Hugging Face's logo

INFReasoning
/
metalimo

Safetensors
Model card Files
xet
Community
KublaiKhan1 commited on
Commit
0532c59
·
verified ·
1 Parent(s): ea73cfb

Add files using upload-large-folder tool

Browse files
Files changed (15) hide show
  1. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/added_tokens.json +24 -0
  2. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/chat_template.jinja +54 -0
  3. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/config.json +58 -0
  4. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/generation_config.json +7 -0
  5. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/merges.txt +0 -0
  6. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/model.safetensors.index.json +347 -0
  7. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/special_tokens_map.json +31 -0
  8. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/tokenizer_config.json +208 -0
  9. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/vocab.json +0 -0
  10. qwen2_5_7b_instruct/limo_filtered_incorrect/trainer_log.jsonl +370 -0
  11. qwen2_5_math_7b/limo/checkpoint-1230/added_tokens.json +24 -0
  12. qwen2_5_math_7b/limo/checkpoint-1230/config.json +59 -0
  13. qwen2_5_math_7b/limo/checkpoint-1230/generation_config.json +6 -0
  14. qwen2_5_math_7b/limo/checkpoint-1230/model.safetensors.index.json +347 -0
  15. qwen2_5_math_7b/limo/checkpoint-1230/special_tokens_map.json +31 -0
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.55.0",
6
+ "use_cache": false
7
+ }
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-370/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo_filtered_incorrect/trainer_log.jsonl ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 1850, "loss": 0.7808, "lr": 5e-06, "epoch": 0.005405405405405406, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "1:46:11"}
2
+ {"current_steps": 2, "total_steps": 1850, "loss": 0.8188, "lr": 4.999996395324314e-06, "epoch": 0.010810810810810811, "percentage": 0.11, "elapsed_time": "0:00:06", "remaining_time": "1:38:22"}
3
+ {"current_steps": 3, "total_steps": 1850, "loss": 0.7499, "lr": 4.99998558130765e-06, "epoch": 0.016216216216216217, "percentage": 0.16, "elapsed_time": "0:00:09", "remaining_time": "1:40:24"}
4
+ {"current_steps": 4, "total_steps": 1850, "loss": 0.6276, "lr": 4.999967557981192e-06, "epoch": 0.021621621621621623, "percentage": 0.22, "elapsed_time": "0:00:11", "remaining_time": "1:30:16"}
5
+ {"current_steps": 5, "total_steps": 1850, "loss": 0.7089, "lr": 4.999942325396917e-06, "epoch": 0.02702702702702703, "percentage": 0.27, "elapsed_time": "0:00:14", "remaining_time": "1:28:34"}
6
+ {"current_steps": 6, "total_steps": 1850, "loss": 0.7681, "lr": 4.999909883627588e-06, "epoch": 0.032432432432432434, "percentage": 0.32, "elapsed_time": "0:00:18", "remaining_time": "1:35:36"}
7
+ {"current_steps": 7, "total_steps": 1850, "loss": 1.2311, "lr": 4.999870232766757e-06, "epoch": 0.03783783783783784, "percentage": 0.38, "elapsed_time": "0:00:21", "remaining_time": "1:33:14"}
8
+ {"current_steps": 8, "total_steps": 1850, "loss": 0.7973, "lr": 4.9998233729287696e-06, "epoch": 0.043243243243243246, "percentage": 0.43, "elapsed_time": "0:00:24", "remaining_time": "1:34:08"}
9
+ {"current_steps": 9, "total_steps": 1850, "loss": 0.6119, "lr": 4.999769304248755e-06, "epoch": 0.04864864864864865, "percentage": 0.49, "elapsed_time": "0:00:26", "remaining_time": "1:31:43"}
10
+ {"current_steps": 10, "total_steps": 1850, "loss": 0.7729, "lr": 4.9997080268826344e-06, "epoch": 0.05405405405405406, "percentage": 0.54, "elapsed_time": "0:00:30", "remaining_time": "1:34:46"}
11
+ {"current_steps": 11, "total_steps": 1850, "loss": 0.5507, "lr": 4.9996395410071165e-06, "epoch": 0.05945945945945946, "percentage": 0.59, "elapsed_time": "0:00:33", "remaining_time": "1:34:05"}
12
+ {"current_steps": 12, "total_steps": 1850, "loss": 0.7063, "lr": 4.999563846819696e-06, "epoch": 0.06486486486486487, "percentage": 0.65, "elapsed_time": "0:00:38", "remaining_time": "1:38:59"}
13
+ {"current_steps": 13, "total_steps": 1850, "loss": 0.7735, "lr": 4.999480944538655e-06, "epoch": 0.07027027027027027, "percentage": 0.7, "elapsed_time": "0:00:40", "remaining_time": "1:34:27"}
14
+ {"current_steps": 14, "total_steps": 1850, "loss": 0.5634, "lr": 4.999390834403063e-06, "epoch": 0.07567567567567568, "percentage": 0.76, "elapsed_time": "0:00:45", "remaining_time": "1:38:56"}
15
+ {"current_steps": 15, "total_steps": 1850, "loss": 0.7101, "lr": 4.999293516672773e-06, "epoch": 0.08108108108108109, "percentage": 0.81, "elapsed_time": "0:00:46", "remaining_time": "1:34:22"}
16
+ {"current_steps": 16, "total_steps": 1850, "loss": 0.7069, "lr": 4.9991889916284255e-06, "epoch": 0.08648648648648649, "percentage": 0.86, "elapsed_time": "0:00:47", "remaining_time": "1:30:19"}
17
+ {"current_steps": 17, "total_steps": 1850, "loss": 0.8364, "lr": 4.999077259571442e-06, "epoch": 0.0918918918918919, "percentage": 0.92, "elapsed_time": "0:00:48", "remaining_time": "1:26:46"}
18
+ {"current_steps": 18, "total_steps": 1850, "loss": 0.6239, "lr": 4.998958320824031e-06, "epoch": 0.0972972972972973, "percentage": 0.97, "elapsed_time": "0:00:52", "remaining_time": "1:29:37"}
19
+ {"current_steps": 19, "total_steps": 1850, "loss": 0.6401, "lr": 4.998832175729179e-06, "epoch": 0.10270270270270271, "percentage": 1.03, "elapsed_time": "0:00:56", "remaining_time": "1:29:57"}
20
+ {"current_steps": 20, "total_steps": 1850, "loss": 0.8762, "lr": 4.998698824650656e-06, "epoch": 0.10810810810810811, "percentage": 1.08, "elapsed_time": "0:00:58", "remaining_time": "1:29:54"}
21
+ {"current_steps": 21, "total_steps": 1850, "loss": 0.6356, "lr": 4.998558267973014e-06, "epoch": 0.11351351351351352, "percentage": 1.14, "elapsed_time": "0:01:01", "remaining_time": "1:29:41"}
22
+ {"current_steps": 22, "total_steps": 1850, "loss": 0.5965, "lr": 4.998410506101579e-06, "epoch": 0.11891891891891893, "percentage": 1.19, "elapsed_time": "0:01:03", "remaining_time": "1:28:28"}
23
+ {"current_steps": 23, "total_steps": 1850, "loss": 0.7616, "lr": 4.9982555394624595e-06, "epoch": 0.12432432432432433, "percentage": 1.24, "elapsed_time": "0:01:06", "remaining_time": "1:28:05"}
24
+ {"current_steps": 24, "total_steps": 1850, "loss": 0.7166, "lr": 4.998093368502539e-06, "epoch": 0.12972972972972974, "percentage": 1.3, "elapsed_time": "0:01:08", "remaining_time": "1:26:37"}
25
+ {"current_steps": 25, "total_steps": 1850, "loss": 0.5398, "lr": 4.9979239936894765e-06, "epoch": 0.13513513513513514, "percentage": 1.35, "elapsed_time": "0:01:11", "remaining_time": "1:26:37"}
26
+ {"current_steps": 26, "total_steps": 1850, "loss": 0.4563, "lr": 4.997747415511705e-06, "epoch": 0.14054054054054055, "percentage": 1.41, "elapsed_time": "0:01:15", "remaining_time": "1:28:25"}
27
+ {"current_steps": 27, "total_steps": 1850, "loss": 0.5254, "lr": 4.997563634478428e-06, "epoch": 0.14594594594594595, "percentage": 1.46, "elapsed_time": "0:01:19", "remaining_time": "1:28:55"}
28
+ {"current_steps": 28, "total_steps": 1850, "loss": 0.3985, "lr": 4.997372651119626e-06, "epoch": 0.15135135135135136, "percentage": 1.51, "elapsed_time": "0:01:23", "remaining_time": "1:30:18"}
29
+ {"current_steps": 29, "total_steps": 1850, "loss": 0.5538, "lr": 4.997174465986044e-06, "epoch": 0.15675675675675677, "percentage": 1.57, "elapsed_time": "0:01:26", "remaining_time": "1:30:27"}
30
+ {"current_steps": 30, "total_steps": 1850, "loss": 0.4613, "lr": 4.996969079649196e-06, "epoch": 0.16216216216216217, "percentage": 1.62, "elapsed_time": "0:01:30", "remaining_time": "1:31:31"}
31
+ {"current_steps": 31, "total_steps": 1850, "loss": 0.5902, "lr": 4.996756492701362e-06, "epoch": 0.16756756756756758, "percentage": 1.68, "elapsed_time": "0:01:31", "remaining_time": "1:29:46"}
32
+ {"current_steps": 32, "total_steps": 1850, "loss": 0.6301, "lr": 4.996536705755591e-06, "epoch": 0.17297297297297298, "percentage": 1.73, "elapsed_time": "0:01:36", "remaining_time": "1:31:25"}
33
+ {"current_steps": 33, "total_steps": 1850, "loss": 0.6533, "lr": 4.996309719445687e-06, "epoch": 0.1783783783783784, "percentage": 1.78, "elapsed_time": "0:01:38", "remaining_time": "1:29:58"}
34
+ {"current_steps": 34, "total_steps": 1850, "loss": 0.656, "lr": 4.996075534426223e-06, "epoch": 0.1837837837837838, "percentage": 1.84, "elapsed_time": "0:01:41", "remaining_time": "1:30:21"}
35
+ {"current_steps": 35, "total_steps": 1850, "loss": 0.7456, "lr": 4.995834151372526e-06, "epoch": 0.1891891891891892, "percentage": 1.89, "elapsed_time": "0:01:46", "remaining_time": "1:31:55"}
36
+ {"current_steps": 36, "total_steps": 1850, "loss": 0.9072, "lr": 4.995585570980685e-06, "epoch": 0.1945945945945946, "percentage": 1.95, "elapsed_time": "0:01:48", "remaining_time": "1:30:54"}
37
+ {"current_steps": 37, "total_steps": 1850, "loss": 0.4235, "lr": 4.995329793967537e-06, "epoch": 0.2, "percentage": 2.0, "elapsed_time": "0:01:49", "remaining_time": "1:29:13"}
38
+ {"current_steps": 38, "total_steps": 1850, "loss": 0.5929, "lr": 4.9950668210706795e-06, "epoch": 0.20540540540540542, "percentage": 2.05, "elapsed_time": "0:01:50", "remaining_time": "1:27:52"}
39
+ {"current_steps": 39, "total_steps": 1850, "loss": 0.582, "lr": 4.994796653048457e-06, "epoch": 0.21081081081081082, "percentage": 2.11, "elapsed_time": "0:01:54", "remaining_time": "1:28:46"}
40
+ {"current_steps": 40, "total_steps": 1850, "loss": 0.6648, "lr": 4.994519290679965e-06, "epoch": 0.21621621621621623, "percentage": 2.16, "elapsed_time": "0:01:57", "remaining_time": "1:28:39"}
41
+ {"current_steps": 41, "total_steps": 1850, "loss": 0.6, "lr": 4.994234734765043e-06, "epoch": 0.22162162162162163, "percentage": 2.22, "elapsed_time": "0:02:02", "remaining_time": "1:30:24"}
42
+ {"current_steps": 42, "total_steps": 1850, "loss": 0.5879, "lr": 4.993942986124278e-06, "epoch": 0.22702702702702704, "percentage": 2.27, "elapsed_time": "0:02:08", "remaining_time": "1:32:17"}
43
+ {"current_steps": 43, "total_steps": 1850, "loss": 0.7423, "lr": 4.9936440455989975e-06, "epoch": 0.23243243243243245, "percentage": 2.32, "elapsed_time": "0:02:11", "remaining_time": "1:32:05"}
44
+ {"current_steps": 44, "total_steps": 1850, "loss": 0.5415, "lr": 4.993337914051266e-06, "epoch": 0.23783783783783785, "percentage": 2.38, "elapsed_time": "0:02:13", "remaining_time": "1:31:04"}
45
+ {"current_steps": 45, "total_steps": 1850, "loss": 0.5937, "lr": 4.99302459236389e-06, "epoch": 0.24324324324324326, "percentage": 2.43, "elapsed_time": "0:02:18", "remaining_time": "1:32:55"}
46
+ {"current_steps": 46, "total_steps": 1850, "loss": 0.6086, "lr": 4.992704081440407e-06, "epoch": 0.24864864864864866, "percentage": 2.49, "elapsed_time": "0:02:19", "remaining_time": "1:31:28"}
47
+ {"current_steps": 47, "total_steps": 1850, "loss": 0.6323, "lr": 4.992376382205088e-06, "epoch": 0.25405405405405407, "percentage": 2.54, "elapsed_time": "0:02:22", "remaining_time": "1:31:17"}
48
+ {"current_steps": 48, "total_steps": 1850, "loss": 0.4514, "lr": 4.992041495602932e-06, "epoch": 0.2594594594594595, "percentage": 2.59, "elapsed_time": "0:02:27", "remaining_time": "1:32:23"}
49
+ {"current_steps": 49, "total_steps": 1850, "loss": 0.7453, "lr": 4.991699422599664e-06, "epoch": 0.2648648648648649, "percentage": 2.65, "elapsed_time": "0:02:29", "remaining_time": "1:31:52"}
50
+ {"current_steps": 50, "total_steps": 1850, "loss": 0.7038, "lr": 4.991350164181735e-06, "epoch": 0.2702702702702703, "percentage": 2.7, "elapsed_time": "0:02:32", "remaining_time": "1:31:46"}
51
+ {"current_steps": 51, "total_steps": 1850, "loss": 0.5296, "lr": 4.990993721356317e-06, "epoch": 0.2756756756756757, "percentage": 2.76, "elapsed_time": "0:02:34", "remaining_time": "1:30:56"}
52
+ {"current_steps": 52, "total_steps": 1850, "loss": 0.5257, "lr": 4.990630095151296e-06, "epoch": 0.2810810810810811, "percentage": 2.81, "elapsed_time": "0:02:36", "remaining_time": "1:30:25"}
53
+ {"current_steps": 53, "total_steps": 1850, "loss": 0.811, "lr": 4.9902592866152765e-06, "epoch": 0.2864864864864865, "percentage": 2.86, "elapsed_time": "0:02:39", "remaining_time": "1:30:04"}
54
+ {"current_steps": 54, "total_steps": 1850, "loss": 0.4431, "lr": 4.989881296817575e-06, "epoch": 0.2918918918918919, "percentage": 2.92, "elapsed_time": "0:02:41", "remaining_time": "1:29:24"}
55
+ {"current_steps": 55, "total_steps": 1850, "loss": 0.3317, "lr": 4.989496126848215e-06, "epoch": 0.2972972972972973, "percentage": 2.97, "elapsed_time": "0:02:45", "remaining_time": "1:30:14"}
56
+ {"current_steps": 56, "total_steps": 1850, "loss": 0.8249, "lr": 4.989103777817928e-06, "epoch": 0.3027027027027027, "percentage": 3.03, "elapsed_time": "0:02:51", "remaining_time": "1:31:33"}
57
+ {"current_steps": 57, "total_steps": 1850, "loss": 0.5625, "lr": 4.988704250858145e-06, "epoch": 0.3081081081081081, "percentage": 3.08, "elapsed_time": "0:02:53", "remaining_time": "1:31:13"}
58
+ {"current_steps": 58, "total_steps": 1850, "loss": 0.397, "lr": 4.988297547121e-06, "epoch": 0.31351351351351353, "percentage": 3.14, "elapsed_time": "0:02:58", "remaining_time": "1:31:53"}
59
+ {"current_steps": 59, "total_steps": 1850, "loss": 0.6648, "lr": 4.98788366777932e-06, "epoch": 0.31891891891891894, "percentage": 3.19, "elapsed_time": "0:03:00", "remaining_time": "1:31:07"}
60
+ {"current_steps": 60, "total_steps": 1850, "loss": 0.5787, "lr": 4.987462614026625e-06, "epoch": 0.32432432432432434, "percentage": 3.24, "elapsed_time": "0:03:02", "remaining_time": "1:30:42"}
61
+ {"current_steps": 61, "total_steps": 1850, "loss": 0.6546, "lr": 4.987034387077126e-06, "epoch": 0.32972972972972975, "percentage": 3.3, "elapsed_time": "0:03:05", "remaining_time": "1:30:40"}
62
+ {"current_steps": 62, "total_steps": 1850, "loss": 0.5057, "lr": 4.986598988165718e-06, "epoch": 0.33513513513513515, "percentage": 3.35, "elapsed_time": "0:03:08", "remaining_time": "1:30:25"}
63
+ {"current_steps": 63, "total_steps": 1850, "loss": 0.6438, "lr": 4.9861564185479785e-06, "epoch": 0.34054054054054056, "percentage": 3.41, "elapsed_time": "0:03:12", "remaining_time": "1:30:59"}
64
+ {"current_steps": 64, "total_steps": 1850, "loss": 0.8114, "lr": 4.985706679500163e-06, "epoch": 0.34594594594594597, "percentage": 3.46, "elapsed_time": "0:03:15", "remaining_time": "1:30:52"}
65
+ {"current_steps": 65, "total_steps": 1850, "loss": 0.6345, "lr": 4.9852497723192025e-06, "epoch": 0.35135135135135137, "percentage": 3.51, "elapsed_time": "0:03:16", "remaining_time": "1:30:04"}
66
+ {"current_steps": 66, "total_steps": 1850, "loss": 0.7756, "lr": 4.9847856983227e-06, "epoch": 0.3567567567567568, "percentage": 3.57, "elapsed_time": "0:03:18", "remaining_time": "1:29:32"}
67
+ {"current_steps": 67, "total_steps": 1850, "loss": 0.7248, "lr": 4.984314458848923e-06, "epoch": 0.3621621621621622, "percentage": 3.62, "elapsed_time": "0:03:20", "remaining_time": "1:28:52"}
68
+ {"current_steps": 68, "total_steps": 1850, "loss": 0.7902, "lr": 4.983836055256804e-06, "epoch": 0.3675675675675676, "percentage": 3.68, "elapsed_time": "0:03:23", "remaining_time": "1:28:58"}
69
+ {"current_steps": 69, "total_steps": 1850, "loss": 0.6512, "lr": 4.983350488925935e-06, "epoch": 0.372972972972973, "percentage": 3.73, "elapsed_time": "0:03:26", "remaining_time": "1:28:38"}
70
+ {"current_steps": 70, "total_steps": 1850, "loss": 0.9753, "lr": 4.982857761256564e-06, "epoch": 0.3783783783783784, "percentage": 3.78, "elapsed_time": "0:03:29", "remaining_time": "1:28:50"}
71
+ {"current_steps": 71, "total_steps": 1850, "loss": 0.5645, "lr": 4.982357873669589e-06, "epoch": 0.3837837837837838, "percentage": 3.84, "elapsed_time": "0:03:30", "remaining_time": "1:28:06"}
72
+ {"current_steps": 72, "total_steps": 1850, "loss": 0.4865, "lr": 4.981850827606556e-06, "epoch": 0.3891891891891892, "percentage": 3.89, "elapsed_time": "0:03:32", "remaining_time": "1:27:39"}
73
+ {"current_steps": 73, "total_steps": 1850, "loss": 0.7247, "lr": 4.981336624529655e-06, "epoch": 0.3945945945945946, "percentage": 3.95, "elapsed_time": "0:03:36", "remaining_time": "1:27:48"}
74
+ {"current_steps": 74, "total_steps": 1850, "loss": 0.8284, "lr": 4.980815265921714e-06, "epoch": 0.4, "percentage": 4.0, "elapsed_time": "0:03:39", "remaining_time": "1:27:48"}
75
+ {"current_steps": 75, "total_steps": 1850, "loss": 0.706, "lr": 4.980286753286196e-06, "epoch": 0.40540540540540543, "percentage": 4.05, "elapsed_time": "0:03:44", "remaining_time": "1:28:29"}
76
+ {"current_steps": 76, "total_steps": 1850, "loss": 0.8405, "lr": 4.979751088147192e-06, "epoch": 0.41081081081081083, "percentage": 4.11, "elapsed_time": "0:03:47", "remaining_time": "1:28:22"}
77
+ {"current_steps": 77, "total_steps": 1850, "loss": 0.8383, "lr": 4.979208272049425e-06, "epoch": 0.41621621621621624, "percentage": 4.16, "elapsed_time": "0:03:49", "remaining_time": "1:27:54"}
78
+ {"current_steps": 78, "total_steps": 1850, "loss": 1.0418, "lr": 4.978658306558235e-06, "epoch": 0.42162162162162165, "percentage": 4.22, "elapsed_time": "0:03:52", "remaining_time": "1:27:53"}
79
+ {"current_steps": 79, "total_steps": 1850, "loss": 0.654, "lr": 4.978101193259578e-06, "epoch": 0.42702702702702705, "percentage": 4.27, "elapsed_time": "0:03:53", "remaining_time": "1:27:18"}
80
+ {"current_steps": 80, "total_steps": 1850, "loss": 0.4631, "lr": 4.977536933760025e-06, "epoch": 0.43243243243243246, "percentage": 4.32, "elapsed_time": "0:03:55", "remaining_time": "1:26:57"}
81
+ {"current_steps": 81, "total_steps": 1850, "loss": 0.5515, "lr": 4.976965529686755e-06, "epoch": 0.43783783783783786, "percentage": 4.38, "elapsed_time": "0:03:58", "remaining_time": "1:26:52"}
82
+ {"current_steps": 82, "total_steps": 1850, "loss": 0.6995, "lr": 4.976386982687548e-06, "epoch": 0.44324324324324327, "percentage": 4.43, "elapsed_time": "0:04:00", "remaining_time": "1:26:22"}
83
+ {"current_steps": 83, "total_steps": 1850, "loss": 0.6191, "lr": 4.9758012944307845e-06, "epoch": 0.4486486486486487, "percentage": 4.49, "elapsed_time": "0:04:03", "remaining_time": "1:26:17"}
84
+ {"current_steps": 84, "total_steps": 1850, "loss": 1.0386, "lr": 4.975208466605436e-06, "epoch": 0.4540540540540541, "percentage": 4.54, "elapsed_time": "0:04:05", "remaining_time": "1:26:01"}
85
+ {"current_steps": 85, "total_steps": 1850, "loss": 0.6995, "lr": 4.974608500921064e-06, "epoch": 0.4594594594594595, "percentage": 4.59, "elapsed_time": "0:04:07", "remaining_time": "1:25:43"}
86
+ {"current_steps": 86, "total_steps": 1850, "loss": 0.5279, "lr": 4.974001399107816e-06, "epoch": 0.4648648648648649, "percentage": 4.65, "elapsed_time": "0:04:09", "remaining_time": "1:25:07"}
87
+ {"current_steps": 87, "total_steps": 1850, "loss": 0.5979, "lr": 4.973387162916415e-06, "epoch": 0.4702702702702703, "percentage": 4.7, "elapsed_time": "0:04:12", "remaining_time": "1:25:22"}
88
+ {"current_steps": 88, "total_steps": 1850, "loss": 0.4009, "lr": 4.972765794118158e-06, "epoch": 0.4756756756756757, "percentage": 4.76, "elapsed_time": "0:04:13", "remaining_time": "1:24:38"}
89
+ {"current_steps": 89, "total_steps": 1850, "loss": 0.6512, "lr": 4.9721372945049114e-06, "epoch": 0.4810810810810811, "percentage": 4.81, "elapsed_time": "0:04:17", "remaining_time": "1:24:57"}
90
+ {"current_steps": 90, "total_steps": 1850, "loss": 0.4848, "lr": 4.971501665889107e-06, "epoch": 0.4864864864864865, "percentage": 4.86, "elapsed_time": "0:04:21", "remaining_time": "1:25:08"}
91
+ {"current_steps": 91, "total_steps": 1850, "loss": 0.3983, "lr": 4.9708589101037306e-06, "epoch": 0.4918918918918919, "percentage": 4.92, "elapsed_time": "0:04:24", "remaining_time": "1:25:08"}
92
+ {"current_steps": 92, "total_steps": 1850, "loss": 0.5519, "lr": 4.970209029002325e-06, "epoch": 0.4972972972972973, "percentage": 4.97, "elapsed_time": "0:04:29", "remaining_time": "1:25:56"}
93
+ {"current_steps": 93, "total_steps": 1850, "loss": 0.7579, "lr": 4.969552024458977e-06, "epoch": 0.5027027027027027, "percentage": 5.03, "elapsed_time": "0:04:33", "remaining_time": "1:26:09"}
94
+ {"current_steps": 94, "total_steps": 1850, "loss": 0.5625, "lr": 4.968887898368318e-06, "epoch": 0.5081081081081081, "percentage": 5.08, "elapsed_time": "0:04:38", "remaining_time": "1:26:40"}
95
+ {"current_steps": 95, "total_steps": 1850, "loss": 0.5626, "lr": 4.968216652645515e-06, "epoch": 0.5135135135135135, "percentage": 5.14, "elapsed_time": "0:04:43", "remaining_time": "1:27:23"}
96
+ {"current_steps": 96, "total_steps": 1850, "loss": 0.7021, "lr": 4.967538289226268e-06, "epoch": 0.518918918918919, "percentage": 5.19, "elapsed_time": "0:04:47", "remaining_time": "1:27:32"}
97
+ {"current_steps": 97, "total_steps": 1850, "loss": 0.5081, "lr": 4.966852810066798e-06, "epoch": 0.5243243243243243, "percentage": 5.24, "elapsed_time": "0:04:51", "remaining_time": "1:27:44"}
98
+ {"current_steps": 98, "total_steps": 1850, "loss": 0.5366, "lr": 4.9661602171438524e-06, "epoch": 0.5297297297297298, "percentage": 5.3, "elapsed_time": "0:04:52", "remaining_time": "1:27:07"}
99
+ {"current_steps": 99, "total_steps": 1850, "loss": 0.6338, "lr": 4.965460512454687e-06, "epoch": 0.5351351351351351, "percentage": 5.35, "elapsed_time": "0:04:54", "remaining_time": "1:26:46"}
100
+ {"current_steps": 100, "total_steps": 1850, "loss": 0.6454, "lr": 4.964753698017071e-06, "epoch": 0.5405405405405406, "percentage": 5.41, "elapsed_time": "0:04:58", "remaining_time": "1:26:55"}
101
+ {"current_steps": 101, "total_steps": 1850, "loss": 0.493, "lr": 4.964039775869271e-06, "epoch": 0.5459459459459459, "percentage": 5.46, "elapsed_time": "0:04:59", "remaining_time": "1:26:23"}
102
+ {"current_steps": 102, "total_steps": 1850, "loss": 0.5626, "lr": 4.963318748070056e-06, "epoch": 0.5513513513513514, "percentage": 5.51, "elapsed_time": "0:05:02", "remaining_time": "1:26:24"}
103
+ {"current_steps": 103, "total_steps": 1850, "loss": 0.6229, "lr": 4.9625906166986815e-06, "epoch": 0.5567567567567567, "percentage": 5.57, "elapsed_time": "0:05:08", "remaining_time": "1:27:13"}
104
+ {"current_steps": 104, "total_steps": 1850, "loss": 0.5698, "lr": 4.961855383854889e-06, "epoch": 0.5621621621621622, "percentage": 5.62, "elapsed_time": "0:05:11", "remaining_time": "1:27:07"}
105
+ {"current_steps": 105, "total_steps": 1850, "loss": 0.4012, "lr": 4.961113051658901e-06, "epoch": 0.5675675675675675, "percentage": 5.68, "elapsed_time": "0:05:13", "remaining_time": "1:26:43"}
106
+ {"current_steps": 106, "total_steps": 1850, "loss": 0.5461, "lr": 4.96036362225141e-06, "epoch": 0.572972972972973, "percentage": 5.73, "elapsed_time": "0:05:15", "remaining_time": "1:26:33"}
107
+ {"current_steps": 107, "total_steps": 1850, "loss": 0.4895, "lr": 4.959607097793575e-06, "epoch": 0.5783783783783784, "percentage": 5.78, "elapsed_time": "0:05:17", "remaining_time": "1:26:20"}
108
+ {"current_steps": 108, "total_steps": 1850, "loss": 0.6228, "lr": 4.9588434804670176e-06, "epoch": 0.5837837837837838, "percentage": 5.84, "elapsed_time": "0:05:21", "remaining_time": "1:26:22"}
109
+ {"current_steps": 109, "total_steps": 1850, "loss": 0.7, "lr": 4.958072772473812e-06, "epoch": 0.5891891891891892, "percentage": 5.89, "elapsed_time": "0:05:24", "remaining_time": "1:26:28"}
110
+ {"current_steps": 110, "total_steps": 1850, "loss": 0.4098, "lr": 4.9572949760364795e-06, "epoch": 0.5945945945945946, "percentage": 5.95, "elapsed_time": "0:05:25", "remaining_time": "1:25:53"}
111
+ {"current_steps": 111, "total_steps": 1850, "loss": 0.4726, "lr": 4.9565100933979835e-06, "epoch": 0.6, "percentage": 6.0, "elapsed_time": "0:05:27", "remaining_time": "1:25:34"}
112
+ {"current_steps": 112, "total_steps": 1850, "loss": 0.8092, "lr": 4.9557181268217225e-06, "epoch": 0.6054054054054054, "percentage": 6.05, "elapsed_time": "0:05:29", "remaining_time": "1:25:17"}
113
+ {"current_steps": 113, "total_steps": 1850, "loss": 0.6809, "lr": 4.954919078591521e-06, "epoch": 0.6108108108108108, "percentage": 6.11, "elapsed_time": "0:05:31", "remaining_time": "1:25:01"}
114
+ {"current_steps": 114, "total_steps": 1850, "loss": 0.5289, "lr": 4.954112951011628e-06, "epoch": 0.6162162162162163, "percentage": 6.16, "elapsed_time": "0:05:35", "remaining_time": "1:25:08"}
115
+ {"current_steps": 115, "total_steps": 1850, "loss": 0.7136, "lr": 4.9532997464067065e-06, "epoch": 0.6216216216216216, "percentage": 6.22, "elapsed_time": "0:05:37", "remaining_time": "1:24:55"}
116
+ {"current_steps": 116, "total_steps": 1850, "loss": 0.8171, "lr": 4.952479467121828e-06, "epoch": 0.6270270270270271, "percentage": 6.27, "elapsed_time": "0:05:39", "remaining_time": "1:24:34"}
117
+ {"current_steps": 117, "total_steps": 1850, "loss": 0.9386, "lr": 4.951652115522463e-06, "epoch": 0.6324324324324324, "percentage": 6.32, "elapsed_time": "0:05:41", "remaining_time": "1:24:12"}
118
+ {"current_steps": 118, "total_steps": 1850, "loss": 0.5044, "lr": 4.950817693994481e-06, "epoch": 0.6378378378378379, "percentage": 6.38, "elapsed_time": "0:05:44", "remaining_time": "1:24:18"}
119
+ {"current_steps": 119, "total_steps": 1850, "loss": 0.5203, "lr": 4.949976204944135e-06, "epoch": 0.6432432432432432, "percentage": 6.43, "elapsed_time": "0:05:47", "remaining_time": "1:24:18"}
120
+ {"current_steps": 120, "total_steps": 1850, "loss": 0.7228, "lr": 4.949127650798063e-06, "epoch": 0.6486486486486487, "percentage": 6.49, "elapsed_time": "0:05:48", "remaining_time": "1:23:47"}
121
+ {"current_steps": 121, "total_steps": 1850, "loss": 0.5169, "lr": 4.948272034003275e-06, "epoch": 0.654054054054054, "percentage": 6.54, "elapsed_time": "0:05:49", "remaining_time": "1:23:14"}
122
+ {"current_steps": 122, "total_steps": 1850, "loss": 0.3863, "lr": 4.947409357027148e-06, "epoch": 0.6594594594594595, "percentage": 6.59, "elapsed_time": "0:05:51", "remaining_time": "1:22:53"}
123
+ {"current_steps": 123, "total_steps": 1850, "loss": 0.7313, "lr": 4.9465396223574165e-06, "epoch": 0.6648648648648648, "percentage": 6.65, "elapsed_time": "0:05:56", "remaining_time": "1:23:21"}
124
+ {"current_steps": 124, "total_steps": 1850, "loss": 0.7378, "lr": 4.945662832502172e-06, "epoch": 0.6702702702702703, "percentage": 6.7, "elapsed_time": "0:05:59", "remaining_time": "1:23:18"}
125
+ {"current_steps": 125, "total_steps": 1850, "loss": 0.7933, "lr": 4.944778989989847e-06, "epoch": 0.6756756756756757, "percentage": 6.76, "elapsed_time": "0:06:01", "remaining_time": "1:23:05"}
126
+ {"current_steps": 126, "total_steps": 1850, "loss": 0.5132, "lr": 4.943888097369216e-06, "epoch": 0.6810810810810811, "percentage": 6.81, "elapsed_time": "0:06:04", "remaining_time": "1:23:05"}
127
+ {"current_steps": 127, "total_steps": 1850, "loss": 0.5264, "lr": 4.942990157209381e-06, "epoch": 0.6864864864864865, "percentage": 6.86, "elapsed_time": "0:06:06", "remaining_time": "1:22:49"}
128
+ {"current_steps": 128, "total_steps": 1850, "loss": 0.6514, "lr": 4.9420851720997674e-06, "epoch": 0.6918918918918919, "percentage": 6.92, "elapsed_time": "0:06:08", "remaining_time": "1:22:43"}
129
+ {"current_steps": 129, "total_steps": 1850, "loss": 1.0914, "lr": 4.94117314465012e-06, "epoch": 0.6972972972972973, "percentage": 6.97, "elapsed_time": "0:06:10", "remaining_time": "1:22:20"}
130
+ {"current_steps": 130, "total_steps": 1850, "loss": 0.5183, "lr": 4.940254077490487e-06, "epoch": 0.7027027027027027, "percentage": 7.03, "elapsed_time": "0:06:13", "remaining_time": "1:22:20"}
131
+ {"current_steps": 131, "total_steps": 1850, "loss": 0.4467, "lr": 4.939327973271222e-06, "epoch": 0.7081081081081081, "percentage": 7.08, "elapsed_time": "0:06:14", "remaining_time": "1:21:58"}
132
+ {"current_steps": 132, "total_steps": 1850, "loss": 0.4674, "lr": 4.9383948346629665e-06, "epoch": 0.7135135135135136, "percentage": 7.14, "elapsed_time": "0:06:16", "remaining_time": "1:21:36"}
133
+ {"current_steps": 133, "total_steps": 1850, "loss": 0.5886, "lr": 4.937454664356652e-06, "epoch": 0.7189189189189189, "percentage": 7.19, "elapsed_time": "0:06:17", "remaining_time": "1:21:18"}
134
+ {"current_steps": 134, "total_steps": 1850, "loss": 0.506, "lr": 4.9365074650634855e-06, "epoch": 0.7243243243243244, "percentage": 7.24, "elapsed_time": "0:06:20", "remaining_time": "1:21:13"}
135
+ {"current_steps": 135, "total_steps": 1850, "loss": 0.783, "lr": 4.9355532395149445e-06, "epoch": 0.7297297297297297, "percentage": 7.3, "elapsed_time": "0:06:24", "remaining_time": "1:21:22"}
136
+ {"current_steps": 136, "total_steps": 1850, "loss": 0.5118, "lr": 4.9345919904627655e-06, "epoch": 0.7351351351351352, "percentage": 7.35, "elapsed_time": "0:06:27", "remaining_time": "1:21:29"}
137
+ {"current_steps": 137, "total_steps": 1850, "loss": 0.5145, "lr": 4.933623720678944e-06, "epoch": 0.7405405405405405, "percentage": 7.41, "elapsed_time": "0:06:31", "remaining_time": "1:21:34"}
138
+ {"current_steps": 138, "total_steps": 1850, "loss": 0.5958, "lr": 4.932648432955718e-06, "epoch": 0.745945945945946, "percentage": 7.46, "elapsed_time": "0:06:34", "remaining_time": "1:21:31"}
139
+ {"current_steps": 139, "total_steps": 1850, "loss": 0.4853, "lr": 4.931666130105564e-06, "epoch": 0.7513513513513513, "percentage": 7.51, "elapsed_time": "0:06:38", "remaining_time": "1:21:39"}
140
+ {"current_steps": 140, "total_steps": 1850, "loss": 0.58, "lr": 4.930676814961189e-06, "epoch": 0.7567567567567568, "percentage": 7.57, "elapsed_time": "0:06:39", "remaining_time": "1:21:20"}
141
+ {"current_steps": 141, "total_steps": 1850, "loss": 0.3721, "lr": 4.92968049037552e-06, "epoch": 0.7621621621621621, "percentage": 7.62, "elapsed_time": "0:06:42", "remaining_time": "1:21:18"}
142
+ {"current_steps": 142, "total_steps": 1850, "loss": 0.6031, "lr": 4.9286771592217005e-06, "epoch": 0.7675675675675676, "percentage": 7.68, "elapsed_time": "0:06:44", "remaining_time": "1:21:00"}
143
+ {"current_steps": 143, "total_steps": 1850, "loss": 0.667, "lr": 4.927666824393076e-06, "epoch": 0.772972972972973, "percentage": 7.73, "elapsed_time": "0:06:46", "remaining_time": "1:20:57"}
144
+ {"current_steps": 144, "total_steps": 1850, "loss": 0.5923, "lr": 4.926649488803191e-06, "epoch": 0.7783783783783784, "percentage": 7.78, "elapsed_time": "0:06:52", "remaining_time": "1:21:28"}
145
+ {"current_steps": 145, "total_steps": 1850, "loss": 0.3196, "lr": 4.925625155385776e-06, "epoch": 0.7837837837837838, "percentage": 7.84, "elapsed_time": "0:06:55", "remaining_time": "1:21:25"}
146
+ {"current_steps": 146, "total_steps": 1850, "loss": 0.712, "lr": 4.924593827094743e-06, "epoch": 0.7891891891891892, "percentage": 7.89, "elapsed_time": "0:06:57", "remaining_time": "1:21:08"}
147
+ {"current_steps": 147, "total_steps": 1850, "loss": 0.4899, "lr": 4.923555506904176e-06, "epoch": 0.7945945945945946, "percentage": 7.95, "elapsed_time": "0:07:01", "remaining_time": "1:21:27"}
148
+ {"current_steps": 148, "total_steps": 1850, "loss": 0.9519, "lr": 4.922510197808321e-06, "epoch": 0.8, "percentage": 8.0, "elapsed_time": "0:07:04", "remaining_time": "1:21:16"}
149
+ {"current_steps": 149, "total_steps": 1850, "loss": 0.489, "lr": 4.921457902821578e-06, "epoch": 0.8054054054054054, "percentage": 8.05, "elapsed_time": "0:07:09", "remaining_time": "1:21:37"}
150
+ {"current_steps": 150, "total_steps": 1850, "loss": 0.974, "lr": 4.920398624978493e-06, "epoch": 0.8108108108108109, "percentage": 8.11, "elapsed_time": "0:07:11", "remaining_time": "1:21:32"}
151
+ {"current_steps": 151, "total_steps": 1850, "loss": 0.5107, "lr": 4.919332367333748e-06, "epoch": 0.8162162162162162, "percentage": 8.16, "elapsed_time": "0:07:14", "remaining_time": "1:21:32"}
152
+ {"current_steps": 152, "total_steps": 1850, "loss": 0.5132, "lr": 4.918259132962154e-06, "epoch": 0.8216216216216217, "percentage": 8.22, "elapsed_time": "0:07:17", "remaining_time": "1:21:23"}
153
+ {"current_steps": 153, "total_steps": 1850, "loss": 0.5708, "lr": 4.917178924958638e-06, "epoch": 0.827027027027027, "percentage": 8.27, "elapsed_time": "0:07:18", "remaining_time": "1:21:03"}
154
+ {"current_steps": 154, "total_steps": 1850, "loss": 0.6738, "lr": 4.916091746438243e-06, "epoch": 0.8324324324324325, "percentage": 8.32, "elapsed_time": "0:07:19", "remaining_time": "1:20:45"}
155
+ {"current_steps": 155, "total_steps": 1850, "loss": 0.5421, "lr": 4.9149976005361085e-06, "epoch": 0.8378378378378378, "percentage": 8.38, "elapsed_time": "0:07:22", "remaining_time": "1:20:42"}
156
+ {"current_steps": 156, "total_steps": 1850, "loss": 0.9456, "lr": 4.913896490407467e-06, "epoch": 0.8432432432432433, "percentage": 8.43, "elapsed_time": "0:07:25", "remaining_time": "1:20:33"}
157
+ {"current_steps": 157, "total_steps": 1850, "loss": 0.5696, "lr": 4.912788419227635e-06, "epoch": 0.8486486486486486, "percentage": 8.49, "elapsed_time": "0:07:29", "remaining_time": "1:20:42"}
158
+ {"current_steps": 158, "total_steps": 1850, "loss": 0.7361, "lr": 4.911673390192002e-06, "epoch": 0.8540540540540541, "percentage": 8.54, "elapsed_time": "0:07:31", "remaining_time": "1:20:31"}
159
+ {"current_steps": 159, "total_steps": 1850, "loss": 0.5894, "lr": 4.910551406516023e-06, "epoch": 0.8594594594594595, "percentage": 8.59, "elapsed_time": "0:07:35", "remaining_time": "1:20:43"}
160
+ {"current_steps": 160, "total_steps": 1850, "loss": 0.8437, "lr": 4.909422471435207e-06, "epoch": 0.8648648648648649, "percentage": 8.65, "elapsed_time": "0:07:37", "remaining_time": "1:20:35"}
161
+ {"current_steps": 161, "total_steps": 1850, "loss": 0.4127, "lr": 4.90828658820511e-06, "epoch": 0.8702702702702703, "percentage": 8.7, "elapsed_time": "0:07:39", "remaining_time": "1:20:24"}
162
+ {"current_steps": 162, "total_steps": 1850, "loss": 0.3873, "lr": 4.907143760101325e-06, "epoch": 0.8756756756756757, "percentage": 8.76, "elapsed_time": "0:07:41", "remaining_time": "1:20:06"}
163
+ {"current_steps": 163, "total_steps": 1850, "loss": 0.4827, "lr": 4.905993990419472e-06, "epoch": 0.8810810810810811, "percentage": 8.81, "elapsed_time": "0:07:44", "remaining_time": "1:20:04"}
164
+ {"current_steps": 164, "total_steps": 1850, "loss": 0.4883, "lr": 4.904837282475187e-06, "epoch": 0.8864864864864865, "percentage": 8.86, "elapsed_time": "0:07:46", "remaining_time": "1:19:51"}
165
+ {"current_steps": 165, "total_steps": 1850, "loss": 0.7961, "lr": 4.9036736396041165e-06, "epoch": 0.8918918918918919, "percentage": 8.92, "elapsed_time": "0:07:49", "remaining_time": "1:19:49"}
166
+ {"current_steps": 166, "total_steps": 1850, "loss": 0.5304, "lr": 4.902503065161905e-06, "epoch": 0.8972972972972973, "percentage": 8.97, "elapsed_time": "0:07:51", "remaining_time": "1:19:44"}
167
+ {"current_steps": 167, "total_steps": 1850, "loss": 0.7701, "lr": 4.901325562524185e-06, "epoch": 0.9027027027027027, "percentage": 9.03, "elapsed_time": "0:07:55", "remaining_time": "1:19:47"}
168
+ {"current_steps": 168, "total_steps": 1850, "loss": 0.4459, "lr": 4.900141135086569e-06, "epoch": 0.9081081081081082, "percentage": 9.08, "elapsed_time": "0:07:58", "remaining_time": "1:19:53"}
169
+ {"current_steps": 169, "total_steps": 1850, "loss": 0.5295, "lr": 4.898949786264638e-06, "epoch": 0.9135135135135135, "percentage": 9.14, "elapsed_time": "0:08:01", "remaining_time": "1:19:48"}
170
+ {"current_steps": 170, "total_steps": 1850, "loss": 0.5185, "lr": 4.897751519493933e-06, "epoch": 0.918918918918919, "percentage": 9.19, "elapsed_time": "0:08:05", "remaining_time": "1:19:55"}
171
+ {"current_steps": 171, "total_steps": 1850, "loss": 0.5937, "lr": 4.896546338229945e-06, "epoch": 0.9243243243243243, "percentage": 9.24, "elapsed_time": "0:08:06", "remaining_time": "1:19:36"}
172
+ {"current_steps": 172, "total_steps": 1850, "loss": 0.4753, "lr": 4.8953342459481034e-06, "epoch": 0.9297297297297298, "percentage": 9.3, "elapsed_time": "0:08:09", "remaining_time": "1:19:36"}
173
+ {"current_steps": 173, "total_steps": 1850, "loss": 0.636, "lr": 4.894115246143768e-06, "epoch": 0.9351351351351351, "percentage": 9.35, "elapsed_time": "0:08:11", "remaining_time": "1:19:24"}
174
+ {"current_steps": 174, "total_steps": 1850, "loss": 0.5151, "lr": 4.892889342332218e-06, "epoch": 0.9405405405405406, "percentage": 9.41, "elapsed_time": "0:08:13", "remaining_time": "1:19:14"}
175
+ {"current_steps": 175, "total_steps": 1850, "loss": 0.7373, "lr": 4.891656538048642e-06, "epoch": 0.9459459459459459, "percentage": 9.46, "elapsed_time": "0:08:19", "remaining_time": "1:19:39"}
176
+ {"current_steps": 176, "total_steps": 1850, "loss": 0.6444, "lr": 4.890416836848128e-06, "epoch": 0.9513513513513514, "percentage": 9.51, "elapsed_time": "0:08:21", "remaining_time": "1:19:34"}
177
+ {"current_steps": 177, "total_steps": 1850, "loss": 0.4956, "lr": 4.889170242305652e-06, "epoch": 0.9567567567567568, "percentage": 9.57, "elapsed_time": "0:08:24", "remaining_time": "1:19:28"}
178
+ {"current_steps": 178, "total_steps": 1850, "loss": 0.7239, "lr": 4.887916758016069e-06, "epoch": 0.9621621621621622, "percentage": 9.62, "elapsed_time": "0:08:28", "remaining_time": "1:19:36"}
179
+ {"current_steps": 179, "total_steps": 1850, "loss": 0.8918, "lr": 4.886656387594104e-06, "epoch": 0.9675675675675676, "percentage": 9.68, "elapsed_time": "0:08:32", "remaining_time": "1:19:42"}
180
+ {"current_steps": 180, "total_steps": 1850, "loss": 0.5549, "lr": 4.885389134674338e-06, "epoch": 0.972972972972973, "percentage": 9.73, "elapsed_time": "0:08:37", "remaining_time": "1:19:57"}
181
+ {"current_steps": 181, "total_steps": 1850, "loss": 0.4737, "lr": 4.884115002911197e-06, "epoch": 0.9783783783783784, "percentage": 9.78, "elapsed_time": "0:08:38", "remaining_time": "1:19:40"}
182
+ {"current_steps": 182, "total_steps": 1850, "loss": 0.6369, "lr": 4.88283399597895e-06, "epoch": 0.9837837837837838, "percentage": 9.84, "elapsed_time": "0:08:43", "remaining_time": "1:19:59"}
183
+ {"current_steps": 183, "total_steps": 1850, "loss": 0.521, "lr": 4.881546117571686e-06, "epoch": 0.9891891891891892, "percentage": 9.89, "elapsed_time": "0:08:45", "remaining_time": "1:19:49"}
184
+ {"current_steps": 184, "total_steps": 1850, "loss": 0.4812, "lr": 4.8802513714033135e-06, "epoch": 0.9945945945945946, "percentage": 9.95, "elapsed_time": "0:08:48", "remaining_time": "1:19:43"}
185
+ {"current_steps": 185, "total_steps": 1850, "loss": 0.824, "lr": 4.878949761207545e-06, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:08:49", "remaining_time": "1:19:23"}
186
+ {"current_steps": 186, "total_steps": 1850, "loss": 0.5431, "lr": 4.8776412907378845e-06, "epoch": 1.0054054054054054, "percentage": 10.05, "elapsed_time": "2:11:32", "remaining_time": "19:36:48"}
187
+ {"current_steps": 187, "total_steps": 1850, "loss": 0.4882, "lr": 4.876325963767623e-06, "epoch": 1.0108108108108107, "percentage": 10.11, "elapsed_time": "2:11:34", "remaining_time": "19:30:03"}
188
+ {"current_steps": 188, "total_steps": 1850, "loss": 0.4796, "lr": 4.875003784089822e-06, "epoch": 1.0162162162162163, "percentage": 10.16, "elapsed_time": "2:11:37", "remaining_time": "19:23:38"}
189
+ {"current_steps": 189, "total_steps": 1850, "loss": 0.5344, "lr": 4.873674755517305e-06, "epoch": 1.0216216216216216, "percentage": 10.22, "elapsed_time": "2:11:39", "remaining_time": "19:17:05"}
190
+ {"current_steps": 190, "total_steps": 1850, "loss": 0.5975, "lr": 4.872338881882645e-06, "epoch": 1.027027027027027, "percentage": 10.27, "elapsed_time": "2:11:42", "remaining_time": "19:10:43"}
191
+ {"current_steps": 191, "total_steps": 1850, "loss": 0.3895, "lr": 4.870996167038154e-06, "epoch": 1.0324324324324325, "percentage": 10.32, "elapsed_time": "2:11:45", "remaining_time": "19:04:30"}
192
+ {"current_steps": 192, "total_steps": 1850, "loss": 0.2855, "lr": 4.869646614855877e-06, "epoch": 1.037837837837838, "percentage": 10.38, "elapsed_time": "2:11:47", "remaining_time": "18:58:03"}
193
+ {"current_steps": 193, "total_steps": 1850, "loss": 0.5976, "lr": 4.868290229227567e-06, "epoch": 1.0432432432432432, "percentage": 10.43, "elapsed_time": "2:11:53", "remaining_time": "18:52:19"}
194
+ {"current_steps": 194, "total_steps": 1850, "loss": 0.2478, "lr": 4.866927014064692e-06, "epoch": 1.0486486486486486, "percentage": 10.49, "elapsed_time": "2:11:55", "remaining_time": "18:46:04"}
195
+ {"current_steps": 195, "total_steps": 1850, "loss": 0.7275, "lr": 4.86555697329841e-06, "epoch": 1.054054054054054, "percentage": 10.54, "elapsed_time": "2:11:57", "remaining_time": "18:39:59"}
196
+ {"current_steps": 196, "total_steps": 1850, "loss": 0.5008, "lr": 4.864180110879562e-06, "epoch": 1.0594594594594595, "percentage": 10.59, "elapsed_time": "2:12:01", "remaining_time": "18:34:07"}
197
+ {"current_steps": 197, "total_steps": 1850, "loss": 0.2901, "lr": 4.862796430778663e-06, "epoch": 1.0648648648648649, "percentage": 10.65, "elapsed_time": "2:12:03", "remaining_time": "18:28:01"}
198
+ {"current_steps": 198, "total_steps": 1850, "loss": 0.4771, "lr": 4.861405936985889e-06, "epoch": 1.0702702702702702, "percentage": 10.7, "elapsed_time": "2:12:07", "remaining_time": "18:22:26"}
199
+ {"current_steps": 199, "total_steps": 1850, "loss": 0.4908, "lr": 4.860008633511059e-06, "epoch": 1.0756756756756758, "percentage": 10.76, "elapsed_time": "2:12:12", "remaining_time": "18:16:55"}
200
+ {"current_steps": 200, "total_steps": 1850, "loss": 0.3358, "lr": 4.8586045243836384e-06, "epoch": 1.0810810810810811, "percentage": 10.81, "elapsed_time": "2:12:16", "remaining_time": "18:11:15"}
201
+ {"current_steps": 201, "total_steps": 1850, "loss": 0.452, "lr": 4.857193613652711e-06, "epoch": 1.0864864864864865, "percentage": 10.86, "elapsed_time": "2:12:19", "remaining_time": "18:05:33"}
202
+ {"current_steps": 202, "total_steps": 1850, "loss": 0.5481, "lr": 4.8557759053869775e-06, "epoch": 1.0918918918918918, "percentage": 10.92, "elapsed_time": "2:12:20", "remaining_time": "17:59:39"}
203
+ {"current_steps": 203, "total_steps": 1850, "loss": 0.3405, "lr": 4.854351403674741e-06, "epoch": 1.0972972972972972, "percentage": 10.97, "elapsed_time": "2:12:22", "remaining_time": "17:53:56"}
204
+ {"current_steps": 204, "total_steps": 1850, "loss": 0.4744, "lr": 4.852920112623895e-06, "epoch": 1.1027027027027028, "percentage": 11.03, "elapsed_time": "2:12:23", "remaining_time": "17:48:11"}
205
+ {"current_steps": 205, "total_steps": 1850, "loss": 0.5865, "lr": 4.851482036361912e-06, "epoch": 1.1081081081081081, "percentage": 11.08, "elapsed_time": "2:12:25", "remaining_time": "17:42:34"}
206
+ {"current_steps": 206, "total_steps": 1850, "loss": 0.4132, "lr": 4.850037179035829e-06, "epoch": 1.1135135135135135, "percentage": 11.14, "elapsed_time": "2:12:27", "remaining_time": "17:37:03"}
207
+ {"current_steps": 207, "total_steps": 1850, "loss": 0.4332, "lr": 4.8485855448122425e-06, "epoch": 1.118918918918919, "percentage": 11.19, "elapsed_time": "2:12:29", "remaining_time": "17:31:33"}
208
+ {"current_steps": 208, "total_steps": 1850, "loss": 0.2827, "lr": 4.847127137877286e-06, "epoch": 1.1243243243243244, "percentage": 11.24, "elapsed_time": "2:12:31", "remaining_time": "17:26:08"}
209
+ {"current_steps": 209, "total_steps": 1850, "loss": 0.6248, "lr": 4.8456619624366285e-06, "epoch": 1.1297297297297297, "percentage": 11.3, "elapsed_time": "2:12:34", "remaining_time": "17:20:54"}
210
+ {"current_steps": 210, "total_steps": 1850, "loss": 0.4907, "lr": 4.844190022715456e-06, "epoch": 1.135135135135135, "percentage": 11.35, "elapsed_time": "2:12:37", "remaining_time": "17:15:41"}
211
+ {"current_steps": 211, "total_steps": 1850, "loss": 0.2463, "lr": 4.84271132295846e-06, "epoch": 1.1405405405405404, "percentage": 11.41, "elapsed_time": "2:12:41", "remaining_time": "17:10:40"}
212
+ {"current_steps": 212, "total_steps": 1850, "loss": 0.4732, "lr": 4.841225867429826e-06, "epoch": 1.145945945945946, "percentage": 11.46, "elapsed_time": "2:12:43", "remaining_time": "17:05:27"}
213
+ {"current_steps": 213, "total_steps": 1850, "loss": 0.687, "lr": 4.839733660413224e-06, "epoch": 1.1513513513513514, "percentage": 11.51, "elapsed_time": "2:12:45", "remaining_time": "17:00:17"}
214
+ {"current_steps": 214, "total_steps": 1850, "loss": 0.4676, "lr": 4.838234706211792e-06, "epoch": 1.1567567567567567, "percentage": 11.57, "elapsed_time": "2:12:48", "remaining_time": "16:55:16"}
215
+ {"current_steps": 215, "total_steps": 1850, "loss": 0.3074, "lr": 4.836729009148124e-06, "epoch": 1.1621621621621623, "percentage": 11.62, "elapsed_time": "2:12:51", "remaining_time": "16:50:20"}
216
+ {"current_steps": 216, "total_steps": 1850, "loss": 0.2425, "lr": 4.835216573564261e-06, "epoch": 1.1675675675675676, "percentage": 11.68, "elapsed_time": "2:12:55", "remaining_time": "16:45:30"}
217
+ {"current_steps": 217, "total_steps": 1850, "loss": 0.4914, "lr": 4.833697403821672e-06, "epoch": 1.172972972972973, "percentage": 11.73, "elapsed_time": "2:12:58", "remaining_time": "16:40:42"}
218
+ {"current_steps": 218, "total_steps": 1850, "loss": 0.4524, "lr": 4.8321715043012516e-06, "epoch": 1.1783783783783783, "percentage": 11.78, "elapsed_time": "2:13:01", "remaining_time": "16:35:52"}
219
+ {"current_steps": 219, "total_steps": 1850, "loss": 0.2911, "lr": 4.830638879403296e-06, "epoch": 1.1837837837837837, "percentage": 11.84, "elapsed_time": "2:13:03", "remaining_time": "16:30:53"}
220
+ {"current_steps": 220, "total_steps": 1850, "loss": 0.3556, "lr": 4.8290995335475e-06, "epoch": 1.1891891891891893, "percentage": 11.89, "elapsed_time": "2:13:04", "remaining_time": "16:25:56"}
221
+ {"current_steps": 221, "total_steps": 1850, "loss": 0.3169, "lr": 4.827553471172935e-06, "epoch": 1.1945945945945946, "percentage": 11.95, "elapsed_time": "2:13:05", "remaining_time": "16:21:03"}
222
+ {"current_steps": 222, "total_steps": 1850, "loss": 0.3369, "lr": 4.826000696738045e-06, "epoch": 1.2, "percentage": 12.0, "elapsed_time": "2:13:07", "remaining_time": "16:16:16"}
223
+ {"current_steps": 223, "total_steps": 1850, "loss": 0.6498, "lr": 4.824441214720629e-06, "epoch": 1.2054054054054055, "percentage": 12.05, "elapsed_time": "2:13:09", "remaining_time": "16:11:33"}
224
+ {"current_steps": 224, "total_steps": 1850, "loss": 0.3416, "lr": 4.8228750296178275e-06, "epoch": 1.2108108108108109, "percentage": 12.11, "elapsed_time": "2:13:12", "remaining_time": "16:06:58"}
225
+ {"current_steps": 225, "total_steps": 1850, "loss": 0.348, "lr": 4.821302145946113e-06, "epoch": 1.2162162162162162, "percentage": 12.16, "elapsed_time": "2:13:14", "remaining_time": "16:02:19"}
226
+ {"current_steps": 226, "total_steps": 1850, "loss": 0.4552, "lr": 4.819722568241274e-06, "epoch": 1.2216216216216216, "percentage": 12.22, "elapsed_time": "2:13:16", "remaining_time": "15:57:40"}
227
+ {"current_steps": 227, "total_steps": 1850, "loss": 0.2841, "lr": 4.818136301058401e-06, "epoch": 1.227027027027027, "percentage": 12.27, "elapsed_time": "2:13:20", "remaining_time": "15:53:18"}
228
+ {"current_steps": 228, "total_steps": 1850, "loss": 0.5053, "lr": 4.816543348971879e-06, "epoch": 1.2324324324324325, "percentage": 12.32, "elapsed_time": "2:13:23", "remaining_time": "15:48:54"}
229
+ {"current_steps": 229, "total_steps": 1850, "loss": 0.5424, "lr": 4.814943716575368e-06, "epoch": 1.2378378378378379, "percentage": 12.38, "elapsed_time": "2:13:24", "remaining_time": "15:44:19"}
230
+ {"current_steps": 230, "total_steps": 1850, "loss": 0.7483, "lr": 4.813337408481793e-06, "epoch": 1.2432432432432432, "percentage": 12.43, "elapsed_time": "2:13:27", "remaining_time": "15:39:59"}
231
+ {"current_steps": 231, "total_steps": 1850, "loss": 0.775, "lr": 4.811724429323329e-06, "epoch": 1.2486486486486488, "percentage": 12.49, "elapsed_time": "2:13:29", "remaining_time": "15:35:34"}
232
+ {"current_steps": 232, "total_steps": 1850, "loss": 0.4056, "lr": 4.810104783751389e-06, "epoch": 1.2540540540540541, "percentage": 12.54, "elapsed_time": "2:13:30", "remaining_time": "15:31:04"}
233
+ {"current_steps": 233, "total_steps": 1850, "loss": 0.3644, "lr": 4.8084784764366125e-06, "epoch": 1.2594594594594595, "percentage": 12.59, "elapsed_time": "2:13:31", "remaining_time": "15:26:37"}
234
+ {"current_steps": 234, "total_steps": 1850, "loss": 0.3727, "lr": 4.806845512068846e-06, "epoch": 1.2648648648648648, "percentage": 12.65, "elapsed_time": "2:13:35", "remaining_time": "15:22:32"}
235
+ {"current_steps": 235, "total_steps": 1850, "loss": 0.5326, "lr": 4.805205895357137e-06, "epoch": 1.2702702702702702, "percentage": 12.7, "elapsed_time": "2:13:36", "remaining_time": "15:18:11"}
236
+ {"current_steps": 236, "total_steps": 1850, "loss": 0.481, "lr": 4.803559631029713e-06, "epoch": 1.2756756756756757, "percentage": 12.76, "elapsed_time": "2:13:38", "remaining_time": "15:14:00"}
237
+ {"current_steps": 237, "total_steps": 1850, "loss": 0.3355, "lr": 4.801906723833973e-06, "epoch": 1.281081081081081, "percentage": 12.81, "elapsed_time": "2:13:41", "remaining_time": "15:09:53"}
238
+ {"current_steps": 238, "total_steps": 1850, "loss": 0.3704, "lr": 4.8002471785364734e-06, "epoch": 1.2864864864864864, "percentage": 12.86, "elapsed_time": "2:13:43", "remaining_time": "15:05:44"}
239
+ {"current_steps": 239, "total_steps": 1850, "loss": 0.511, "lr": 4.798580999922913e-06, "epoch": 1.291891891891892, "percentage": 12.92, "elapsed_time": "2:13:45", "remaining_time": "15:01:36"}
240
+ {"current_steps": 240, "total_steps": 1850, "loss": 0.4304, "lr": 4.796908192798117e-06, "epoch": 1.2972972972972974, "percentage": 12.97, "elapsed_time": "2:13:46", "remaining_time": "14:57:23"}
241
+ {"current_steps": 241, "total_steps": 1850, "loss": 0.4452, "lr": 4.7952287619860276e-06, "epoch": 1.3027027027027027, "percentage": 13.03, "elapsed_time": "2:13:48", "remaining_time": "14:53:23"}
242
+ {"current_steps": 242, "total_steps": 1850, "loss": 0.7567, "lr": 4.793542712329689e-06, "epoch": 1.308108108108108, "percentage": 13.08, "elapsed_time": "2:13:51", "remaining_time": "14:49:28"}
243
+ {"current_steps": 243, "total_steps": 1850, "loss": 0.3997, "lr": 4.791850048691228e-06, "epoch": 1.3135135135135134, "percentage": 13.14, "elapsed_time": "2:13:55", "remaining_time": "14:45:40"}
244
+ {"current_steps": 244, "total_steps": 1850, "loss": 0.4549, "lr": 4.79015077595185e-06, "epoch": 1.318918918918919, "percentage": 13.19, "elapsed_time": "2:14:01", "remaining_time": "14:42:06"}
245
+ {"current_steps": 245, "total_steps": 1850, "loss": 0.3966, "lr": 4.788444899011816e-06, "epoch": 1.3243243243243243, "percentage": 13.24, "elapsed_time": "2:14:03", "remaining_time": "14:38:14"}
246
+ {"current_steps": 246, "total_steps": 1850, "loss": 0.2961, "lr": 4.786732422790432e-06, "epoch": 1.3297297297297297, "percentage": 13.3, "elapsed_time": "2:14:06", "remaining_time": "14:34:26"}
247
+ {"current_steps": 247, "total_steps": 1850, "loss": 0.4778, "lr": 4.785013352226036e-06, "epoch": 1.3351351351351353, "percentage": 13.35, "elapsed_time": "2:14:07", "remaining_time": "14:30:28"}
248
+ {"current_steps": 248, "total_steps": 1850, "loss": 0.2098, "lr": 4.7832876922759805e-06, "epoch": 1.3405405405405406, "percentage": 13.41, "elapsed_time": "2:14:12", "remaining_time": "14:26:55"}
249
+ {"current_steps": 249, "total_steps": 1850, "loss": 0.5266, "lr": 4.781555447916622e-06, "epoch": 1.345945945945946, "percentage": 13.46, "elapsed_time": "2:14:17", "remaining_time": "14:23:25"}
250
+ {"current_steps": 250, "total_steps": 1850, "loss": 0.3362, "lr": 4.779816624143302e-06, "epoch": 1.3513513513513513, "percentage": 13.51, "elapsed_time": "2:14:18", "remaining_time": "14:19:34"}
251
+ {"current_steps": 251, "total_steps": 1850, "loss": 0.6469, "lr": 4.77807122597034e-06, "epoch": 1.3567567567567567, "percentage": 13.57, "elapsed_time": "2:14:22", "remaining_time": "14:16:01"}
252
+ {"current_steps": 252, "total_steps": 1850, "loss": 0.3717, "lr": 4.776319258431009e-06, "epoch": 1.3621621621621622, "percentage": 13.62, "elapsed_time": "2:14:26", "remaining_time": "14:12:30"}
253
+ {"current_steps": 253, "total_steps": 1850, "loss": 0.3343, "lr": 4.77456072657753e-06, "epoch": 1.3675675675675676, "percentage": 13.68, "elapsed_time": "2:14:28", "remaining_time": "14:08:49"}
254
+ {"current_steps": 254, "total_steps": 1850, "loss": 0.4309, "lr": 4.772795635481053e-06, "epoch": 1.372972972972973, "percentage": 13.73, "elapsed_time": "2:14:29", "remaining_time": "14:05:07"}
255
+ {"current_steps": 255, "total_steps": 1850, "loss": 0.7661, "lr": 4.77102399023164e-06, "epoch": 1.3783783783783785, "percentage": 13.78, "elapsed_time": "2:14:32", "remaining_time": "14:01:35"}
256
+ {"current_steps": 256, "total_steps": 1850, "loss": 0.3661, "lr": 4.769245795938261e-06, "epoch": 1.3837837837837839, "percentage": 13.84, "elapsed_time": "2:14:34", "remaining_time": "13:57:58"}
257
+ {"current_steps": 257, "total_steps": 1850, "loss": 0.3434, "lr": 4.767461057728763e-06, "epoch": 1.3891891891891892, "percentage": 13.89, "elapsed_time": "2:14:37", "remaining_time": "13:54:28"}
258
+ {"current_steps": 258, "total_steps": 1850, "loss": 0.5388, "lr": 4.76566978074987e-06, "epoch": 1.3945945945945946, "percentage": 13.95, "elapsed_time": "2:14:41", "remaining_time": "13:51:06"}
259
+ {"current_steps": 259, "total_steps": 1850, "loss": 0.4927, "lr": 4.7638719701671586e-06, "epoch": 1.4, "percentage": 14.0, "elapsed_time": "2:14:45", "remaining_time": "13:47:46"}
260
+ {"current_steps": 260, "total_steps": 1850, "loss": 0.7173, "lr": 4.762067631165049e-06, "epoch": 1.4054054054054055, "percentage": 14.05, "elapsed_time": "2:14:47", "remaining_time": "13:44:16"}
261
+ {"current_steps": 261, "total_steps": 1850, "loss": 0.3186, "lr": 4.760256768946787e-06, "epoch": 1.4108108108108108, "percentage": 14.11, "elapsed_time": "2:14:50", "remaining_time": "13:40:53"}
262
+ {"current_steps": 262, "total_steps": 1850, "loss": 0.6477, "lr": 4.758439388734429e-06, "epoch": 1.4162162162162162, "percentage": 14.16, "elapsed_time": "2:14:51", "remaining_time": "13:37:23"}
263
+ {"current_steps": 263, "total_steps": 1850, "loss": 0.8846, "lr": 4.7566154957688276e-06, "epoch": 1.4216216216216218, "percentage": 14.22, "elapsed_time": "2:14:53", "remaining_time": "13:33:56"}
264
+ {"current_steps": 264, "total_steps": 1850, "loss": 0.5446, "lr": 4.754785095309617e-06, "epoch": 1.427027027027027, "percentage": 14.27, "elapsed_time": "2:14:54", "remaining_time": "13:30:30"}
265
+ {"current_steps": 265, "total_steps": 1850, "loss": 0.395, "lr": 4.752948192635199e-06, "epoch": 1.4324324324324325, "percentage": 14.32, "elapsed_time": "2:14:56", "remaining_time": "13:27:06"}
266
+ {"current_steps": 266, "total_steps": 1850, "loss": 0.713, "lr": 4.751104793042722e-06, "epoch": 1.4378378378378378, "percentage": 14.38, "elapsed_time": "2:15:00", "remaining_time": "13:23:59"}
267
+ {"current_steps": 267, "total_steps": 1850, "loss": 0.4474, "lr": 4.7492549018480725e-06, "epoch": 1.4432432432432432, "percentage": 14.43, "elapsed_time": "2:15:03", "remaining_time": "13:20:46"}
268
+ {"current_steps": 268, "total_steps": 1850, "loss": 0.7754, "lr": 4.747398524385858e-06, "epoch": 1.4486486486486487, "percentage": 14.49, "elapsed_time": "2:15:06", "remaining_time": "13:17:30"}
269
+ {"current_steps": 269, "total_steps": 1850, "loss": 0.4424, "lr": 4.745535666009389e-06, "epoch": 1.454054054054054, "percentage": 14.54, "elapsed_time": "2:15:09", "remaining_time": "13:14:22"}
270
+ {"current_steps": 270, "total_steps": 1850, "loss": 0.3137, "lr": 4.743666332090664e-06, "epoch": 1.4594594594594594, "percentage": 14.59, "elapsed_time": "2:15:13", "remaining_time": "13:11:19"}
271
+ {"current_steps": 271, "total_steps": 1850, "loss": 0.49, "lr": 4.74179052802036e-06, "epoch": 1.464864864864865, "percentage": 14.65, "elapsed_time": "2:15:15", "remaining_time": "13:08:07"}
272
+ {"current_steps": 272, "total_steps": 1850, "loss": 0.6437, "lr": 4.739908259207807e-06, "epoch": 1.4702702702702704, "percentage": 14.7, "elapsed_time": "2:15:17", "remaining_time": "13:04:54"}
273
+ {"current_steps": 273, "total_steps": 1850, "loss": 0.4127, "lr": 4.738019531080981e-06, "epoch": 1.4756756756756757, "percentage": 14.76, "elapsed_time": "2:15:20", "remaining_time": "13:01:48"}
274
+ {"current_steps": 274, "total_steps": 1850, "loss": 0.4739, "lr": 4.7361243490864825e-06, "epoch": 1.481081081081081, "percentage": 14.81, "elapsed_time": "2:15:25", "remaining_time": "12:58:55"}
275
+ {"current_steps": 275, "total_steps": 1850, "loss": 0.5618, "lr": 4.734222718689527e-06, "epoch": 1.4864864864864864, "percentage": 14.86, "elapsed_time": "2:15:30", "remaining_time": "12:56:03"}
276
+ {"current_steps": 276, "total_steps": 1850, "loss": 0.405, "lr": 4.732314645373922e-06, "epoch": 1.491891891891892, "percentage": 14.92, "elapsed_time": "2:15:33", "remaining_time": "12:53:04"}
277
+ {"current_steps": 277, "total_steps": 1850, "loss": 0.5677, "lr": 4.730400134642055e-06, "epoch": 1.4972972972972973, "percentage": 14.97, "elapsed_time": "2:15:36", "remaining_time": "12:50:06"}
278
+ {"current_steps": 278, "total_steps": 1850, "loss": 0.7171, "lr": 4.728479192014879e-06, "epoch": 1.5027027027027027, "percentage": 15.03, "elapsed_time": "2:15:39", "remaining_time": "12:47:09"}
279
+ {"current_steps": 279, "total_steps": 1850, "loss": 0.4442, "lr": 4.726551823031895e-06, "epoch": 1.5081081081081082, "percentage": 15.08, "elapsed_time": "2:15:43", "remaining_time": "12:44:16"}
280
+ {"current_steps": 280, "total_steps": 1850, "loss": 0.4034, "lr": 4.7246180332511335e-06, "epoch": 1.5135135135135136, "percentage": 15.14, "elapsed_time": "2:15:45", "remaining_time": "12:41:15"}
281
+ {"current_steps": 281, "total_steps": 1850, "loss": 0.948, "lr": 4.722677828249142e-06, "epoch": 1.518918918918919, "percentage": 15.19, "elapsed_time": "2:15:49", "remaining_time": "12:38:21"}
282
+ {"current_steps": 282, "total_steps": 1850, "loss": 0.7035, "lr": 4.720731213620972e-06, "epoch": 1.5243243243243243, "percentage": 15.24, "elapsed_time": "2:15:52", "remaining_time": "12:35:27"}
283
+ {"current_steps": 283, "total_steps": 1850, "loss": 0.4648, "lr": 4.718778194980152e-06, "epoch": 1.5297297297297296, "percentage": 15.3, "elapsed_time": "2:15:54", "remaining_time": "12:32:34"}
284
+ {"current_steps": 284, "total_steps": 1850, "loss": 0.5399, "lr": 4.7168187779586805e-06, "epoch": 1.535135135135135, "percentage": 15.35, "elapsed_time": "2:15:57", "remaining_time": "12:29:42"}
285
+ {"current_steps": 285, "total_steps": 1850, "loss": 0.5363, "lr": 4.71485296820701e-06, "epoch": 1.5405405405405406, "percentage": 15.41, "elapsed_time": "2:15:59", "remaining_time": "12:26:45"}
286
+ {"current_steps": 286, "total_steps": 1850, "loss": 0.3132, "lr": 4.7128807713940245e-06, "epoch": 1.545945945945946, "percentage": 15.46, "elapsed_time": "2:16:04", "remaining_time": "12:24:06"}
287
+ {"current_steps": 287, "total_steps": 1850, "loss": 0.3854, "lr": 4.710902193207028e-06, "epoch": 1.5513513513513515, "percentage": 15.51, "elapsed_time": "2:16:09", "remaining_time": "12:21:31"}
288
+ {"current_steps": 288, "total_steps": 1850, "loss": 0.3459, "lr": 4.708917239351727e-06, "epoch": 1.5567567567567568, "percentage": 15.57, "elapsed_time": "2:16:12", "remaining_time": "12:18:43"}
289
+ {"current_steps": 289, "total_steps": 1850, "loss": 0.7623, "lr": 4.706925915552214e-06, "epoch": 1.5621621621621622, "percentage": 15.62, "elapsed_time": "2:16:14", "remaining_time": "12:15:51"}
290
+ {"current_steps": 290, "total_steps": 1850, "loss": 0.5251, "lr": 4.704928227550949e-06, "epoch": 1.5675675675675675, "percentage": 15.68, "elapsed_time": "2:16:17", "remaining_time": "12:13:11"}
291
+ {"current_steps": 291, "total_steps": 1850, "loss": 0.3659, "lr": 4.702924181108745e-06, "epoch": 1.572972972972973, "percentage": 15.73, "elapsed_time": "2:16:20", "remaining_time": "12:10:24"}
292
+ {"current_steps": 292, "total_steps": 1850, "loss": 0.3186, "lr": 4.700913782004755e-06, "epoch": 1.5783783783783782, "percentage": 15.78, "elapsed_time": "2:16:22", "remaining_time": "12:07:38"}
293
+ {"current_steps": 293, "total_steps": 1850, "loss": 0.4038, "lr": 4.698897036036446e-06, "epoch": 1.5837837837837838, "percentage": 15.84, "elapsed_time": "2:16:26", "remaining_time": "12:05:03"}
294
+ {"current_steps": 294, "total_steps": 1850, "loss": 0.7577, "lr": 4.696873949019591e-06, "epoch": 1.5891891891891892, "percentage": 15.89, "elapsed_time": "2:16:29", "remaining_time": "12:02:21"}
295
+ {"current_steps": 295, "total_steps": 1850, "loss": 0.3112, "lr": 4.694844526788248e-06, "epoch": 1.5945945945945947, "percentage": 15.95, "elapsed_time": "2:16:33", "remaining_time": "11:59:51"}
296
+ {"current_steps": 296, "total_steps": 1850, "loss": 0.319, "lr": 4.692808775194745e-06, "epoch": 1.6, "percentage": 16.0, "elapsed_time": "2:16:36", "remaining_time": "11:57:13"}
297
+ {"current_steps": 297, "total_steps": 1850, "loss": 0.3089, "lr": 4.690766700109659e-06, "epoch": 1.6054054054054054, "percentage": 16.05, "elapsed_time": "2:16:42", "remaining_time": "11:54:48"}
298
+ {"current_steps": 298, "total_steps": 1850, "loss": 0.7288, "lr": 4.688718307421807e-06, "epoch": 1.6108108108108108, "percentage": 16.11, "elapsed_time": "2:16:43", "remaining_time": "11:52:06"}
299
+ {"current_steps": 299, "total_steps": 1850, "loss": 0.5617, "lr": 4.686663603038222e-06, "epoch": 1.6162162162162161, "percentage": 16.16, "elapsed_time": "2:16:45", "remaining_time": "11:49:22"}
300
+ {"current_steps": 300, "total_steps": 1850, "loss": 0.6138, "lr": 4.6846025928841365e-06, "epoch": 1.6216216216216215, "percentage": 16.22, "elapsed_time": "2:16:49", "remaining_time": "11:46:57"}
301
+ {"current_steps": 301, "total_steps": 1850, "loss": 0.3983, "lr": 4.6825352829029705e-06, "epoch": 1.627027027027027, "percentage": 16.27, "elapsed_time": "2:16:53", "remaining_time": "11:44:27"}
302
+ {"current_steps": 302, "total_steps": 1850, "loss": 0.384, "lr": 4.68046167905631e-06, "epoch": 1.6324324324324324, "percentage": 16.32, "elapsed_time": "2:16:55", "remaining_time": "11:41:53"}
303
+ {"current_steps": 303, "total_steps": 1850, "loss": 0.6028, "lr": 4.678381787323889e-06, "epoch": 1.637837837837838, "percentage": 16.38, "elapsed_time": "2:17:00", "remaining_time": "11:39:30"}
304
+ {"current_steps": 304, "total_steps": 1850, "loss": 0.5691, "lr": 4.676295613703577e-06, "epoch": 1.6432432432432433, "percentage": 16.43, "elapsed_time": "2:17:03", "remaining_time": "11:37:03"}
305
+ {"current_steps": 305, "total_steps": 1850, "loss": 0.5875, "lr": 4.674203164211357e-06, "epoch": 1.6486486486486487, "percentage": 16.49, "elapsed_time": "2:17:06", "remaining_time": "11:34:30"}
306
+ {"current_steps": 306, "total_steps": 1850, "loss": 0.5387, "lr": 4.67210444488131e-06, "epoch": 1.654054054054054, "percentage": 16.54, "elapsed_time": "2:17:09", "remaining_time": "11:32:03"}
307
+ {"current_steps": 307, "total_steps": 1850, "loss": 0.5641, "lr": 4.669999461765599e-06, "epoch": 1.6594594594594594, "percentage": 16.59, "elapsed_time": "2:17:10", "remaining_time": "11:29:29"}
308
+ {"current_steps": 308, "total_steps": 1850, "loss": 0.6177, "lr": 4.6678882209344474e-06, "epoch": 1.6648648648648647, "percentage": 16.65, "elapsed_time": "2:17:14", "remaining_time": "11:27:06"}
309
+ {"current_steps": 309, "total_steps": 1850, "loss": 0.5682, "lr": 4.665770728476127e-06, "epoch": 1.6702702702702703, "percentage": 16.7, "elapsed_time": "2:17:17", "remaining_time": "11:24:42"}
310
+ {"current_steps": 310, "total_steps": 1850, "loss": 0.4661, "lr": 4.663646990496939e-06, "epoch": 1.6756756756756757, "percentage": 16.76, "elapsed_time": "2:17:23", "remaining_time": "11:22:29"}
311
+ {"current_steps": 311, "total_steps": 1850, "loss": 0.7667, "lr": 4.661517013121189e-06, "epoch": 1.6810810810810812, "percentage": 16.81, "elapsed_time": "2:17:26", "remaining_time": "11:20:06"}
312
+ {"current_steps": 312, "total_steps": 1850, "loss": 0.5567, "lr": 4.659380802491181e-06, "epoch": 1.6864864864864866, "percentage": 16.86, "elapsed_time": "2:17:26", "remaining_time": "11:17:33"}
313
+ {"current_steps": 313, "total_steps": 1850, "loss": 0.2624, "lr": 4.6572383647671915e-06, "epoch": 1.691891891891892, "percentage": 16.92, "elapsed_time": "2:17:29", "remaining_time": "11:15:09"}
314
+ {"current_steps": 314, "total_steps": 1850, "loss": 0.3569, "lr": 4.655089706127457e-06, "epoch": 1.6972972972972973, "percentage": 16.97, "elapsed_time": "2:17:35", "remaining_time": "11:13:02"}
315
+ {"current_steps": 315, "total_steps": 1850, "loss": 0.3578, "lr": 4.652934832768148e-06, "epoch": 1.7027027027027026, "percentage": 17.03, "elapsed_time": "2:17:40", "remaining_time": "11:10:54"}
316
+ {"current_steps": 316, "total_steps": 1850, "loss": 0.4817, "lr": 4.650773750903363e-06, "epoch": 1.708108108108108, "percentage": 17.08, "elapsed_time": "2:17:45", "remaining_time": "11:08:42"}
317
+ {"current_steps": 317, "total_steps": 1850, "loss": 0.4623, "lr": 4.6486064667651005e-06, "epoch": 1.7135135135135136, "percentage": 17.14, "elapsed_time": "2:17:49", "remaining_time": "11:06:30"}
318
+ {"current_steps": 318, "total_steps": 1850, "loss": 0.6034, "lr": 4.646432986603245e-06, "epoch": 1.718918918918919, "percentage": 17.19, "elapsed_time": "2:17:54", "remaining_time": "11:04:21"}
319
+ {"current_steps": 319, "total_steps": 1850, "loss": 0.5898, "lr": 4.644253316685552e-06, "epoch": 1.7243243243243245, "percentage": 17.24, "elapsed_time": "2:17:55", "remaining_time": "11:01:59"}
320
+ {"current_steps": 320, "total_steps": 1850, "loss": 0.4271, "lr": 4.6420674632976205e-06, "epoch": 1.7297297297297298, "percentage": 17.3, "elapsed_time": "2:17:58", "remaining_time": "10:59:43"}
321
+ {"current_steps": 321, "total_steps": 1850, "loss": 0.4306, "lr": 4.639875432742886e-06, "epoch": 1.7351351351351352, "percentage": 17.35, "elapsed_time": "2:17:59", "remaining_time": "10:57:18"}
322
+ {"current_steps": 322, "total_steps": 1850, "loss": 0.574, "lr": 4.6376772313425975e-06, "epoch": 1.7405405405405405, "percentage": 17.41, "elapsed_time": "2:18:00", "remaining_time": "10:54:56"}
323
+ {"current_steps": 323, "total_steps": 1850, "loss": 0.5807, "lr": 4.635472865435795e-06, "epoch": 1.7459459459459459, "percentage": 17.46, "elapsed_time": "2:18:03", "remaining_time": "10:52:42"}
324
+ {"current_steps": 324, "total_steps": 1850, "loss": 0.6298, "lr": 4.6332623413792995e-06, "epoch": 1.7513513513513512, "percentage": 17.51, "elapsed_time": "2:18:06", "remaining_time": "10:50:26"}
325
+ {"current_steps": 325, "total_steps": 1850, "loss": 0.338, "lr": 4.6310456655476874e-06, "epoch": 1.7567567567567568, "percentage": 17.57, "elapsed_time": "2:18:07", "remaining_time": "10:48:09"}
326
+ {"current_steps": 326, "total_steps": 1850, "loss": 0.3887, "lr": 4.6288228443332786e-06, "epoch": 1.7621621621621621, "percentage": 17.62, "elapsed_time": "2:18:09", "remaining_time": "10:45:51"}
327
+ {"current_steps": 327, "total_steps": 1850, "loss": 0.5677, "lr": 4.626593884146111e-06, "epoch": 1.7675675675675677, "percentage": 17.68, "elapsed_time": "2:18:12", "remaining_time": "10:43:43"}
328
+ {"current_steps": 328, "total_steps": 1850, "loss": 0.4496, "lr": 4.624358791413928e-06, "epoch": 1.772972972972973, "percentage": 17.73, "elapsed_time": "2:18:16", "remaining_time": "10:41:37"}
329
+ {"current_steps": 329, "total_steps": 1850, "loss": 0.519, "lr": 4.622117572582159e-06, "epoch": 1.7783783783783784, "percentage": 17.78, "elapsed_time": "2:18:19", "remaining_time": "10:39:30"}
330
+ {"current_steps": 330, "total_steps": 1850, "loss": 0.7875, "lr": 4.619870234113894e-06, "epoch": 1.7837837837837838, "percentage": 17.84, "elapsed_time": "2:18:20", "remaining_time": "10:37:14"}
331
+ {"current_steps": 331, "total_steps": 1850, "loss": 0.5327, "lr": 4.617616782489878e-06, "epoch": 1.7891891891891891, "percentage": 17.89, "elapsed_time": "2:18:23", "remaining_time": "10:35:07"}
332
+ {"current_steps": 332, "total_steps": 1850, "loss": 0.3327, "lr": 4.615357224208477e-06, "epoch": 1.7945945945945945, "percentage": 17.95, "elapsed_time": "2:18:28", "remaining_time": "10:33:10"}
333
+ {"current_steps": 333, "total_steps": 1850, "loss": 0.6386, "lr": 4.613091565785674e-06, "epoch": 1.8, "percentage": 18.0, "elapsed_time": "2:18:34", "remaining_time": "10:31:17"}
334
+ {"current_steps": 334, "total_steps": 1850, "loss": 0.4145, "lr": 4.610819813755038e-06, "epoch": 1.8054054054054054, "percentage": 18.05, "elapsed_time": "2:18:40", "remaining_time": "10:29:24"}
335
+ {"current_steps": 335, "total_steps": 1850, "loss": 0.339, "lr": 4.608541974667714e-06, "epoch": 1.810810810810811, "percentage": 18.11, "elapsed_time": "2:18:44", "remaining_time": "10:27:25"}
336
+ {"current_steps": 336, "total_steps": 1850, "loss": 0.4042, "lr": 4.606258055092397e-06, "epoch": 1.8162162162162163, "percentage": 18.16, "elapsed_time": "2:18:47", "remaining_time": "10:25:25"}
337
+ {"current_steps": 337, "total_steps": 1850, "loss": 0.4566, "lr": 4.603968061615321e-06, "epoch": 1.8216216216216217, "percentage": 18.22, "elapsed_time": "2:18:50", "remaining_time": "10:23:20"}
338
+ {"current_steps": 338, "total_steps": 1850, "loss": 0.7003, "lr": 4.601672000840231e-06, "epoch": 1.827027027027027, "percentage": 18.27, "elapsed_time": "2:18:53", "remaining_time": "10:21:17"}
339
+ {"current_steps": 339, "total_steps": 1850, "loss": 0.2668, "lr": 4.5993698793883715e-06, "epoch": 1.8324324324324324, "percentage": 18.32, "elapsed_time": "2:18:55", "remaining_time": "10:19:12"}
340
+ {"current_steps": 340, "total_steps": 1850, "loss": 0.8249, "lr": 4.597061703898462e-06, "epoch": 1.8378378378378377, "percentage": 18.38, "elapsed_time": "2:18:56", "remaining_time": "10:17:04"}
341
+ {"current_steps": 341, "total_steps": 1850, "loss": 0.3457, "lr": 4.594747481026685e-06, "epoch": 1.8432432432432433, "percentage": 18.43, "elapsed_time": "2:19:00", "remaining_time": "10:15:06"}
342
+ {"current_steps": 342, "total_steps": 1850, "loss": 0.325, "lr": 4.592427217446656e-06, "epoch": 1.8486486486486486, "percentage": 18.49, "elapsed_time": "2:19:01", "remaining_time": "10:13:01"}
343
+ {"current_steps": 343, "total_steps": 1850, "loss": 0.8412, "lr": 4.590100919849413e-06, "epoch": 1.8540540540540542, "percentage": 18.54, "elapsed_time": "2:19:03", "remaining_time": "10:10:57"}
344
+ {"current_steps": 344, "total_steps": 1850, "loss": 0.4915, "lr": 4.587768594943396e-06, "epoch": 1.8594594594594596, "percentage": 18.59, "elapsed_time": "2:19:06", "remaining_time": "10:08:59"}
345
+ {"current_steps": 345, "total_steps": 1850, "loss": 0.3661, "lr": 4.585430249454426e-06, "epoch": 1.864864864864865, "percentage": 18.65, "elapsed_time": "2:19:07", "remaining_time": "10:06:56"}
346
+ {"current_steps": 346, "total_steps": 1850, "loss": 0.5055, "lr": 4.583085890125682e-06, "epoch": 1.8702702702702703, "percentage": 18.7, "elapsed_time": "2:19:10", "remaining_time": "10:04:57"}
347
+ {"current_steps": 347, "total_steps": 1850, "loss": 0.4834, "lr": 4.5807355237176896e-06, "epoch": 1.8756756756756756, "percentage": 18.76, "elapsed_time": "2:19:16", "remaining_time": "10:03:13"}
348
+ {"current_steps": 348, "total_steps": 1850, "loss": 0.3639, "lr": 4.578379157008296e-06, "epoch": 1.881081081081081, "percentage": 18.81, "elapsed_time": "2:19:19", "remaining_time": "10:01:18"}
349
+ {"current_steps": 349, "total_steps": 1850, "loss": 0.3676, "lr": 4.57601679679265e-06, "epoch": 1.8864864864864865, "percentage": 18.86, "elapsed_time": "2:19:22", "remaining_time": "9:59:24"}
350
+ {"current_steps": 350, "total_steps": 1850, "loss": 0.5806, "lr": 4.573648449883188e-06, "epoch": 1.8918918918918919, "percentage": 18.92, "elapsed_time": "2:19:25", "remaining_time": "9:57:32"}
351
+ {"current_steps": 351, "total_steps": 1850, "loss": 0.3274, "lr": 4.571274123109606e-06, "epoch": 1.8972972972972975, "percentage": 18.97, "elapsed_time": "2:19:26", "remaining_time": "9:55:32"}
352
+ {"current_steps": 352, "total_steps": 1850, "loss": 0.5008, "lr": 4.568893823318847e-06, "epoch": 1.9027027027027028, "percentage": 19.03, "elapsed_time": "2:19:32", "remaining_time": "9:53:51"}
353
+ {"current_steps": 353, "total_steps": 1850, "loss": 0.4848, "lr": 4.566507557375077e-06, "epoch": 1.9081081081081082, "percentage": 19.08, "elapsed_time": "2:19:36", "remaining_time": "9:52:03"}
354
+ {"current_steps": 354, "total_steps": 1850, "loss": 0.3779, "lr": 4.5641153321596684e-06, "epoch": 1.9135135135135135, "percentage": 19.14, "elapsed_time": "2:19:38", "remaining_time": "9:50:08"}
355
+ {"current_steps": 355, "total_steps": 1850, "loss": 0.7481, "lr": 4.56171715457118e-06, "epoch": 1.9189189189189189, "percentage": 19.19, "elapsed_time": "2:19:40", "remaining_time": "9:48:13"}
356
+ {"current_steps": 356, "total_steps": 1850, "loss": 0.435, "lr": 4.559313031525331e-06, "epoch": 1.9243243243243242, "percentage": 19.24, "elapsed_time": "2:19:42", "remaining_time": "9:46:19"}
357
+ {"current_steps": 357, "total_steps": 1850, "loss": 0.4895, "lr": 4.55690296995499e-06, "epoch": 1.9297297297297298, "percentage": 19.3, "elapsed_time": "2:19:44", "remaining_time": "9:44:24"}
358
+ {"current_steps": 358, "total_steps": 1850, "loss": 0.8648, "lr": 4.554486976810149e-06, "epoch": 1.9351351351351351, "percentage": 19.35, "elapsed_time": "2:19:45", "remaining_time": "9:42:29"}
359
+ {"current_steps": 359, "total_steps": 1850, "loss": 0.578, "lr": 4.552065059057906e-06, "epoch": 1.9405405405405407, "percentage": 19.41, "elapsed_time": "2:19:47", "remaining_time": "9:40:36"}
360
+ {"current_steps": 360, "total_steps": 1850, "loss": 0.9823, "lr": 4.549637223682441e-06, "epoch": 1.945945945945946, "percentage": 19.46, "elapsed_time": "2:19:49", "remaining_time": "9:38:41"}
361
+ {"current_steps": 361, "total_steps": 1850, "loss": 0.6065, "lr": 4.547203477685005e-06, "epoch": 1.9513513513513514, "percentage": 19.51, "elapsed_time": "2:19:53", "remaining_time": "9:36:59"}
362
+ {"current_steps": 362, "total_steps": 1850, "loss": 0.3985, "lr": 4.544763828083888e-06, "epoch": 1.9567567567567568, "percentage": 19.57, "elapsed_time": "2:19:57", "remaining_time": "9:35:18"}
363
+ {"current_steps": 363, "total_steps": 1850, "loss": 0.6149, "lr": 4.542318281914405e-06, "epoch": 1.962162162162162, "percentage": 19.62, "elapsed_time": "2:20:00", "remaining_time": "9:33:33"}
364
+ {"current_steps": 364, "total_steps": 1850, "loss": 0.5578, "lr": 4.53986684622888e-06, "epoch": 1.9675675675675675, "percentage": 19.68, "elapsed_time": "2:20:04", "remaining_time": "9:31:51"}
365
+ {"current_steps": 365, "total_steps": 1850, "loss": 0.4855, "lr": 4.537409528096615e-06, "epoch": 1.972972972972973, "percentage": 19.73, "elapsed_time": "2:20:06", "remaining_time": "9:30:00"}
366
+ {"current_steps": 366, "total_steps": 1850, "loss": 0.3366, "lr": 4.534946334603879e-06, "epoch": 1.9783783783783784, "percentage": 19.78, "elapsed_time": "2:20:09", "remaining_time": "9:28:16"}
367
+ {"current_steps": 367, "total_steps": 1850, "loss": 0.4031, "lr": 4.532477272853882e-06, "epoch": 1.983783783783784, "percentage": 19.84, "elapsed_time": "2:20:12", "remaining_time": "9:26:35"}
368
+ {"current_steps": 368, "total_steps": 1850, "loss": 0.3215, "lr": 4.530002349966759e-06, "epoch": 1.9891891891891893, "percentage": 19.89, "elapsed_time": "2:20:14", "remaining_time": "9:24:48"}
369
+ {"current_steps": 369, "total_steps": 1850, "loss": 0.4393, "lr": 4.5275215730795445e-06, "epoch": 1.9945945945945946, "percentage": 19.95, "elapsed_time": "2:20:17", "remaining_time": "9:23:03"}
370
+ {"current_steps": 370, "total_steps": 1850, "loss": 0.4536, "lr": 4.525034949346156e-06, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "2:20:18", "remaining_time": "9:21:14"}
qwen2_5_math_7b/limo/checkpoint-1230/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2_5_math_7b/limo/checkpoint-1230/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 4096,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 10000,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152064
59
+ }
qwen2_5_math_7b/limo/checkpoint-1230/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.55.0"
6
+ }
qwen2_5_math_7b/limo/checkpoint-1230/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen2_5_math_7b/limo/checkpoint-1230/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }