Hugging Face's logo

INFReasoning
/
metalimo

Safetensors
Model card Files
xet
Community
KublaiKhan1 commited on
Commit
1388a76
·
verified ·
1 Parent(s): 60f1d10

Add files using upload-large-folder tool

Browse files
Files changed (13) hide show
  1. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/added_tokens.json +24 -0
  2. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/chat_template.jinja +54 -0
  3. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/config.json +58 -0
  4. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/generation_config.json +7 -0
  5. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/merges.txt +0 -0
  6. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/model.safetensors.index.json +347 -0
  7. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/special_tokens_map.json +31 -0
  8. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/tokenizer_config.json +208 -0
  9. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/trainer_state.json +1343 -0
  10. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/vocab.json +0 -0
  11. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-935/generation_config.json +7 -0
  12. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-935/model.safetensors.index.json +347 -0
  13. qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-935/trainer_state.json +0 -0
qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/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_combined/checkpoint-187/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_combined/checkpoint-187/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_combined/checkpoint-187/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_combined/checkpoint-187/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/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_combined/checkpoint-187/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_combined/checkpoint-187/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_combined/checkpoint-187/trainer_state.json ADDED
@@ -0,0 +1,1343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 187,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0053475935828877,
14
+ "grad_norm": 6.294301986694336,
15
+ "learning_rate": 5e-06,
16
+ "loss": 0.7362,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0106951871657754,
21
+ "grad_norm": 5.736287593841553,
22
+ "learning_rate": 4.99999647201733e-06,
23
+ "loss": 0.8761,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.016042780748663103,
28
+ "grad_norm": 3.8208789825439453,
29
+ "learning_rate": 4.999985888079276e-06,
30
+ "loss": 0.694,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0213903743315508,
35
+ "grad_norm": 3.2889552116394043,
36
+ "learning_rate": 4.999968248215712e-06,
37
+ "loss": 0.9727,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.026737967914438502,
42
+ "grad_norm": 4.675001621246338,
43
+ "learning_rate": 4.999943552476422e-06,
44
+ "loss": 1.0233,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.03208556149732621,
49
+ "grad_norm": 5.071417808532715,
50
+ "learning_rate": 4.999911800931108e-06,
51
+ "loss": 0.7918,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0374331550802139,
56
+ "grad_norm": 5.211335182189941,
57
+ "learning_rate": 4.999872993669387e-06,
58
+ "loss": 0.7691,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0427807486631016,
63
+ "grad_norm": 3.086021900177002,
64
+ "learning_rate": 4.999827130800785e-06,
65
+ "loss": 0.8749,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0481283422459893,
70
+ "grad_norm": 3.1104187965393066,
71
+ "learning_rate": 4.999774212454746e-06,
72
+ "loss": 0.5954,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.053475935828877004,
77
+ "grad_norm": 2.4257028102874756,
78
+ "learning_rate": 4.999714238780626e-06,
79
+ "loss": 0.7079,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.058823529411764705,
84
+ "grad_norm": 2.3247926235198975,
85
+ "learning_rate": 4.999647209947694e-06,
86
+ "loss": 0.7153,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.06417112299465241,
91
+ "grad_norm": 1.6301634311676025,
92
+ "learning_rate": 4.999573126145132e-06,
93
+ "loss": 0.4587,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.06951871657754011,
98
+ "grad_norm": 2.1408276557922363,
99
+ "learning_rate": 4.999491987582032e-06,
100
+ "loss": 0.5516,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0748663101604278,
105
+ "grad_norm": 2.4830322265625,
106
+ "learning_rate": 4.999403794487399e-06,
107
