Hugging Face's logo

INFReasoning
/
metalimo

Safetensors
Model card Files
xet
Community
KublaiKhan1 commited on
Commit
c88cab8
·
verified ·
1 Parent(s): e00b6b6

Add files using upload-large-folder tool

Browse files
Files changed (27) hide show
  1. qwen2_5_math_7b/limo/checkpoint-1025/added_tokens.json +24 -0
  2. qwen2_5_math_7b/limo/checkpoint-1025/config.json +59 -0
  3. qwen2_5_math_7b/limo/checkpoint-1025/tokenizer_config.json +208 -0
  4. qwen2_5_math_7b/limo/checkpoint-1435/generation_config.json +6 -0
  5. qwen2_5_math_7b/limo/checkpoint-1435/merges.txt +0 -0
  6. qwen2_5_math_7b/limo/checkpoint-1435/model.safetensors.index.json +347 -0
  7. qwen2_5_math_7b/limo/checkpoint-1435/special_tokens_map.json +31 -0
  8. qwen2_5_math_7b/limo/checkpoint-1435/vocab.json +0 -0
  9. qwen2_5_math_7b/limo/checkpoint-1640/added_tokens.json +24 -0
  10. qwen2_5_math_7b/limo/checkpoint-1640/chat_template.jinja +54 -0
  11. qwen2_5_math_7b/limo/checkpoint-1640/config.json +59 -0
  12. qwen2_5_math_7b/limo/checkpoint-1640/generation_config.json +6 -0
  13. qwen2_5_math_7b/limo/checkpoint-1640/merges.txt +0 -0
  14. qwen2_5_math_7b/limo/checkpoint-1640/model.safetensors.index.json +347 -0
  15. qwen2_5_math_7b/limo/checkpoint-1640/special_tokens_map.json +31 -0
  16. qwen2_5_math_7b/limo/checkpoint-1640/tokenizer_config.json +208 -0
  17. qwen2_5_math_7b/limo/checkpoint-1640/vocab.json +0 -0
  18. qwen2_5_math_7b/limo/checkpoint-205/added_tokens.json +24 -0
  19. qwen2_5_math_7b/limo/checkpoint-205/chat_template.jinja +54 -0
  20. qwen2_5_math_7b/limo/checkpoint-205/config.json +59 -0
  21. qwen2_5_math_7b/limo/checkpoint-205/generation_config.json +6 -0
  22. qwen2_5_math_7b/limo/checkpoint-205/merges.txt +0 -0
  23. qwen2_5_math_7b/limo/checkpoint-205/model.safetensors.index.json +347 -0
  24. qwen2_5_math_7b/limo/checkpoint-205/special_tokens_map.json +31 -0
  25. qwen2_5_math_7b/limo/checkpoint-205/tokenizer_config.json +208 -0
  26. qwen2_5_math_7b/limo/checkpoint-205/trainer_state.json +1469 -0
  27. qwen2_5_math_7b/limo/checkpoint-205/vocab.json +0 -0
qwen2_5_math_7b/limo/checkpoint-1025/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2_5_math_7b/limo/checkpoint-1025/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 4096,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 10000,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152064
59
+ }
qwen2_5_math_7b/limo/checkpoint-1025/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_math_7b/limo/checkpoint-1435/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.55.0"
6
+ }
qwen2_5_math_7b/limo/checkpoint-1435/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_math_7b/limo/checkpoint-1435/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen2_5_math_7b/limo/checkpoint-1435/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_math_7b/limo/checkpoint-1435/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_math_7b/limo/checkpoint-1640/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2_5_math_7b/limo/checkpoint-1640/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
+ {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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_math_7b/limo/checkpoint-1640/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 4096,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 10000,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152064
59
+ }
qwen2_5_math_7b/limo/checkpoint-1640/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.55.0"
6
+ }
qwen2_5_math_7b/limo/checkpoint-1640/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_math_7b/limo/checkpoint-1640/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen2_5_math_7b/limo/checkpoint-1640/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_math_7b/limo/checkpoint-1640/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_math_7b/limo/checkpoint-1640/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_math_7b/limo/checkpoint-205/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2_5_math_7b/limo/checkpoint-205/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
+ {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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_math_7b/limo/checkpoint-205/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 4096,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 10000,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152064
59
+ }
qwen2_5_math_7b/limo/checkpoint-205/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.55.0"
6
+ }
qwen2_5_math_7b/limo/checkpoint-205/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_math_7b/limo/checkpoint-205/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen2_5_math_7b/limo/checkpoint-205/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_math_7b/limo/checkpoint-205/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_math_7b/limo/checkpoint-205/trainer_state.json ADDED
@@ -0,0 +1,1469 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 205,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.004878048780487805,
14
+ "grad_norm": 22.138404846191406,
15
+ "learning_rate": 5e-06,
16
+ "loss": 2.0514,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.00975609756097561,
21
+ "grad_norm": 26.447072982788086,
22
+ "learning_rate": 4.999997064365715e-06,
23
+ "loss": 1.4083,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.014634146341463415,
28
+ "grad_norm": 15.023693084716797,
29
+ "learning_rate": 4.999988257469751e-06,
30
+ "loss": 1.3992,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.01951219512195122,
35
+ "grad_norm": 10.351157188415527,
36
+ "learning_rate": 4.999973579332793e-06,
37
+ "loss": 1.6141,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.024390243902439025,
42
+ "grad_norm": 13.528725624084473,
43
+ "learning_rate": 4.999953029989312e-06,
44
+ "loss": 1.7049,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.02926829268292683,
49
+ "grad_norm": 6.363333225250244,
50
+ "learning_rate": 4.999926609487568e-06,
51
+ "loss": 1.0504,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.03414634146341464,
56
+ "grad_norm": 18.042160034179688,
57
+ "learning_rate": 4.9998943178896106e-06,
58
+ "loss": 1.7691,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.03902439024390244,
63
+ "grad_norm": 18.375417709350586,
64
+ "learning_rate": 4.999856155271276e-06,
65
+ "loss": 2.3735,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.04390243902439024,
70
+ "grad_norm": 13.300468444824219,
71
+ "learning_rate": 4.999812121722191e-06,
72
+ "loss": 1.9056,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.04878048780487805,
77
+ "grad_norm": 9.966270446777344,
78
+ "learning_rate": 4.999762217345766e-06,
79
+ "loss": 2.5472,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.05365853658536585,
84
+ "grad_norm": 9.960493087768555,
85
+ "learning_rate": 4.999706442259205e-06,
86
+ "loss": 1.2451,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.05853658536585366,
91
+ "grad_norm": 6.841569900512695,
92
+ "learning_rate": 4.999644796593492e-06,
93
+ "loss": 1.3519,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.06341463414634146,
98
+ "grad_norm": 8.004615783691406,
99
+ "learning_rate": 4.999577280493407e-06,
100
+ "loss": 1.2908,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.06829268292682927,
105
+ "grad_norm": 8.352128982543945,
106
+ "learning_rate": 4.99950389411751e-06,
107
+ "loss": 1.5136,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.07317073170731707,
112
+ "grad_norm": 2.6472861766815186,
113
+ "learning_rate": 4.999424637638148e-06,
114
+ "loss": 0.6843,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.07804878048780488,
119
+ "grad_norm": 74.31636047363281,
120
+ "learning_rate": 4.999339511241458e-06,
121
+ "loss": 0.944,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.08292682926829269,
126
+ "grad_norm": 65.4996337890625,
127
+ "learning_rate": 4.9992485151273584e-06,
128
+ "loss": 2.024,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.08780487804878048,
133
+ "grad_norm": 16.723800659179688,
134
+ "learning_rate": 4.999151649509554e-06,
135
+ "loss": 1.5804,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.09268292682926829,
140
+ "grad_norm": 12.863594055175781,
141
+ "learning_rate": 4.9990489146155356e-06,
142
+ "loss": 1.3615,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.0975609756097561,
147
+ "grad_norm": 12.398324012756348,
148
+ "learning_rate": 4.9989403106865765e-06,
149
+ "loss": 1.4979,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1024390243902439,
154
+ "grad_norm": 4.8458123207092285,
155
+ "learning_rate": 4.9988258379777334e-06,
156
+ "loss": 0.8265,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.1073170731707317,
161
+ "grad_norm": 5.1296844482421875,
162
+ "learning_rate": 4.998705496757846e-06,
163
+ "loss": 1.0549,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.11219512195121951,
168
+ "grad_norm": 11.290125846862793,
169
+ "learning_rate": 4.998579287309538e-06,
170
+ "loss": 1.9388,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.11707317073170732,
175
+ "grad_norm": 10.525015830993652,
176
+ "learning_rate": 4.998447209929211e-06,
177
+ "loss": 1.4569,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.12195121951219512,
182
+ "grad_norm": 1.7889195680618286,
183
+ "learning_rate": 4.998309264927053e-06,
184
+ "loss": 0.5703,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.12682926829268293,
189
+ "grad_norm": 6.902492523193359,
190
+ "learning_rate": 4.998165452627025e-06,
191
+ "loss": 0.8576,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.13170731707317074,
196
+ "grad_norm": 11.605420112609863,
197
+ "learning_rate": 4.998015773366874e-06,
198
+ "loss": 1.1532,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.13658536585365855,
203
+ "grad_norm": 3.192915678024292,
204
+ "learning_rate": 4.997860227498122e-06,
205
+ "loss": 0.6788,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.14146341463414633,
210
+ "grad_norm": 13.133618354797363,
211
+ "learning_rate": 4.99769881538607e-06,
212
+ "loss": 1.5092,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.14634146341463414,
217
+ "grad_norm": 12.705998420715332,
218
+ "learning_rate": 4.997531537409794e-06,
219
+ "loss": 1.4641,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.15121951219512195,
224
+ "grad_norm": 28.609262466430664,
225
+ "learning_rate": 4.99735839396215e-06,
226
+ "loss": 0.8727,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.15609756097560976,
231
+ "grad_norm": 91.81269836425781,
232
+ "learning_rate": 4.9971793854497655e-06,
233
+ "loss": 0.9704,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.16097560975609757,
238
+ "grad_norm": 10.507450103759766,
239
+ "learning_rate": 4.996994512293042e-06,
240
+ "loss": 1.4177,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.16585365853658537,
245
+ "grad_norm": 13.195033073425293,
246
+ "learning_rate": 4.996803774926157e-06,
247
+ "loss": 1.1937,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.17073170731707318,
252
+ "grad_norm": 2.8658792972564697,
253
+ "learning_rate": 4.996607173797059e-06,
254
+ "loss": 1.191,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.17560975609756097,
259
+ "grad_norm": 9.105996131896973,
260
+ "learning_rate": 4.996404709367466e-06,
261
+ "loss": 1.1722,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.18048780487804877,
266
+ "grad_norm": 8.545594215393066,
267
+ "learning_rate": 4.996196382112868e-06,
268
+ "loss": 0.8455,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.18536585365853658,
273
+ "grad_norm": 14.379878044128418,
274
+ "learning_rate": 4.9959821925225235e-06,
275
+ "loss": 1.0889,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.1902439024390244,
280
+ "grad_norm": 17.579647064208984,
281
+ "learning_rate": 4.995762141099456e-06,
282
+ "loss": 0.9452,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.1951219512195122,
287
+ "grad_norm": 4.446125507354736,
288
+ "learning_rate": 4.995536228360461e-06,
289
+ "loss": 0.9954,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2,
294
+ "grad_norm": 2.606940984725952,
295
+ "learning_rate": 4.995304454836095e-06,
296
+ "loss": 0.8706,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.2048780487804878,
301
+ "grad_norm": 4.837315559387207,
302
+ "learning_rate": 4.9950668210706795e-06,
303
+ "loss": 1.0195,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.2097560975609756,
308
+ "grad_norm": 7.445003032684326,
309
+ "learning_rate": 4.994823327622299e-06,
310
+ "loss": 1.2063,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.2146341463414634,
315
+ "grad_norm": 6.544964790344238,
316
+ "learning_rate": 4.9945739750628e-06,
317
+ "loss": 0.8807,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.21951219512195122,
322
+ "grad_norm": 8.999876022338867,
323
+ "learning_rate": 4.994318763977789e-06,
324
+ "loss": 1.0277,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.22439024390243903,
329
+ "grad_norm": 9.390464782714844,
330
+ "learning_rate": 4.994057694966632e-06,
331
+ "loss": 1.1352,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.22926829268292684,
336
+ "grad_norm": 4.313526153564453,
337
+ "learning_rate": 4.993790768642449e-06,
338
+ "loss": 1.0033,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.23414634146341465,
343
+ "grad_norm": 10.303829193115234,
344
+ "learning_rate": 4.99351798563212e-06,
345
+ "loss": 1.6233,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.23902439024390243,
350
+ "grad_norm": 4.707674503326416,
351
+ "learning_rate": 4.993239346576278e-06,
352
+ "loss": 1.0956,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.24390243902439024,
357
+ "grad_norm": 3.8843674659729004,
358
+ "learning_rate": 4.99295485212931e-06,
359
+ "loss": 1.236,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.24878048780487805,
364
+ "grad_norm": 6.579261779785156,
365
+ "learning_rate": 4.992664502959351e-06,
366
+ "loss": 1.1403,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.25365853658536586,
371
+ "grad_norm": 1.7781167030334473,
372
+ "learning_rate": 4.99236829974829e-06,
373
+ "loss": 0.6883,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.25853658536585367,
378
+ "grad_norm": 3.223673105239868,
379
+ "learning_rate": 4.992066243191762e-06,
380
+ "loss": 1.0185,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.2634146341463415,
385
+ "grad_norm": 2.5291311740875244,
386
+ "learning_rate": 4.991758333999148e-06,
387
+ "loss": 0.7823,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.2682926829268293,
392
+ "grad_norm": 3.9081308841705322,
393
+ "learning_rate": 4.991444572893575e-06,
394
+ "loss": 0.7634,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.2731707317073171,
399
+ "grad_norm": 1.7186449766159058,
400
+ "learning_rate": 4.991124960611916e-06,
401
+ "loss": 0.5396,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.2780487804878049,
406
+ "grad_norm": 3.7625038623809814,
407
+ "learning_rate": 4.99079949790478e-06,
408
+ "loss": 0.8568,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.28292682926829266,
413
+ "grad_norm": 4.833764553070068,
414
+ "learning_rate": 4.99046818553652e-06,
415
+ "loss": 0.9866,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.28780487804878047,
420
+ "grad_norm": 17.990612030029297,
421
+ "learning_rate": 4.9901310242852246e-06,
422
+ "loss": 1.0425,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.2926829268292683,
427
+ "grad_norm": 6.425568580627441,
428
+ "learning_rate": 4.9897880149427206e-06,
429
+ "loss": 1.085,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.2975609756097561,
434
+ "grad_norm": 5.177443027496338,
435
+ "learning_rate": 4.989439158314566e-06,
436
+ "loss": 1.0767,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.3024390243902439,
441
+ "grad_norm": 2.572352886199951,
442
+ "learning_rate": 4.989084455220056e-06,
443
+ "loss": 0.5224,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.3073170731707317,
448
+ "grad_norm": 2.277250051498413,
449
+ "learning_rate": 4.988723906492212e-06,
450
+ "loss": 0.8736,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.3121951219512195,
455
+ "grad_norm": 4.4316935539245605,
456
+ "learning_rate": 4.988357512977785e-06,
457
+ "loss": 0.5605,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.3170731707317073,
462
+ "grad_norm": 2.4577624797821045,
463
+ "learning_rate": 4.987985275537252e-06,
464
+ "loss": 0.5415,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.32195121951219513,
469
+ "grad_norm": 7.362552165985107,
470
+ "learning_rate": 4.9876071950448185e-06,
471
+ "loss": 0.9167,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.32682926829268294,
476
+ "grad_norm": 2.687702178955078,
477
+ "learning_rate": 4.987223272388407e-06,
478
+ "loss": 0.6806,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.33170731707317075,
483
+ "grad_norm": 4.988495349884033,
484
+ "learning_rate": 4.986833508469663e-06,
485
+ "loss": 0.9808,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.33658536585365856,
490
+ "grad_norm": 4.317763805389404,
491
+ "learning_rate": 4.98643790420395e-06,
492
+ "loss": 0.8506,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.34146341463414637,
497
+ "grad_norm": 3.347094774246216,
498
+ "learning_rate": 4.986036460520348e-06,
499
+ "loss": 0.8512,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.3463414634146341,
504
+ "grad_norm": 6.8587775230407715,
505
+ "learning_rate": 4.98562917836165e-06,
506
+ "loss": 1.1533,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.35121951219512193,
511
+ "grad_norm": 3.214782238006592,
512
+ "learning_rate": 4.985216058684362e-06,
513
+ "loss": 0.7506,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.35609756097560974,
518
+ "grad_norm": 2.6237006187438965,
519
+ "learning_rate": 4.984797102458697e-06,
520
+ "loss": 1.0345,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.36097560975609755,
525
+ "grad_norm": 1.8713479042053223,
526
+ "learning_rate": 4.984372310668579e-06,
527
+ "loss": 0.5752,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.36585365853658536,
532
+ "grad_norm": 2.518427610397339,
533
+ "learning_rate": 4.983941684311633e-06,
534
+ "loss": 1.2944,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.37073170731707317,
539
+ "grad_norm": 3.947360038757324,
540
+ "learning_rate": 4.983505224399188e-06,
541
+ "loss": 0.8142,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.375609756097561,
546
+ "grad_norm": 3.0242512226104736,
547
+ "learning_rate": 4.983062931956275e-06,
548
+ "loss": 0.8578,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.3804878048780488,
553
+ "grad_norm": 2.711573600769043,
554
+ "learning_rate": 4.9826148080216195e-06,
555
+ "loss": 0.9262,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.3853658536585366,
560
+ "grad_norm": 2.975578784942627,
561
+ "learning_rate": 4.9821608536476445e-06,
562
+ "loss": 1.2846,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.3902439024390244,
567
+ "grad_norm": 4.4119415283203125,
568
+ "learning_rate": 4.981701069900465e-06,
569
+ "loss": 0.942,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.3951219512195122,
574
+ "grad_norm": 3.3930721282958984,
575
+ "learning_rate": 4.9812354578598876e-06,
576
+ "loss": 0.7599,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.4,
581
+ "grad_norm": 2.192596435546875,
582
+ "learning_rate": 4.980764018619405e-06,
583
+ "loss": 0.7835,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.40487804878048783,
588
+ "grad_norm": 3.237403631210327,
589
+ "learning_rate": 4.980286753286196e-06,
590
+ "loss": 0.9365,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.4097560975609756,
595
+ "grad_norm": 2.1691837310791016,
596
+ "learning_rate": 4.97980366298112e-06,
597
+ "loss": 0.782,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.4146341463414634,
602
+ "grad_norm": 2.8383233547210693,
603
+ "learning_rate": 4.97931474883872e-06,
604
+ "loss": 0.8006,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.4195121951219512,
609
+ "grad_norm": 2.01986026763916,
610
+ "learning_rate": 4.978820012007213e-06,
611
+ "loss": 0.8591,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.424390243902439,
616
+ "grad_norm": 2.3000314235687256,
617
+ "learning_rate": 4.978319453648495e-06,
618
+ "loss": 0.9201,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.4292682926829268,
623
+ "grad_norm": 2.3446927070617676,
624
+ "learning_rate": 4.977813074938128e-06,
625
+ "loss": 0.8661,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.43414634146341463,
630
+ "grad_norm": 2.113168239593506,
631
+ "learning_rate": 4.977300877065347e-06,
632
+ "loss": 0.8441,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.43902439024390244,
637
+ "grad_norm": 2.4370508193969727,
638
+ "learning_rate": 4.976782861233053e-06,
639
+ "loss": 0.6732,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.44390243902439025,
644
+ "grad_norm": 3.2290725708007812,
645
+ "learning_rate": 4.976259028657812e-06,
646
+ "loss": 0.6321,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.44878048780487806,
651
+ "grad_norm": 4.33652925491333,
652
+ "learning_rate": 4.975729380569845e-06,
653
+ "loss": 0.7268,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.45365853658536587,
658
+ "grad_norm": 1.8476589918136597,
659
+ "learning_rate": 4.975193918213035e-06,
660
+ "loss": 0.465,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.4585365853658537,
665
+ "grad_norm": 1.528070092201233,
666
+ "learning_rate": 4.974652642844921e-06,
667
+ "loss": 0.6325,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.4634146341463415,
672
+ "grad_norm": 3.360761880874634,
673
+ "learning_rate": 4.974105555736693e-06,
674
+ "loss": 1.0014,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.4682926829268293,
679
+ "grad_norm": 1.6910600662231445,
680
+ "learning_rate": 4.973552658173186e-06,
681
+ "loss": 0.6367,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.47317073170731705,
686
+ "grad_norm": 2.9577507972717285,
687
+ "learning_rate": 4.972993951452887e-06,
688
+ "loss": 0.8256,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.47804878048780486,
693
+ "grad_norm": 2.4482178688049316,
694
+ "learning_rate": 4.9724294368879214e-06,
695
+ "loss": 0.7554,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.48292682926829267,
700
+ "grad_norm": 2.077953815460205,
701
+ "learning_rate": 4.971859115804055e-06,
702
+ "loss": 0.9382,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.4878048780487805,
707
+ "grad_norm": 2.2485179901123047,
708
+ "learning_rate": 4.9712829895406935e-06,
709
+ "loss": 0.7396,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.4926829268292683,
714
+ "grad_norm": 2.3033151626586914,
715
+ "learning_rate": 4.970701059450872e-06,
716
+ "loss": 0.5185,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.4975609756097561,
721
+ "grad_norm": 1.8318403959274292,
722
+ "learning_rate": 4.970113326901258e-06,
723
+ "loss": 0.8857,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.5024390243902439,
728
+ "grad_norm": 1.961539626121521,
729
+ "learning_rate": 4.9695197932721455e-06,
730
+ "loss": 0.8248,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.5073170731707317,
735
+ "grad_norm": 2.156985282897949,
736
+ "learning_rate": 4.968920459957453e-06,
737
+ "loss": 0.8533,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.5121951219512195,
742
+ "grad_norm": 2.9577434062957764,
743
+ "learning_rate": 4.968315328364719e-06,
744
+ "loss": 0.9013,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.5170731707317073,
749
+ "grad_norm": 1.8476804494857788,
750
+ "learning_rate": 4.9677043999151e-06,
751
+ "loss": 1.0077,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.5219512195121951,
756
+ "grad_norm": 1.9346246719360352,
757
+ "learning_rate": 4.967087676043366e-06,
758
+ "loss": 0.4618,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.526829268292683,
763
+ "grad_norm": 2.0548758506774902,
764
+ "learning_rate": 4.966465158197897e-06,
765
+ "loss": 0.8305,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.5317073170731708,
770
+ "grad_norm": 2.133976697921753,
771
+ "learning_rate": 4.965836847840681e-06,
772
+ "loss": 0.6311,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.5365853658536586,
777
+ "grad_norm": 2.1547298431396484,
778
+ "learning_rate": 4.96520274644731e-06,
779
+ "loss": 0.8104,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.5414634146341464,
784
+ "grad_norm": 1.4163529872894287,
785
+ "learning_rate": 4.964562855506976e-06,
786
+ "loss": 0.636,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.5463414634146342,
791
+ "grad_norm": 1.8655451536178589,
792
+ "learning_rate": 4.963917176522466e-06,
793
+ "loss": 0.5861,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.551219512195122,
798
+ "grad_norm": 2.7667734622955322,
799
+ "learning_rate": 4.963265711010164e-06,
800
+ "loss": 0.9409,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.5560975609756098,
805
+ "grad_norm": 3.6238114833831787,
806
+ "learning_rate": 4.9626084605000395e-06,
807
+ "loss": 0.771,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.5609756097560976,
812
+ "grad_norm": 2.039236545562744,
813
+ "learning_rate": 4.961945426535652e-06,
814
+ "loss": 0.5164,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.5658536585365853,
819
+ "grad_norm": 2.7303946018218994,
820
+ "learning_rate": 4.961276610674141e-06,
821
+ "loss": 0.8206,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.5707317073170731,
826
+ "grad_norm": 1.6661245822906494,
827
+ "learning_rate": 4.960602014486225e-06,
828
+ "loss": 0.8942,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.5756097560975609,
833
+ "grad_norm": 1.6690449714660645,
834
+ "learning_rate": 4.959921639556199e-06,
835
+ "loss": 0.6978,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.5804878048780487,
840
+ "grad_norm": 1.6131573915481567,
841
+ "learning_rate": 4.959235487481928e-06,
842
+ "loss": 0.8862,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.5853658536585366,
847
+ "grad_norm": 1.6374850273132324,
848
+ "learning_rate": 4.958543559874846e-06,
849
+ "loss": 0.4928,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.5902439024390244,
854
+ "grad_norm": 1.8508459329605103,
855
+ "learning_rate": 4.9578458583599495e-06,
856
+ "loss": 0.718,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.5951219512195122,
861
+ "grad_norm": 1.9640874862670898,
862
+ "learning_rate": 4.957142384575795e-06,
863
+ "loss": 0.6702,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.6,
868
+ "grad_norm": 1.5142700672149658,
869
+ "learning_rate": 4.956433140174498e-06,
870
+ "loss": 0.7402,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.6048780487804878,
875
+ "grad_norm": 1.8278406858444214,
876
+ "learning_rate": 4.9557181268217225e-06,
877
+ "loss": 0.7641,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.6097560975609756,
882
+ "grad_norm": 1.6352994441986084,
883
+ "learning_rate": 4.954997346196683e-06,
884
+ "loss": 1.1429,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.6146341463414634,
889
+ "grad_norm": 1.539684772491455,
890
+ "learning_rate": 4.954270799992138e-06,
891
+ "loss": 0.6404,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.6195121951219512,
896
+ "grad_norm": 1.8513871431350708,
897
+ "learning_rate": 4.953538489914387e-06,
898
+ "loss": 0.6615,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.624390243902439,
903
+ "grad_norm": 2.163950204849243,
904
+ "learning_rate": 4.9528004176832654e-06,
905
+ "loss": 0.5475,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.6292682926829268,
910
+ "grad_norm": 2.240516185760498,
911
+ "learning_rate": 4.952056585032142e-06,
912
+ "loss": 0.9359,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.6341463414634146,
917
+ "grad_norm": 1.5975580215454102,
918
+ "learning_rate": 4.951306993707913e-06,
919
+ "loss": 0.7296,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.6390243902439025,
924
+ "grad_norm": 1.6257214546203613,
925
+ "learning_rate": 4.950551645470998e-06,
926
+ "loss": 0.6884,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.6439024390243903,
931
+ "grad_norm": 1.7229961156845093,
932
+ "learning_rate": 4.9497905420953406e-06,
933
+ "loss": 0.6359,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.6487804878048781,
938
+ "grad_norm": 1.9853991270065308,
939
+ "learning_rate": 4.949023685368395e-06,
940
+ "loss": 0.6608,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.6536585365853659,
945
+ "grad_norm": 2.1698012351989746,
946
+ "learning_rate": 4.948251077091131e-06,
947
+ "loss": 0.9688,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.6585365853658537,
952
+ "grad_norm": 2.5448765754699707,
953
+ "learning_rate": 4.947472719078025e-06,
954
+ "loss": 0.7493,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.6634146341463415,
959
+ "grad_norm": 1.4268618822097778,
960
+ "learning_rate": 4.9466886131570565e-06,
961
+ "loss": 0.7836,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.6682926829268293,
966
+ "grad_norm": 1.5412968397140503,
967
+ "learning_rate": 4.945898761169704e-06,
968
+ "loss": 0.9513,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.6731707317073171,
973
+ "grad_norm": 1.6611838340759277,
974
+ "learning_rate": 4.945103164970941e-06,
975
+ "loss": 0.548,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.6780487804878049,
980
+ "grad_norm": 1.582939863204956,
981
+ "learning_rate": 4.9443018264292304e-06,
982
+ "loss": 0.6658,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.6829268292682927,
987
+ "grad_norm": 2.266261100769043,
988
+ "learning_rate": 4.9434947474265225e-06,
989
+ "loss": 0.827,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.6878048780487804,
994
+ "grad_norm": 1.6282507181167603,
995
+ "learning_rate": 4.942681929858249e-06,
996
+ "loss": 0.9394,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.6926829268292682,
1001
+ "grad_norm": 8.833651542663574,
1002
+ "learning_rate": 4.941863375633315e-06,
1003
+ "loss": 0.8216,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.697560975609756,
1008
+ "grad_norm": 1.7979482412338257,
1009
+ "learning_rate": 4.9410390866741056e-06,
1010
+ "loss": 0.686,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.7024390243902439,
1015
+ "grad_norm": 1.6304007768630981,
1016
+ "learning_rate": 4.9402090649164655e-06,
1017
+ "loss": 0.6699,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.7073170731707317,
1022
+ "grad_norm": 2.643566846847534,
1023
+ "learning_rate": 4.9393733123097085e-06,
1024
+ "loss": 0.9212,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.7121951219512195,
1029
+ "grad_norm": 2.0324487686157227,
1030
+ "learning_rate": 4.9385318308166065e-06,
1031
+ "loss": 0.7961,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.7170731707317073,
1036
+ "grad_norm": 1.8635185956954956,
1037
+ "learning_rate": 4.937684622413385e-06,
1038
+ "loss": 0.5226,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.7219512195121951,
1043
+ "grad_norm": 2.0762131214141846,
1044
+ "learning_rate": 4.9368316890897185e-06,
1045
+ "loss": 0.8788,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.7268292682926829,
1050
+ "grad_norm": 1.3568695783615112,
1051
+ "learning_rate": 4.9359730328487264e-06,
1052
+ "loss": 0.4686,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.7317073170731707,
1057
+ "grad_norm": 1.3983228206634521,
1058
+ "learning_rate": 4.935108655706972e-06,
1059
+ "loss": 0.7091,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.7365853658536585,
1064
+ "grad_norm": 1.679435133934021,
1065
+ "learning_rate": 4.934238559694448e-06,
1066
+ "loss": 0.9544,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.7414634146341463,
1071
+ "grad_norm": 2.03104305267334,
1072
+ "learning_rate": 4.9333627468545845e-06,
1073
+ "loss": 0.6214,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.7463414634146341,
1078
+ "grad_norm": 1.6827820539474487,
1079
+ "learning_rate": 4.932481219244231e-06,
1080
+ "loss": 0.7024,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.751219512195122,
1085
+ "grad_norm": 1.92439603805542,
1086
+ "learning_rate": 4.931593978933666e-06,
1087
+ "loss": 0.6718,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.7560975609756098,
1092
+ "grad_norm": 1.4603160619735718,
1093
+ "learning_rate": 4.930701028006577e-06,
1094
+ "loss": 0.843,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.7609756097560976,
1099
+ "grad_norm": 2.8143606185913086,
1100
+ "learning_rate": 4.929802368560066e-06,
1101
+ "loss": 0.6528,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.7658536585365854,
1106
+ "grad_norm": 1.8976019620895386,
1107
+ "learning_rate": 4.928898002704642e-06,
1108
+ "loss": 0.7805,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.7707317073170732,
1113
+ "grad_norm": 1.811642050743103,
1114
+ "learning_rate": 4.927987932564215e-06,
1115
+ "loss": 0.6496,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.775609756097561,
1120
+ "grad_norm": 1.4345223903656006,
1121
+ "learning_rate": 4.927072160276092e-06,
1122
+ "loss": 0.6856,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.7804878048780488,
1127
+ "grad_norm": 3.1401326656341553,
1128
+ "learning_rate": 4.926150687990969e-06,
1129
+ "loss": 0.5397,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.7853658536585366,
1134
+ "grad_norm": 2.784783124923706,
1135
+ "learning_rate": 4.925223517872934e-06,
1136
+ "loss": 0.8164,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.7902439024390244,
1141
+ "grad_norm": 2.388042449951172,
1142
+ "learning_rate": 4.9242906520994484e-06,
1143
+ "loss": 0.8993,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.7951219512195122,
1148
+ "grad_norm": 1.573328971862793,
1149
+ "learning_rate": 4.923352092861358e-06,
1150
+ "loss": 0.754,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.8,
1155
+ "grad_norm": 1.765645980834961,
1156
+ "learning_rate": 4.922407842362875e-06,
1157
+ "loss": 0.5589,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.8048780487804879,
1162
+ "grad_norm": 1.603736400604248,
1163
+ "learning_rate": 4.921457902821578e-06,
1164
+ "loss": 0.8421,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.8097560975609757,
1169
+ "grad_norm": 1.7012734413146973,
1170
+ "learning_rate": 4.920502276468408e-06,
1171
+ "loss": 0.7829,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.8146341463414634,
1176
+ "grad_norm": 1.4824273586273193,
1177
+ "learning_rate": 4.9195409655476605e-06,
1178
+ "loss": 0.6344,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.8195121951219512,
1183
+ "grad_norm": 1.7648383378982544,
1184
+ "learning_rate": 4.918573972316982e-06,
1185
+ "loss": 0.8857,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.824390243902439,
1190
+ "grad_norm": 1.6718090772628784,
1191
+ "learning_rate": 4.917601299047361e-06,
1192
+ "loss": 0.7153,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.8292682926829268,
1197
+ "grad_norm": 1.5050429105758667,
1198
+ "learning_rate": 4.916622948023129e-06,
1199
+ "loss": 0.6855,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.8341463414634146,
1204
+ "grad_norm": 1.5966042280197144,
1205
+ "learning_rate": 4.915638921541952e-06,
1206
+ "loss": 0.5559,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.8390243902439024,
1211
+ "grad_norm": 2.0568573474884033,
1212
+ "learning_rate": 4.914649221914822e-06,
1213
+ "loss": 0.7972,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.8439024390243902,
1218
+ "grad_norm": 1.8847912549972534,
1219
+ "learning_rate": 4.913653851466057e-06,
1220
+ "loss": 0.572,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.848780487804878,
1225
+ "grad_norm": 1.6164286136627197,
1226
+ "learning_rate": 4.912652812533291e-06,
1227
+ "loss": 0.7195,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.8536585365853658,
1232
+ "grad_norm": 1.5945544242858887,
1233
+ "learning_rate": 4.911646107467472e-06,
1234
+ "loss": 0.7432,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.8585365853658536,
1239
+ "grad_norm": 1.3156569004058838,
1240
+ "learning_rate": 4.9106337386328524e-06,
1241
+ "loss": 0.8753,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.8634146341463415,
1246
+ "grad_norm": 1.6262340545654297,
1247
+ "learning_rate": 4.909615708406991e-06,
1248
+ "loss": 0.7642,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.8682926829268293,
1253
+ "grad_norm": 1.4175578355789185,
1254
+ "learning_rate": 4.908592019180738e-06,
1255
+ "loss": 0.5936,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.8731707317073171,
1260
+ "grad_norm": 1.1894031763076782,
1261
+ "learning_rate": 4.907562673358234e-06,
1262
+ "loss": 0.5751,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.8780487804878049,
1267
+ "grad_norm": 1.251502275466919,
1268
+ "learning_rate": 4.906527673356907e-06,
1269
+ "loss": 0.5285,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.8829268292682927,
1274
+ "grad_norm": 1.7352757453918457,
1275
+ "learning_rate": 4.905487021607462e-06,
1276
+ "loss": 0.4379,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.8878048780487805,
1281
+ "grad_norm": 1.9421669244766235,
1282
+ "learning_rate": 4.904440720553876e-06,
1283
+ "loss": 0.7487,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.8926829268292683,
1288
+ "grad_norm": 1.370103120803833,
1289
+ "learning_rate": 4.903388772653396e-06,
1290
+ "loss": 0.6868,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.8975609756097561,
1295
+ "grad_norm": 1.7440688610076904,
1296
+ "learning_rate": 4.902331180376529e-06,
1297
+ "loss": 0.7203,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.9024390243902439,
1302
+ "grad_norm": 1.4112497568130493,
1303
+ "learning_rate": 4.901267946207038e-06,
1304
+ "loss": 0.8253,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.9073170731707317,
1309
+ "grad_norm": 1.677984356880188,
1310
+ "learning_rate": 4.900199072641937e-06,
1311
+ "loss": 0.6319,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.9121951219512195,
1316
+ "grad_norm": 1.313682198524475,
1317
+ "learning_rate": 4.899124562191484e-06,
1318
+ "loss": 0.5418,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.9170731707317074,
1323
+ "grad_norm": 1.233353853225708,
1324
+ "learning_rate": 4.8980444173791735e-06,
1325
+ "loss": 0.4473,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.9219512195121952,
1330
+ "grad_norm": 1.7652136087417603,
1331
+ "learning_rate": 4.896958640741735e-06,
1332
+ "loss": 0.765,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.926829268292683,
1337
+ "grad_norm": 1.6560442447662354,
1338
+ "learning_rate": 4.895867234829121e-06,
1339
+ "loss": 0.8341,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.9317073170731708,
1344
+ "grad_norm": 1.4490306377410889,
1345
+ "learning_rate": 4.894770202204509e-06,
1346
+ "loss": 0.6267,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.9365853658536586,
1351
+ "grad_norm": 2.1652960777282715,
1352
+ "learning_rate": 4.893667545444285e-06,
1353
+ "loss": 0.75,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.9414634146341463,
1358
+ "grad_norm": 1.3940919637680054,
1359
+ "learning_rate": 4.8925592671380495e-06,
1360
+ "loss": 0.599,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.9463414634146341,
1365
+ "grad_norm": 1.0715932846069336,
1366
+ "learning_rate": 4.891445369888601e-06,
1367
+ "loss": 0.4761,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.9512195121951219,
1372
+ "grad_norm": 1.3872371912002563,
1373
+ "learning_rate": 4.890325856311936e-06,
1374
+ "loss": 0.7884,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.9560975609756097,
1379
+ "grad_norm": 1.485743522644043,
1380
+ "learning_rate": 4.889200729037241e-06,
1381
+ "loss": 0.7216,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.9609756097560975,
1386
+ "grad_norm": 1.3263616561889648,
1387
+ "learning_rate": 4.888069990706884e-06,
1388
+ "loss": 0.5775,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.9658536585365853,
1393
+ "grad_norm": 3.2764222621917725,
1394
+ "learning_rate": 4.886933643976414e-06,
1395
+ "loss": 0.4755,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.9707317073170731,
1400
+ "grad_norm": 1.3251742124557495,
1401
+ "learning_rate": 4.885791691514548e-06,
1402
+ "loss": 0.4295,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.975609756097561,
1407
+ "grad_norm": 1.2534489631652832,
1408
+ "learning_rate": 4.884644136003172e-06,
1409
+ "loss": 0.5451,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.9804878048780488,
1414
+ "grad_norm": 1.5479427576065063,
1415
+ "learning_rate": 4.883490980137327e-06,
1416
+ "loss": 1.1673,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.9853658536585366,
1421
+ "grad_norm": 1.5993766784667969,
1422
+ "learning_rate": 4.882332226625208e-06,
1423
+ "loss": 0.6849,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.9902439024390244,
1428
+ "grad_norm": 1.1724447011947632,
1429
+ "learning_rate": 4.881167878188158e-06,
1430
+ "loss": 0.7465,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.9951219512195122,
1435
+ "grad_norm": 1.5650769472122192,
1436
+ "learning_rate": 4.8799979375606565e-06,
1437
+ "loss": 0.6518,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 1.0,
1442
+ "grad_norm": 1.4839268922805786,
1443
+ "learning_rate": 4.878822407490319e-06,
1444
+ "loss": 0.6304,
1445
+ "step": 205
1446
+ }
1447
+ ],
1448
+ "logging_steps": 1,
1449
+ "max_steps": 2050,
1450
+ "num_input_tokens_seen": 0,
1451
+ "num_train_epochs": 10,
1452
+ "save_steps": 500,
1453
+ "stateful_callbacks": {
1454
+ "TrainerControl": {
1455
+ "args": {
1456
+ "should_epoch_stop": false,
1457
+ "should_evaluate": false,
1458
+ "should_log": false,
1459
+ "should_save": true,
1460
+ "should_training_stop": false
1461
+ },
1462
+ "attributes": {}
1463
+ }
1464
+ },
1465
+ "total_flos": 6.049419025291674e+16,
1466
+ "train_batch_size": 1,
1467
+ "trial_name": null,
1468
+ "trial_params": null
1469
+ }
qwen2_5_math_7b/limo/checkpoint-205/vocab.json ADDED
The diff for this file is too large to render. See raw diff