-05, "epoch": 0.5842105263157895, "percentage": 29.21, "elapsed_time": "6:01:26", "remaining_time": "14:35:55"}
112
+ {"current_steps": 1120, "total_steps": 3800, "loss": 0.26168193817138674, "lr": 1.7783008295737184e-05, "epoch": 0.5894736842105263, "percentage": 29.47, "elapsed_time": "6:04:40", "remaining_time": "14:32:36"}
113
+ {"current_steps": 1130, "total_steps": 3800, "loss": 0.2635683059692383, "lr": 1.7725002973954877e-05, "epoch": 0.5947368421052631, "percentage": 29.74, "elapsed_time": "6:07:54", "remaining_time": "14:29:18"}
114
+ {"current_steps": 1140, "total_steps": 3800, "loss": 0.26383979320526124, "lr": 1.766634580897956e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "6:11:08", "remaining_time": "14:25:59"}
115
+ {"current_steps": 1150, "total_steps": 3800, "loss": 0.2703020334243774, "lr": 1.7607041750359306e-05, "epoch": 0.6052631578947368, "percentage": 30.26, "elapsed_time": "6:14:21", "remaining_time": "14:22:38"}
116
+ {"current_steps": 1160, "total_steps": 3800, "loss": 0.25947682857513427, "lr": 1.7547095802227723e-05, "epoch": 0.6105263157894737, "percentage": 30.53, "elapsed_time": "6:17:33", "remaining_time": "14:19:16"}
117
+ {"current_steps": 1170, "total_steps": 3800, "loss": 0.2625890731811523, "lr": 1.7486513022881658e-05, "epoch": 0.6157894736842106, "percentage": 30.79, "elapsed_time": "6:20:46", "remaining_time": "14:15:55"}
118
+ {"current_steps": 1180, "total_steps": 3800, "loss": 0.2612356185913086, "lr": 1.7425298524354403e-05, "epoch": 0.6210526315789474, "percentage": 31.05, "elapsed_time": "6:23:58", "remaining_time": "14:12:33"}
119
+ {"current_steps": 1190, "total_steps": 3800, "loss": 0.26089015007019045, "lr": 1.7363457471984312e-05, "epoch": 0.6263157894736842, "percentage": 31.32, "elapsed_time": "6:27:10", "remaining_time": "14:09:11"}
120
+ {"current_steps": 1200, "total_steps": 3800, "loss": 0.26446876525878904, "lr": 1.7300995083978965e-05, "epoch": 0.631578947368421, "percentage": 31.58, "elapsed_time": "6:30:23", "remaining_time": "14:05:51"}
121
+ {"current_steps": 1210, "total_steps": 3800, "loss": 0.26449496746063234, "lr": 1.723791663097483e-05, "epoch": 0.6368421052631579, "percentage": 31.84, "elapsed_time": "6:35:10", "remaining_time": "14:05:51"}
122
+ {"current_steps": 1220, "total_steps": 3800, "loss": 0.2561885118484497, "lr": 1.7174227435592544e-05, "epoch": 0.6421052631578947, "percentage": 32.11, "elapsed_time": "6:38:25", "remaining_time": "14:02:34"}
123
+ {"current_steps": 1230, "total_steps": 3800, "loss": 0.26837003231048584, "lr": 1.7109932871987766e-05, "epoch": 0.6473684210526316, "percentage": 32.37, "elapsed_time": "6:41:40", "remaining_time": "13:59:16"}
124
+ {"current_steps": 1240, "total_steps": 3800, "loss": 0.2621891975402832, "lr": 1.7045038365397715e-05, "epoch": 0.6526315789473685, "percentage": 32.63, "elapsed_time": "6:44:55", "remaining_time": "13:55:58"}
125
+ {"current_steps": 1250, "total_steps": 3800, "loss": 0.25557448863983157, "lr": 1.697954939168338e-05, "epoch": 0.6578947368421053, "percentage": 32.89, "elapsed_time": "6:48:09", "remaining_time": "13:52:39"}
126
+ {"current_steps": 1260, "total_steps": 3800, "loss": 0.258845853805542, "lr": 1.6913471476867448e-05, "epoch": 0.6631578947368421, "percentage": 33.16, "elapsed_time": "6:51:22", "remaining_time": "13:49:16"}
127
+ {"current_steps": 1270, "total_steps": 3800, "loss": 0.25761024951934813, "lr": 1.684681019666803e-05, "epoch": 0.6684210526315789, "percentage": 33.42, "elapsed_time": "6:54:34", "remaining_time": "13:45:54"}
128
+ {"current_steps": 1280, "total_steps": 3800, "loss": 0.2636724948883057, "lr": 1.6779571176028163e-05, "epoch": 0.6736842105263158, "percentage": 33.68, "elapsed_time": "6:57:47", "remaining_time": "13:42:32"}
129
+ {"current_steps": 1290, "total_steps": 3800, "loss": 0.26073036193847654, "lr": 1.6711760088641197e-05, "epoch": 0.6789473684210526, "percentage": 33.95, "elapsed_time": "7:01:00", "remaining_time": "13:39:10"}
130
+ {"current_steps": 1300, "total_steps": 3800, "loss": 0.2574197053909302, "lr": 1.6643382656472006e-05, "epoch": 0.6842105263157895, "percentage": 34.21, "elapsed_time": "7:04:15", "remaining_time": "13:35:52"}
131
+ {"current_steps": 1310, "total_steps": 3800, "loss": 0.2566478729248047, "lr": 1.657444464927419e-05, "epoch": 0.6894736842105263, "percentage": 34.47, "elapsed_time": "7:07:27", "remaining_time": "13:32:30"}
132
+ {"current_steps": 1320, "total_steps": 3800, "loss": 0.2704493045806885, "lr": 1.650495188410321e-05, "epoch": 0.6947368421052632, "percentage": 34.74, "elapsed_time": "7:10:39", "remaining_time": "13:29:06"}
133
+ {"current_steps": 1330, "total_steps": 3800, "loss": 0.2584094762802124, "lr": 1.643491022482554e-05, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "7:13:55", "remaining_time": "13:25:51"}
134
+ {"current_steps": 1340, "total_steps": 3800, "loss": 0.260040283203125, "lr": 1.6364325581623864e-05, "epoch": 0.7052631578947368, "percentage": 35.26, "elapsed_time": "7:17:11", "remaining_time": "13:22:35"}
135
+ {"current_steps": 1350, "total_steps": 3800, "loss": 0.25489492416381837, "lr": 1.6293203910498375e-05, "epoch": 0.7105263157894737, "percentage": 35.53, "elapsed_time": "7:20:23", "remaining_time": "13:19:13"}
136
+ {"current_steps": 1360, "total_steps": 3800, "loss": 0.26243014335632325, "lr": 1.6221551212764204e-05, "epoch": 0.7157894736842105, "percentage": 35.79, "elapsed_time": "7:23:36", "remaining_time": "13:15:52"}
137
+ {"current_steps": 1370, "total_steps": 3800, "loss": 0.26453495025634766, "lr": 1.6149373534545008e-05, "epoch": 0.7210526315789474, "percentage": 36.05, "elapsed_time": "7:26:48", "remaining_time": "13:12:30"}
138
+ {"current_steps": 1380, "total_steps": 3800, "loss": 0.25987796783447265, "lr": 1.6076676966262815e-05, "epoch": 0.7263157894736842, "percentage": 36.32, "elapsed_time": "7:30:00", "remaining_time": "13:09:09"}
139
+ {"current_steps": 1390, "total_steps": 3800, "loss": 0.2542286396026611, "lr": 1.6003467642124086e-05, "epoch": 0.7315789473684211, "percentage": 36.58, "elapsed_time": "7:33:14", "remaining_time": "13:05:50"}
140
+ {"current_steps": 1400, "total_steps": 3800, "loss": 0.2617928981781006, "lr": 1.592975173960212e-05, "epoch": 0.7368421052631579, "percentage": 36.84, "elapsed_time": "7:36:29", "remaining_time": "13:02:33"}
141
+ {"current_steps": 1410, "total_steps": 3800, "loss": 0.2531562566757202, "lr": 1.5855535478915793e-05, "epoch": 0.7421052631578947, "percentage": 37.11, "elapsed_time": "7:39:43", "remaining_time": "12:59:14"}
142
+ {"current_steps": 1420, "total_steps": 3800, "loss": 0.25049700736999514, "lr": 1.5780825122504672e-05, "epoch": 0.7473684210526316, "percentage": 37.37, "elapsed_time": "7:42:57", "remaining_time": "12:55:56"}
143
+ {"current_steps": 1430, "total_steps": 3800, "loss": 0.25526843070983884, "lr": 1.5705626974500613e-05, "epoch": 0.7526315789473684, "percentage": 37.63, "elapsed_time": "7:46:12", "remaining_time": "12:52:39"}
144
+ {"current_steps": 1440, "total_steps": 3800, "loss": 0.2525237798690796, "lr": 1.5629947380195786e-05, "epoch": 0.7578947368421053, "percentage": 37.89, "elapsed_time": "7:49:26", "remaining_time": "12:49:21"}
145
+ {"current_steps": 1450, "total_steps": 3800, "loss": 0.2499521255493164, "lr": 1.5553792725507265e-05, "epoch": 0.7631578947368421, "percentage": 38.16, "elapsed_time": "7:52:41", "remaining_time": "12:46:05"}
146
+ {"current_steps": 1460, "total_steps": 3800, "loss": 0.2529642581939697, "lr": 1.5477169436438178e-05, "epoch": 0.7684210526315789, "percentage": 38.42, "elapsed_time": "7:55:57", "remaining_time": "12:42:49"}
147
+ {"current_steps": 1470, "total_steps": 3800, "loss": 0.2528361797332764, "lr": 1.5400083978535475e-05, "epoch": 0.7736842105263158, "percentage": 38.68, "elapsed_time": "7:59:10", "remaining_time": "12:39:30"}
148
+ {"current_steps": 1480, "total_steps": 3800, "loss": 0.2572028160095215, "lr": 1.532254285634435e-05, "epoch": 0.7789473684210526, "percentage": 38.95, "elapsed_time": "8:02:24", "remaining_time": "12:36:12"}
149
+ {"current_steps": 1490, "total_steps": 3800, "loss": 0.25772078037261964, "lr": 1.5244552612859407e-05, "epoch": 0.7842105263157895, "percentage": 39.21, "elapsed_time": "8:05:37", "remaining_time": "12:32:53"}
150
+ {"current_steps": 1500, "total_steps": 3800, "loss": 0.2603304386138916, "lr": 1.5166119828972515e-05, "epoch": 0.7894736842105263, "percentage": 39.47, "elapsed_time": "8:08:55", "remaining_time": "12:29:40"}
151
+ {"current_steps": 1510, "total_steps": 3800, "loss": 0.2549354791641235, "lr": 1.5087251122917543e-05, "epoch": 0.7947368421052632, "percentage": 39.74, "elapsed_time": "8:12:10", "remaining_time": "12:26:24"}
152
+ {"current_steps": 1520, "total_steps": 3800, "loss": 0.2570181369781494, "lr": 1.5007953149711885e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "8:15:23", "remaining_time": "12:23:05"}
153
+ {"current_steps": 1530, "total_steps": 3800, "loss": 0.25235695838928224, "lr": 1.4928232600594916e-05, "epoch": 0.8052631578947368, "percentage": 40.26, "elapsed_time": "8:18:37", "remaining_time": "12:19:47"}
154
+ {"current_steps": 1540, "total_steps": 3800, "loss": 0.26191277503967286, "lr": 1.4848096202463373e-05, "epoch": 0.8105263157894737, "percentage": 40.53, "elapsed_time": "8:21:51", "remaining_time": "12:16:30"}
155
+ {"current_steps": 1550, "total_steps": 3800, "loss": 0.2493319034576416, "lr": 1.4767550717303726e-05, "epoch": 0.8157894736842105, "percentage": 40.79, "elapsed_time": "8:25:06", "remaining_time": "12:13:13"}
156
+ {"current_steps": 1560, "total_steps": 3800, "loss": 0.2586613655090332, "lr": 1.4686602941621618e-05, "epoch": 0.8210526315789474, "percentage": 41.05, "elapsed_time": "8:28:20", "remaining_time": "12:09:55"}
157
+ {"current_steps": 1570, "total_steps": 3800, "loss": 0.2521392345428467, "lr": 1.4605259705868334e-05, "epoch": 0.8263157894736842, "percentage": 41.32, "elapsed_time": "8:31:32", "remaining_time": "12:06:35"}
158
+ {"current_steps": 1580, "total_steps": 3800, "loss": 0.25809125900268554, "lr": 1.4523527873864474e-05, "epoch": 0.8315789473684211, "percentage": 41.58, "elapsed_time": "8:34:47", "remaining_time": "12:03:19"}
159
+ {"current_steps": 1590, "total_steps": 3800, "loss": 0.25009665489196775, "lr": 1.4441414342220762e-05, "epoch": 0.8368421052631579, "percentage": 41.84, "elapsed_time": "8:38:03", "remaining_time": "12:00:04"}
160
+ {"current_steps": 1600, "total_steps": 3800, "loss": 0.25235395431518554, "lr": 1.4358926039756106e-05, "epoch": 0.8421052631578947, "percentage": 42.11, "elapsed_time": "8:41:17", "remaining_time": "11:56:46"}
161
+ {"current_steps": 1610, "total_steps": 3800, "loss": 0.2509817838668823, "lr": 1.4276069926912934e-05, "epoch": 0.8473684210526315, "percentage": 42.37, "elapsed_time": "8:46:03", "remaining_time": "11:55:34"}
162
+ {"current_steps": 1620, "total_steps": 3800, "loss": 0.2587169647216797, "lr": 1.4192852995169868e-05, "epoch": 0.8526315789473684, "percentage": 42.63, "elapsed_time": "8:49:18", "remaining_time": "11:52:16"}
163
+ {"current_steps": 1630, "total_steps": 3800, "loss": 0.2517398834228516, "lr": 1.4109282266451777e-05, "epoch": 0.8578947368421053, "percentage": 42.89, "elapsed_time": "8:52:30", "remaining_time": "11:48:55"}
164
+ {"current_steps": 1640, "total_steps": 3800, "loss": 0.25503859519958494, "lr": 1.4025364792537264e-05, "epoch": 0.8631578947368421, "percentage": 43.16, "elapsed_time": "8:55:42", "remaining_time": "11:45:33"}
165
+ {"current_steps": 1650, "total_steps": 3800, "loss": 0.25129916667938235, "lr": 1.3941107654463619e-05, "epoch": 0.868421052631579, "percentage": 43.42, "elapsed_time": "8:58:56", "remaining_time": "11:42:14"}
166
+ {"current_steps": 1660, "total_steps": 3800, "loss": 0.25026085376739504, "lr": 1.3856517961929323e-05, "epoch": 0.8736842105263158, "percentage": 43.68, "elapsed_time": "9:02:10", "remaining_time": "11:38:56"}
167
+ {"current_steps": 1670, "total_steps": 3800, "loss": 0.24895100593566893, "lr": 1.3771602852694127e-05, "epoch": 0.8789473684210526, "percentage": 43.95, "elapsed_time": "9:05:23", "remaining_time": "11:35:36"}
168
+ {"current_steps": 1680, "total_steps": 3800, "loss": 0.2604621171951294, "lr": 1.3686369491976748e-05, "epoch": 0.8842105263157894, "percentage": 44.21, "elapsed_time": "9:08:36", "remaining_time": "11:32:16"}
169
+ {"current_steps": 1690, "total_steps": 3800, "loss": 0.24665045738220215, "lr": 1.3600825071850282e-05, "epoch": 0.8894736842105263, "percentage": 44.47, "elapsed_time": "9:11:48", "remaining_time": "11:28:57"}
170
+ {"current_steps": 1700, "total_steps": 3800, "loss": 0.25367374420166017, "lr": 1.3514976810635302e-05, "epoch": 0.8947368421052632, "percentage": 44.74, "elapsed_time": "9:15:01", "remaining_time": "11:25:37"}
171
+ {"current_steps": 1710, "total_steps": 3800, "loss": 0.24983105659484864, "lr": 1.3428831952290803e-05, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "9:18:15", "remaining_time": "11:22:18"}
172
+ {"current_steps": 1720, "total_steps": 3800, "loss": 0.2547269105911255, "lr": 1.3342397765802918e-05, "epoch": 0.9052631578947369, "percentage": 45.26, "elapsed_time": "9:21:30", "remaining_time": "11:19:02"}
173
+ {"current_steps": 1730, "total_steps": 3800, "loss": 0.25430710315704347, "lr": 1.3255681544571568e-05, "epoch": 0.9105263157894737, "percentage": 45.53, "elapsed_time": "9:24:43", "remaining_time": "11:15:42"}
174
+ {"current_steps": 1740, "total_steps": 3800, "loss": 0.25717883110046386, "lr": 1.3168690605795044e-05, "epoch": 0.9157894736842105, "percentage": 45.79, "elapsed_time": "9:27:57", "remaining_time": "11:12:24"}
175
+ {"current_steps": 1750, "total_steps": 3800, "loss": 0.24728927612304688, "lr": 1.3081432289852566e-05, "epoch": 0.9210526315789473, "percentage": 46.05, "elapsed_time": "9:31:10", "remaining_time": "11:09:05"}
176
+ {"current_steps": 1760, "total_steps": 3800, "loss": 0.24457645416259766, "lr": 1.2993913959684897e-05, "epoch": 0.9263157894736842, "percentage": 46.32, "elapsed_time": "9:34:24", "remaining_time": "11:05:47"}
177
+ {"current_steps": 1770, "total_steps": 3800, "loss": 0.25548529624938965, "lr": 1.2906143000173041e-05, "epoch": 0.9315789473684211, "percentage": 46.58, "elapsed_time": "9:37:38", "remaining_time": "11:02:29"}
178
+ {"current_steps": 1780, "total_steps": 3800, "loss": 0.24899468421936036, "lr": 1.2818126817515126e-05, "epoch": 0.9368421052631579, "percentage": 46.84, "elapsed_time": "9:40:52", "remaining_time": "10:59:12"}
179
+ {"current_steps": 1790, "total_steps": 3800, "loss": 0.247794246673584, "lr": 1.2729872838601436e-05, "epoch": 0.9421052631578948, "percentage": 47.11, "elapsed_time": "9:44:05", "remaining_time": "10:55:52"}
180
+ {"current_steps": 1800, "total_steps": 3800, "loss": 0.2530705213546753, "lr": 1.2641388510387733e-05, "epoch": 0.9473684210526315, "percentage": 47.37, "elapsed_time": "9:47:19", "remaining_time": "10:52:34"}
181
+ {"current_steps": 1810, "total_steps": 3800, "loss": 0.2409834384918213, "lr": 1.2552681299266873e-05, "epoch": 0.9526315789473684, "percentage": 47.63, "elapsed_time": "9:50:32", "remaining_time": "10:49:15"}
182
+ {"current_steps": 1820, "total_steps": 3800, "loss": 0.24837055206298828, "lr": 1.2463758690438793e-05, "epoch": 0.9578947368421052, "percentage": 47.89, "elapsed_time": "9:53:44", "remaining_time": "10:45:56"}
183
+ {"current_steps": 1830, "total_steps": 3800, "loss": 0.2476038694381714, "lr": 1.2374628187278888e-05, "epoch": 0.9631578947368421, "percentage": 48.16, "elapsed_time": "9:56:57", "remaining_time": "10:42:37"}
184
+ {"current_steps": 1840, "total_steps": 3800, "loss": 0.25147113800048826, "lr": 1.2285297310704883e-05, "epoch": 0.968421052631579, "percentage": 48.42, "elapsed_time": "10:00:11", "remaining_time": "10:39:19"}
185
+ {"current_steps": 1850, "total_steps": 3800, "loss": 0.2510018825531006, "lr": 1.21957735985422e-05, "epoch": 0.9736842105263158, "percentage": 48.68, "elapsed_time": "10:03:25", "remaining_time": "10:36:02"}
186
+ {"current_steps": 1860, "total_steps": 3800, "loss": 0.24750916957855223, "lr": 1.210606460488792e-05, "epoch": 0.9789473684210527, "percentage": 48.95, "elapsed_time": "10:06:38", "remaining_time": "10:32:44"}
187
+ {"current_steps": 1870, "total_steps": 3800, "loss": 0.2443995952606201, "lr": 1.2016177899473344e-05, "epoch": 0.9842105263157894, "percentage": 49.21, "elapsed_time": "10:09:50", "remaining_time": "10:29:24"}
188
+ {"current_steps": 1880, "total_steps": 3800, "loss": 0.2498345136642456, "lr": 1.1926121067025278e-05, "epoch": 0.9894736842105263, "percentage": 49.47, "elapsed_time": "10:13:02", "remaining_time": "10:26:05"}
189
+ {"current_steps": 1890, "total_steps": 3800, "loss": 0.24004738330841063, "lr": 1.1835901706626e-05, "epoch": 0.9947368421052631, "percentage": 49.74, "elapsed_time": "10:16:14", "remaining_time": "10:22:46"}
190
+ {"current_steps": 1900, "total_steps": 3800, "loss": 0.24387748241424562, "lr": 1.1745527431072052e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "10:19:29", "remaining_time": "10:19:29"}
191
+ {"current_steps": 1910, "total_steps": 3800, "loss": 0.20784101486206055, "lr": 1.1655005866231874e-05, "epoch": 1.0052631578947369, "percentage": 50.26, "elapsed_time": "10:22:44", "remaining_time": "10:16:12"}
192
+ {"current_steps": 1920, "total_steps": 3800, "loss": 0.2094496250152588, "lr": 1.156434465040231e-05, "epoch": 1.0105263157894737, "percentage": 50.53, "elapsed_time": "10:25:57", "remaining_time": "10:12:55"}
193
+ {"current_steps": 1930, "total_steps": 3800, "loss": 0.2063742160797119, "lr": 1.1473551433664093e-05, "epoch": 1.0157894736842106, "percentage": 50.79, "elapsed_time": "10:29:11", "remaining_time": "10:09:38"}
194
+ {"current_steps": 1940, "total_steps": 3800, "loss": 0.2070340633392334, "lr": 1.1382633877236321e-05, "epoch": 1.0210526315789474, "percentage": 51.05, "elapsed_time": "10:32:23", "remaining_time": "10:06:18"}
195
+ {"current_steps": 1950, "total_steps": 3800, "loss": 0.20527045726776122, "lr": 1.1291599652829994e-05, "epoch": 1.0263157894736843, "percentage": 51.32, "elapsed_time": "10:35:37", "remaining_time": "10:03:01"}
196
+ {"current_steps": 1960, "total_steps": 3800, "loss": 0.20804226398468018, "lr": 1.1200456442000667e-05, "epoch": 1.0315789473684212, "percentage": 51.58, "elapsed_time": "10:38:52", "remaining_time": "9:59:45"}
197
+ {"current_steps": 1970, "total_steps": 3800, "loss": 0.20433292388916016, "lr": 1.110921193550027e-05, "epoch": 1.0368421052631578, "percentage": 51.84, "elapsed_time": "10:42:06", "remaining_time": "9:56:28"}
198
+ {"current_steps": 1980, "total_steps": 3800, "loss": 0.20756316184997559, "lr": 1.1017873832628172e-05, "epoch": 1.0421052631578946, "percentage": 52.11, "elapsed_time": "10:45:21", "remaining_time": "9:53:12"}
199
+ {"current_steps": 1990, "total_steps": 3800, "loss": 0.2041926383972168, "lr": 1.0926449840581478e-05, "epoch": 1.0473684210526315, "percentage": 52.37, "elapsed_time": "10:48:33", "remaining_time": "9:49:53"}
200
+ {"current_steps": 2000, "total_steps": 3800, "loss": 0.20382113456726075, "lr": 1.0834947673804722e-05, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "10:51:48", "remaining_time": "9:46:37"}
201
+ {"current_steps": 2010, "total_steps": 3800, "loss": 0.20006492137908935, "lr": 1.0743375053338879e-05, "epoch": 1.0578947368421052, "percentage": 52.89, "elapsed_time": "10:56:33", "remaining_time": "9:44:42"}
202
+ {"current_steps": 2020, "total_steps": 3800, "loss": 0.20051677227020265, "lr": 1.0651739706169884e-05, "epoch": 1.063157894736842, "percentage": 53.16, "elapsed_time": "10:59:45", "remaining_time": "9:41:22"}
203
+ {"current_steps": 2030, "total_steps": 3800, "loss": 0.20347986221313477, "lr": 1.0560049364576614e-05, "epoch": 1.068421052631579, "percentage": 53.42, "elapsed_time": "11:03:00", "remaining_time": "9:38:05"}
204
+ {"current_steps": 2040, "total_steps": 3800, "loss": 0.19931771755218505, "lr": 1.0468311765478426e-05, "epoch": 1.0736842105263158, "percentage": 53.68, "elapsed_time": "11:06:14", "remaining_time": "9:34:47"}
205
+ {"current_steps": 2050, "total_steps": 3800, "loss": 0.20710306167602538, "lr": 1.0376534649782304e-05, "epoch": 1.0789473684210527, "percentage": 53.95, "elapsed_time": "11:09:28", "remaining_time": "9:31:30"}
206
+ {"current_steps": 2060, "total_steps": 3800, "loss": 0.20461549758911132, "lr": 1.028472576172969e-05, "epoch": 1.0842105263157895, "percentage": 54.21, "elapsed_time": "11:12:40", "remaining_time": "9:28:11"}
207
+ {"current_steps": 2070, "total_steps": 3800, "loss": 0.20261452198028565, "lr": 1.0192892848243003e-05, "epoch": 1.0894736842105264, "percentage": 54.47, "elapsed_time": "11:15:55", "remaining_time": "9:24:54"}
208
+ {"current_steps": 2080, "total_steps": 3800, "loss": 0.1989670991897583, "lr": 1.0101043658271954e-05, "epoch": 1.0947368421052632, "percentage": 54.74, "elapsed_time": "11:19:09", "remaining_time": "9:21:36"}
209
+ {"current_steps": 2090, "total_steps": 3800, "loss": 0.20732603073120118, "lr": 1.0009185942139676e-05, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "11:22:22", "remaining_time": "9:18:18"}
210
+ {"current_steps": 2100, "total_steps": 3800, "loss": 0.20671296119689941, "lr": 9.917327450888751e-06, "epoch": 1.1052631578947367, "percentage": 55.26, "elapsed_time": "11:25:36", "remaining_time": "9:15:00"}
211
+ {"current_steps": 2110, "total_steps": 3800, "loss": 0.2034555196762085, "lr": 9.825475935627165e-06, "epoch": 1.1105263157894736, "percentage": 55.53, "elapsed_time": "11:28:50", "remaining_time": "9:11:43"}
212
+ {"current_steps": 2120, "total_steps": 3800, "loss": 0.20147459506988524, "lr": 9.733639146874266e-06, "epoch": 1.1157894736842104, "percentage": 55.79, "elapsed_time": "11:32:03", "remaining_time": "9:08:25"}
213
+ {"current_steps": 2130, "total_steps": 3800, "loss": 0.20112955570220947, "lr": 9.641824833906754e-06, "epoch": 1.1210526315789473, "percentage": 56.05, "elapsed_time": "11:35:19", "remaining_time": "9:05:09"}
214
+ {"current_steps": 2140, "total_steps": 3800, "loss": 0.2055084228515625, "lr": 9.550040744104817e-06, "epoch": 1.1263157894736842, "percentage": 56.32, "elapsed_time": "11:38:33", "remaining_time": "9:01:52"}
215
+ {"current_steps": 2150, "total_steps": 3800, "loss": 0.20572924613952637, "lr": 9.458294622298371e-06, "epoch": 1.131578947368421, "percentage": 56.58, "elapsed_time": "11:41:45", "remaining_time": "8:58:33"}
216
+ {"current_steps": 2160, "total_steps": 3800, "loss": 0.20209026336669922, "lr": 9.366594210113564e-06, "epoch": 1.1368421052631579, "percentage": 56.84, "elapsed_time": "11:44:56", "remaining_time": "8:55:14"}
217
+ {"current_steps": 2170, "total_steps": 3800, "loss": 0.20527091026306152, "lr": 9.27494724531951e-06, "epoch": 1.1421052631578947, "percentage": 57.11, "elapsed_time": "11:48:10", "remaining_time": "8:51:56"}
218
+ {"current_steps": 2180, "total_steps": 3800, "loss": 0.2078498125076294, "lr": 9.183361461175397e-06, "epoch": 1.1473684210526316, "percentage": 57.37, "elapsed_time": "11:51:22", "remaining_time": "8:48:38"}
219
+ {"current_steps": 2190, "total_steps": 3800, "loss": 0.2069688081741333, "lr": 9.091844585777919e-06, "epoch": 1.1526315789473685, "percentage": 57.63, "elapsed_time": "11:54:36", "remaining_time": "8:45:21"}
220
+ {"current_steps": 2200, "total_steps": 3800, "loss": 0.1988505244255066, "lr": 9.00040434140919e-06, "epoch": 1.1578947368421053, "percentage": 57.89, "elapsed_time": "11:57:48", "remaining_time": "8:42:02"}
221
+ {"current_steps": 2210, "total_steps": 3800, "loss": 0.20135457515716554, "lr": 8.909048443885114e-06, "epoch": 1.1631578947368422, "percentage": 58.16, "elapsed_time": "12:01:05", "remaining_time": "8:38:47"}
222
+ {"current_steps": 2220, "total_steps": 3800, "loss": 0.21084017753601075, "lr": 8.817784601904342e-06, "epoch": 1.168421052631579, "percentage": 58.42, "elapsed_time": "12:04:18", "remaining_time": "8:35:29"}
223
+ {"current_steps": 2230, "total_steps": 3800, "loss": 0.20522718429565429, "lr": 8.726620516397777e-06, "epoch": 1.1736842105263159, "percentage": 58.68, "elapsed_time": "12:07:31", "remaining_time": "8:32:12"}
224
+ {"current_steps": 2240, "total_steps": 3800, "loss": 0.20526511669158937, "lr": 8.635563879878784e-06, "epoch": 1.1789473684210527, "percentage": 58.95, "elapsed_time": "12:10:43", "remaining_time": "8:28:53"}
225
+ {"current_steps": 2250, "total_steps": 3800, "loss": 0.20150189399719237, "lr": 8.544622375794064e-06, "epoch": 1.1842105263157894, "percentage": 59.21, "elapsed_time": "12:13:56", "remaining_time": "8:25:36"}
226
+ {"current_steps": 2260, "total_steps": 3800, "loss": 0.20268006324768068, "lr": 8.453803677875355e-06, "epoch": 1.1894736842105262, "percentage": 59.47, "elapsed_time": "12:17:09", "remaining_time": "8:22:18"}
227
+ {"current_steps": 2270, "total_steps": 3800, "loss": 0.19919428825378419, "lr": 8.363115449491875e-06, "epoch": 1.194736842105263, "percentage": 59.74, "elapsed_time": "12:20:22", "remaining_time": "8:19:01"}
228
+ {"current_steps": 2280, "total_steps": 3800, "loss": 0.20649614334106445, "lr": 8.2725653430037e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "12:23:34", "remaining_time": "8:15:42"}
229
+ {"current_steps": 2290, "total_steps": 3800, "loss": 0.19812414646148682, "lr": 8.182160999116046e-06, "epoch": 1.2052631578947368, "percentage": 60.26, "elapsed_time": "12:26:46", "remaining_time": "8:12:25"}
230
+ {"current_steps": 2300, "total_steps": 3800, "loss": 0.20605757236480712, "lr": 8.091910046234552e-06, "epoch": 1.2105263157894737, "percentage": 60.53, "elapsed_time": "12:30:00", "remaining_time": "8:09:08"}
231
+ {"current_steps": 2310, "total_steps": 3800, "loss": 0.20103375911712645, "lr": 8.001820099821566e-06, "epoch": 1.2157894736842105, "percentage": 60.79, "elapsed_time": "12:33:14", "remaining_time": "8:05:51"}
232
+ {"current_steps": 2320, "total_steps": 3800, "loss": 0.20387532711029052, "lr": 7.91189876175355e-06, "epoch": 1.2210526315789474, "percentage": 61.05, "elapsed_time": "12:36:28", "remaining_time": "8:02:34"}
233
+ {"current_steps": 2330, "total_steps": 3800, "loss": 0.20924797058105468, "lr": 7.822153619679644e-06, "epoch": 1.2263157894736842, "percentage": 61.32, "elapsed_time": "12:39:40", "remaining_time": "7:59:17"}
234
+ {"current_steps": 2340, "total_steps": 3800, "loss": 0.19755966663360597, "lr": 7.732592246381392e-06, "epoch": 1.231578947368421, "percentage": 61.58, "elapsed_time": "12:42:53", "remaining_time": "7:55:59"}
235
+ {"current_steps": 2350, "total_steps": 3800, "loss": 0.20248010158538818, "lr": 7.643222199133758e-06, "epoch": 1.236842105263158, "percentage": 61.84, "elapsed_time": "12:46:07", "remaining_time": "7:52:42"}
236
+ {"current_steps": 2360, "total_steps": 3800, "loss": 0.20098273754119872, "lr": 7.554051019067421e-06, "epoch": 1.2421052631578948, "percentage": 62.11, "elapsed_time": "12:49:21", "remaining_time": "7:49:26"}
237
+ {"current_steps": 2370, "total_steps": 3800, "loss": 0.20353875160217286, "lr": 7.46508623053246e-06, "epoch": 1.2473684210526317, "percentage": 62.37, "elapsed_time": "12:52:32", "remaining_time": "7:46:07"}
238
+ {"current_steps": 2380, "total_steps": 3800, "loss": 0.20233564376831054, "lr": 7.376335340463442e-06, "epoch": 1.2526315789473683, "percentage": 62.63, "elapsed_time": "12:55:45", "remaining_time": "7:42:50"}
239
+ {"current_steps": 2390, "total_steps": 3800, "loss": 0.19838900566101075, "lr": 7.2878058377459716e-06, "epoch": 1.2578947368421054, "percentage": 62.89, "elapsed_time": "12:58:58", "remaining_time": "7:39:33"}
240
+ {"current_steps": 2400, "total_steps": 3800, "loss": 0.2026752710342407, "lr": 7.199505192584772e-06, "epoch": 1.263157894736842, "percentage": 63.16, "elapsed_time": "13:02:10", "remaining_time": "7:36:16"}
241
+ {"current_steps": 2410, "total_steps": 3800, "loss": 0.2023756980895996, "lr": 7.111440855873346e-06, "epoch": 1.268421052631579, "percentage": 63.42, "elapsed_time": "13:06:58", "remaining_time": "7:33:53"}
242
+ {"current_steps": 2420, "total_steps": 3800, "loss": 0.19736809730529786, "lr": 7.023620258565271e-06, "epoch": 1.2736842105263158, "percentage": 63.68, "elapsed_time": "13:10:12", "remaining_time": "7:30:36"}
243
+ {"current_steps": 2430, "total_steps": 3800, "loss": 0.2012228012084961, "lr": 6.9360508110471526e-06, "epoch": 1.2789473684210526, "percentage": 63.95, "elapsed_time": "13:13:23", "remaining_time": "7:27:18"}
244
+ {"current_steps": 2440, "total_steps": 3800, "loss": 0.20069727897644044, "lr": 6.848739902513327e-06, "epoch": 1.2842105263157895, "percentage": 64.21, "elapsed_time": "13:16:38", "remaining_time": "7:24:02"}
245
+ {"current_steps": 2450, "total_steps": 3800, "loss": 0.20128388404846193, "lr": 6.761694900342373e-06, "epoch": 1.2894736842105263, "percentage": 64.47, "elapsed_time": "13:19:53", "remaining_time": "7:20:45"}
246
+ {"current_steps": 2460, "total_steps": 3800, "loss": 0.2063040018081665, "lr": 6.674923149475433e-06, "epoch": 1.2947368421052632, "percentage": 64.74, "elapsed_time": "13:23:04", "remaining_time": "7:17:26"}
247
+ {"current_steps": 2470, "total_steps": 3800, "loss": 0.2017989158630371, "lr": 6.588431971796439e-06, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "13:26:16", "remaining_time": "7:14:09"}
248
+ {"current_steps": 2480, "total_steps": 3800, "loss": 0.20122807025909423, "lr": 6.502228665514284e-06, "epoch": 1.305263157894737, "percentage": 65.26, "elapsed_time": "13:29:30", "remaining_time": "7:10:51"}
249
+ {"current_steps": 2490, "total_steps": 3800, "loss": 0.1991926074028015, "lr": 6.4163205045469975e-06, "epoch": 1.3105263157894738, "percentage": 65.53, "elapsed_time": "13:32:43", "remaining_time": "7:07:34"}
250
+ {"current_steps": 2500, "total_steps": 3800, "loss": 0.20284779071807862, "lr": 6.330714737907968e-06, "epoch": 1.3157894736842106, "percentage": 65.79, "elapsed_time": "13:36:00", "remaining_time": "7:04:19"}
251
+ {"current_steps": 2510, "total_steps": 3800, "loss": 0.19527244567871094, "lr": 6.245418589094254e-06, "epoch": 1.3210526315789473, "percentage": 66.05, "elapsed_time": "13:39:12", "remaining_time": "7:01:01"}
252
+ {"current_steps": 2520, "total_steps": 3800, "loss": 0.1968228578567505, "lr": 6.1604392554770635e-06, "epoch": 1.3263157894736843, "percentage": 66.32, "elapsed_time": "13:42:26", "remaining_time": "6:57:44"}
253
+ {"current_steps": 2530, "total_steps": 3800, "loss": 0.20151681900024415, "lr": 6.07578390769443e-06, "epoch": 1.331578947368421, "percentage": 66.58, "elapsed_time": "13:45:41", "remaining_time": "6:54:28"}
254
+ {"current_steps": 2540, "total_steps": 3800, "loss": 0.19509825706481934, "lr": 5.9914596890461615e-06, "epoch": 1.3368421052631578, "percentage": 66.84, "elapsed_time": "13:48:57", "remaining_time": "6:51:12"}
255
+ {"current_steps": 2550, "total_steps": 3800, "loss": 0.20209035873413086, "lr": 5.907473714891061e-06, "epoch": 1.3421052631578947, "percentage": 67.11, "elapsed_time": "13:52:08", "remaining_time": "6:47:54"}
256
+ {"current_steps": 2560, "total_steps": 3800, "loss": 0.20028293132781982, "lr": 5.823833072046538e-06, "epoch": 1.3473684210526315, "percentage": 67.37, "elapsed_time": "13:55:22", "remaining_time": "6:44:38"}
257
+ {"current_steps": 2570, "total_steps": 3800, "loss": 0.20040664672851563, "lr": 5.7405448181906045e-06, "epoch": 1.3526315789473684, "percentage": 67.63, "elapsed_time": "13:58:35", "remaining_time": "6:41:21"}
258
+ {"current_steps": 2580, "total_steps": 3800, "loss": 0.19900851249694823, "lr": 5.657615981266373e-06, "epoch": 1.3578947368421053, "percentage": 67.89, "elapsed_time": "14:01:48", "remaining_time": "6:38:03"}
259
+ {"current_steps": 2590, "total_steps": 3800, "loss": 0.20092666149139404, "lr": 5.5750535588889895e-06, "epoch": 1.3631578947368421, "percentage": 68.16, "elapsed_time": "14:05:03", "remaining_time": "6:34:47"}
260
+ {"current_steps": 2600, "total_steps": 3800, "loss": 0.1961138963699341, "lr": 5.4928645177551895e-06, "epoch": 1.368421052631579, "percentage": 68.42, "elapsed_time": "14:08:14", "remaining_time": "6:31:29"}
261
+ {"current_steps": 2610, "total_steps": 3800, "loss": 0.1972240090370178, "lr": 5.411055793055442e-06, "epoch": 1.3736842105263158, "percentage": 68.68, "elapsed_time": "14:11:27", "remaining_time": "6:28:12"}
262
+ {"current_steps": 2620, "total_steps": 3800, "loss": 0.19740312099456786, "lr": 5.329634287888752e-06, "epoch": 1.3789473684210527, "percentage": 68.95, "elapsed_time": "14:14:40", "remaining_time": "6:24:56"}
263
+ {"current_steps": 2630, "total_steps": 3800, "loss": 0.20692920684814453, "lr": 5.248606872680169e-06, "epoch": 1.3842105263157896, "percentage": 69.21, "elapsed_time": "14:17:53", "remaining_time": "6:21:39"}
264
+ {"current_steps": 2640, "total_steps": 3800, "loss": 0.19995032548904418, "lr": 5.167980384601041e-06, "epoch": 1.3894736842105262, "percentage": 69.47, "elapsed_time": "14:21:06", "remaining_time": "6:18:21"}
265
+ {"current_steps": 2650, "total_steps": 3800, "loss": 0.19773465394973755, "lr": 5.087761626992111e-06, "epoch": 1.3947368421052633, "percentage": 69.74, "elapsed_time": "14:24:18", "remaining_time": "6:15:04"}
266
+ {"current_steps": 2660, "total_steps": 3800, "loss": 0.19896183013916016, "lr": 5.0079573687894225e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "14:27:31", "remaining_time": "6:11:47"}
267
+ {"current_steps": 2670, "total_steps": 3800, "loss": 0.2002697229385376, "lr": 4.928574343953171e-06, "epoch": 1.4052631578947368, "percentage": 70.26, "elapsed_time": "14:30:44", "remaining_time": "6:08:30"}
268
+ {"current_steps": 2680, "total_steps": 3800, "loss": 0.20564062595367433, "lr": 4.849619250899458e-06, "epoch": 1.4105263157894736, "percentage": 70.53, "elapsed_time": "14:33:55", "remaining_time": "6:05:13"}
269
+ {"current_steps": 2690, "total_steps": 3800, "loss": 0.20029211044311523, "lr": 4.7710987519351085e-06, "epoch": 1.4157894736842105, "percentage": 70.79, "elapsed_time": "14:37:09", "remaining_time": "6:01:57"}
270
+ {"current_steps": 2700, "total_steps": 3800, "loss": 0.1956094980239868, "lr": 4.693019472695462e-06, "epoch": 1.4210526315789473, "percentage": 71.05, "elapsed_time": "14:40:23", "remaining_time": "5:58:40"}
271
+ {"current_steps": 2710, "total_steps": 3800, "loss": 0.19753397703170777, "lr": 4.615388001585326e-06, "epoch": 1.4263157894736842, "percentage": 71.32, "elapsed_time": "14:43:36", "remaining_time": "5:55:24"}
272
+ {"current_steps": 2720, "total_steps": 3800, "loss": 0.19277102947235109, "lr": 4.538210889223016e-06, "epoch": 1.431578947368421, "percentage": 71.58, "elapsed_time": "14:46:48", "remaining_time": "5:52:06"}
273
+ {"current_steps": 2730, "total_steps": 3800, "loss": 0.1982126235961914, "lr": 4.4614946478876305e-06, "epoch": 1.436842105263158, "percentage": 71.84, "elapsed_time": "14:50:02", "remaining_time": "5:48:50"}
274
+ {"current_steps": 2740, "total_steps": 3800, "loss": 0.19417320489883422, "lr": 4.3852457509695115e-06, "epoch": 1.4421052631578948, "percentage": 72.11, "elapsed_time": "14:53:16", "remaining_time": "5:45:34"}
275
+ {"current_steps": 2750, "total_steps": 3800, "loss": 0.1932328462600708, "lr": 4.309470632424045e-06, "epoch": 1.4473684210526316, "percentage": 72.37, "elapsed_time": "14:56:29", "remaining_time": "5:42:17"}
276
+ {"current_steps": 2760, "total_steps": 3800, "loss": 0.1982268810272217, "lr": 4.234175686228728e-06, "epoch": 1.4526315789473685, "percentage": 72.63, "elapsed_time": "14:59:43", "remaining_time": "5:39:01"}
277
+ {"current_steps": 2770, "total_steps": 3800, "loss": 0.19260333776473998, "lr": 4.159367265843662e-06, "epoch": 1.4578947368421051, "percentage": 72.89, "elapsed_time": "15:02:57", "remaining_time": "5:35:45"}
278
+ {"current_steps": 2780, "total_steps": 3800, "loss": 0.1973806858062744, "lr": 4.085051683675424e-06, "epoch": 1.4631578947368422, "percentage": 73.16, "elapsed_time": "15:06:08", "remaining_time": "5:32:28"}
279
+ {"current_steps": 2790, "total_steps": 3800, "loss": 0.1963602900505066, "lr": 4.011235210544435e-06, "epoch": 1.4684210526315788, "percentage": 73.42, "elapsed_time": "15:09:22", "remaining_time": "5:29:11"}
280
+ {"current_steps": 2800, "total_steps": 3800, "loss": 0.2008979082107544, "lr": 3.937924075155807e-06, "epoch": 1.4736842105263157, "percentage": 73.68, "elapsed_time": "15:12:35", "remaining_time": "5:25:55"}
281
+ {"current_steps": 2810, "total_steps": 3800, "loss": 0.19697009325027465, "lr": 3.865124463573774e-06, "epoch": 1.4789473684210526, "percentage": 73.95, "elapsed_time": "15:17:23", "remaining_time": "5:23:12"}
282
+ {"current_steps": 2820, "total_steps": 3800, "loss": 0.20015451908111573, "lr": 3.792842518699689e-06, "epoch": 1.4842105263157894, "percentage": 74.21, "elapsed_time": "15:20:36", "remaining_time": "5:19:55"}
283
+ {"current_steps": 2830, "total_steps": 3800, "loss": 0.19725344181060792, "lr": 3.721084339753702e-06, "epoch": 1.4894736842105263, "percentage": 74.47, "elapsed_time": "15:23:48", "remaining_time": "5:16:38"}
284
+ {"current_steps": 2840, "total_steps": 3800, "loss": 0.19772164821624755, "lr": 3.6498559817600764e-06, "epoch": 1.4947368421052631, "percentage": 74.74, "elapsed_time": "15:27:00", "remaining_time": "5:13:21"}
285
+ {"current_steps": 2850, "total_steps": 3800, "loss": 0.1974316954612732, "lr": 3.5791634550362865e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "15:30:14", "remaining_time": "5:10:04"}
286
+ {"current_steps": 2860, "total_steps": 3800, "loss": 0.19579846858978273, "lr": 3.5090127246858318e-06, "epoch": 1.5052631578947369, "percentage": 75.26, "elapsed_time": "15:33:26", "remaining_time": "5:06:47"}
287
+ {"current_steps": 2870, "total_steps": 3800, "loss": 0.19849755764007568, "lr": 3.4394097100949286e-06, "epoch": 1.5105263157894737, "percentage": 75.53, "elapsed_time": "15:36:40", "remaining_time": "5:03:31"}
288
+ {"current_steps": 2880, "total_steps": 3800, "loss": 0.1946340799331665, "lr": 3.3703602844329963e-06, "epoch": 1.5157894736842106, "percentage": 75.79, "elapsed_time": "15:39:54", "remaining_time": "5:00:14"}
289
+ {"current_steps": 2890, "total_steps": 3800, "loss": 0.1969212770462036, "lr": 3.3018702741570976e-06, "epoch": 1.5210526315789474, "percentage": 76.05, "elapsed_time": "15:43:08", "remaining_time": "4:56:58"}
290
+ {"current_steps": 2900, "total_steps": 3800, "loss": 0.19296889305114745, "lr": 3.2339454585202756e-06, "epoch": 1.526315789473684, "percentage": 76.32, "elapsed_time": "15:46:23", "remaining_time": "4:53:42"}
291
+ {"current_steps": 2910, "total_steps": 3800, "loss": 0.1954205870628357, "lr": 3.1665915690839165e-06, "epoch": 1.5315789473684212, "percentage": 76.58, "elapsed_time": "15:49:36", "remaining_time": "4:50:25"}
292
+ {"current_steps": 2920, "total_steps": 3800, "loss": 0.19373153448104857, "lr": 3.0998142892340932e-06, "epoch": 1.5368421052631578, "percentage": 76.84, "elapsed_time": "15:52:50", "remaining_time": "4:47:09"}
293
+ {"current_steps": 2930, "total_steps": 3800, "loss": 0.1956033229827881, "lr": 3.0336192537020157e-06, "epoch": 1.5421052631578949, "percentage": 77.11, "elapsed_time": "15:56:04", "remaining_time": "4:43:53"}
294
+ {"current_steps": 2940, "total_steps": 3800, "loss": 0.19107308387756347, "lr": 2.968012048088548e-06, "epoch": 1.5473684210526315, "percentage": 77.37, "elapsed_time": "15:59:19", "remaining_time": "4:40:37"}
295
+ {"current_steps": 2950, "total_steps": 3800, "loss": 0.20056076049804689, "lr": 2.9029982083929088e-06, "epoch": 1.5526315789473686, "percentage": 77.63, "elapsed_time": "16:02:30", "remaining_time": "4:37:20"}
296
+ {"current_steps": 2960, "total_steps": 3800, "loss": 0.20021560192108154, "lr": 2.83858322054552e-06, "epoch": 1.5578947368421052, "percentage": 77.89, "elapsed_time": "16:05:47", "remaining_time": "4:34:04"}
297
+ {"current_steps": 2970, "total_steps": 3800, "loss": 0.19537402391433717, "lr": 2.774772519945116e-06, "epoch": 1.563157894736842, "percentage": 78.16, "elapsed_time": "16:09:00", "remaining_time": "4:30:48"}
298
+ {"current_steps": 2980, "total_steps": 3800, "loss": 0.19449059963226317, "lr": 2.7115714910000835e-06, "epoch": 1.568421052631579, "percentage": 78.42, "elapsed_time": "16:12:13", "remaining_time": "4:27:31"}
299
+ {"current_steps": 2990, "total_steps": 3800, "loss": 0.1968981981277466, "lr": 2.6489854666741344e-06, "epoch": 1.5736842105263158, "percentage": 78.68, "elapsed_time": "16:15:28", "remaining_time": "4:24:15"}
300
+ {"current_steps": 3000, "total_steps": 3800, "loss": 0.195830774307251, "lr": 2.587019728036292e-06, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "16:18:45", "remaining_time": "4:21:00"}
301
+ {"current_steps": 3010, "total_steps": 3800, "loss": 0.1970442295074463, "lr": 2.5256795038152824e-06, "epoch": 1.5842105263157895, "percentage": 79.21, "elapsed_time": "16:21:58", "remaining_time": "4:17:43"}
302
+ {"current_steps": 3020, "total_steps": 3800, "loss": 0.2002091407775879, "lr": 2.464969969958314e-06, "epoch": 1.5894736842105264, "percentage": 79.47, "elapsed_time": "16:25:13", "remaining_time": "4:14:27"}
303
+ {"current_steps": 3030, "total_steps": 3800, "loss": 0.19861750602722167, "lr": 2.404896249194346e-06, "epoch": 1.594736842105263, "percentage": 79.74, "elapsed_time": "16:28:27", "remaining_time": "4:11:11"}
304
+ {"current_steps": 3040, "total_steps": 3800, "loss": 0.19542500972747803, "lr": 2.345463410601805e-06, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "16:31:42", "remaining_time": "4:07:55"}
305
+ {"current_steps": 3050, "total_steps": 3800, "loss": 0.19709043502807616, "lr": 2.286676469180871e-06, "epoch": 1.6052631578947367, "percentage": 80.26, "elapsed_time": "16:34:57", "remaining_time": "4:04:39"}
306
+ {"current_steps": 3060, "total_steps": 3800, "loss": 0.1949392557144165, "lr": 2.2285403854302912e-06, "epoch": 1.6105263157894738, "percentage": 80.53, "elapsed_time": "16:38:11", "remaining_time": "4:01:23"}
307
+ {"current_steps": 3070, "total_steps": 3800, "loss": 0.19625964164733886, "lr": 2.171060064928824e-06, "epoch": 1.6157894736842104, "percentage": 80.79, "elapsed_time": "16:41:25", "remaining_time": "3:58:07"}
308
+ {"current_steps": 3080, "total_steps": 3800, "loss": 0.1958683729171753, "lr": 2.114240357921283e-06, "epoch": 1.6210526315789475, "percentage": 81.05, "elapsed_time": "16:44:40", "remaining_time": "3:54:51"}
309
+ {"current_steps": 3090, "total_steps": 3800, "loss": 0.19081616401672363, "lr": 2.0580860589092897e-06, "epoch": 1.6263157894736842, "percentage": 81.32, "elapsed_time": "16:47:54", "remaining_time": "3:51:35"}
310
+ {"current_steps": 3100, "total_steps": 3800, "loss": 0.1947636842727661, "lr": 2.0026019062466882e-06, "epoch": 1.631578947368421, "percentage": 81.58, "elapsed_time": "16:51:08", "remaining_time": "3:48:19"}
311
+ {"current_steps": 3110, "total_steps": 3800, "loss": 0.19309258460998535, "lr": 1.9477925817397358e-06, "epoch": 1.6368421052631579, "percentage": 81.84, "elapsed_time": "16:54:19", "remaining_time": "3:45:02"}
312
+ {"current_steps": 3120, "total_steps": 3800, "loss": 0.19541804790496825, "lr": 1.8936627102520321e-06, "epoch": 1.6421052631578947, "percentage": 82.11, "elapsed_time": "16:57:32", "remaining_time": "3:41:46"}
313
+ {"current_steps": 3130, "total_steps": 3800, "loss": 0.19962093830108643, "lr": 1.8402168593142855e-06, "epoch": 1.6473684210526316, "percentage": 82.37, "elapsed_time": "17:00:48", "remaining_time": "3:38:30"}
314
+ {"current_steps": 3140, "total_steps": 3800, "loss": 0.195822012424469, "lr": 1.7874595387388815e-06, "epoch": 1.6526315789473685, "percentage": 82.63, "elapsed_time": "17:04:00", "remaining_time": "3:35:14"}
315
+ {"current_steps": 3150, "total_steps": 3800, "loss": 0.19865849018096923, "lr": 1.7353952002393604e-06, "epoch": 1.6578947368421053, "percentage": 82.89, "elapsed_time": "17:07:16", "remaining_time": "3:31:58"}
316
+ {"current_steps": 3160, "total_steps": 3800, "loss": 0.19288280010223388, "lr": 1.6840282370547568e-06, "epoch": 1.663157894736842, "percentage": 83.16, "elapsed_time": "17:10:29", "remaining_time": "3:28:42"}
317
+ {"current_steps": 3170, "total_steps": 3800, "loss": 0.19533854722976685, "lr": 1.6333629835789154e-06, "epoch": 1.668421052631579, "percentage": 83.42, "elapsed_time": "17:13:43", "remaining_time": "3:25:26"}
318
+ {"current_steps": 3180, "total_steps": 3800, "loss": 0.19245790243148803, "lr": 1.5834037149947291e-06, "epoch": 1.6736842105263157, "percentage": 83.68, "elapsed_time": "17:16:56", "remaining_time": "3:22:10"}
319
+ {"current_steps": 3190, "total_steps": 3800, "loss": 0.19166877269744872, "lr": 1.534154646913416e-06, "epoch": 1.6789473684210527, "percentage": 83.95, "elapsed_time": "17:20:10", "remaining_time": "3:18:54"}
320
+ {"current_steps": 3200, "total_steps": 3800, "loss": 0.19105905294418335, "lr": 1.4856199350187806e-06, "epoch": 1.6842105263157894, "percentage": 84.21, "elapsed_time": "17:23:21", "remaining_time": "3:15:37"}
321
+ {"current_steps": 3210, "total_steps": 3800, "loss": 0.19024944305419922, "lr": 1.4378036747165746e-06, "epoch": 1.6894736842105265, "percentage": 84.47, "elapsed_time": "17:28:09", "remaining_time": "3:12:39"}
322
+ {"current_steps": 3220, "total_steps": 3800, "loss": 0.19398729801177977, "lr": 1.3907099007889023e-06, "epoch": 1.694736842105263, "percentage": 84.74, "elapsed_time": "17:31:22", "remaining_time": "3:09:22"}
323
+ {"current_steps": 3230, "total_steps": 3800, "loss": 0.19313373565673828, "lr": 1.344342587053782e-06, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "17:34:35", "remaining_time": "3:06:06"}
324
+ {"current_steps": 3240, "total_steps": 3800, "loss": 0.19442253112792968, "lr": 1.2987056460298108e-06, "epoch": 1.7052631578947368, "percentage": 85.26, "elapsed_time": "17:37:48", "remaining_time": "3:02:49"}
325
+ {"current_steps": 3250, "total_steps": 3800, "loss": 0.19540021419525147, "lr": 1.2538029286060428e-06, "epoch": 1.7105263157894737, "percentage": 85.53, "elapsed_time": "17:41:04", "remaining_time": "2:59:34"}
326
+ {"current_steps": 3260, "total_steps": 3800, "loss": 0.19183417558670043, "lr": 1.2096382237170279e-06, "epoch": 1.7157894736842105, "percentage": 85.79, "elapsed_time": "17:44:18", "remaining_time": "2:56:17"}
327
+ {"current_steps": 3270, "total_steps": 3800, "loss": 0.1944838285446167, "lr": 1.1662152580231145e-06, "epoch": 1.7210526315789474, "percentage": 86.05, "elapsed_time": "17:47:31", "remaining_time": "2:53:01"}
328
+ {"current_steps": 3280, "total_steps": 3800, "loss": 0.19714293479919434, "lr": 1.1235376955959787e-06, "epoch": 1.7263157894736842, "percentage": 86.32, "elapsed_time": "17:50:44", "remaining_time": "2:49:45"}
329
+ {"current_steps": 3290, "total_steps": 3800, "loss": 0.18858647346496582, "lr": 1.081609137609455e-06, "epoch": 1.731578947368421, "percentage": 86.58, "elapsed_time": "17:53:57", "remaining_time": "2:46:28"}
330
+ {"current_steps": 3300, "total_steps": 3800, "loss": 0.19322052001953124, "lr": 1.0404331220356568e-06, "epoch": 1.736842105263158, "percentage": 86.84, "elapsed_time": "17:57:10", "remaining_time": "2:43:12"}
331
+ {"current_steps": 3310, "total_steps": 3800, "loss": 0.19312400817871095, "lr": 1.0000131233464484e-06, "epoch": 1.7421052631578946, "percentage": 87.11, "elapsed_time": "18:00:24", "remaining_time": "2:39:56"}
332
+ {"current_steps": 3320, "total_steps": 3800, "loss": 0.18943675756454467, "lr": 9.60352552220256e-07, "epoch": 1.7473684210526317, "percentage": 87.37, "elapsed_time": "18:03:36", "remaining_time": "2:36:39"}
333
+ {"current_steps": 3330, "total_steps": 3800, "loss": 0.19052280187606813, "lr": 9.21454755254283e-07, "epoch": 1.7526315789473683, "percentage": 87.63, "elapsed_time": "18:06:49", "remaining_time": "2:33:23"}
334
+ {"current_steps": 3340, "total_steps": 3800, "loss": 0.19586782455444335, "lr": 8.833230146821059e-07, "epoch": 1.7578947368421054, "percentage": 87.89, "elapsed_time": "18:10:03", "remaining_time": "2:30:07"}
335
+ {"current_steps": 3350, "total_steps": 3800, "loss": 0.19273494482040404, "lr": 8.459605480967348e-07, "epoch": 1.763157894736842, "percentage": 88.16, "elapsed_time": "18:13:15", "remaining_time": "2:26:51"}
336
+ {"current_steps": 3360, "total_steps": 3800, "loss": 0.19584423303604126, "lr": 8.093705081790892e-07, "epoch": 1.768421052631579, "percentage": 88.42, "elapsed_time": "18:16:28", "remaining_time": "2:23:35"}
337
+ {"current_steps": 3370, "total_steps": 3800, "loss": 0.1967606544494629, "lr": 7.735559824319905e-07, "epoch": 1.7736842105263158, "percentage": 88.68, "elapsed_time": "18:19:40", "remaining_time": "2:20:18"}
338
+ {"current_steps": 3380, "total_steps": 3800, "loss": 0.19085731506347656, "lr": 7.385199929196241e-07, "epoch": 1.7789473684210526, "percentage": 88.95, "elapsed_time": "18:22:52", "remaining_time": "2:17:02"}
339
+ {"current_steps": 3390, "total_steps": 3800, "loss": 0.1873401403427124, "lr": 7.042654960125339e-07, "epoch": 1.7842105263157895, "percentage": 89.21, "elapsed_time": "18:26:05", "remaining_time": "2:13:46"}
340
+ {"current_steps": 3400, "total_steps": 3800, "loss": 0.19778637886047362, "lr": 6.70795382138173e-07, "epoch": 1.7894736842105263, "percentage": 89.47, "elapsed_time": "18:29:16", "remaining_time": "2:10:30"}
341
+ {"current_steps": 3410, "total_steps": 3800, "loss": 0.19017722606658935, "lr": 6.381124755369938e-07, "epoch": 1.7947368421052632, "percentage": 89.74, "elapsed_time": "18:32:31", "remaining_time": "2:07:14"}
342
+ {"current_steps": 3420, "total_steps": 3800, "loss": 0.19560375213623046, "lr": 6.062195340241406e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "18:35:44", "remaining_time": "2:03:58"}
343
+ {"current_steps": 3430, "total_steps": 3800, "loss": 0.1918318510055542, "lr": 5.751192487567426e-07, "epoch": 1.805263157894737, "percentage": 90.26, "elapsed_time": "18:38:56", "remaining_time": "2:00:42"}
344
+ {"current_steps": 3440, "total_steps": 3800, "loss": 0.1960618257522583, "lr": 5.448142440068316e-07, "epoch": 1.8105263157894735, "percentage": 90.53, "elapsed_time": "18:42:09", "remaining_time": "1:57:26"}
345
+ {"current_steps": 3450, "total_steps": 3800, "loss": 0.1913236141204834, "lr": 5.15307076939906e-07, "epoch": 1.8157894736842106, "percentage": 90.79, "elapsed_time": "18:45:23", "remaining_time": "1:54:10"}
346
+ {"current_steps": 3460, "total_steps": 3800, "loss": 0.1932381272315979, "lr": 4.866002373991474e-07, "epoch": 1.8210526315789473, "percentage": 91.05, "elapsed_time": "18:48:35", "remaining_time": "1:50:54"}
347
+ {"current_steps": 3470, "total_steps": 3800, "loss": 0.1993856430053711, "lr": 4.586961476953311e-07, "epoch": 1.8263157894736843, "percentage": 91.32, "elapsed_time": "18:51:48", "remaining_time": "1:47:38"}
348
+ {"current_steps": 3480, "total_steps": 3800, "loss": 0.19607802629470825, "lr": 4.3159716240242954e-07, "epoch": 1.831578947368421, "percentage": 91.58, "elapsed_time": "18:55:02", "remaining_time": "1:44:22"}
349
+ {"current_steps": 3490, "total_steps": 3800, "loss": 0.19404864311218262, "lr": 4.05305568158928e-07, "epoch": 1.836842105263158, "percentage": 91.84, "elapsed_time": "18:58:16", "remaining_time": "1:41:06"}
350
+ {"current_steps": 3500, "total_steps": 3800, "loss": 0.19020428657531738, "lr": 3.798235834748787e-07, "epoch": 1.8421052631578947, "percentage": 92.11, "elapsed_time": "19:01:27", "remaining_time": "1:37:50"}
351
+ {"current_steps": 3510, "total_steps": 3800, "loss": 0.19170570373535156, "lr": 3.5515335854469534e-07, "epoch": 1.8473684210526315, "percentage": 92.37, "elapsed_time": "19:04:41", "remaining_time": "1:34:34"}
352
+ {"current_steps": 3520, "total_steps": 3800, "loss": 0.19208167791366576, "lr": 3.3129697506572467e-07, "epoch": 1.8526315789473684, "percentage": 92.63, "elapsed_time": "19:07:53", "remaining_time": "1:31:18"}
353
+ {"current_steps": 3530, "total_steps": 3800, "loss": 0.19290330410003662, "lr": 3.082564460625903e-07, "epoch": 1.8578947368421053, "percentage": 92.89, "elapsed_time": "19:11:06", "remaining_time": "1:28:02"}
354
+ {"current_steps": 3540, "total_steps": 3800, "loss": 0.19398319721221924, "lr": 2.860337157173243e-07, "epoch": 1.8631578947368421, "percentage": 93.16, "elapsed_time": "19:14:18", "remaining_time": "1:24:46"}
355
+ {"current_steps": 3550, "total_steps": 3800, "loss": 0.19711978435516359, "lr": 2.646306592053205e-07, "epoch": 1.868421052631579, "percentage": 93.42, "elapsed_time": "19:17:30", "remaining_time": "1:21:30"}
356
+ {"current_steps": 3560, "total_steps": 3800, "loss": 0.193030047416687, "lr": 2.440490825371078e-07, "epoch": 1.8736842105263158, "percentage": 93.68, "elapsed_time": "19:20:44", "remaining_time": "1:18:15"}
357
+ {"current_steps": 3570, "total_steps": 3800, "loss": 0.1917279005050659, "lr": 2.2429072240595428e-07, "epoch": 1.8789473684210525, "percentage": 93.95, "elapsed_time": "19:23:54", "remaining_time": "1:14:59"}
358
+ {"current_steps": 3580, "total_steps": 3800, "loss": 0.19180333614349365, "lr": 2.0535724604132223e-07, "epoch": 1.8842105263157896, "percentage": 94.21, "elapsed_time": "19:27:09", "remaining_time": "1:11:43"}
359
+ {"current_steps": 3590, "total_steps": 3800, "loss": 0.19407191276550292, "lr": 1.8725025106818506e-07, "epoch": 1.8894736842105262, "percentage": 94.47, "elapsed_time": "19:30:22", "remaining_time": "1:08:27"}
360
+ {"current_steps": 3600, "total_steps": 3800, "loss": 0.19175976514816284, "lr": 1.699712653722241e-07, "epoch": 1.8947368421052633, "percentage": 94.74, "elapsed_time": "19:33:34", "remaining_time": "1:05:11"}
361
+ {"current_steps": 3610, "total_steps": 3800, "loss": 0.19339519739151, "lr": 1.535217469708994e-07, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "19:38:25", "remaining_time": "1:02:01"}
362
+ {"current_steps": 3620, "total_steps": 3800, "loss": 0.19258456230163573, "lr": 1.3790308389042051e-07, "epoch": 1.905263157894737, "percentage": 95.26, "elapsed_time": "19:41:36", "remaining_time": "0:58:45"}
363
+ {"current_steps": 3630, "total_steps": 3800, "loss": 0.19650962352752685, "lr": 1.231165940486234e-07, "epoch": 1.9105263157894736, "percentage": 95.53, "elapsed_time": "19:44:50", "remaining_time": "0:55:29"}
364
+ {"current_steps": 3640, "total_steps": 3800, "loss": 0.1936952829360962, "lr": 1.0916352514376616e-07, "epoch": 1.9157894736842105, "percentage": 95.79, "elapsed_time": "19:48:02", "remaining_time": "0:52:13"}
365
+ {"current_steps": 3650, "total_steps": 3800, "loss": 0.1929107904434204, "lr": 9.604505454924529e-08, "epoch": 1.9210526315789473, "percentage": 96.05, "elapsed_time": "19:51:16", "remaining_time": "0:48:57"}
366
+ {"current_steps": 3660, "total_steps": 3800, "loss": 0.18853404521942138, "lr": 8.376228921424867e-08, "epoch": 1.9263157894736842, "percentage": 96.32, "elapsed_time": "19:54:31", "remaining_time": "0:45:41"}
367
+ {"current_steps": 3670, "total_steps": 3800, "loss": 0.19240450859069824, "lr": 7.231626557034687e-08, "epoch": 1.931578947368421, "percentage": 96.58, "elapsed_time": "19:57:45", "remaining_time": "0:42:25"}
368
+ {"current_steps": 3680, "total_steps": 3800, "loss": 0.19327850341796876, "lr": 6.170794944404201e-08, "epoch": 1.936842105263158, "percentage": 96.84, "elapsed_time": "20:00:57", "remaining_time": "0:39:09"}
369
+ {"current_steps": 3690, "total_steps": 3800, "loss": 0.19556995630264282, "lr": 5.193823597526959e-08, "epoch": 1.9421052631578948, "percentage": 97.11, "elapsed_time": "20:04:10", "remaining_time": "0:35:53"}
370
+ {"current_steps": 3700, "total_steps": 3800, "loss": 0.19019975662231445, "lr": 4.300794954186227e-08, "epoch": 1.9473684210526314, "percentage": 97.37, "elapsed_time": "20:07:22", "remaining_time": "0:32:37"}
371
+ {"current_steps": 3710, "total_steps": 3800, "loss": 0.18893930912017823, "lr": 3.491784368999329e-08, "epoch": 1.9526315789473685, "percentage": 97.63, "elapsed_time": "20:10:35", "remaining_time": "0:29:22"}
372
+ {"current_steps": 3720, "total_steps": 3800, "loss": 0.19152721166610717, "lr": 2.766860107058844e-08, "epoch": 1.9578947368421051, "percentage": 97.89, "elapsed_time": "20:13:49", "remaining_time": "0:26:06"}
373
+ {"current_steps": 3730, "total_steps": 3800, "loss": 0.1897812604904175, "lr": 2.1260833381724355e-08, "epoch": 1.9631578947368422, "percentage": 98.16, "elapsed_time": "20:17:02", "remaining_time": "0:22:50"}
374
+ {"current_steps": 3740, "total_steps": 3800, "loss": 0.19254502058029174, "lr": 1.569508131701092e-08, "epoch": 1.9684210526315788, "percentage": 98.42, "elapsed_time": "20:20:15", "remaining_time": "0:19:34"}
375
+ {"current_steps": 3750, "total_steps": 3800, "loss": 0.1893929958343506, "lr": 1.097181451996887e-08, "epoch": 1.973684210526316, "percentage": 98.68, "elapsed_time": "20:23:28", "remaining_time": "0:16:18"}
376
+ {"current_steps": 3760, "total_steps": 3800, "loss": 0.18963019847869872, "lr": 7.091431544401506e-09, "epoch": 1.9789473684210526, "percentage": 98.95, "elapsed_time": "20:26:41", "remaining_time": "0:13:02"}
377
+ {"current_steps": 3770, "total_steps": 3800, "loss": 0.19097139835357665, "lr": 4.0542598207626846e-09, "epoch": 1.9842105263157894, "percentage": 99.21, "elapsed_time": "20:29:56", "remaining_time": "0:09:47"}
378
+ {"current_steps": 3780, "total_steps": 3800, "loss": 0.19803013801574706, "lr": 1.860555628527827e-09, "epoch": 1.9894736842105263, "percentage": 99.47, "elapsed_time": "20:33:10", "remaining_time": "0:06:31"}
379
+ {"current_steps": 3790, "total_steps": 3800, "loss": 0.19267313480377196, "lr": 5.105040745689848e-10, "epoch": 1.9947368421052631, "percentage": 99.74, "elapsed_time": "20:36:25", "remaining_time": "0:03:15"}
380
+ {"current_steps": 3800, "total_steps": 3800, "loss": 0.18964411020278932, "lr": 4.2190775395578586e-12, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "20:39:40", "remaining_time": "0:00:00"}
381
+ {"current_steps": 3800, "total_steps": 3800, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "20:41:14", "remaining_time": "0:00:00"}
designcoder_qwen3.5_9b_adamw_bs16_step3800/trainer_state.json ADDED
@@ -0,0 +1,2703 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 3800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005263157894736842,
14
+ "grad_norm": 2.472523828663311,
15
+ "learning_rate": 4.7368421052631585e-07,
16
+ "loss": 0.5256161212921142,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.010526315789473684,
21
+ "grad_norm": 1.5005127853437605,
22
+ "learning_rate": 1.0000000000000002e-06,
23
+ "loss": 0.5117449760437012,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.015789473684210527,
28
+ "grad_norm": 0.8717308993191117,
29
+ "learning_rate": 1.5263157894736844e-06,
30
+ "loss": 0.47916154861450194,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.021052631578947368,
35
+ "grad_norm": 0.6509838744572901,
36
+ "learning_rate": 2.0526315789473687e-06,
37
+ "loss": 0.4465330123901367,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.02631578947368421,
42
+ "grad_norm": 0.6237826194989842,
43
+ "learning_rate": 2.578947368421053e-06,
44
+ "loss": 0.42493352890014646,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.031578947368421054,
49
+ "grad_norm": 0.6213718187969164,
50
+ "learning_rate": 3.1052631578947372e-06,
51
+ "loss": 0.39734339714050293,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.03684210526315789,
56
+ "grad_norm": 0.6259977375188969,
57
+ "learning_rate": 3.6315789473684217e-06,
58
+ "loss": 0.3773430109024048,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.042105263157894736,
63
+ "grad_norm": 0.5780871733065431,
64
+ "learning_rate": 4.157894736842106e-06,
65
+ "loss": 0.37105565071105956,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.04736842105263158,
70
+ "grad_norm": 0.9461020080624207,
71
+ "learning_rate": 4.68421052631579e-06,
72
+ "loss": 0.36675457954406737,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.05263157894736842,
77
+ "grad_norm": 0.5891981950890374,
78
+ "learning_rate": 5.210526315789474e-06,
79
+ "loss": 0.3579871654510498,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.05789473684210526,
84
+ "grad_norm": 0.5987208236418651,
85
+ "learning_rate": 5.736842105263158e-06,
86
+ "loss": 0.35358657836914065,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.06315789473684211,
91
+ "grad_norm": 0.6259402926756378,
92
+ "learning_rate": 6.263157894736842e-06,
93
+ "loss": 0.3630886793136597,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.06842105263157895,
98
+ "grad_norm": 0.5794757942861436,
99
+ "learning_rate": 6.789473684210527e-06,
100
+ "loss": 0.3483468532562256,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.07368421052631578,
105
+ "grad_norm": 0.6640194485201639,
106
+ "learning_rate": 7.315789473684212e-06,
107
+ "loss": 0.335282039642334,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.07894736842105263,
112
+ "grad_norm": 0.5305814351988093,
113
+ "learning_rate": 7.842105263157895e-06,
114
+ "loss": 0.3350475311279297,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.08421052631578947,
119
+ "grad_norm": 0.5694398717463255,
120
+ "learning_rate": 8.36842105263158e-06,
121
+ "loss": 0.33222599029541017,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.08947368421052632,
126
+ "grad_norm": 0.5316791584020387,
127
+ "learning_rate": 8.894736842105264e-06,
128
+ "loss": 0.3343937873840332,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.09473684210526316,
133
+ "grad_norm": 0.5389140103035891,
134
+ "learning_rate": 9.421052631578949e-06,
135
+ "loss": 0.3304591178894043,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.1,
140
+ "grad_norm": 0.5234802569667512,
141
+ "learning_rate": 9.947368421052632e-06,
142
+ "loss": 0.3218997001647949,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.10526315789473684,
147
+ "grad_norm": 0.511359820685006,
148
+ "learning_rate": 1.0473684210526316e-05,
149
+ "loss": 0.3258413076400757,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.11052631578947368,
154
+ "grad_norm": 0.498328123890139,
155
+ "learning_rate": 1.1000000000000001e-05,
156
+ "loss": 0.3291585445404053,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.11578947368421053,
161
+ "grad_norm": 0.4934555545441858,
162
+ "learning_rate": 1.1526315789473685e-05,
163
+ "loss": 0.31838207244873046,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.12105263157894737,
168
+ "grad_norm": 0.5023528461702268,
169
+ "learning_rate": 1.2052631578947369e-05,
170
+ "loss": 0.31834683418273924,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.12631578947368421,
175
+ "grad_norm": 0.6457086269060067,
176
+ "learning_rate": 1.2578947368421052e-05,
177
+ "loss": 0.3187001943588257,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.13157894736842105,
182
+ "grad_norm": 0.5217424019401136,
183
+ "learning_rate": 1.310526315789474e-05,
184
+ "loss": 0.31230387687683103,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1368421052631579,
189
+ "grad_norm": 0.5071570364198046,
190
+ "learning_rate": 1.3631578947368423e-05,
191
+ "loss": 0.3076712846755981,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.14210526315789473,
196
+ "grad_norm": 0.4728285383449402,
197
+ "learning_rate": 1.4157894736842107e-05,
198
+ "loss": 0.3154590606689453,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.14736842105263157,
203
+ "grad_norm": 0.5144494149579036,
204
+ "learning_rate": 1.468421052631579e-05,
205
+ "loss": 0.30873308181762693,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.15263157894736842,
210
+ "grad_norm": 0.4814773271324151,
211
+ "learning_rate": 1.5210526315789476e-05,
212
+ "loss": 0.3070851802825928,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.15789473684210525,
217
+ "grad_norm": 0.5313319465247397,
218
+ "learning_rate": 1.573684210526316e-05,
219
+ "loss": 0.31069626808166506,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.1631578947368421,
224
+ "grad_norm": 0.47415199131136837,
225
+ "learning_rate": 1.6263157894736843e-05,
226
+ "loss": 0.3106666088104248,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.16842105263157894,
231
+ "grad_norm": 0.4802094044283446,
232
+ "learning_rate": 1.6789473684210526e-05,
233
+ "loss": 0.3167429447174072,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.1736842105263158,
238
+ "grad_norm": 0.43399177594830274,
239
+ "learning_rate": 1.7315789473684213e-05,
240
+ "loss": 0.31033878326416015,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.17894736842105263,
245
+ "grad_norm": 0.4647785307142974,
246
+ "learning_rate": 1.7842105263157897e-05,
247
+ "loss": 0.3044872760772705,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.18421052631578946,
252
+ "grad_norm": 0.4849056484263613,
253
+ "learning_rate": 1.836842105263158e-05,
254
+ "loss": 0.3083398103713989,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.18947368421052632,
259
+ "grad_norm": 0.4503892536980415,
260
+ "learning_rate": 1.8894736842105264e-05,
261
+ "loss": 0.31491541862487793,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.19473684210526315,
266
+ "grad_norm": 0.40185057648868033,
267
+ "learning_rate": 1.9421052631578948e-05,
268
+ "loss": 0.305939245223999,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.2,
273
+ "grad_norm": 0.4403647520815703,
274
+ "learning_rate": 1.994736842105263e-05,
275
+ "loss": 0.3013646125793457,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.20526315789473684,
280
+ "grad_norm": 0.4186333124896718,
281
+ "learning_rate": 1.9999658256641746e-05,
282
+ "loss": 0.30339813232421875,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.21052631578947367,
287
+ "grad_norm": 0.41935530958429196,
288
+ "learning_rate": 1.9998476951563914e-05,
289
+ "loss": 0.2942552089691162,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.21578947368421053,
294
+ "grad_norm": 0.42294688630625693,
295
+ "learning_rate": 1.999645196536862e-05,
296
+ "loss": 0.30738029479980467,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.22105263157894736,
301
+ "grad_norm": 0.393260279007574,
302
+ "learning_rate": 1.9993583468926155e-05,
303
+ "loss": 0.3012552738189697,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.22631578947368422,
308
+ "grad_norm": 0.4031620962596939,
309
+ "learning_rate": 1.9989871704283007e-05,
310
+ "loss": 0.2997457027435303,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.23157894736842105,
315
+ "grad_norm": 0.43562667552699363,
316
+ "learning_rate": 1.9985316984641456e-05,
317
+ "loss": 0.30234060287475584,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.23684210526315788,
322
+ "grad_norm": 0.410616583962392,
323
+ "learning_rate": 1.9979919694333134e-05,
324
+ "loss": 0.29965386390686033,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.24210526315789474,
329
+ "grad_norm": 0.3848448235963453,
330
+ "learning_rate": 1.9973680288786593e-05,
331
+ "loss": 0.29823567867279055,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.24736842105263157,
336
+ "grad_norm": 0.4051948689025974,
337
+ "learning_rate": 1.996659929448889e-05,
338
+ "loss": 0.2968828916549683,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.25263157894736843,
343
+ "grad_norm": 0.37927841614618585,
344
+ "learning_rate": 1.995867730894114e-05,
345
+ "loss": 0.29349508285522463,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.2578947368421053,
350
+ "grad_norm": 0.3839301197442169,
351
+ "learning_rate": 1.9949915000608117e-05,
352
+ "loss": 0.29422550201416015,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.2631578947368421,
357
+ "grad_norm": 0.3759777087410165,
358
+ "learning_rate": 1.9940313108861838e-05,
359
+ "loss": 0.29750072956085205,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.26842105263157895,
364
+ "grad_norm": 0.4098679252692369,
365
+ "learning_rate": 1.9929872443919184e-05,
366
+ "loss": 0.29425339698791503,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.2736842105263158,
371
+ "grad_norm": 0.40654136262396373,
372
+ "learning_rate": 1.9918593886773517e-05,
373
+ "loss": 0.28567793369293215,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2789473684210526,
378
+ "grad_norm": 0.36338663599238585,
379
+ "learning_rate": 1.9906478389120353e-05,
380
+ "loss": 0.286260986328125,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.28421052631578947,
385
+ "grad_norm": 0.3645922122070194,
386
+ "learning_rate": 1.9893526973277058e-05,
387
+ "loss": 0.289249062538147,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.2894736842105263,
392
+ "grad_norm": 0.37625211711799234,
393
+ "learning_rate": 1.9879740732096578e-05,
394
+ "loss": 0.2874547004699707,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.29473684210526313,
399
+ "grad_norm": 0.34838277332463985,
400
+ "learning_rate": 1.9865120828875226e-05,
401
+ "loss": 0.2794506072998047,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.3,
406
+ "grad_norm": 0.39563068637802595,
407
+ "learning_rate": 1.984966849725452e-05,
408
+ "loss": 0.2895684242248535,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.30526315789473685,
413
+ "grad_norm": 0.38098936532231065,
414
+ "learning_rate": 1.9833385041117084e-05,
415
+ "loss": 0.29196949005126954,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.3105263157894737,
420
+ "grad_norm": 0.35040294369871705,
421
+ "learning_rate": 1.9816271834476642e-05,
422
+ "loss": 0.28489394187927247,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.3157894736842105,
427
+ "grad_norm": 0.3547688759584724,
428
+ "learning_rate": 1.979833032136205e-05,
429
+ "loss": 0.28308355808258057,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.32105263157894737,
434
+ "grad_norm": 0.3590211082920023,
435
+ "learning_rate": 1.9779562015695472e-05,
436
+ "loss": 0.2814664840698242,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.3263157894736842,
441
+ "grad_norm": 0.3843159848024641,
442
+ "learning_rate": 1.975996850116462e-05,
443
+ "loss": 0.2858001470565796,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.33157894736842103,
448
+ "grad_norm": 0.4005823415419153,
449
+ "learning_rate": 1.9739551431089127e-05,
450
+ "loss": 0.28349668979644777,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.3368421052631579,
455
+ "grad_norm": 0.33783688412384855,
456
+ "learning_rate": 1.9718312528281032e-05,
457
+ "loss": 0.2791487216949463,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.34210526315789475,
462
+ "grad_norm": 0.34686678617294825,
463
+ "learning_rate": 1.969625358489942e-05,
464
+ "loss": 0.281187629699707,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.3473684210526316,
469
+ "grad_norm": 0.37219308281398455,
470
+ "learning_rate": 1.9673376462299186e-05,
471
+ "loss": 0.28690199851989745,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.3526315789473684,
476
+ "grad_norm": 0.3523197227930877,
477
+ "learning_rate": 1.9649683090873966e-05,
478
+ "loss": 0.2867712497711182,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.35789473684210527,
483
+ "grad_norm": 0.3424601813185377,
484
+ "learning_rate": 1.9625175469893274e-05,
485
+ "loss": 0.2830781936645508,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.3631578947368421,
490
+ "grad_norm": 0.3704358558481498,
491
+ "learning_rate": 1.9599855667333775e-05,
492
+ "loss": 0.2801445484161377,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.3684210526315789,
497
+ "grad_norm": 0.3505446013566416,
498
+ "learning_rate": 1.95737258197048e-05,
499
+ "loss": 0.2798027038574219,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.3736842105263158,
504
+ "grad_norm": 0.3595890485451611,
505
+ "learning_rate": 1.9546788131868066e-05,
506
+ "loss": 0.27515039443969724,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.37894736842105264,
511
+ "grad_norm": 0.3539457947713692,
512
+ "learning_rate": 1.9519044876851625e-05,
513
+ "loss": 0.27915568351745607,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.38421052631578945,
518
+ "grad_norm": 0.3624625326291939,
519
+ "learning_rate": 1.9490498395658065e-05,
520
+ "loss": 0.2834479331970215,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.3894736842105263,
525
+ "grad_norm": 0.34248993342247835,
526
+ "learning_rate": 1.9461151097066966e-05,
527
+ "loss": 0.27811641693115235,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.39473684210526316,
532
+ "grad_norm": 0.3513901906524033,
533
+ "learning_rate": 1.9431005457431654e-05,
534
+ "loss": 0.27672529220581055,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.4,
539
+ "grad_norm": 0.3624436223016265,
540
+ "learning_rate": 1.9400064020470248e-05,
541
+ "loss": 0.27708661556243896,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.4052631578947368,
546
+ "grad_norm": 0.3431620270550116,
547
+ "learning_rate": 1.9368329397051005e-05,
548
+ "loss": 0.2778616428375244,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.4105263157894737,
553
+ "grad_norm": 0.35302474596968153,
554
+ "learning_rate": 1.9335804264972018e-05,
555
+ "loss": 0.2797053575515747,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.41578947368421054,
560
+ "grad_norm": 0.3476617347147986,
561
+ "learning_rate": 1.930249136873527e-05,
562
+ "loss": 0.2725248098373413,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.42105263157894735,
567
+ "grad_norm": 0.3504063065008235,
568
+ "learning_rate": 1.9268393519315037e-05,
569
+ "loss": 0.2721980571746826,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.4263157894736842,
574
+ "grad_norm": 0.3316242624925787,
575
+ "learning_rate": 1.923351359392071e-05,
576
+ "loss": 0.27883172035217285,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.43157894736842106,
581
+ "grad_norm": 0.34972655352739723,
582
+ "learning_rate": 1.919785453575398e-05,
583
+ "loss": 0.2791574478149414,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.4368421052631579,
588
+ "grad_norm": 0.34528876602055164,
589
+ "learning_rate": 1.9161419353760537e-05,
590
+ "loss": 0.2733182907104492,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.4421052631578947,
595
+ "grad_norm": 0.3589285002649645,
596
+ "learning_rate": 1.9124211122376138e-05,
597
+ "loss": 0.2692681312561035,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.4473684210526316,
602
+ "grad_norm": 0.36293901876437584,
603
+ "learning_rate": 1.9086232981267193e-05,
604
+ "loss": 0.27492191791534426,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.45263157894736844,
609
+ "grad_norm": 0.31257415339843775,
610
+ "learning_rate": 1.9047488135065838e-05,
611
+ "loss": 0.2736824035644531,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.45789473684210524,
616
+ "grad_norm": 0.4666981990734814,
617
+ "learning_rate": 1.900797985309952e-05,
618
+ "loss": 0.26795847415924073,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.4631578947368421,
623
+ "grad_norm": 0.34154156386892,
624
+ "learning_rate": 1.8967711469115125e-05,
625
+ "loss": 0.27838611602783203,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.46842105263157896,
630
+ "grad_norm": 0.3390711387499649,
631
+ "learning_rate": 1.89266863809977e-05,
632
+ "loss": 0.2694388866424561,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.47368421052631576,
637
+ "grad_norm": 0.3388108150043773,
638
+ "learning_rate": 1.8884908050483694e-05,
639
+ "loss": 0.2662887334823608,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.4789473684210526,
644
+ "grad_norm": 0.31573245518836707,
645
+ "learning_rate": 1.884238000286889e-05,
646
+ "loss": 0.2719233512878418,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.4842105263157895,
651
+ "grad_norm": 0.3136635452616895,
652
+ "learning_rate": 1.8799105826710907e-05,
653
+ "loss": 0.27722165584564207,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.48947368421052634,
658
+ "grad_norm": 0.3540196876080697,
659
+ "learning_rate": 1.875508917352643e-05,
660
+ "loss": 0.27123408317565917,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.49473684210526314,
665
+ "grad_norm": 0.3401617301678034,
666
+ "learning_rate": 1.871033375748305e-05,
667
+ "loss": 0.2743401050567627,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.5,
672
+ "grad_norm": 0.3325607602585638,
673
+ "learning_rate": 1.8664843355085897e-05,
674
+ "loss": 0.2736999988555908,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.5052631578947369,
679
+ "grad_norm": 0.3355960311687728,
680
+ "learning_rate": 1.8618621804858942e-05,
681
+ "loss": 0.2695770740509033,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.5105263157894737,
686
+ "grad_norm": 0.34917963265085344,
687
+ "learning_rate": 1.8571673007021124e-05,
688
+ "loss": 0.2674164533615112,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.5157894736842106,
693
+ "grad_norm": 0.3154374575194281,
694
+ "learning_rate": 1.8524000923157236e-05,
695
+ "loss": 0.2656900644302368,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.5210526315789473,
700
+ "grad_norm": 0.3396417899342089,
701
+ "learning_rate": 1.847560957588364e-05,
702
+ "loss": 0.2646545648574829,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.5263157894736842,
707
+ "grad_norm": 0.3176523061404554,
708
+ "learning_rate": 1.8426503048508837e-05,
709
+ "loss": 0.2751678228378296,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.531578947368421,
714
+ "grad_norm": 0.3473340546341962,
715
+ "learning_rate": 1.8376685484688917e-05,
716
+ "loss": 0.2681708335876465,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.5368421052631579,
721
+ "grad_norm": 0.34073609252261294,
722
+ "learning_rate": 1.8326161088077905e-05,
723
+ "loss": 0.2672728538513184,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.5421052631578948,
728
+ "grad_norm": 0.3049103876323376,
729
+ "learning_rate": 1.8274934121973063e-05,
730
+ "loss": 0.2671975135803223,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.5473684210526316,
735
+ "grad_norm": 0.3387769506721435,
736
+ "learning_rate": 1.8223008908955142e-05,
737
+ "loss": 0.26558561325073243,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.5526315789473685,
742
+ "grad_norm": 0.33910647138812194,
743
+ "learning_rate": 1.817038983052364e-05,
744
+ "loss": 0.26291708946228026,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.5578947368421052,
749
+ "grad_norm": 0.32379165812728467,
750
+ "learning_rate": 1.811708132672708e-05,
751
+ "loss": 0.26275482177734377,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.5631578947368421,
756
+ "grad_norm": 0.3345835482426037,
757
+ "learning_rate": 1.806308789578838e-05,
758
+ "loss": 0.26116185188293456,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.5684210526315789,
763
+ "grad_norm": 0.32562338583447364,
764
+ "learning_rate": 1.800841409372525e-05,
765
+ "loss": 0.26714067459106444,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.5736842105263158,
770
+ "grad_norm": 0.30190873036266547,
771
+ "learning_rate": 1.7953064533965786e-05,
772
+ "loss": 0.2601884126663208,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.5789473684210527,
777
+ "grad_norm": 0.3053022157842351,
778
+ "learning_rate": 1.789704388695916e-05,
779
+ "loss": 0.2656057834625244,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.5842105263157895,
784
+ "grad_norm": 0.31119083135305803,
785
+ "learning_rate": 1.784035687978153e-05,
786
+ "loss": 0.26111807823181155,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.5894736842105263,
791
+ "grad_norm": 0.3187190869116883,
792
+ "learning_rate": 1.7783008295737184e-05,
793
+ "loss": 0.26168193817138674,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.5947368421052631,
798
+ "grad_norm": 0.30514773092013386,
799
+ "learning_rate": 1.7725002973954877e-05,
800
+ "loss": 0.2635683059692383,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.6,
805
+ "grad_norm": 0.30411409793985456,
806
+ "learning_rate": 1.766634580897956e-05,
807
+ "loss": 0.26383979320526124,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.6052631578947368,
812
+ "grad_norm": 0.31697070613811223,
813
+ "learning_rate": 1.7607041750359306e-05,
814
+ "loss": 0.2703020334243774,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.6105263157894737,
819
+ "grad_norm": 0.3176295184769418,
820
+ "learning_rate": 1.7547095802227723e-05,
821
+ "loss": 0.25947682857513427,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.6157894736842106,
826
+ "grad_norm": 0.3037747745258026,
827
+ "learning_rate": 1.7486513022881658e-05,
828
+ "loss": 0.2625890731811523,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.6210526315789474,
833
+ "grad_norm": 0.2990251306790103,
834
+ "learning_rate": 1.7425298524354403e-05,
835
+ "loss": 0.2612356185913086,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.6263157894736842,
840
+ "grad_norm": 0.34736281610591246,
841
+ "learning_rate": 1.7363457471984312e-05,
842
+ "loss": 0.26089015007019045,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.631578947368421,
847
+ "grad_norm": 0.3234773014146318,
848
+ "learning_rate": 1.7300995083978965e-05,
849
+ "loss": 0.26446876525878904,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.6368421052631579,
854
+ "grad_norm": 0.32659606350966197,
855
+ "learning_rate": 1.723791663097483e-05,
856
+ "loss": 0.26449496746063234,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.6421052631578947,
861
+ "grad_norm": 0.31857571620751646,
862
+ "learning_rate": 1.7174227435592544e-05,
863
+ "loss": 0.2561885118484497,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.6473684210526316,
868
+ "grad_norm": 0.31782135086280616,
869
+ "learning_rate": 1.7109932871987766e-05,
870
+ "loss": 0.26837003231048584,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.6526315789473685,
875
+ "grad_norm": 0.3026957257600272,
876
+ "learning_rate": 1.7045038365397715e-05,
877
+ "loss": 0.2621891975402832,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.6578947368421053,
882
+ "grad_norm": 0.31988751110754715,
883
+ "learning_rate": 1.697954939168338e-05,
884
+ "loss": 0.25557448863983157,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.6631578947368421,
889
+ "grad_norm": 0.30063142165262846,
890
+ "learning_rate": 1.6913471476867448e-05,
891
+ "loss": 0.258845853805542,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.6684210526315789,
896
+ "grad_norm": 0.3329982518496743,
897
+ "learning_rate": 1.684681019666803e-05,
898
+ "loss": 0.25761024951934813,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.6736842105263158,
903
+ "grad_norm": 0.307300254052826,
904
+ "learning_rate": 1.6779571176028163e-05,
905
+ "loss": 0.2636724948883057,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.6789473684210526,
910
+ "grad_norm": 0.3445508029288134,
911
+ "learning_rate": 1.6711760088641197e-05,
912
+ "loss": 0.26073036193847654,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.6842105263157895,
917
+ "grad_norm": 0.3066359325162919,
918
+ "learning_rate": 1.6643382656472006e-05,
919
+ "loss": 0.2574197053909302,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.6894736842105263,
924
+ "grad_norm": 0.30990898369085396,
925
+ "learning_rate": 1.657444464927419e-05,
926
+ "loss": 0.2566478729248047,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.6947368421052632,
931
+ "grad_norm": 0.3045472737563618,
932
+ "learning_rate": 1.650495188410321e-05,
933
+ "loss": 0.2704493045806885,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.7,
938
+ "grad_norm": 0.30911152135235415,
939
+ "learning_rate": 1.643491022482554e-05,
940
+ "loss": 0.2584094762802124,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.7052631578947368,
945
+ "grad_norm": 0.29455407732231376,
946
+ "learning_rate": 1.6364325581623864e-05,
947
+ "loss": 0.260040283203125,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.7105263157894737,
952
+ "grad_norm": 0.2964765485206893,
953
+ "learning_rate": 1.6293203910498375e-05,
954
+ "loss": 0.25489492416381837,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.7157894736842105,
959
+ "grad_norm": 0.30140017539745534,
960
+ "learning_rate": 1.6221551212764204e-05,
961
+ "loss": 0.26243014335632325,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.7210526315789474,
966
+ "grad_norm": 0.3062849737975478,
967
+ "learning_rate": 1.6149373534545008e-05,
968
+ "loss": 0.26453495025634766,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.7263157894736842,
973
+ "grad_norm": 0.3077155586073205,
974
+ "learning_rate": 1.6076676966262815e-05,
975
+ "loss": 0.25987796783447265,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.7315789473684211,
980
+ "grad_norm": 0.3312975381674833,
981
+ "learning_rate": 1.6003467642124086e-05,
982
+ "loss": 0.2542286396026611,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.7368421052631579,
987
+ "grad_norm": 0.31551791426113573,
988
+ "learning_rate": 1.592975173960212e-05,
989
+ "loss": 0.2617928981781006,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.7421052631578947,
994
+ "grad_norm": 0.30285289051308956,
995
+ "learning_rate": 1.5855535478915793e-05,
996
+ "loss": 0.2531562566757202,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.7473684210526316,
1001
+ "grad_norm": 0.3073808947692201,
1002
+ "learning_rate": 1.5780825122504672e-05,
1003
+ "loss": 0.25049700736999514,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.7526315789473684,
1008
+ "grad_norm": 0.33339299865726996,
1009
+ "learning_rate": 1.5705626974500613e-05,
1010
+ "loss": 0.25526843070983884,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.7578947368421053,
1015
+ "grad_norm": 0.3058399225988297,
1016
+ "learning_rate": 1.5629947380195786e-05,
1017
+ "loss": 0.2525237798690796,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.7631578947368421,
1022
+ "grad_norm": 0.3203191556565657,
1023
+ "learning_rate": 1.5553792725507265e-05,
1024
+ "loss": 0.2499521255493164,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.7684210526315789,
1029
+ "grad_norm": 0.2968933270555803,
1030
+ "learning_rate": 1.5477169436438178e-05,
1031
+ "loss": 0.2529642581939697,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.7736842105263158,
1036
+ "grad_norm": 0.31537161119609625,
1037
+ "learning_rate": 1.5400083978535475e-05,
1038
+ "loss": 0.2528361797332764,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.7789473684210526,
1043
+ "grad_norm": 0.30053640034930956,
1044
+ "learning_rate": 1.532254285634435e-05,
1045
+ "loss": 0.2572028160095215,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.7842105263157895,
1050
+ "grad_norm": 0.2872891239024344,
1051
+ "learning_rate": 1.5244552612859407e-05,
1052
+ "loss": 0.25772078037261964,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.7894736842105263,
1057
+ "grad_norm": 0.3114653675819462,
1058
+ "learning_rate": 1.5166119828972515e-05,
1059
+ "loss": 0.2603304386138916,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.7947368421052632,
1064
+ "grad_norm": 0.30385823021839925,
1065
+ "learning_rate": 1.5087251122917543e-05,
1066
+ "loss": 0.2549354791641235,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.8,
1071
+ "grad_norm": 0.3195778732427886,
1072
+ "learning_rate": 1.5007953149711885e-05,
1073
+ "loss": 0.2570181369781494,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.8052631578947368,
1078
+ "grad_norm": 0.32222451716138956,
1079
+ "learning_rate": 1.4928232600594916e-05,
1080
+ "loss": 0.25235695838928224,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.8105263157894737,
1085
+ "grad_norm": 0.3170829707020739,
1086
+ "learning_rate": 1.4848096202463373e-05,
1087
+ "loss": 0.26191277503967286,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.8157894736842105,
1092
+ "grad_norm": 0.3186275075149321,
1093
+ "learning_rate": 1.4767550717303726e-05,
1094
+ "loss": 0.2493319034576416,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.8210526315789474,
1099
+ "grad_norm": 0.29863089121966946,
1100
+ "learning_rate": 1.4686602941621618e-05,
1101
+ "loss": 0.2586613655090332,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.8263157894736842,
1106
+ "grad_norm": 0.2982239867778827,
1107
+ "learning_rate": 1.4605259705868334e-05,
1108
+ "loss": 0.2521392345428467,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.8315789473684211,
1113
+ "grad_norm": 0.31962705193402735,
1114
+ "learning_rate": 1.4523527873864474e-05,
1115
+ "loss": 0.25809125900268554,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.8368421052631579,
1120
+ "grad_norm": 0.2963945418337864,
1121
+ "learning_rate": 1.4441414342220762e-05,
1122
+ "loss": 0.25009665489196775,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.8421052631578947,
1127
+ "grad_norm": 0.3285629437505493,
1128
+ "learning_rate": 1.4358926039756106e-05,
1129
+ "loss": 0.25235395431518554,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.8473684210526315,
1134
+ "grad_norm": 0.3039719782091077,
1135
+ "learning_rate": 1.4276069926912934e-05,
1136
+ "loss": 0.2509817838668823,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.8526315789473684,
1141
+ "grad_norm": 0.3062469619116883,
1142
+ "learning_rate": 1.4192852995169868e-05,
1143
+ "loss": 0.2587169647216797,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.8578947368421053,
1148
+ "grad_norm": 0.2874124311095995,
1149
+ "learning_rate": 1.4109282266451777e-05,
1150
+ "loss": 0.2517398834228516,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.8631578947368421,
1155
+ "grad_norm": 0.30194631166275687,
1156
+ "learning_rate": 1.4025364792537264e-05,
1157
+ "loss": 0.25503859519958494,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.868421052631579,
1162
+ "grad_norm": 0.27840841442231024,
1163
+ "learning_rate": 1.3941107654463619e-05,
1164
+ "loss": 0.25129916667938235,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.8736842105263158,
1169
+ "grad_norm": 0.29521313529164417,
1170
+ "learning_rate": 1.3856517961929323e-05,
1171
+ "loss": 0.25026085376739504,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.8789473684210526,
1176
+ "grad_norm": 0.287267013868479,
1177
+ "learning_rate": 1.3771602852694127e-05,
1178
+ "loss": 0.24895100593566893,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.8842105263157894,
1183
+ "grad_norm": 0.2800736838648925,
1184
+ "learning_rate": 1.3686369491976748e-05,
1185
+ "loss": 0.2604621171951294,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.8894736842105263,
1190
+ "grad_norm": 0.2938288334198985,
1191
+ "learning_rate": 1.3600825071850282e-05,
1192
+ "loss": 0.24665045738220215,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.8947368421052632,
1197
+ "grad_norm": 0.3128575984880149,
1198
+ "learning_rate": 1.3514976810635302e-05,
1199
+ "loss": 0.25367374420166017,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.9,
1204
+ "grad_norm": 0.2919310094441612,
1205
+ "learning_rate": 1.3428831952290803e-05,
1206
+ "loss": 0.24983105659484864,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.9052631578947369,
1211
+ "grad_norm": 0.2833541904724715,
1212
+ "learning_rate": 1.3342397765802918e-05,
1213
+ "loss": 0.2547269105911255,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.9105263157894737,
1218
+ "grad_norm": 0.30713365035643586,
1219
+ "learning_rate": 1.3255681544571568e-05,
1220
+ "loss": 0.25430710315704347,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.9157894736842105,
1225
+ "grad_norm": 0.28478003136396524,
1226
+ "learning_rate": 1.3168690605795044e-05,
1227
+ "loss": 0.25717883110046386,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.9210526315789473,
1232
+ "grad_norm": 0.28797295415784185,
1233
+ "learning_rate": 1.3081432289852566e-05,
1234
+ "loss": 0.24728927612304688,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.9263157894736842,
1239
+ "grad_norm": 0.2924949280898957,
1240
+ "learning_rate": 1.2993913959684897e-05,
1241
+ "loss": 0.24457645416259766,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.9315789473684211,
1246
+ "grad_norm": 0.29430607804640396,
1247
+ "learning_rate": 1.2906143000173041e-05,
1248
+ "loss": 0.25548529624938965,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.9368421052631579,
1253
+ "grad_norm": 0.29586161226286145,
1254
+ "learning_rate": 1.2818126817515126e-05,
1255
+ "loss": 0.24899468421936036,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.9421052631578948,
1260
+ "grad_norm": 0.29458651167215955,
1261
+ "learning_rate": 1.2729872838601436e-05,
1262
+ "loss": 0.247794246673584,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.9473684210526315,
1267
+ "grad_norm": 0.28694243726477203,
1268
+ "learning_rate": 1.2641388510387733e-05,
1269
+ "loss": 0.2530705213546753,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.9526315789473684,
1274
+ "grad_norm": 0.28400804260339213,
1275
+ "learning_rate": 1.2552681299266873e-05,
1276
+ "loss": 0.2409834384918213,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.9578947368421052,
1281
+ "grad_norm": 0.2971761947306559,
1282
+ "learning_rate": 1.2463758690438793e-05,
1283
+ "loss": 0.24837055206298828,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.9631578947368421,
1288
+ "grad_norm": 0.29860383694291737,
1289
+ "learning_rate": 1.2374628187278888e-05,
1290
+ "loss": 0.2476038694381714,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.968421052631579,
1295
+ "grad_norm": 0.290827103571914,
1296
+ "learning_rate": 1.2285297310704883e-05,
1297
+ "loss": 0.25147113800048826,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.9736842105263158,
1302
+ "grad_norm": 0.28426661834511,
1303
+ "learning_rate": 1.21957735985422e-05,
1304
+ "loss": 0.2510018825531006,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.9789473684210527,
1309
+ "grad_norm": 0.26967543352672735,
1310
+ "learning_rate": 1.210606460488792e-05,
1311
+ "loss": 0.24750916957855223,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.9842105263157894,
1316
+ "grad_norm": 0.2778869516386811,
1317
+ "learning_rate": 1.2016177899473344e-05,
1318
+ "loss": 0.2443995952606201,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.9894736842105263,
1323
+ "grad_norm": 0.28049614667702366,
1324
+ "learning_rate": 1.1926121067025278e-05,
1325
+ "loss": 0.2498345136642456,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.9947368421052631,
1330
+ "grad_norm": 0.28037158504163623,
1331
+ "learning_rate": 1.1835901706626e-05,
1332
+ "loss": 0.24004738330841063,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 1.0,
1337
+ "grad_norm": 0.2818284300722421,
1338
+ "learning_rate": 1.1745527431072052e-05,
1339
+ "loss": 0.24387748241424562,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 1.0052631578947369,
1344
+ "grad_norm": 0.3048554539804919,
1345
+ "learning_rate": 1.1655005866231874e-05,
1346
+ "loss": 0.20784101486206055,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 1.0105263157894737,
1351
+ "grad_norm": 0.29644627179752464,
1352
+ "learning_rate": 1.156434465040231e-05,
1353
+ "loss": 0.2094496250152588,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 1.0157894736842106,
1358
+ "grad_norm": 0.3054894159097575,
1359
+ "learning_rate": 1.1473551433664093e-05,
1360
+ "loss": 0.2063742160797119,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 1.0210526315789474,
1365
+ "grad_norm": 0.3222861706808871,
1366
+ "learning_rate": 1.1382633877236321e-05,
1367
+ "loss": 0.2070340633392334,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 1.0263157894736843,
1372
+ "grad_norm": 0.29342069909331125,
1373
+ "learning_rate": 1.1291599652829994e-05,
1374
+ "loss": 0.20527045726776122,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 1.0315789473684212,
1379
+ "grad_norm": 0.2955655882030927,
1380
+ "learning_rate": 1.1200456442000667e-05,
1381
+ "loss": 0.20804226398468018,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 1.0368421052631578,
1386
+ "grad_norm": 0.28866589963820566,
1387
+ "learning_rate": 1.110921193550027e-05,
1388
+ "loss": 0.20433292388916016,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 1.0421052631578946,
1393
+ "grad_norm": 0.2898988220159749,
1394
+ "learning_rate": 1.1017873832628172e-05,
1395
+ "loss": 0.20756316184997559,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 1.0473684210526315,
1400
+ "grad_norm": 0.2991635984885633,
1401
+ "learning_rate": 1.0926449840581478e-05,
1402
+ "loss": 0.2041926383972168,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 1.0526315789473684,
1407
+ "grad_norm": 0.32168764414717305,
1408
+ "learning_rate": 1.0834947673804722e-05,
1409
+ "loss": 0.20382113456726075,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 1.0578947368421052,
1414
+ "grad_norm": 0.29933072336184285,
1415
+ "learning_rate": 1.0743375053338879e-05,
1416
+ "loss": 0.20006492137908935,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 1.063157894736842,
1421
+ "grad_norm": 0.28416943028027664,
1422
+ "learning_rate": 1.0651739706169884e-05,
1423
+ "loss": 0.20051677227020265,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 1.068421052631579,
1428
+ "grad_norm": 0.28950963633810445,
1429
+ "learning_rate": 1.0560049364576614e-05,
1430
+ "loss": 0.20347986221313477,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 1.0736842105263158,
1435
+ "grad_norm": 0.2870660918588074,
1436
+ "learning_rate": 1.0468311765478426e-05,
1437
+ "loss": 0.19931771755218505,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 1.0789473684210527,
1442
+ "grad_norm": 0.3034555482186645,
1443
+ "learning_rate": 1.0376534649782304e-05,
1444
+ "loss": 0.20710306167602538,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 1.0842105263157895,
1449
+ "grad_norm": 0.2932959815430872,
1450
+ "learning_rate": 1.028472576172969e-05,
1451
+ "loss": 0.20461549758911132,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 1.0894736842105264,
1456
+ "grad_norm": 0.3109353160792062,
1457
+ "learning_rate": 1.0192892848243003e-05,
1458
+ "loss": 0.20261452198028565,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 1.0947368421052632,
1463
+ "grad_norm": 0.297460936728559,
1464
+ "learning_rate": 1.0101043658271954e-05,
1465
+ "loss": 0.1989670991897583,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 1.1,
1470
+ "grad_norm": 0.27720496221464697,
1471
+ "learning_rate": 1.0009185942139676e-05,
1472
+ "loss": 0.20732603073120118,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 1.1052631578947367,
1477
+ "grad_norm": 0.2985385675259771,
1478
+ "learning_rate": 9.917327450888751e-06,
1479
+ "loss": 0.20671296119689941,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 1.1105263157894736,
1484
+ "grad_norm": 0.31136164698617336,
1485
+ "learning_rate": 9.825475935627165e-06,
1486
+ "loss": 0.2034555196762085,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 1.1157894736842104,
1491
+ "grad_norm": 0.30054254710870915,
1492
+ "learning_rate": 9.733639146874266e-06,
1493
+ "loss": 0.20147459506988524,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 1.1210526315789473,
1498
+ "grad_norm": 0.29677515325155296,
1499
+ "learning_rate": 9.641824833906754e-06,
1500
+ "loss": 0.20112955570220947,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 1.1263157894736842,
1505
+ "grad_norm": 0.31331520271935587,
1506
+ "learning_rate": 9.550040744104817e-06,
1507
+ "loss": 0.2055084228515625,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 1.131578947368421,
1512
+ "grad_norm": 0.2885840563649805,
1513
+ "learning_rate": 9.458294622298371e-06,
1514
+ "loss": 0.20572924613952637,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 1.1368421052631579,
1519
+ "grad_norm": 0.2932744024313575,
1520
+ "learning_rate": 9.366594210113564e-06,
1521
+ "loss": 0.20209026336669922,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 1.1421052631578947,
1526
+ "grad_norm": 0.29152430251874945,
1527
+ "learning_rate": 9.27494724531951e-06,
1528
+ "loss": 0.20527091026306152,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 1.1473684210526316,
1533
+ "grad_norm": 0.31590689009981915,
1534
+ "learning_rate": 9.183361461175397e-06,
1535
+ "loss": 0.2078498125076294,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 1.1526315789473685,
1540
+ "grad_norm": 0.29762327843090924,
1541
+ "learning_rate": 9.091844585777919e-06,
1542
+ "loss": 0.2069688081741333,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 1.1578947368421053,
1547
+ "grad_norm": 0.28262921806447805,
1548
+ "learning_rate": 9.00040434140919e-06,
1549
+ "loss": 0.1988505244255066,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 1.1631578947368422,
1554
+ "grad_norm": 0.2799568419681113,
1555
+ "learning_rate": 8.909048443885114e-06,
1556
+ "loss": 0.20135457515716554,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 1.168421052631579,
1561
+ "grad_norm": 0.2993135920520277,
1562
+ "learning_rate": 8.817784601904342e-06,
1563
+ "loss": 0.21084017753601075,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 1.1736842105263159,
1568
+ "grad_norm": 0.3022897692019414,
1569
+ "learning_rate": 8.726620516397777e-06,
1570
+ "loss": 0.20522718429565429,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 1.1789473684210527,
1575
+ "grad_norm": 0.28993342202926187,
1576
+ "learning_rate": 8.635563879878784e-06,
1577
+ "loss": 0.20526511669158937,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 1.1842105263157894,
1582
+ "grad_norm": 0.31799992182247755,
1583
+ "learning_rate": 8.544622375794064e-06,
1584
+ "loss": 0.20150189399719237,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 1.1894736842105262,
1589
+ "grad_norm": 0.2985470458176931,
1590
+ "learning_rate": 8.453803677875355e-06,
1591
+ "loss": 0.20268006324768068,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 1.194736842105263,
1596
+ "grad_norm": 0.28979231675165595,
1597
+ "learning_rate": 8.363115449491875e-06,
1598
+ "loss": 0.19919428825378419,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 1.2,
1603
+ "grad_norm": 0.3059530322183295,
1604
+ "learning_rate": 8.2725653430037e-06,
1605
+ "loss": 0.20649614334106445,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 1.2052631578947368,
1610
+ "grad_norm": 0.303324522007814,
1611
+ "learning_rate": 8.182160999116046e-06,
1612
+ "loss": 0.19812414646148682,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 1.2105263157894737,
1617
+ "grad_norm": 0.28591286519904724,
1618
+ "learning_rate": 8.091910046234552e-06,
1619
+ "loss": 0.20605757236480712,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 1.2157894736842105,
1624
+ "grad_norm": 0.30188287112312784,
1625
+ "learning_rate": 8.001820099821566e-06,
1626
+ "loss": 0.20103375911712645,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 1.2210526315789474,
1631
+ "grad_norm": 0.31180884775561374,
1632
+ "learning_rate": 7.91189876175355e-06,
1633
+ "loss": 0.20387532711029052,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 1.2263157894736842,
1638
+ "grad_norm": 0.29721196375007514,
1639
+ "learning_rate": 7.822153619679644e-06,
1640
+ "loss": 0.20924797058105468,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 1.231578947368421,
1645
+ "grad_norm": 0.28325623352157336,
1646
+ "learning_rate": 7.732592246381392e-06,
1647
+ "loss": 0.19755966663360597,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 1.236842105263158,
1652
+ "grad_norm": 0.3023877905491012,
1653
+ "learning_rate": 7.643222199133758e-06,
1654
+ "loss": 0.20248010158538818,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 1.2421052631578948,
1659
+ "grad_norm": 0.30648223105953865,
1660
+ "learning_rate": 7.554051019067421e-06,
1661
+ "loss": 0.20098273754119872,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 1.2473684210526317,
1666
+ "grad_norm": 0.31504307543876336,
1667
+ "learning_rate": 7.46508623053246e-06,
1668
+ "loss": 0.20353875160217286,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 1.2526315789473683,
1673
+ "grad_norm": 0.27531435699526163,
1674
+ "learning_rate": 7.376335340463442e-06,
1675
+ "loss": 0.20233564376831054,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 1.2578947368421054,
1680
+ "grad_norm": 0.3010785114920091,
1681
+ "learning_rate": 7.2878058377459716e-06,
1682
+ "loss": 0.19838900566101075,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 1.263157894736842,
1687
+ "grad_norm": 0.31236685732293407,
1688
+ "learning_rate": 7.199505192584772e-06,
1689
+ "loss": 0.2026752710342407,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 1.268421052631579,
1694
+ "grad_norm": 0.29020505050561235,
1695
+ "learning_rate": 7.111440855873346e-06,
1696
+ "loss": 0.2023756980895996,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 1.2736842105263158,
1701
+ "grad_norm": 0.27242043820035505,
1702
+ "learning_rate": 7.023620258565271e-06,
1703
+ "loss": 0.19736809730529786,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 1.2789473684210526,
1708
+ "grad_norm": 0.28155787559665607,
1709
+ "learning_rate": 6.9360508110471526e-06,
1710
+ "loss": 0.2012228012084961,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 1.2842105263157895,
1715
+ "grad_norm": 0.2906665637553726,
1716
+ "learning_rate": 6.848739902513327e-06,
1717
+ "loss": 0.20069727897644044,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 1.2894736842105263,
1722
+ "grad_norm": 0.2969930467731607,
1723
+ "learning_rate": 6.761694900342373e-06,
1724
+ "loss": 0.20128388404846193,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 1.2947368421052632,
1729
+ "grad_norm": 0.2952679778339934,
1730
+ "learning_rate": 6.674923149475433e-06,
1731
+ "loss": 0.2063040018081665,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 1.3,
1736
+ "grad_norm": 0.2989682606009563,
1737
+ "learning_rate": 6.588431971796439e-06,
1738
+ "loss": 0.2017989158630371,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 1.305263157894737,
1743
+ "grad_norm": 0.2981062384864771,
1744
+ "learning_rate": 6.502228665514284e-06,
1745
+ "loss": 0.20122807025909423,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 1.3105263157894738,
1750
+ "grad_norm": 0.2965980275952424,
1751
+ "learning_rate": 6.4163205045469975e-06,
1752
+ "loss": 0.1991926074028015,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 1.3157894736842106,
1757
+ "grad_norm": 0.28759714007677384,
1758
+ "learning_rate": 6.330714737907968e-06,
1759
+ "loss": 0.20284779071807862,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 1.3210526315789473,
1764
+ "grad_norm": 0.2998763973199278,
1765
+ "learning_rate": 6.245418589094254e-06,
1766
+ "loss": 0.19527244567871094,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 1.3263157894736843,
1771
+ "grad_norm": 0.28795604606380654,
1772
+ "learning_rate": 6.1604392554770635e-06,
1773
+ "loss": 0.1968228578567505,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 1.331578947368421,
1778
+ "grad_norm": 0.2872245467986166,
1779
+ "learning_rate": 6.07578390769443e-06,
1780
+ "loss": 0.20151681900024415,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 1.3368421052631578,
1785
+ "grad_norm": 0.30229809608213143,
1786
+ "learning_rate": 5.9914596890461615e-06,
1787
+ "loss": 0.19509825706481934,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 1.3421052631578947,
1792
+ "grad_norm": 0.2989302800988638,
1793
+ "learning_rate": 5.907473714891061e-06,
1794
+ "loss": 0.20209035873413086,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 1.3473684210526315,
1799
+ "grad_norm": 0.2870762674759193,
1800
+ "learning_rate": 5.823833072046538e-06,
1801
+ "loss": 0.20028293132781982,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 1.3526315789473684,
1806
+ "grad_norm": 0.3039557572074681,
1807
+ "learning_rate": 5.7405448181906045e-06,
1808
+ "loss": 0.20040664672851563,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 1.3578947368421053,
1813
+ "grad_norm": 0.3102440280841076,
1814
+ "learning_rate": 5.657615981266373e-06,
1815
+ "loss": 0.19900851249694823,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 1.3631578947368421,
1820
+ "grad_norm": 0.268867053303318,
1821
+ "learning_rate": 5.5750535588889895e-06,
1822
+ "loss": 0.20092666149139404,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 1.368421052631579,
1827
+ "grad_norm": 0.2897322479842339,
1828
+ "learning_rate": 5.4928645177551895e-06,
1829
+ "loss": 0.1961138963699341,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 1.3736842105263158,
1834
+ "grad_norm": 0.2846696497795479,
1835
+ "learning_rate": 5.411055793055442e-06,
1836
+ "loss": 0.1972240090370178,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 1.3789473684210527,
1841
+ "grad_norm": 0.2926637587930832,
1842
+ "learning_rate": 5.329634287888752e-06,
1843
+ "loss": 0.19740312099456786,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 1.3842105263157896,
1848
+ "grad_norm": 0.315472468130149,
1849
+ "learning_rate": 5.248606872680169e-06,
1850
+ "loss": 0.20692920684814453,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 1.3894736842105262,
1855
+ "grad_norm": 0.2863125094171611,
1856
+ "learning_rate": 5.167980384601041e-06,
1857
+ "loss": 0.19995032548904418,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 1.3947368421052633,
1862
+ "grad_norm": 0.2875507180332521,
1863
+ "learning_rate": 5.087761626992111e-06,
1864
+ "loss": 0.19773465394973755,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 1.4,
1869
+ "grad_norm": 0.27514484247099974,
1870
+ "learning_rate": 5.0079573687894225e-06,
1871
+ "loss": 0.19896183013916016,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 1.4052631578947368,
1876
+ "grad_norm": 0.29696367433422627,
1877
+ "learning_rate": 4.928574343953171e-06,
1878
+ "loss": 0.2002697229385376,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 1.4105263157894736,
1883
+ "grad_norm": 0.29576260105912455,
1884
+ "learning_rate": 4.849619250899458e-06,
1885
+ "loss": 0.20564062595367433,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 1.4157894736842105,
1890
+ "grad_norm": 0.28660371612870283,
1891
+ "learning_rate": 4.7710987519351085e-06,
1892
+ "loss": 0.20029211044311523,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 1.4210526315789473,
1897
+ "grad_norm": 0.3146854080289369,
1898
+ "learning_rate": 4.693019472695462e-06,
1899
+ "loss": 0.1956094980239868,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 1.4263157894736842,
1904
+ "grad_norm": 0.2804606823712097,
1905
+ "learning_rate": 4.615388001585326e-06,
1906
+ "loss": 0.19753397703170777,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 1.431578947368421,
1911
+ "grad_norm": 0.2792985512272783,
1912
+ "learning_rate": 4.538210889223016e-06,
1913
+ "loss": 0.19277102947235109,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 1.436842105263158,
1918
+ "grad_norm": 0.2833443963075602,
1919
+ "learning_rate": 4.4614946478876305e-06,
1920
+ "loss": 0.1982126235961914,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 1.4421052631578948,
1925
+ "grad_norm": 0.29400711523072615,
1926
+ "learning_rate": 4.3852457509695115e-06,
1927
+ "loss": 0.19417320489883422,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 1.4473684210526316,
1932
+ "grad_norm": 0.27524878982303125,
1933
+ "learning_rate": 4.309470632424045e-06,
1934
+ "loss": 0.1932328462600708,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 1.4526315789473685,
1939
+ "grad_norm": 0.27779514446087283,
1940
+ "learning_rate": 4.234175686228728e-06,
1941
+ "loss": 0.1982268810272217,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 1.4578947368421051,
1946
+ "grad_norm": 0.2989592360185482,
1947
+ "learning_rate": 4.159367265843662e-06,
1948
+ "loss": 0.19260333776473998,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 1.4631578947368422,
1953
+ "grad_norm": 0.3192699548185505,
1954
+ "learning_rate": 4.085051683675424e-06,
1955
+ "loss": 0.1973806858062744,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 1.4684210526315788,
1960
+ "grad_norm": 0.29426497608472496,
1961
+ "learning_rate": 4.011235210544435e-06,
1962
+ "loss": 0.1963602900505066,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 1.4736842105263157,
1967
+ "grad_norm": 0.29769140386912735,
1968
+ "learning_rate": 3.937924075155807e-06,
1969
+ "loss": 0.2008979082107544,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 1.4789473684210526,
1974
+ "grad_norm": 0.293520582186647,
1975
+ "learning_rate": 3.865124463573774e-06,
1976
+ "loss": 0.19697009325027465,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 1.4842105263157894,
1981
+ "grad_norm": 0.3110219104992736,
1982
+ "learning_rate": 3.792842518699689e-06,
1983
+ "loss": 0.20015451908111573,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 1.4894736842105263,
1988
+ "grad_norm": 0.2662469294030466,
1989
+ "learning_rate": 3.721084339753702e-06,
1990
+ "loss": 0.19725344181060792,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 1.4947368421052631,
1995
+ "grad_norm": 0.2973079431497986,
1996
+ "learning_rate": 3.6498559817600764e-06,
1997
+ "loss": 0.19772164821624755,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 1.5,
2002
+ "grad_norm": 0.27656646463678614,
2003
+ "learning_rate": 3.5791634550362865e-06,
2004
+ "loss": 0.1974316954612732,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 1.5052631578947369,
2009
+ "grad_norm": 0.29432945850940034,
2010
+ "learning_rate": 3.5090127246858318e-06,
2011
+ "loss": 0.19579846858978273,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 1.5105263157894737,
2016
+ "grad_norm": 0.2730282935979345,
2017
+ "learning_rate": 3.4394097100949286e-06,
2018
+ "loss": 0.19849755764007568,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 1.5157894736842106,
2023
+ "grad_norm": 0.3009001641795391,
2024
+ "learning_rate": 3.3703602844329963e-06,
2025
+ "loss": 0.1946340799331665,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 1.5210526315789474,
2030
+ "grad_norm": 0.29707980101419085,
2031
+ "learning_rate": 3.3018702741570976e-06,
2032
+ "loss": 0.1969212770462036,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 1.526315789473684,
2037
+ "grad_norm": 0.2833257974831692,
2038
+ "learning_rate": 3.2339454585202756e-06,
2039
+ "loss": 0.19296889305114745,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 1.5315789473684212,
2044
+ "grad_norm": 0.29149445930134404,
2045
+ "learning_rate": 3.1665915690839165e-06,
2046
+ "loss": 0.1954205870628357,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 1.5368421052631578,
2051
+ "grad_norm": 0.2894059020433222,
2052
+ "learning_rate": 3.0998142892340932e-06,
2053
+ "loss": 0.19373153448104857,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 1.5421052631578949,
2058
+ "grad_norm": 0.28732530129119566,
2059
+ "learning_rate": 3.0336192537020157e-06,
2060
+ "loss": 0.1956033229827881,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 1.5473684210526315,
2065
+ "grad_norm": 0.29049669943929063,
2066
+ "learning_rate": 2.968012048088548e-06,
2067
+ "loss": 0.19107308387756347,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 1.5526315789473686,
2072
+ "grad_norm": 0.299178739593467,
2073
+ "learning_rate": 2.9029982083929088e-06,
2074
+ "loss": 0.20056076049804689,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 1.5578947368421052,
2079
+ "grad_norm": 0.2833198287263072,
2080
+ "learning_rate": 2.83858322054552e-06,
2081
+ "loss": 0.20021560192108154,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 1.563157894736842,
2086
+ "grad_norm": 0.29924363610382615,
2087
+ "learning_rate": 2.774772519945116e-06,
2088
+ "loss": 0.19537402391433717,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 1.568421052631579,
2093
+ "grad_norm": 0.28886141672793486,
2094
+ "learning_rate": 2.7115714910000835e-06,
2095
+ "loss": 0.19449059963226317,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 1.5736842105263158,
2100
+ "grad_norm": 0.31548710546836684,
2101
+ "learning_rate": 2.6489854666741344e-06,
2102
+ "loss": 0.1968981981277466,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 1.5789473684210527,
2107
+ "grad_norm": 0.284433584281696,
2108
+ "learning_rate": 2.587019728036292e-06,
2109
+ "loss": 0.195830774307251,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 1.5842105263157895,
2114
+ "grad_norm": 0.2982575086808407,
2115
+ "learning_rate": 2.5256795038152824e-06,
2116
+ "loss": 0.1970442295074463,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 1.5894736842105264,
2121
+ "grad_norm": 0.3005703600480316,
2122
+ "learning_rate": 2.464969969958314e-06,
2123
+ "loss": 0.2002091407775879,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 1.594736842105263,
2128
+ "grad_norm": 0.28179334651984334,
2129
+ "learning_rate": 2.404896249194346e-06,
2130
+ "loss": 0.19861750602722167,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 1.6,
2135
+ "grad_norm": 0.29760859194543926,
2136
+ "learning_rate": 2.345463410601805e-06,
2137
+ "loss": 0.19542500972747803,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 1.6052631578947367,
2142
+ "grad_norm": 0.2844638710382113,
2143
+ "learning_rate": 2.286676469180871e-06,
2144
+ "loss": 0.19709043502807616,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 1.6105263157894738,
2149
+ "grad_norm": 0.2775597261131208,
2150
+ "learning_rate": 2.2285403854302912e-06,
2151
+ "loss": 0.1949392557144165,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 1.6157894736842104,
2156
+ "grad_norm": 0.33174305706801116,
2157
+ "learning_rate": 2.171060064928824e-06,
2158
+ "loss": 0.19625964164733886,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 1.6210526315789475,
2163
+ "grad_norm": 0.29899003284923736,
2164
+ "learning_rate": 2.114240357921283e-06,
2165
+ "loss": 0.1958683729171753,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 1.6263157894736842,
2170
+ "grad_norm": 0.30253519828831077,
2171
+ "learning_rate": 2.0580860589092897e-06,
2172
+ "loss": 0.19081616401672363,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 1.631578947368421,
2177
+ "grad_norm": 0.2923811724101823,
2178
+ "learning_rate": 2.0026019062466882e-06,
2179
+ "loss": 0.1947636842727661,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 1.6368421052631579,
2184
+ "grad_norm": 0.29746280981406426,
2185
+ "learning_rate": 1.9477925817397358e-06,
2186
+ "loss": 0.19309258460998535,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 1.6421052631578947,
2191
+ "grad_norm": 0.2955090985547228,
2192
+ "learning_rate": 1.8936627102520321e-06,
2193
+ "loss": 0.19541804790496825,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 1.6473684210526316,
2198
+ "grad_norm": 0.27712959308372376,
2199
+ "learning_rate": 1.8402168593142855e-06,
2200
+ "loss": 0.19962093830108643,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 1.6526315789473685,
2205
+ "grad_norm": 0.3103301707016284,
2206
+ "learning_rate": 1.7874595387388815e-06,
2207
+ "loss": 0.195822012424469,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 1.6578947368421053,
2212
+ "grad_norm": 0.29888909648538525,
2213
+ "learning_rate": 1.7353952002393604e-06,
2214
+ "loss": 0.19865849018096923,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 1.663157894736842,
2219
+ "grad_norm": 0.28809870742786514,
2220
+ "learning_rate": 1.6840282370547568e-06,
2221
+ "loss": 0.19288280010223388,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 1.668421052631579,
2226
+ "grad_norm": 0.30077409967188035,
2227
+ "learning_rate": 1.6333629835789154e-06,
2228
+ "loss": 0.19533854722976685,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 1.6736842105263157,
2233
+ "grad_norm": 0.2964519664959678,
2234
+ "learning_rate": 1.5834037149947291e-06,
2235
+ "loss": 0.19245790243148803,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 1.6789473684210527,
2240
+ "grad_norm": 0.29159107489483826,
2241
+ "learning_rate": 1.534154646913416e-06,
2242
+ "loss": 0.19166877269744872,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 1.6842105263157894,
2247
+ "grad_norm": 0.29747162517438613,
2248
+ "learning_rate": 1.4856199350187806e-06,
2249
+ "loss": 0.19105905294418335,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 1.6894736842105265,
2254
+ "grad_norm": 0.287287526073104,
2255
+ "learning_rate": 1.4378036747165746e-06,
2256
+ "loss": 0.19024944305419922,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 1.694736842105263,
2261
+ "grad_norm": 0.28363603807951976,
2262
+ "learning_rate": 1.3907099007889023e-06,
2263
+ "loss": 0.19398729801177977,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 1.7,
2268
+ "grad_norm": 0.2938937872670202,
2269
+ "learning_rate": 1.344342587053782e-06,
2270
+ "loss": 0.19313373565673828,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 1.7052631578947368,
2275
+ "grad_norm": 0.27763402414614136,
2276
+ "learning_rate": 1.2987056460298108e-06,
2277
+ "loss": 0.19442253112792968,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 1.7105263157894737,
2282
+ "grad_norm": 0.28223075675741766,
2283
+ "learning_rate": 1.2538029286060428e-06,
2284
+ "loss": 0.19540021419525147,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 1.7157894736842105,
2289
+ "grad_norm": 0.278656390864509,
2290
+ "learning_rate": 1.2096382237170279e-06,
2291
+ "loss": 0.19183417558670043,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 1.7210526315789474,
2296
+ "grad_norm": 0.28873665435752643,
2297
+ "learning_rate": 1.1662152580231145e-06,
2298
+ "loss": 0.1944838285446167,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 1.7263157894736842,
2303
+ "grad_norm": 0.31876773999709895,
2304
+ "learning_rate": 1.1235376955959787e-06,
2305
+ "loss": 0.19714293479919434,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 1.731578947368421,
2310
+ "grad_norm": 0.29295715482299295,
2311
+ "learning_rate": 1.081609137609455e-06,
2312
+ "loss": 0.18858647346496582,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 1.736842105263158,
2317
+ "grad_norm": 0.28742910267889765,
2318
+ "learning_rate": 1.0404331220356568e-06,
2319
+ "loss": 0.19322052001953124,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 1.7421052631578946,
2324
+ "grad_norm": 0.2872553234950761,
2325
+ "learning_rate": 1.0000131233464484e-06,
2326
+ "loss": 0.19312400817871095,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 1.7473684210526317,
2331
+ "grad_norm": 0.27442072867090284,
2332
+ "learning_rate": 9.60352552220256e-07,
2333
+ "loss": 0.18943675756454467,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 1.7526315789473683,
2338
+ "grad_norm": 0.2866164552689707,
2339
+ "learning_rate": 9.21454755254283e-07,
2340
+ "loss": 0.19052280187606813,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 1.7578947368421054,
2345
+ "grad_norm": 0.2767334020331424,
2346
+ "learning_rate": 8.833230146821059e-07,
2347
+ "loss": 0.19586782455444335,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 1.763157894736842,
2352
+ "grad_norm": 0.278242499350201,
2353
+ "learning_rate": 8.459605480967348e-07,
2354
+ "loss": 0.19273494482040404,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 1.768421052631579,
2359
+ "grad_norm": 0.2786174068598798,
2360
+ "learning_rate": 8.093705081790892e-07,
2361
+ "loss": 0.19584423303604126,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 1.7736842105263158,
2366
+ "grad_norm": 0.2747780780375689,
2367
+ "learning_rate": 7.735559824319905e-07,
2368
+ "loss": 0.1967606544494629,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 1.7789473684210526,
2373
+ "grad_norm": 0.289633650322816,
2374
+ "learning_rate": 7.385199929196241e-07,
2375
+ "loss": 0.19085731506347656,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 1.7842105263157895,
2380
+ "grad_norm": 0.2866260302858027,
2381
+ "learning_rate": 7.042654960125339e-07,
2382
+ "loss": 0.1873401403427124,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 1.7894736842105263,
2387
+ "grad_norm": 0.27869706668392513,
2388
+ "learning_rate": 6.70795382138173e-07,
2389
+ "loss": 0.19778637886047362,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 1.7947368421052632,
2394
+ "grad_norm": 0.2725510557917072,
2395
+ "learning_rate": 6.381124755369938e-07,
2396
+ "loss": 0.19017722606658935,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 1.8,
2401
+ "grad_norm": 0.3050619918202974,
2402
+ "learning_rate": 6.062195340241406e-07,
2403
+ "loss": 0.19560375213623046,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 1.805263157894737,
2408
+ "grad_norm": 0.2802024587835483,
2409
+ "learning_rate": 5.751192487567426e-07,
2410
+ "loss": 0.1918318510055542,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 1.8105263157894735,
2415
+ "grad_norm": 0.29355370886954935,
2416
+ "learning_rate": 5.448142440068316e-07,
2417
+ "loss": 0.1960618257522583,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 1.8157894736842106,
2422
+ "grad_norm": 0.3035953668043707,
2423
+ "learning_rate": 5.15307076939906e-07,
2424
+ "loss": 0.1913236141204834,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 1.8210526315789473,
2429
+ "grad_norm": 0.30254806899706643,
2430
+ "learning_rate": 4.866002373991474e-07,
2431
+ "loss": 0.1932381272315979,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 1.8263157894736843,
2436
+ "grad_norm": 0.2975886256951145,
2437
+ "learning_rate": 4.586961476953311e-07,
2438
+ "loss": 0.1993856430053711,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 1.831578947368421,
2443
+ "grad_norm": 0.2833020604734312,
2444
+ "learning_rate": 4.3159716240242954e-07,
2445
+ "loss": 0.19607802629470825,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 1.836842105263158,
2450
+ "grad_norm": 0.30640219615757136,
2451
+ "learning_rate": 4.05305568158928e-07,
2452
+ "loss": 0.19404864311218262,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 1.8421052631578947,
2457
+ "grad_norm": 0.2828179475804135,
2458
+ "learning_rate": 3.798235834748787e-07,
2459
+ "loss": 0.19020428657531738,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 1.8473684210526315,
2464
+ "grad_norm": 0.29953692477667465,
2465
+ "learning_rate": 3.5515335854469534e-07,
2466
+ "loss": 0.19170570373535156,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 1.8526315789473684,
2471
+ "grad_norm": 0.2891386367058248,
2472
+ "learning_rate": 3.3129697506572467e-07,
2473
+ "loss": 0.19208167791366576,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 1.8578947368421053,
2478
+ "grad_norm": 0.31323367351448866,
2479
+ "learning_rate": 3.082564460625903e-07,
2480
+ "loss": 0.19290330410003662,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 1.8631578947368421,
2485
+ "grad_norm": 0.2933935067787299,
2486
+ "learning_rate": 2.860337157173243e-07,
2487
+ "loss": 0.19398319721221924,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 1.868421052631579,
2492
+ "grad_norm": 0.3078978042307047,
2493
+ "learning_rate": 2.646306592053205e-07,
2494
+ "loss": 0.19711978435516359,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 1.8736842105263158,
2499
+ "grad_norm": 0.29795908157726503,
2500
+ "learning_rate": 2.440490825371078e-07,
2501
+ "loss": 0.193030047416687,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 1.8789473684210525,
2506
+ "grad_norm": 0.2807982610862735,
2507
+ "learning_rate": 2.2429072240595428e-07,
2508
+ "loss": 0.1917279005050659,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 1.8842105263157896,
2513
+ "grad_norm": 0.28111746070486754,
2514
+ "learning_rate": 2.0535724604132223e-07,
2515
+ "loss": 0.19180333614349365,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 1.8894736842105262,
2520
+ "grad_norm": 0.28658449153442855,
2521
+ "learning_rate": 1.8725025106818506e-07,
2522
+ "loss": 0.19407191276550292,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 1.8947368421052633,
2527
+ "grad_norm": 0.2761520673492774,
2528
+ "learning_rate": 1.699712653722241e-07,
2529
+ "loss": 0.19175976514816284,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 1.9,
2534
+ "grad_norm": 0.2976135322441451,
2535
+ "learning_rate": 1.535217469708994e-07,
2536
+ "loss": 0.19339519739151,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 1.905263157894737,
2541
+ "grad_norm": 0.2979367712514626,
2542
+ "learning_rate": 1.3790308389042051e-07,
2543
+ "loss": 0.19258456230163573,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 1.9105263157894736,
2548
+ "grad_norm": 0.283723763736556,
2549
+ "learning_rate": 1.231165940486234e-07,
2550
+ "loss": 0.19650962352752685,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 1.9157894736842105,
2555
+ "grad_norm": 0.2911720022886965,
2556
+ "learning_rate": 1.0916352514376616e-07,
2557
+ "loss": 0.1936952829360962,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 1.9210526315789473,
2562
+ "grad_norm": 0.2787135941737864,
2563
+ "learning_rate": 9.604505454924529e-08,
2564
+ "loss": 0.1929107904434204,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 1.9263157894736842,
2569
+ "grad_norm": 0.3013292787016172,
2570
+ "learning_rate": 8.376228921424867e-08,
2571
+ "loss": 0.18853404521942138,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 1.931578947368421,
2576
+ "grad_norm": 0.2924692814983718,
2577
+ "learning_rate": 7.231626557034687e-08,
2578
+ "loss": 0.19240450859069824,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 1.936842105263158,
2583
+ "grad_norm": 0.28756860436955656,
2584
+ "learning_rate": 6.170794944404201e-08,
2585
+ "loss": 0.19327850341796876,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 1.9421052631578948,
2590
+ "grad_norm": 0.29133261440202207,
2591
+ "learning_rate": 5.193823597526959e-08,
2592
+ "loss": 0.19556995630264282,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 1.9473684210526314,
2597
+ "grad_norm": 0.26150539414829593,
2598
+ "learning_rate": 4.300794954186227e-08,
2599
+ "loss": 0.19019975662231445,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 1.9526315789473685,
2604
+ "grad_norm": 0.2836242919874467,
2605
+ "learning_rate": 3.491784368999329e-08,
2606
+ "loss": 0.18893930912017823,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 1.9578947368421051,
2611
+ "grad_norm": 0.27897514847744354,
2612
+ "learning_rate": 2.766860107058844e-08,
2613
+ "loss": 0.19152721166610717,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 1.9631578947368422,
2618
+ "grad_norm": 0.26524253642728374,
2619
+ "learning_rate": 2.1260833381724355e-08,
2620
+ "loss": 0.1897812604904175,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 1.9684210526315788,
2625
+ "grad_norm": 0.2850408412648559,
2626
+ "learning_rate": 1.569508131701092e-08,
2627
+ "loss": 0.19254502058029174,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 1.973684210526316,
2632
+ "grad_norm": 0.294780708447123,
2633
+ "learning_rate": 1.097181451996887e-08,
2634
+ "loss": 0.1893929958343506,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 1.9789473684210526,
2639
+ "grad_norm": 0.29593292264288545,
2640
+ "learning_rate": 7.091431544401506e-09,
2641
+ "loss": 0.18963019847869872,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 1.9842105263157894,
2646
+ "grad_norm": 0.2816791384313079,
2647
+ "learning_rate": 4.0542598207626846e-09,
2648
+ "loss": 0.19097139835357665,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 1.9894736842105263,
2653
+ "grad_norm": 0.3012979650181145,
2654
+ "learning_rate": 1.860555628527827e-09,
2655
+ "loss": 0.19803013801574706,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 1.9947368421052631,
2660
+ "grad_norm": 0.29395519945414206,
2661
+ "learning_rate": 5.105040745689848e-10,
2662
+ "loss": 0.19267313480377196,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 2.0,
2667
+ "grad_norm": 0.2885933559760845,
2668
+ "learning_rate": 4.2190775395578586e-12,
2669
+ "loss": 0.18964411020278932,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 2.0,
2674
+ "step": 3800,
2675
+ "total_flos": 1.76068140990464e+16,
2676
+ "train_loss": 0.24053681511628,
2677
+ "train_runtime": 74474.5181,
2678
+ "train_samples_per_second": 0.816,
2679
+ "train_steps_per_second": 0.051
2680
+ }
2681
+ ],
2682
+ "logging_steps": 10,
2683
+ "max_steps": 3800,
2684
+ "num_input_tokens_seen": 0,
2685
+ "num_train_epochs": 2,
2686
+ "save_steps": 400,
2687
+ "stateful_callbacks": {
2688
+ "TrainerControl": {
2689
+ "args": {
2690
+ "should_epoch_stop": false,
2691
+ "should_evaluate": false,
2692
+ "should_log": false,
2693
+ "should_save": true,
2694
+ "should_training_stop": true
2695
+ },
2696
+ "attributes": {}
2697
+ }
2698
+ },
2699
+ "total_flos": 1.76068140990464e+16,
2700
+ "train_batch_size": 1,
2701
+ "trial_name": null,
2702
+ "trial_params": null
2703
+ }
designcoder_qwen3.5_9b_adamw_bs16_step3800/training_loss.png ADDED