+ "loss": 0.7896,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.08021390374331551,
112
+ "grad_norm": 2.1608150005340576,
113
+ "learning_rate": 4.999308547110147e-06,
114
+ "loss": 0.6201,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0855614973262032,
119
+ "grad_norm": 2.4077577590942383,
120
+ "learning_rate": 4.9992062457191005e-06,
121
+ "loss": 0.7472,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.09090909090909091,
126
+ "grad_norm": 1.8394675254821777,
127
+ "learning_rate": 4.999096890602996e-06,
128
+ "loss": 0.5349,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0962566844919786,
133
+ "grad_norm": 1.5571492910385132,
134
+ "learning_rate": 4.998980482070473e-06,
135
+ "loss": 0.5106,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.10160427807486631,
140
+ "grad_norm": 1.9318442344665527,
141
+ "learning_rate": 4.998857020450084e-06,
142
+ "loss": 0.8202,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.10695187165775401,
147
+ "grad_norm": 1.8744639158248901,
148
+ "learning_rate": 4.998726506090283e-06,
149
+ "loss": 0.6655,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.11229946524064172,
154
+ "grad_norm": 3.2361857891082764,
155
+ "learning_rate": 4.998588939359435e-06,
156
+ "loss": 0.6727,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.11764705882352941,
161
+ "grad_norm": 1.6848551034927368,
162
+ "learning_rate": 4.998444320645803e-06,
163
+ "loss": 0.6334,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.12299465240641712,
168
+ "grad_norm": 2.074486017227173,
169
+ "learning_rate": 4.998292650357558e-06,
170
+ "loss": 0.6681,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.12834224598930483,
175
+ "grad_norm": 1.732974648475647,
176
+ "learning_rate": 4.998133928922773e-06,
177
+ "loss": 0.7036,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.13368983957219252,
182
+ "grad_norm": 1.8715782165527344,
183
+ "learning_rate": 4.99796815678942e-06,
184
+ "loss": 0.4874,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.13903743315508021,
189
+ "grad_norm": 1.5994693040847778,
190
+ "learning_rate": 4.997795334425372e-06,
191
+ "loss": 0.5452,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.1443850267379679,
196
+ "grad_norm": 1.5286586284637451,
197
+ "learning_rate": 4.997615462318403e-06,
198
+ "loss": 0.5984,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.1497326203208556,
203
+ "grad_norm": 1.6239455938339233,
204
+ "learning_rate": 4.997428540976177e-06,
205
+ "loss": 0.6339,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.15508021390374332,
210
+ "grad_norm": 1.6466116905212402,
211
+ "learning_rate": 4.997234570926263e-06,
212
+ "loss": 0.4739,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.16042780748663102,
217
+ "grad_norm": 2.0347392559051514,
218
+ "learning_rate": 4.997033552716116e-06,
219
+ "loss": 0.6412,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.1657754010695187,
224
+ "grad_norm": 1.990586280822754,
225
+ "learning_rate": 4.9968254869130885e-06,
226
+ "loss": 0.5992,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.1711229946524064,
231
+ "grad_norm": 2.5395407676696777,
232
+ "learning_rate": 4.996610374104422e-06,
233
+ "loss": 0.5365,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.17647058823529413,
238
+ "grad_norm": 2.5586252212524414,
239
+ "learning_rate": 4.9963882148972475e-06,
240
+ "loss": 1.0359,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.18181818181818182,
245
+ "grad_norm": 2.682323455810547,
246
+ "learning_rate": 4.996159009918586e-06,
247
+ "loss": 0.8264,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.18716577540106952,
252
+ "grad_norm": 2.4657132625579834,
253
+ "learning_rate": 4.9959227598153395e-06,
254
+ "loss": 0.6522,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.1925133689839572,
259
+ "grad_norm": 2.639517068862915,
260
+ "learning_rate": 4.9956794652542994e-06,
261
+ "loss": 0.732,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.19786096256684493,
266
+ "grad_norm": 1.8087797164916992,
267
+ "learning_rate": 4.9954291269221364e-06,
268
+ "loss": 0.5377,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.20320855614973263,
273
+ "grad_norm": 1.2785123586654663,
274
+ "learning_rate": 4.995171745525401e-06,
275
+ "loss": 0.4624,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.20855614973262032,
280
+ "grad_norm": 1.5121687650680542,
281
+ "learning_rate": 4.994907321790524e-06,
282
+ "loss": 0.5233,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.21390374331550802,
287
+ "grad_norm": 1.5517159700393677,
288
+ "learning_rate": 4.994635856463811e-06,
289
+ "loss": 0.4253,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2192513368983957,
294
+ "grad_norm": 1.9111347198486328,
295
+ "learning_rate": 4.994357350311441e-06,
296
+ "loss": 0.7568,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.22459893048128343,
301
+ "grad_norm": 2.263079881668091,
302
+ "learning_rate": 4.994071804119467e-06,
303
+ "loss": 0.794,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.22994652406417113,
308
+ "grad_norm": 1.844992756843567,
309
+ "learning_rate": 4.993779218693811e-06,
310
+ "loss": 0.7615,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.23529411764705882,
315
+ "grad_norm": 1.8086172342300415,
316
+ "learning_rate": 4.99347959486026e-06,
317
+ "loss": 0.5096,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.24064171122994651,
322
+ "grad_norm": 1.6230318546295166,
323
+ "learning_rate": 4.99317293346447e-06,
324
+ "loss": 0.5449,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.24598930481283424,
329
+ "grad_norm": 1.9326215982437134,
330
+ "learning_rate": 4.992859235371958e-06,
331
+ "loss": 0.5284,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.25133689839572193,
336
+ "grad_norm": 1.6559189558029175,
337
+ "learning_rate": 4.992538501468101e-06,
338
+ "loss": 0.4632,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.25668449197860965,
343
+ "grad_norm": 1.669198989868164,
344
+ "learning_rate": 4.992210732658132e-06,
345
+ "loss": 0.5606,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.2620320855614973,
350
+ "grad_norm": 1.9434726238250732,
351
+ "learning_rate": 4.991875929867143e-06,
352
+ "loss": 0.6725,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.26737967914438504,
357
+ "grad_norm": 1.8069108724594116,
358
+ "learning_rate": 4.991534094040077e-06,
359
+ "loss": 0.4451,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.2727272727272727,
364
+ "grad_norm": 2.617253541946411,
365
+ "learning_rate": 4.991185226141726e-06,
366
+ "loss": 0.7146,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.27807486631016043,
371
+ "grad_norm": 1.9495006799697876,
372
+ "learning_rate": 4.990829327156729e-06,
373
+ "loss": 0.8155,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.28342245989304815,
378
+ "grad_norm": 2.382274866104126,
379
+ "learning_rate": 4.990466398089571e-06,
380
+ "loss": 0.7197,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.2887700534759358,
385
+ "grad_norm": 1.387713074684143,
386
+ "learning_rate": 4.99009643996458e-06,
387
+ "loss": 0.379,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.29411764705882354,
392
+ "grad_norm": 2.0043537616729736,
393
+ "learning_rate": 4.989719453825918e-06,
394
+ "loss": 0.5046,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.2994652406417112,
399
+ "grad_norm": 1.754691243171692,
400
+ "learning_rate": 4.989335440737587e-06,
401
+ "loss": 0.4966,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.3048128342245989,
406
+ "grad_norm": 1.939621925354004,
407
+ "learning_rate": 4.9889444017834185e-06,
408
+ "loss": 0.6735,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.31016042780748665,
413
+ "grad_norm": 1.6981756687164307,
414
+ "learning_rate": 4.988546338067078e-06,
415
+ "loss": 0.6731,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.3155080213903743,
420
+ "grad_norm": 1.6673622131347656,
421
+ "learning_rate": 4.988141250712053e-06,
422
+ "loss": 0.618,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.32085561497326204,
427
+ "grad_norm": 3.2902991771698,
428
+ "learning_rate": 4.987729140861657e-06,
429
+ "loss": 0.7822,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.32620320855614976,
434
+ "grad_norm": 2.318052291870117,
435
+ "learning_rate": 4.987310009679023e-06,
436
+ "loss": 0.7347,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.3315508021390374,
441
+ "grad_norm": 1.9186023473739624,
442
+ "learning_rate": 4.986883858347101e-06,
443
+ "loss": 0.675,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.33689839572192515,
448
+ "grad_norm": 1.5926198959350586,
449
+ "learning_rate": 4.986450688068655e-06,
450
+ "loss": 0.424,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.3422459893048128,
455
+ "grad_norm": 1.627715826034546,
456
+ "learning_rate": 4.986010500066258e-06,
457
+ "loss": 0.5794,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.34759358288770054,
462
+ "grad_norm": 2.109992742538452,
463
+ "learning_rate": 4.985563295582292e-06,
464
+ "loss": 0.6393,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.35294117647058826,
469
+ "grad_norm": 1.9046299457550049,
470
+ "learning_rate": 4.98510907587894e-06,
471
+ "loss": 0.5987,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.3582887700534759,
476
+ "grad_norm": 1.637699007987976,
477
+ "learning_rate": 4.984647842238185e-06,
478
+ "loss": 0.732,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.36363636363636365,
483
+ "grad_norm": 1.8627448081970215,
484
+ "learning_rate": 4.984179595961806e-06,
485
+ "loss": 0.4187,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.3689839572192513,
490
+ "grad_norm": 1.9662399291992188,
491
+ "learning_rate": 4.983704338371375e-06,
492
+ "loss": 0.6175,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.37433155080213903,
497
+ "grad_norm": 1.9179377555847168,
498
+ "learning_rate": 4.983222070808255e-06,
499
+ "loss": 0.4697,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.37967914438502676,
504
+ "grad_norm": 2.297417640686035,
505
+ "learning_rate": 4.982732794633588e-06,
506
+ "loss": 0.7984,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.3850267379679144,
511
+ "grad_norm": 2.2231695652008057,
512
+ "learning_rate": 4.982236511228301e-06,
513
+ "loss": 0.6579,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.39037433155080214,
518
+ "grad_norm": 1.5652674436569214,
519
+ "learning_rate": 4.981733221993099e-06,
520
+ "loss": 0.7144,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.39572192513368987,
525
+ "grad_norm": 1.5447490215301514,
526
+ "learning_rate": 4.981222928348456e-06,
527
+ "loss": 0.5134,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.40106951871657753,
532
+ "grad_norm": 1.6722451448440552,
533
+ "learning_rate": 4.98070563173462e-06,
534
+ "loss": 0.5398,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.40641711229946526,
539
+ "grad_norm": 1.586342215538025,
540
+ "learning_rate": 4.980181333611601e-06,
541
+ "loss": 0.4843,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.4117647058823529,
546
+ "grad_norm": 1.8715976476669312,
547
+ "learning_rate": 4.979650035459171e-06,
548
+ "loss": 0.5477,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.41711229946524064,
553
+ "grad_norm": 1.7622662782669067,
554
+ "learning_rate": 4.9791117387768575e-06,
555
+ "loss": 0.8197,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.42245989304812837,
560
+ "grad_norm": 1.9834645986557007,
561
+ "learning_rate": 4.978566445083942e-06,
562
+ "loss": 0.4906,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.42780748663101603,
567
+ "grad_norm": 2.183394193649292,
568
+ "learning_rate": 4.978014155919455e-06,
569
+ "loss": 0.6046,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.43315508021390375,
574
+ "grad_norm": 2.0138163566589355,
575
+ "learning_rate": 4.977454872842169e-06,
576
+ "loss": 0.5781,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.4385026737967914,
581
+ "grad_norm": 1.867531657218933,
582
+ "learning_rate": 4.976888597430597e-06,
583
+ "loss": 0.7309,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.44385026737967914,
588
+ "grad_norm": 1.992043375968933,
589
+ "learning_rate": 4.976315331282985e-06,
590
+ "loss": 0.647,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.44919786096256686,
595
+ "grad_norm": 1.718663215637207,
596
+ "learning_rate": 4.9757350760173144e-06,
597
+ "loss": 0.5681,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.45454545454545453,
602
+ "grad_norm": 1.5433567762374878,
603
+ "learning_rate": 4.975147833271288e-06,
604
+ "loss": 0.6864,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.45989304812834225,
609
+ "grad_norm": 1.6821852922439575,
610
+ "learning_rate": 4.974553604702332e-06,
611
+ "loss": 0.5284,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.46524064171123,
616
+ "grad_norm": 1.9842617511749268,
617
+ "learning_rate": 4.973952391987589e-06,
618
+ "loss": 0.7241,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.47058823529411764,
623
+ "grad_norm": 2.3025224208831787,
624
+ "learning_rate": 4.9733441968239125e-06,
625
+ "loss": 0.9194,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.47593582887700536,
630
+ "grad_norm": 1.653467059135437,
631
+ "learning_rate": 4.972729020927866e-06,
632
+ "loss": 0.5116,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.48128342245989303,
637
+ "grad_norm": 1.9229518175125122,
638
+ "learning_rate": 4.97210686603571e-06,
639
+ "loss": 0.6996,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.48663101604278075,
644
+ "grad_norm": 1.8346918821334839,
645
+ "learning_rate": 4.97147773390341e-06,
646
+ "loss": 0.5221,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.4919786096256685,
651
+ "grad_norm": 1.8530116081237793,
652
+ "learning_rate": 4.970841626306617e-06,
653
+ "loss": 0.5329,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.49732620320855614,
658
+ "grad_norm": 1.5837336778640747,
659
+ "learning_rate": 4.970198545040673e-06,
660
+ "loss": 0.5976,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.5026737967914439,
665
+ "grad_norm": 2.3146016597747803,
666
+ "learning_rate": 4.969548491920603e-06,
667
+ "loss": 0.6309,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.5080213903743316,
672
+ "grad_norm": 1.9704936742782593,
673
+ "learning_rate": 4.968891468781105e-06,
674
+ "loss": 0.7315,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.5133689839572193,
679
+ "grad_norm": 2.6443569660186768,
680
+ "learning_rate": 4.968227477476554e-06,
681
+ "loss": 0.6956,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.5187165775401069,
686
+ "grad_norm": 1.6732944250106812,
687
+ "learning_rate": 4.9675565198809905e-06,
688
+ "loss": 0.6776,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.5240641711229946,
693
+ "grad_norm": 1.894516110420227,
694
+ "learning_rate": 4.966878597888114e-06,
695
+ "loss": 0.5907,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.5294117647058824,
700
+ "grad_norm": 2.241065502166748,
701
+ "learning_rate": 4.966193713411284e-06,
702
+ "loss": 0.5485,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.5347593582887701,
707
+ "grad_norm": 1.7710485458374023,
708
+ "learning_rate": 4.965501868383507e-06,
709
+ "loss": 0.4389,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.5401069518716578,
714
+ "grad_norm": 1.7130372524261475,
715
+ "learning_rate": 4.964803064757438e-06,
716
+ "loss": 0.5357,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.5454545454545454,
721
+ "grad_norm": 1.7136304378509521,
722
+ "learning_rate": 4.964097304505371e-06,
723
+ "loss": 0.6074,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.5508021390374331,
728
+ "grad_norm": 1.6565794944763184,
729
+ "learning_rate": 4.963384589619233e-06,
730
+ "loss": 0.4962,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.5561497326203209,
735
+ "grad_norm": 2.1922948360443115,
736
+ "learning_rate": 4.962664922110581e-06,
737
+ "loss": 0.7595,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.5614973262032086,
742
+ "grad_norm": 1.9012060165405273,
743
+ "learning_rate": 4.9619383040105954e-06,
744
+ "loss": 0.8247,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.5668449197860963,
749
+ "grad_norm": 2.3666958808898926,
750
+ "learning_rate": 4.961204737370071e-06,
751
+ "loss": 0.6886,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.5721925133689839,
756
+ "grad_norm": 1.8199653625488281,
757
+ "learning_rate": 4.960464224259418e-06,
758
+ "loss": 0.8274,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.5775401069518716,
763
+ "grad_norm": 1.8745530843734741,
764
+ "learning_rate": 4.95971676676865e-06,
765
+ "loss": 0.4473,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.5828877005347594,
770
+ "grad_norm": 1.9484905004501343,
771
+ "learning_rate": 4.958962367007381e-06,
772
+ "loss": 0.7518,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.5882352941176471,
777
+ "grad_norm": 1.7162541151046753,
778
+ "learning_rate": 4.958201027104818e-06,
779
+ "loss": 0.5641,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.5935828877005348,
784
+ "grad_norm": 1.5666559934616089,
785
+ "learning_rate": 4.957432749209755e-06,
786
+ "loss": 0.3825,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.5989304812834224,
791
+ "grad_norm": 1.7929071187973022,
792
+ "learning_rate": 4.95665753549057e-06,
793
+ "loss": 0.6255,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.6042780748663101,
798
+ "grad_norm": 2.12982439994812,
799
+ "learning_rate": 4.9558753881352165e-06,
800
+ "loss": 1.0517,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.6096256684491979,
805
+ "grad_norm": 2.282458782196045,
806
+ "learning_rate": 4.955086309351213e-06,
807
+ "loss": 0.858,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.6149732620320856,
812
+ "grad_norm": 1.9612908363342285,
813
+ "learning_rate": 4.9542903013656485e-06,
814
+ "loss": 0.4834,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.6203208556149733,
819
+ "grad_norm": 1.7210649251937866,
820
+ "learning_rate": 4.953487366425163e-06,
821
+ "loss": 0.5308,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.6256684491978609,
826
+ "grad_norm": 1.9125163555145264,
827
+ "learning_rate": 4.952677506795949e-06,
828
+ "loss": 0.4905,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.6310160427807486,
833
+ "grad_norm": 2.0173189640045166,
834
+ "learning_rate": 4.951860724763743e-06,
835
+ "loss": 0.6062,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.6363636363636364,
840
+ "grad_norm": 1.7658207416534424,
841
+ "learning_rate": 4.95103702263382e-06,
842
+ "loss": 0.6076,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.6417112299465241,
847
+ "grad_norm": 1.7931920289993286,
848
+ "learning_rate": 4.950206402730984e-06,
849
+ "loss": 0.5761,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.6470588235294118,
854
+ "grad_norm": 1.9867966175079346,
855
+ "learning_rate": 4.949368867399567e-06,
856
+ "loss": 0.444,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.6524064171122995,
861
+ "grad_norm": 1.8381093740463257,
862
+ "learning_rate": 4.948524419003415e-06,
863
+ "loss": 0.9731,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.6577540106951871,
868
+ "grad_norm": 1.760453462600708,
869
+ "learning_rate": 4.947673059925889e-06,
870
+ "loss": 0.5679,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.6631016042780749,
875
+ "grad_norm": 1.673497200012207,
876
+ "learning_rate": 4.9468147925698525e-06,
877
+ "loss": 0.7147,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.6684491978609626,
882
+ "grad_norm": 1.7764105796813965,
883
+ "learning_rate": 4.945949619357668e-06,
884
+ "loss": 0.5621,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.6737967914438503,
889
+ "grad_norm": 1.646117925643921,
890
+ "learning_rate": 4.945077542731188e-06,
891
+ "loss": 0.424,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.679144385026738,
896
+ "grad_norm": 1.6160390377044678,
897
+ "learning_rate": 4.94419856515175e-06,
898
+ "loss": 0.6275,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.6844919786096256,
903
+ "grad_norm": 2.0285964012145996,
904
+ "learning_rate": 4.943312689100166e-06,
905
+ "loss": 0.7424,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.6898395721925134,
910
+ "grad_norm": 1.6698577404022217,
911
+ "learning_rate": 4.942419917076723e-06,
912
+ "loss": 0.4564,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.6951871657754011,
917
+ "grad_norm": 1.7816758155822754,
918
+ "learning_rate": 4.941520251601167e-06,
919
+ "loss": 0.6168,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.7005347593582888,
924
+ "grad_norm": 1.6667686700820923,
925
+ "learning_rate": 4.940613695212702e-06,
926
+ "loss": 0.4273,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.7058823529411765,
931
+ "grad_norm": 2.1824095249176025,
932
+ "learning_rate": 4.939700250469979e-06,
933
+ "loss": 0.7779,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.7112299465240641,
938
+ "grad_norm": 1.7985590696334839,
939
+ "learning_rate": 4.938779919951092e-06,
940
+ "loss": 0.7177,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.7165775401069518,
945
+ "grad_norm": 1.5667469501495361,
946
+ "learning_rate": 4.93785270625357e-06,
947
+ "loss": 0.4234,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.7219251336898396,
952
+ "grad_norm": 1.4437174797058105,
953
+ "learning_rate": 4.936918611994368e-06,
954
+ "loss": 0.4277,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.7272727272727273,
959
+ "grad_norm": 1.7203410863876343,
960
+ "learning_rate": 4.935977639809861e-06,
961
+ "loss": 0.6203,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.732620320855615,
966
+ "grad_norm": 1.3566652536392212,
967
+ "learning_rate": 4.935029792355834e-06,
968
+ "loss": 0.4342,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.7379679144385026,
973
+ "grad_norm": 1.8581316471099854,
974
+ "learning_rate": 4.934075072307481e-06,
975
+ "loss": 0.8276,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.7433155080213903,
980
+ "grad_norm": 1.8015589714050293,
981
+ "learning_rate": 4.933113482359388e-06,
982
+ "loss": 0.4481,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.7486631016042781,
987
+ "grad_norm": 2.1754965782165527,
988
+ "learning_rate": 4.932145025225535e-06,
989
+ "loss": 0.6064,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.7540106951871658,
994
+ "grad_norm": 1.8877915143966675,
995
+ "learning_rate": 4.931169703639282e-06,
996
+ "loss": 0.7172,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.7593582887700535,
1001
+ "grad_norm": 1.3962950706481934,
1002
+ "learning_rate": 4.930187520353363e-06,
1003
+ "loss": 0.4936,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.7647058823529411,
1008
+ "grad_norm": 2.133310317993164,
1009
+ "learning_rate": 4.929198478139877e-06,
1010
+ "loss": 0.53,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.7700534759358288,
1015
+ "grad_norm": 1.7312599420547485,
1016
+ "learning_rate": 4.928202579790285e-06,
1017
+ "loss": 0.4556,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.7754010695187166,
1022
+ "grad_norm": 1.7864582538604736,
1023
+ "learning_rate": 4.927199828115395e-06,
1024
+ "loss": 0.6126,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.7807486631016043,
1029
+ "grad_norm": 1.9493857622146606,
1030
+ "learning_rate": 4.9261902259453616e-06,
1031
+ "loss": 0.6721,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.786096256684492,
1036
+ "grad_norm": 2.2574429512023926,
1037
+ "learning_rate": 4.925173776129669e-06,
1038
+ "loss": 0.7753,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.7914438502673797,
1043
+ "grad_norm": 1.5487452745437622,
1044
+ "learning_rate": 4.9241504815371346e-06,
1045
+ "loss": 0.4158,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.7967914438502673,
1050
+ "grad_norm": 1.5651286840438843,
1051
+ "learning_rate": 4.923120345055887e-06,
1052
+ "loss": 0.5639,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.8021390374331551,
1057
+ "grad_norm": 1.8858426809310913,
1058
+ "learning_rate": 4.922083369593372e-06,
1059
+ "loss": 0.5185,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.8074866310160428,
1064
+ "grad_norm": 1.4627087116241455,
1065
+ "learning_rate": 4.921039558076335e-06,
1066
+ "loss": 0.6371,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.8128342245989305,
1071
+ "grad_norm": 1.2393488883972168,
1072
+ "learning_rate": 4.919988913450812e-06,
1073
+ "loss": 0.3465,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.8181818181818182,
1078
+ "grad_norm": 1.4756773710250854,
1079
+ "learning_rate": 4.918931438682132e-06,
1080
+ "loss": 0.6041,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.8235294117647058,
1085
+ "grad_norm": 1.850448727607727,
1086
+ "learning_rate": 4.917867136754894e-06,
1087
+ "loss": 0.7382,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.8288770053475936,
1092
+ "grad_norm": 1.5880764722824097,
1093
+ "learning_rate": 4.916796010672969e-06,
1094
+ "loss": 0.5838,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.8342245989304813,
1099
+ "grad_norm": 1.60927414894104,
1100
+ "learning_rate": 4.91571806345949e-06,
1101
+ "loss": 0.6274,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.839572192513369,
1106
+ "grad_norm": 2.0539658069610596,
1107
+ "learning_rate": 4.91463329815684e-06,
1108
+ "loss": 0.7024,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.8449197860962567,
1113
+ "grad_norm": 1.4041088819503784,
1114
+ "learning_rate": 4.913541717826645e-06,
1115
+ "loss": 0.4419,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.8502673796791443,
1120
+ "grad_norm": 1.3182406425476074,
1121
+ "learning_rate": 4.912443325549767e-06,
1122
+ "loss": 0.3842,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.8556149732620321,
1127
+ "grad_norm": 1.4476114511489868,
1128
+ "learning_rate": 4.911338124426291e-06,
1129
+ "loss": 0.4929,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.8609625668449198,
1134
+ "grad_norm": 1.6259913444519043,
1135
+ "learning_rate": 4.910226117575525e-06,
1136
+ "loss": 0.6165,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.8663101604278075,
1141
+ "grad_norm": 1.608425498008728,
1142
+ "learning_rate": 4.909107308135978e-06,
1143
+ "loss": 0.4232,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.8716577540106952,
1148
+ "grad_norm": 2.0656051635742188,
1149
+ "learning_rate": 4.907981699265364e-06,
1150
+ "loss": 0.5169,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.8770053475935828,
1155
+ "grad_norm": 1.874157428741455,
1156
+ "learning_rate": 4.906849294140587e-06,
1157
+ "loss": 0.5935,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.8823529411764706,
1162
+ "grad_norm": 1.4374042749404907,
1163
+ "learning_rate": 4.9057100959577285e-06,
1164
+ "loss": 0.4568,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.8877005347593583,
1169
+ "grad_norm": 2.1897101402282715,
1170
+ "learning_rate": 4.904564107932048e-06,
1171
+ "loss": 0.8229,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.893048128342246,
1176
+ "grad_norm": 1.757002353668213,
1177
+ "learning_rate": 4.903411333297966e-06,
1178
+ "loss": 0.7094,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.8983957219251337,
1183
+ "grad_norm": 1.8555337190628052,
1184
+ "learning_rate": 4.902251775309057e-06,
1185
+ "loss": 0.6363,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.9037433155080213,
1190
+ "grad_norm": 1.2612260580062866,
1191
+ "learning_rate": 4.901085437238041e-06,
1192
+ "loss": 0.3461,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.9090909090909091,
1197
+ "grad_norm": 1.7964407205581665,
1198
+ "learning_rate": 4.899912322376776e-06,
1199
+ "loss": 0.81,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.9144385026737968,
1204
+ "grad_norm": 2.0083279609680176,
1205
+ "learning_rate": 4.8987324340362445e-06,
1206
+ "loss": 0.6614,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.9197860962566845,
1211
+ "grad_norm": 2.3292622566223145,
1212
+ "learning_rate": 4.897545775546545e-06,
1213
+ "loss": 0.6843,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.9251336898395722,
1218
+ "grad_norm": 1.884008526802063,
1219
+ "learning_rate": 4.8963523502568886e-06,
1220
+ "loss": 0.8555,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.93048128342246,
1225
+ "grad_norm": 2.3420653343200684,
1226
+ "learning_rate": 4.895152161535582e-06,
1227
+ "loss": 0.6267,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.9358288770053476,
1232
+ "grad_norm": 1.9454401731491089,
1233
+ "learning_rate": 4.893945212770019e-06,
1234
+ "loss": 0.5758,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.9411764705882353,
1239
+ "grad_norm": 1.483435034751892,
1240
+ "learning_rate": 4.892731507366678e-06,
1241
+ "loss": 0.6295,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.946524064171123,
1246
+ "grad_norm": 1.553695559501648,
1247
+ "learning_rate": 4.891511048751102e-06,
1248
+ "loss": 0.5734,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.9518716577540107,
1253
+ "grad_norm": 1.973617672920227,
1254
+ "learning_rate": 4.890283840367898e-06,
1255
+ "loss": 0.9304,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.9572192513368984,
1260
+ "grad_norm": 1.5934555530548096,
1261
+ "learning_rate": 4.889049885680721e-06,
1262
+ "loss": 0.5013,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.9625668449197861,
1267
+ "grad_norm": 2.033491849899292,
1268
+ "learning_rate": 4.887809188172268e-06,
1269
+ "loss": 0.602,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.9679144385026738,
1274
+ "grad_norm": 1.9204297065734863,
1275
+ "learning_rate": 4.886561751344266e-06,
1276
+ "loss": 0.6782,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.9732620320855615,
1281
+ "grad_norm": 1.589028000831604,
1282
+ "learning_rate": 4.885307578717464e-06,
1283
+ "loss": 0.568,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.9786096256684492,
1288
+ "grad_norm": 1.565994381904602,
1289
+ "learning_rate": 4.8840466738316216e-06,
1290
+ "loss": 0.6008,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.983957219251337,
1295
+ "grad_norm": 1.8866958618164062,
1296
+ "learning_rate": 4.882779040245499e-06,
1297
+ "loss": 0.6444,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.9893048128342246,
1302
+ "grad_norm": 1.4093397855758667,
1303
+ "learning_rate": 4.881504681536847e-06,
1304
+ "loss": 0.4101,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.9946524064171123,
1309
+ "grad_norm": 1.4958691596984863,
1310
+ "learning_rate": 4.880223601302398e-06,
1311
+ "loss": 0.4476,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 1.0,
1316
+ "grad_norm": 1.6625601053237915,
1317
+ "learning_rate": 4.878935803157856e-06,
1318
+ "loss": 0.4528,
1319
+ "step": 187
1320
+ }
1321
+ ],
1322
+ "logging_steps": 1,
1323
+ "max_steps": 1870,
1324
+ "num_input_tokens_seen": 0,
1325
+ "num_train_epochs": 10,
1326
+ "save_steps": 208,
1327
+ "stateful_callbacks": {
1328
+ "TrainerControl": {
1329
+ "args": {
1330
+ "should_epoch_stop": false,
1331
+ "should_evaluate": false,
1332
+ "should_log": false,
1333
+ "should_save": true,
1334
+ "should_training_stop": false
1335
+ },
1336
+ "attributes": {}
1337
+ }
1338
+ },
1339
+ "total_flos": 5.12625839397929e+16,
1340
+ "train_batch_size": 1,
1341
+ "trial_name": null,
1342
+ "trial_params": null
1343
+ }
qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-187/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo_filtered_combined/checkpoint-935/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_combined/checkpoint-935/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_combined/checkpoint-935/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff