KublaiKhan1 commited on
Commit
0c7163c
·
verified ·
1 Parent(s): 4d317de

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1496/tokenizer_config.json +208 -0
  2. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1496/vocab.json +0 -0
  3. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/added_tokens.json +24 -0
  4. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/chat_template.jinja +54 -0
  5. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/config.json +58 -0
  6. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/generation_config.json +9 -0
  7. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/merges.txt +0 -0
  8. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/model.safetensors.index.json +347 -0
  9. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/special_tokens_map.json +31 -0
  10. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/tokenizer_config.json +208 -0
  11. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/trainer_state.json +0 -0
  12. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/vocab.json +0 -0
  13. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/added_tokens.json +24 -0
  14. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/chat_template.jinja +54 -0
  15. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/config.json +58 -0
  16. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/generation_config.json +9 -0
  17. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/merges.txt +0 -0
  18. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/model.safetensors.index.json +347 -0
  19. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/special_tokens_map.json +31 -0
  20. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/tokenizer_config.json +208 -0
  21. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/trainer_state.json +1343 -0
  22. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/vocab.json +0 -0
  23. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/added_tokens.json +24 -0
  24. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/chat_template.jinja +54 -0
  25. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/config.json +58 -0
  26. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/generation_config.json +9 -0
  27. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/merges.txt +0 -0
  28. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/model.safetensors.index.json +347 -0
  29. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/special_tokens_map.json +31 -0
  30. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/trainer_state.json +2652 -0
  31. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/vocab.json +0 -0
  32. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/added_tokens.json +24 -0
  33. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/chat_template.jinja +54 -0
  34. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/config.json +58 -0
  35. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/generation_config.json +9 -0
  36. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/merges.txt +0 -0
  37. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/model.safetensors.index.json +347 -0
  38. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/special_tokens_map.json +31 -0
  39. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/tokenizer_config.json +208 -0
  40. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/trainer_state.json +0 -0
  41. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/vocab.json +0 -0
  42. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/added_tokens.json +24 -0
  43. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/chat_template.jinja +54 -0
  44. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/config.json +58 -0
  45. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/generation_config.json +9 -0
  46. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/merges.txt +0 -0
  47. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/model.safetensors.index.json +347 -0
  48. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/special_tokens_map.json +31 -0
  49. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/tokenizer_config.json +208 -0
  50. qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/trainer_state.json +0 -0
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1496/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1496/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/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 %}
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 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": 10000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "4.55.0"
9
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-1683/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- '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 %}
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 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": 10000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "4.55.0"
9
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/trainer_state.json ADDED
@@ -0,0 +1,1343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 187,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0053475935828877,
14
+ "grad_norm": 32.667198181152344,
15
+ "learning_rate": 5e-06,
16
+ "loss": 3.2539,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0106951871657754,
21
+ "grad_norm": 38.2481803894043,
22
+ "learning_rate": 4.99999647201733e-06,
23
+ "loss": 6.258,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.016042780748663103,
28
+ "grad_norm": 26.6931209564209,
29
+ "learning_rate": 4.999985888079276e-06,
30
+ "loss": 2.4767,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0213903743315508,
35
+ "grad_norm": 36.4799919128418,
36
+ "learning_rate": 4.999968248215712e-06,
37
+ "loss": 5.4026,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.026737967914438502,
42
+ "grad_norm": 23.325607299804688,
43
+ "learning_rate": 4.999943552476422e-06,
44
+ "loss": 3.818,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.03208556149732621,
49
+ "grad_norm": 17.09689712524414,
50
+ "learning_rate": 4.999911800931108e-06,
51
+ "loss": 2.7186,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0374331550802139,
56
+ "grad_norm": 6.150149345397949,
57
+ "learning_rate": 4.999872993669387e-06,
58
+ "loss": 1.2419,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0427807486631016,
63
+ "grad_norm": 8.962457656860352,
64
+ "learning_rate": 4.999827130800785e-06,
65
+ "loss": 2.443,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0481283422459893,
70
+ "grad_norm": 17.777889251708984,
71
+ "learning_rate": 4.999774212454746e-06,
72
+ "loss": 3.1664,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.053475935828877004,
77
+ "grad_norm": 6.9644694328308105,
78
+ "learning_rate": 4.999714238780626e-06,
79
+ "loss": 2.4137,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.058823529411764705,
84
+ "grad_norm": 7.578589916229248,
85
+ "learning_rate": 4.999647209947694e-06,
86
+ "loss": 2.2937,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.06417112299465241,
91
+ "grad_norm": 5.47304630279541,
92
+ "learning_rate": 4.999573126145132e-06,
93
+ "loss": 2.1922,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.06951871657754011,
98
+ "grad_norm": 4.273566246032715,
99
+ "learning_rate": 4.999491987582032e-06,
100
+ "loss": 1.5914,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0748663101604278,
105
+ "grad_norm": 7.62272310256958,
106
+ "learning_rate": 4.999403794487399e-06,
107
+ "loss": 2.5434,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.08021390374331551,
112
+ "grad_norm": 4.374003887176514,
113
+ "learning_rate": 4.999308547110147e-06,
114
+ "loss": 1.6044,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0855614973262032,
119
+ "grad_norm": 3.7834177017211914,
120
+ "learning_rate": 4.9992062457191005e-06,
121
+ "loss": 1.6413,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.09090909090909091,
126
+ "grad_norm": 3.5481460094451904,
127
+ "learning_rate": 4.999096890602996e-06,
128
+ "loss": 1.601,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0962566844919786,
133
+ "grad_norm": 4.520628452301025,
134
+ "learning_rate": 4.998980482070473e-06,
135
+ "loss": 1.7445,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.10160427807486631,
140
+ "grad_norm": 4.576196670532227,
141
+ "learning_rate": 4.998857020450084e-06,
142
+ "loss": 2.3176,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.10695187165775401,
147
+ "grad_norm": 3.1453230381011963,
148
+ "learning_rate": 4.998726506090283e-06,
149
+ "loss": 1.3387,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.11229946524064172,
154
+ "grad_norm": 2.1666250228881836,
155
+ "learning_rate": 4.998588939359435e-06,
156
+ "loss": 1.0422,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.11764705882352941,
161
+ "grad_norm": 4.155343532562256,
162
+ "learning_rate": 4.998444320645803e-06,
163
+ "loss": 1.8809,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.12299465240641712,
168
+ "grad_norm": 3.580847978591919,
169
+ "learning_rate": 4.998292650357558e-06,
170
+ "loss": 1.5926,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.12834224598930483,
175
+ "grad_norm": 5.140923976898193,
176
+ "learning_rate": 4.998133928922773e-06,
177
+ "loss": 2.4575,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.13368983957219252,
182
+ "grad_norm": 4.047446250915527,
183
+ "learning_rate": 4.99796815678942e-06,
184
+ "loss": 1.3485,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.13903743315508021,
189
+ "grad_norm": 4.0677571296691895,
190
+ "learning_rate": 4.997795334425372e-06,
191
+ "loss": 1.9172,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.1443850267379679,
196
+ "grad_norm": 5.883276462554932,
197
+ "learning_rate": 4.997615462318403e-06,
198
+ "loss": 2.1168,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.1497326203208556,
203
+ "grad_norm": 3.6615514755249023,
204
+ "learning_rate": 4.997428540976177e-06,
205
+ "loss": 1.5822,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.15508021390374332,
210
+ "grad_norm": 2.608039617538452,
211
+ "learning_rate": 4.997234570926263e-06,
212
+ "loss": 1.2184,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.16042780748663102,
217
+ "grad_norm": 2.280423879623413,
218
+ "learning_rate": 4.997033552716116e-06,
219
+ "loss": 1.0216,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.1657754010695187,
224
+ "grad_norm": 1.7143268585205078,
225
+ "learning_rate": 4.9968254869130885e-06,
226
+ "loss": 0.9795,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.1711229946524064,
231
+ "grad_norm": 1.4858453273773193,
232
+ "learning_rate": 4.996610374104422e-06,
233
+ "loss": 0.7698,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.17647058823529413,
238
+ "grad_norm": 1.51152503490448,
239
+ "learning_rate": 4.9963882148972475e-06,
240
+ "loss": 1.3918,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.18181818181818182,
245
+ "grad_norm": 1.6170848608016968,
246
+ "learning_rate": 4.996159009918586e-06,
247
+ "loss": 1.1074,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.18716577540106952,
252
+ "grad_norm": 2.591637372970581,
253
+ "learning_rate": 4.9959227598153395e-06,
254
+ "loss": 1.4097,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.1925133689839572,
259
+ "grad_norm": 2.9409682750701904,
260
+ "learning_rate": 4.9956794652542994e-06,
261
+ "loss": 1.6475,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.19786096256684493,
266
+ "grad_norm": 1.9114937782287598,
267
+ "learning_rate": 4.9954291269221364e-06,
268
+ "loss": 1.0298,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.20320855614973263,
273
+ "grad_norm": 4.106937408447266,
274
+ "learning_rate": 4.995171745525401e-06,
275
+ "loss": 1.6997,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.20855614973262032,
280
+ "grad_norm": 4.7484822273254395,
281
+ "learning_rate": 4.994907321790524e-06,
282
+ "loss": 1.4041,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.21390374331550802,
287
+ "grad_norm": 2.5232057571411133,
288
+ "learning_rate": 4.994635856463811e-06,
289
+ "loss": 1.023,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2192513368983957,
294
+ "grad_norm": 2.975825548171997,
295
+ "learning_rate": 4.994357350311441e-06,
296
+ "loss": 1.6556,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.22459893048128343,
301
+ "grad_norm": 2.3416595458984375,
302
+ "learning_rate": 4.994071804119467e-06,
303
+ "loss": 1.2464,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.22994652406417113,
308
+ "grad_norm": 3.6734139919281006,
309
+ "learning_rate": 4.993779218693811e-06,
310
+ "loss": 1.8306,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.23529411764705882,
315
+ "grad_norm": 2.287463903427124,
316
+ "learning_rate": 4.99347959486026e-06,
317
+ "loss": 1.0122,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.24064171122994651,
322
+ "grad_norm": 1.5980703830718994,
323
+ "learning_rate": 4.99317293346447e-06,
324
+ "loss": 0.8706,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.24598930481283424,
329
+ "grad_norm": 1.4346195459365845,
330
+ "learning_rate": 4.992859235371958e-06,
331
+ "loss": 0.7815,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.25133689839572193,
336
+ "grad_norm": 1.635718822479248,
337
+ "learning_rate": 4.992538501468101e-06,
338
+ "loss": 0.8891,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.25668449197860965,
343
+ "grad_norm": 3.2847158908843994,
344
+ "learning_rate": 4.992210732658132e-06,
345
+ "loss": 1.3393,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.2620320855614973,
350
+ "grad_norm": 3.3003337383270264,
351
+ "learning_rate": 4.991875929867143e-06,
352
+ "loss": 1.4412,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.26737967914438504,
357
+ "grad_norm": 1.588843584060669,
358
+ "learning_rate": 4.991534094040077e-06,
359
+ "loss": 0.8567,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.2727272727272727,
364
+ "grad_norm": 1.4450788497924805,
365
+ "learning_rate": 4.991185226141726e-06,
366
+ "loss": 0.8855,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.27807486631016043,
371
+ "grad_norm": 1.6408952474594116,
372
+ "learning_rate": 4.990829327156729e-06,
373
+ "loss": 1.1081,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.28342245989304815,
378
+ "grad_norm": 1.3315808773040771,
379
+ "learning_rate": 4.990466398089571e-06,
380
+ "loss": 0.9124,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.2887700534759358,
385
+ "grad_norm": 1.460076928138733,
386
+ "learning_rate": 4.99009643996458e-06,
387
+ "loss": 0.6002,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.29411764705882354,
392
+ "grad_norm": 1.4954642057418823,
393
+ "learning_rate": 4.989719453825918e-06,
394
+ "loss": 0.7522,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.2994652406417112,
399
+ "grad_norm": 1.6860841512680054,
400
+ "learning_rate": 4.989335440737587e-06,
401
+ "loss": 0.7829,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.3048128342245989,
406
+ "grad_norm": 1.5118118524551392,
407
+ "learning_rate": 4.9889444017834185e-06,
408
+ "loss": 0.9124,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.31016042780748665,
413
+ "grad_norm": 1.4117275476455688,
414
+ "learning_rate": 4.988546338067078e-06,
415
+ "loss": 0.9708,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.3155080213903743,
420
+ "grad_norm": 2.2665367126464844,
421
+ "learning_rate": 4.988141250712053e-06,
422
+ "loss": 1.1277,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.32085561497326204,
427
+ "grad_norm": 1.3910932540893555,
428
+ "learning_rate": 4.987729140861657e-06,
429
+ "loss": 0.9477,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.32620320855614976,
434
+ "grad_norm": 1.618573784828186,
435
+ "learning_rate": 4.987310009679023e-06,
436
+ "loss": 0.9895,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.3315508021390374,
441
+ "grad_norm": 1.3848469257354736,
442
+ "learning_rate": 4.986883858347101e-06,
443
+ "loss": 0.8927,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.33689839572192515,
448
+ "grad_norm": 1.4412480592727661,
449
+ "learning_rate": 4.986450688068655e-06,
450
+ "loss": 0.657,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.3422459893048128,
455
+ "grad_norm": 1.462384819984436,
456
+ "learning_rate": 4.986010500066258e-06,
457
+ "loss": 0.8561,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.34759358288770054,
462
+ "grad_norm": 1.3507061004638672,
463
+ "learning_rate": 4.985563295582292e-06,
464
+ "loss": 0.8016,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.35294117647058826,
469
+ "grad_norm": 2.146437406539917,
470
+ "learning_rate": 4.98510907587894e-06,
471
+ "loss": 0.9754,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.3582887700534759,
476
+ "grad_norm": 2.181367874145508,
477
+ "learning_rate": 4.984647842238185e-06,
478
+ "loss": 1.2643,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.36363636363636365,
483
+ "grad_norm": 1.5960901975631714,
484
+ "learning_rate": 4.984179595961806e-06,
485
+ "loss": 0.6543,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.3689839572192513,
490
+ "grad_norm": 1.0785574913024902,
491
+ "learning_rate": 4.983704338371375e-06,
492
+ "loss": 0.7784,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.37433155080213903,
497
+ "grad_norm": 1.322706937789917,
498
+ "learning_rate": 4.983222070808255e-06,
499
+ "loss": 0.6633,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.37967914438502676,
504
+ "grad_norm": 1.806099534034729,
505
+ "learning_rate": 4.982732794633588e-06,
506
+ "loss": 1.0887,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.3850267379679144,
511
+ "grad_norm": 1.2431350946426392,
512
+ "learning_rate": 4.982236511228301e-06,
513
+ "loss": 0.8154,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.39037433155080214,
518
+ "grad_norm": 2.1100635528564453,
519
+ "learning_rate": 4.981733221993099e-06,
520
+ "loss": 1.2385,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.39572192513368987,
525
+ "grad_norm": 2.499673843383789,
526
+ "learning_rate": 4.981222928348456e-06,
527
+ "loss": 1.0381,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.40106951871657753,
532
+ "grad_norm": 1.7459089756011963,
533
+ "learning_rate": 4.98070563173462e-06,
534
+ "loss": 0.9279,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.40641711229946526,
539
+ "grad_norm": 1.6326146125793457,
540
+ "learning_rate": 4.980181333611601e-06,
541
+ "loss": 0.7559,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.4117647058823529,
546
+ "grad_norm": 1.2402805089950562,
547
+ "learning_rate": 4.979650035459171e-06,
548
+ "loss": 0.7301,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.41711229946524064,
553
+ "grad_norm": 1.5247249603271484,
554
+ "learning_rate": 4.9791117387768575e-06,
555
+ "loss": 1.1018,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.42245989304812837,
560
+ "grad_norm": 1.19709312915802,
561
+ "learning_rate": 4.978566445083942e-06,
562
+ "loss": 0.6179,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.42780748663101603,
567
+ "grad_norm": 1.3535789251327515,
568
+ "learning_rate": 4.978014155919455e-06,
569
+ "loss": 0.734,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.43315508021390375,
574
+ "grad_norm": 1.3790255784988403,
575
+ "learning_rate": 4.977454872842169e-06,
576
+ "loss": 0.7967,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.4385026737967914,
581
+ "grad_norm": 1.6345816850662231,
582
+ "learning_rate": 4.976888597430597e-06,
583
+ "loss": 1.0332,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.44385026737967914,
588
+ "grad_norm": 1.5695714950561523,
589
+ "learning_rate": 4.976315331282985e-06,
590
+ "loss": 0.9266,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.44919786096256686,
595
+ "grad_norm": 1.2244231700897217,
596
+ "learning_rate": 4.9757350760173144e-06,
597
+ "loss": 0.7738,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.45454545454545453,
602
+ "grad_norm": 1.674436330795288,
603
+ "learning_rate": 4.975147833271288e-06,
604
+ "loss": 1.0436,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.45989304812834225,
609
+ "grad_norm": 1.718598484992981,
610
+ "learning_rate": 4.974553604702332e-06,
611
+ "loss": 0.7659,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.46524064171123,
616
+ "grad_norm": 1.2509411573410034,
617
+ "learning_rate": 4.973952391987589e-06,
618
+ "loss": 0.8631,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.47058823529411764,
623
+ "grad_norm": 1.9576022624969482,
624
+ "learning_rate": 4.9733441968239125e-06,
625
+ "loss": 1.1419,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.47593582887700536,
630
+ "grad_norm": 1.14915132522583,
631
+ "learning_rate": 4.972729020927866e-06,
632
+ "loss": 0.6647,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.48128342245989303,
637
+ "grad_norm": 1.0880329608917236,
638
+ "learning_rate": 4.97210686603571e-06,
639
+ "loss": 0.8533,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.48663101604278075,
644
+ "grad_norm": 1.60923171043396,
645
+ "learning_rate": 4.97147773390341e-06,
646
+ "loss": 0.7872,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.4919786096256685,
651
+ "grad_norm": 2.191762685775757,
652
+ "learning_rate": 4.970841626306617e-06,
653
+ "loss": 0.8983,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.49732620320855614,
658
+ "grad_norm": 1.805025577545166,
659
+ "learning_rate": 4.970198545040673e-06,
660
+ "loss": 1.0416,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.5026737967914439,
665
+ "grad_norm": 1.670198917388916,
666
+ "learning_rate": 4.969548491920603e-06,
667
+ "loss": 0.9088,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.5080213903743316,
672
+ "grad_norm": 1.5051180124282837,
673
+ "learning_rate": 4.968891468781105e-06,
674
+ "loss": 0.9928,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.5133689839572193,
679
+ "grad_norm": 1.380786418914795,
680
+ "learning_rate": 4.968227477476554e-06,
681
+ "loss": 0.8154,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.5187165775401069,
686
+ "grad_norm": 1.744243860244751,
687
+ "learning_rate": 4.9675565198809905e-06,
688
+ "loss": 1.1196,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.5240641711229946,
693
+ "grad_norm": 3.3793137073516846,
694
+ "learning_rate": 4.966878597888114e-06,
695
+ "loss": 0.966,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.5294117647058824,
700
+ "grad_norm": 1.2802485227584839,
701
+ "learning_rate": 4.966193713411284e-06,
702
+ "loss": 0.6863,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.5347593582887701,
707
+ "grad_norm": 1.1910849809646606,
708
+ "learning_rate": 4.965501868383507e-06,
709
+ "loss": 0.6748,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.5401069518716578,
714
+ "grad_norm": 2.020167827606201,
715
+ "learning_rate": 4.964803064757438e-06,
716
+ "loss": 0.9697,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.5454545454545454,
721
+ "grad_norm": 1.1739224195480347,
722
+ "learning_rate": 4.964097304505371e-06,
723
+ "loss": 0.7805,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.5508021390374331,
728
+ "grad_norm": 1.1704705953598022,
729
+ "learning_rate": 4.963384589619233e-06,
730
+ "loss": 0.6536,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.5561497326203209,
735
+ "grad_norm": 1.3174995183944702,
736
+ "learning_rate": 4.962664922110581e-06,
737
+ "loss": 0.8689,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.5614973262032086,
742
+ "grad_norm": 1.2126598358154297,
743
+ "learning_rate": 4.9619383040105954e-06,
744
+ "loss": 0.9955,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.5668449197860963,
749
+ "grad_norm": 1.365536093711853,
750
+ "learning_rate": 4.961204737370071e-06,
751
+ "loss": 0.9104,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.5721925133689839,
756
+ "grad_norm": 1.4193490743637085,
757
+ "learning_rate": 4.960464224259418e-06,
758
+ "loss": 1.1661,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.5775401069518716,
763
+ "grad_norm": 1.108224868774414,
764
+ "learning_rate": 4.95971676676865e-06,
765
+ "loss": 0.5704,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.5828877005347594,
770
+ "grad_norm": 1.0754598379135132,
771
+ "learning_rate": 4.958962367007381e-06,
772
+ "loss": 0.8837,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.5882352941176471,
777
+ "grad_norm": 1.194149374961853,
778
+ "learning_rate": 4.958201027104818e-06,
779
+ "loss": 0.7352,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.5935828877005348,
784
+ "grad_norm": 3.193861246109009,
785
+ "learning_rate": 4.957432749209755e-06,
786
+ "loss": 0.6904,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.5989304812834224,
791
+ "grad_norm": 1.7174736261367798,
792
+ "learning_rate": 4.95665753549057e-06,
793
+ "loss": 0.8564,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.6042780748663101,
798
+ "grad_norm": 1.452724814414978,
799
+ "learning_rate": 4.9558753881352165e-06,
800
+ "loss": 1.2627,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.6096256684491979,
805
+ "grad_norm": 1.489687442779541,
806
+ "learning_rate": 4.955086309351213e-06,
807
+ "loss": 1.0371,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.6149732620320856,
812
+ "grad_norm": 1.0586612224578857,
813
+ "learning_rate": 4.9542903013656485e-06,
814
+ "loss": 0.5672,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.6203208556149733,
819
+ "grad_norm": 1.2536990642547607,
820
+ "learning_rate": 4.953487366425163e-06,
821
+ "loss": 0.7125,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.6256684491978609,
826
+ "grad_norm": 1.1650030612945557,
827
+ "learning_rate": 4.952677506795949e-06,
828
+ "loss": 0.5989,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.6310160427807486,
833
+ "grad_norm": 1.286164402961731,
834
+ "learning_rate": 4.951860724763743e-06,
835
+ "loss": 0.7466,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.6363636363636364,
840
+ "grad_norm": 1.132703423500061,
841
+ "learning_rate": 4.95103702263382e-06,
842
+ "loss": 0.7379,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.6417112299465241,
847
+ "grad_norm": 1.340989589691162,
848
+ "learning_rate": 4.950206402730984e-06,
849
+ "loss": 0.7781,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.6470588235294118,
854
+ "grad_norm": 1.0583947896957397,
855
+ "learning_rate": 4.949368867399567e-06,
856
+ "loss": 0.5383,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.6524064171122995,
861
+ "grad_norm": 1.2740116119384766,
862
+ "learning_rate": 4.948524419003415e-06,
863
+ "loss": 1.185,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.6577540106951871,
868
+ "grad_norm": 1.3854238986968994,
869
+ "learning_rate": 4.947673059925889e-06,
870
+ "loss": 0.8494,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.6631016042780749,
875
+ "grad_norm": 1.0074819326400757,
876
+ "learning_rate": 4.9468147925698525e-06,
877
+ "loss": 0.8941,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.6684491978609626,
882
+ "grad_norm": 1.1346782445907593,
883
+ "learning_rate": 4.945949619357668e-06,
884
+ "loss": 0.6798,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.6737967914438503,
889
+ "grad_norm": 1.1151247024536133,
890
+ "learning_rate": 4.945077542731188e-06,
891
+ "loss": 0.5321,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.679144385026738,
896
+ "grad_norm": 1.3562278747558594,
897
+ "learning_rate": 4.94419856515175e-06,
898
+ "loss": 0.8688,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.6844919786096256,
903
+ "grad_norm": 1.1577609777450562,
904
+ "learning_rate": 4.943312689100166e-06,
905
+ "loss": 0.8504,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.6898395721925134,
910
+ "grad_norm": 1.0710453987121582,
911
+ "learning_rate": 4.942419917076723e-06,
912
+ "loss": 0.6366,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.6951871657754011,
917
+ "grad_norm": 1.153254508972168,
918
+ "learning_rate": 4.941520251601167e-06,
919
+ "loss": 0.7544,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.7005347593582888,
924
+ "grad_norm": 0.9147224426269531,
925
+ "learning_rate": 4.940613695212702e-06,
926
+ "loss": 0.4771,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.7058823529411765,
931
+ "grad_norm": 1.7819873094558716,
932
+ "learning_rate": 4.939700250469979e-06,
933
+ "loss": 1.0403,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.7112299465240641,
938
+ "grad_norm": 1.1828848123550415,
939
+ "learning_rate": 4.938779919951092e-06,
940
+ "loss": 0.8482,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.7165775401069518,
945
+ "grad_norm": 1.1376489400863647,
946
+ "learning_rate": 4.93785270625357e-06,
947
+ "loss": 0.5515,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.7219251336898396,
952
+ "grad_norm": 1.601025938987732,
953
+ "learning_rate": 4.936918611994368e-06,
954
+ "loss": 0.706,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.7272727272727273,
959
+ "grad_norm": 1.2240617275238037,
960
+ "learning_rate": 4.935977639809861e-06,
961
+ "loss": 0.8308,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.732620320855615,
966
+ "grad_norm": 1.088484287261963,
967
+ "learning_rate": 4.935029792355834e-06,
968
+ "loss": 0.642,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.7379679144385026,
973
+ "grad_norm": 1.3206232786178589,
974
+ "learning_rate": 4.934075072307481e-06,
975
+ "loss": 1.0115,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.7433155080213903,
980
+ "grad_norm": 1.1618086099624634,
981
+ "learning_rate": 4.933113482359388e-06,
982
+ "loss": 0.5455,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.7486631016042781,
987
+ "grad_norm": 1.2013949155807495,
988
+ "learning_rate": 4.932145025225535e-06,
989
+ "loss": 0.6958,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.7540106951871658,
994
+ "grad_norm": 1.3020150661468506,
995
+ "learning_rate": 4.931169703639282e-06,
996
+ "loss": 0.8664,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.7593582887700535,
1001
+ "grad_norm": 1.3776401281356812,
1002
+ "learning_rate": 4.930187520353363e-06,
1003
+ "loss": 0.7594,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.7647058823529411,
1008
+ "grad_norm": 1.0648787021636963,
1009
+ "learning_rate": 4.929198478139877e-06,
1010
+ "loss": 0.6382,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.7700534759358288,
1015
+ "grad_norm": 1.1864025592803955,
1016
+ "learning_rate": 4.928202579790285e-06,
1017
+ "loss": 0.5924,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.7754010695187166,
1022
+ "grad_norm": 1.1243900060653687,
1023
+ "learning_rate": 4.927199828115395e-06,
1024
+ "loss": 0.7163,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.7807486631016043,
1029
+ "grad_norm": 1.2532908916473389,
1030
+ "learning_rate": 4.9261902259453616e-06,
1031
+ "loss": 0.8453,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.786096256684492,
1036
+ "grad_norm": 1.3941049575805664,
1037
+ "learning_rate": 4.925173776129669e-06,
1038
+ "loss": 1.0382,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.7914438502673797,
1043
+ "grad_norm": 0.9239159822463989,
1044
+ "learning_rate": 4.9241504815371346e-06,
1045
+ "loss": 0.4883,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.7967914438502673,
1050
+ "grad_norm": 1.1004669666290283,
1051
+ "learning_rate": 4.923120345055887e-06,
1052
+ "loss": 0.7326,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.8021390374331551,
1057
+ "grad_norm": 1.2339757680892944,
1058
+ "learning_rate": 4.922083369593372e-06,
1059
+ "loss": 0.6372,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.8074866310160428,
1064
+ "grad_norm": 1.3842638731002808,
1065
+ "learning_rate": 4.921039558076335e-06,
1066
+ "loss": 0.9323,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.8128342245989305,
1071
+ "grad_norm": 1.7399688959121704,
1072
+ "learning_rate": 4.919988913450812e-06,
1073
+ "loss": 0.4532,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.8181818181818182,
1078
+ "grad_norm": 1.526694893836975,
1079
+ "learning_rate": 4.918931438682132e-06,
1080
+ "loss": 0.8714,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.8235294117647058,
1085
+ "grad_norm": 1.208390712738037,
1086
+ "learning_rate": 4.917867136754894e-06,
1087
+ "loss": 0.8822,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.8288770053475936,
1092
+ "grad_norm": 1.0740225315093994,
1093
+ "learning_rate": 4.916796010672969e-06,
1094
+ "loss": 0.7539,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.8342245989304813,
1099
+ "grad_norm": 1.097008228302002,
1100
+ "learning_rate": 4.91571806345949e-06,
1101
+ "loss": 0.7797,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.839572192513369,
1106
+ "grad_norm": 1.231980800628662,
1107
+ "learning_rate": 4.91463329815684e-06,
1108
+ "loss": 0.8074,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.8449197860962567,
1113
+ "grad_norm": 1.1179982423782349,
1114
+ "learning_rate": 4.913541717826645e-06,
1115
+ "loss": 0.5812,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.8502673796791443,
1120
+ "grad_norm": 0.9882096648216248,
1121
+ "learning_rate": 4.912443325549767e-06,
1122
+ "loss": 0.4967,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.8556149732620321,
1127
+ "grad_norm": 1.3861775398254395,
1128
+ "learning_rate": 4.911338124426291e-06,
1129
+ "loss": 0.7436,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.8609625668449198,
1134
+ "grad_norm": 1.204852819442749,
1135
+ "learning_rate": 4.910226117575525e-06,
1136
+ "loss": 0.8118,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.8663101604278075,
1141
+ "grad_norm": 0.9527103304862976,
1142
+ "learning_rate": 4.909107308135978e-06,
1143
+ "loss": 0.5164,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.8716577540106952,
1148
+ "grad_norm": 1.0612897872924805,
1149
+ "learning_rate": 4.907981699265364e-06,
1150
+ "loss": 0.5894,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.8770053475935828,
1155
+ "grad_norm": 1.610545039176941,
1156
+ "learning_rate": 4.906849294140587e-06,
1157
+ "loss": 0.8476,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.8823529411764706,
1162
+ "grad_norm": 1.483162760734558,
1163
+ "learning_rate": 4.9057100959577285e-06,
1164
+ "loss": 0.6834,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.8877005347593583,
1169
+ "grad_norm": 1.2938721179962158,
1170
+ "learning_rate": 4.904564107932048e-06,
1171
+ "loss": 0.944,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.893048128342246,
1176
+ "grad_norm": 1.2777775526046753,
1177
+ "learning_rate": 4.903411333297966e-06,
1178
+ "loss": 0.8709,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.8983957219251337,
1183
+ "grad_norm": 1.1637930870056152,
1184
+ "learning_rate": 4.902251775309057e-06,
1185
+ "loss": 0.7839,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.9037433155080213,
1190
+ "grad_norm": 2.035766363143921,
1191
+ "learning_rate": 4.901085437238041e-06,
1192
+ "loss": 0.5654,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.9090909090909091,
1197
+ "grad_norm": 1.155563473701477,
1198
+ "learning_rate": 4.899912322376776e-06,
1199
+ "loss": 0.9413,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.9144385026737968,
1204
+ "grad_norm": 1.466346263885498,
1205
+ "learning_rate": 4.8987324340362445e-06,
1206
+ "loss": 0.8642,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.9197860962566845,
1211
+ "grad_norm": 1.1183879375457764,
1212
+ "learning_rate": 4.897545775546545e-06,
1213
+ "loss": 0.7851,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.9251336898395722,
1218
+ "grad_norm": 1.460421085357666,
1219
+ "learning_rate": 4.8963523502568886e-06,
1220
+ "loss": 1.0241,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.93048128342246,
1225
+ "grad_norm": 1.4027538299560547,
1226
+ "learning_rate": 4.895152161535582e-06,
1227
+ "loss": 0.7254,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.9358288770053476,
1232
+ "grad_norm": 1.183846116065979,
1233
+ "learning_rate": 4.893945212770019e-06,
1234
+ "loss": 0.6877,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.9411764705882353,
1239
+ "grad_norm": 1.288653016090393,
1240
+ "learning_rate": 4.892731507366678e-06,
1241
+ "loss": 0.8022,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.946524064171123,
1246
+ "grad_norm": 1.063643455505371,
1247
+ "learning_rate": 4.891511048751102e-06,
1248
+ "loss": 0.7123,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.9518716577540107,
1253
+ "grad_norm": 1.2285932302474976,
1254
+ "learning_rate": 4.890283840367898e-06,
1255
+ "loss": 1.1568,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.9572192513368984,
1260
+ "grad_norm": 1.3358500003814697,
1261
+ "learning_rate": 4.889049885680721e-06,
1262
+ "loss": 0.7538,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.9625668449197861,
1267
+ "grad_norm": 1.2650320529937744,
1268
+ "learning_rate": 4.887809188172268e-06,
1269
+ "loss": 0.683,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.9679144385026738,
1274
+ "grad_norm": 1.1596193313598633,
1275
+ "learning_rate": 4.886561751344266e-06,
1276
+ "loss": 0.7824,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.9732620320855615,
1281
+ "grad_norm": 1.2235304117202759,
1282
+ "learning_rate": 4.885307578717464e-06,
1283
+ "loss": 0.7969,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.9786096256684492,
1288
+ "grad_norm": 1.364279866218567,
1289
+ "learning_rate": 4.8840466738316216e-06,
1290
+ "loss": 0.8376,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.983957219251337,
1295
+ "grad_norm": 1.3247216939926147,
1296
+ "learning_rate": 4.882779040245499e-06,
1297
+ "loss": 0.7356,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.9893048128342246,
1302
+ "grad_norm": 1.0848944187164307,
1303
+ "learning_rate": 4.881504681536847e-06,
1304
+ "loss": 0.5837,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.9946524064171123,
1309
+ "grad_norm": 1.0679181814193726,
1310
+ "learning_rate": 4.880223601302398e-06,
1311
+ "loss": 0.5883,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 1.0,
1316
+ "grad_norm": 1.0577597618103027,
1317
+ "learning_rate": 4.878935803157856e-06,
1318
+ "loss": 0.5789,
1319
+ "step": 187
1320
+ }
1321
+ ],
1322
+ "logging_steps": 1,
1323
+ "max_steps": 1870,
1324
+ "num_input_tokens_seen": 0,
1325
+ "num_train_epochs": 10,
1326
+ "save_steps": 208,
1327
+ "stateful_callbacks": {
1328
+ "TrainerControl": {
1329
+ "args": {
1330
+ "should_epoch_stop": false,
1331
+ "should_evaluate": false,
1332
+ "should_log": false,
1333
+ "should_save": true,
1334
+ "should_training_stop": false
1335
+ },
1336
+ "attributes": {}
1337
+ }
1338
+ },
1339
+ "total_flos": 5.12625839397929e+16,
1340
+ "train_batch_size": 1,
1341
+ "trial_name": null,
1342
+ "trial_params": null
1343
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-187/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/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 %}
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 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": 10000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "4.55.0"
9
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/trainer_state.json ADDED
@@ -0,0 +1,2652 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 374,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0053475935828877,
14
+ "grad_norm": 33.1566276550293,
15
+ "learning_rate": 5e-06,
16
+ "loss": 3.2546,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0106951871657754,
21
+ "grad_norm": 38.23825454711914,
22
+ "learning_rate": 4.99999647201733e-06,
23
+ "loss": 6.2602,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.016042780748663103,
28
+ "grad_norm": 26.855318069458008,
29
+ "learning_rate": 4.999985888079276e-06,
30
+ "loss": 2.4817,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0213903743315508,
35
+ "grad_norm": 36.444278717041016,
36
+ "learning_rate": 4.999968248215712e-06,
37
+ "loss": 5.4087,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.026737967914438502,
42
+ "grad_norm": 23.40522003173828,
43
+ "learning_rate": 4.999943552476422e-06,
44
+ "loss": 3.8247,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.03208556149732621,
49
+ "grad_norm": 17.143104553222656,
50
+ "learning_rate": 4.999911800931108e-06,
51
+ "loss": 2.721,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0374331550802139,
56
+ "grad_norm": 6.178084373474121,
57
+ "learning_rate": 4.999872993669387e-06,
58
+ "loss": 1.2431,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0427807486631016,
63
+ "grad_norm": 9.11890697479248,
64
+ "learning_rate": 4.999827130800785e-06,
65
+ "loss": 2.4435,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0481283422459893,
70
+ "grad_norm": 17.97541046142578,
71
+ "learning_rate": 4.999774212454746e-06,
72
+ "loss": 3.1703,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.053475935828877004,
77
+ "grad_norm": 7.057154655456543,
78
+ "learning_rate": 4.999714238780626e-06,
79
+ "loss": 2.4133,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.058823529411764705,
84
+ "grad_norm": 6.11304235458374,
85
+ "learning_rate": 4.999647209947694e-06,
86
+ "loss": 2.2949,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.06417112299465241,
91
+ "grad_norm": 5.536357402801514,
92
+ "learning_rate": 4.999573126145132e-06,
93
+ "loss": 2.1922,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.06951871657754011,
98
+ "grad_norm": 4.266939640045166,
99
+ "learning_rate": 4.999491987582032e-06,
100
+ "loss": 1.5896,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0748663101604278,
105
+ "grad_norm": 7.528456211090088,
106
+ "learning_rate": 4.999403794487399e-06,
107
+ "loss": 2.5367,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.08021390374331551,
112
+ "grad_norm": 4.016458511352539,
113
+ "learning_rate": 4.999308547110147e-06,
114
+ "loss": 1.5976,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0855614973262032,
119
+ "grad_norm": 3.720717191696167,
120
+ "learning_rate": 4.9992062457191005e-06,
121
+ "loss": 1.6389,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.09090909090909091,
126
+ "grad_norm": 3.6238253116607666,
127
+ "learning_rate": 4.999096890602996e-06,
128
+ "loss": 1.5972,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0962566844919786,
133
+ "grad_norm": 4.565600395202637,
134
+ "learning_rate": 4.998980482070473e-06,
135
+ "loss": 1.7411,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.10160427807486631,
140
+ "grad_norm": 4.566473484039307,
141
+ "learning_rate": 4.998857020450084e-06,
142
+ "loss": 2.314,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.10695187165775401,
147
+ "grad_norm": 2.8942017555236816,
148
+ "learning_rate": 4.998726506090283e-06,
149
+ "loss": 1.3353,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.11229946524064172,
154
+ "grad_norm": 2.2742292881011963,
155
+ "learning_rate": 4.998588939359435e-06,
156
+ "loss": 1.0411,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.11764705882352941,
161
+ "grad_norm": 3.9768784046173096,
162
+ "learning_rate": 4.998444320645803e-06,
163
+ "loss": 1.8797,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.12299465240641712,
168
+ "grad_norm": 3.5094716548919678,
169
+ "learning_rate": 4.998292650357558e-06,
170
+ "loss": 1.5896,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.12834224598930483,
175
+ "grad_norm": 5.135786056518555,
176
+ "learning_rate": 4.998133928922773e-06,
177
+ "loss": 2.4532,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.13368983957219252,
182
+ "grad_norm": 4.1221137046813965,
183
+ "learning_rate": 4.99796815678942e-06,
184
+ "loss": 1.345,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.13903743315508021,
189
+ "grad_norm": 4.138923168182373,
190
+ "learning_rate": 4.997795334425372e-06,
191
+ "loss": 1.9137,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.1443850267379679,
196
+ "grad_norm": 5.832969665527344,
197
+ "learning_rate": 4.997615462318403e-06,
198
+ "loss": 2.1113,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.1497326203208556,
203
+ "grad_norm": 3.526876211166382,
204
+ "learning_rate": 4.997428540976177e-06,
205
+ "loss": 1.5781,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.15508021390374332,
210
+ "grad_norm": 2.8027870655059814,
211
+ "learning_rate": 4.997234570926263e-06,
212
+ "loss": 1.2156,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.16042780748663102,
217
+ "grad_norm": 2.06381893157959,
218
+ "learning_rate": 4.997033552716116e-06,
219
+ "loss": 1.0182,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.1657754010695187,
224
+ "grad_norm": 1.7289892435073853,
225
+ "learning_rate": 4.9968254869130885e-06,
226
+ "loss": 0.9784,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.1711229946524064,
231
+ "grad_norm": 1.4886785745620728,
232
+ "learning_rate": 4.996610374104422e-06,
233
+ "loss": 0.7698,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.17647058823529413,
238
+ "grad_norm": 1.5368430614471436,
239
+ "learning_rate": 4.9963882148972475e-06,
240
+ "loss": 1.3913,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.18181818181818182,
245
+ "grad_norm": 1.6178289651870728,
246
+ "learning_rate": 4.996159009918586e-06,
247
+ "loss": 1.107,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.18716577540106952,
252
+ "grad_norm": 3.0166125297546387,
253
+ "learning_rate": 4.9959227598153395e-06,
254
+ "loss": 1.4073,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.1925133689839572,
259
+ "grad_norm": 2.9860498905181885,
260
+ "learning_rate": 4.9956794652542994e-06,
261
+ "loss": 1.6449,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.19786096256684493,
266
+ "grad_norm": 1.8518357276916504,
267
+ "learning_rate": 4.9954291269221364e-06,
268
+ "loss": 1.027,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.20320855614973263,
273
+ "grad_norm": 4.099643230438232,
274
+ "learning_rate": 4.995171745525401e-06,
275
+ "loss": 1.6984,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.20855614973262032,
280
+ "grad_norm": 4.766246318817139,
281
+ "learning_rate": 4.994907321790524e-06,
282
+ "loss": 1.404,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.21390374331550802,
287
+ "grad_norm": 2.479170322418213,
288
+ "learning_rate": 4.994635856463811e-06,
289
+ "loss": 1.0219,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2192513368983957,
294
+ "grad_norm": 3.09324312210083,
295
+ "learning_rate": 4.994357350311441e-06,
296
+ "loss": 1.6548,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.22459893048128343,
301
+ "grad_norm": 2.2945520877838135,
302
+ "learning_rate": 4.994071804119467e-06,
303
+ "loss": 1.2466,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.22994652406417113,
308
+ "grad_norm": 3.7042086124420166,
309
+ "learning_rate": 4.993779218693811e-06,
310
+ "loss": 1.8289,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.23529411764705882,
315
+ "grad_norm": 2.2880146503448486,
316
+ "learning_rate": 4.99347959486026e-06,
317
+ "loss": 1.0114,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.24064171122994651,
322
+ "grad_norm": 1.4041022062301636,
323
+ "learning_rate": 4.99317293346447e-06,
324
+ "loss": 0.8712,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.24598930481283424,
329
+ "grad_norm": 1.4102976322174072,
330
+ "learning_rate": 4.992859235371958e-06,
331
+ "loss": 0.7802,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.25133689839572193,
336
+ "grad_norm": 1.7079635858535767,
337
+ "learning_rate": 4.992538501468101e-06,
338
+ "loss": 0.8861,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.25668449197860965,
343
+ "grad_norm": 2.992180585861206,
344
+ "learning_rate": 4.992210732658132e-06,
345
+ "loss": 1.3396,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.2620320855614973,
350
+ "grad_norm": 3.28358793258667,
351
+ "learning_rate": 4.991875929867143e-06,
352
+ "loss": 1.438,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.26737967914438504,
357
+ "grad_norm": 1.6233373880386353,
358
+ "learning_rate": 4.991534094040077e-06,
359
+ "loss": 0.8549,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.2727272727272727,
364
+ "grad_norm": 1.4550182819366455,
365
+ "learning_rate": 4.991185226141726e-06,
366
+ "loss": 0.8859,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.27807486631016043,
371
+ "grad_norm": 1.6386096477508545,
372
+ "learning_rate": 4.990829327156729e-06,
373
+ "loss": 1.1078,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.28342245989304815,
378
+ "grad_norm": 1.3336036205291748,
379
+ "learning_rate": 4.990466398089571e-06,
380
+ "loss": 0.9122,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.2887700534759358,
385
+ "grad_norm": 1.359571099281311,
386
+ "learning_rate": 4.99009643996458e-06,
387
+ "loss": 0.6012,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.29411764705882354,
392
+ "grad_norm": 1.5287796258926392,
393
+ "learning_rate": 4.989719453825918e-06,
394
+ "loss": 0.752,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.2994652406417112,
399
+ "grad_norm": 1.6703654527664185,
400
+ "learning_rate": 4.989335440737587e-06,
401
+ "loss": 0.7823,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.3048128342245989,
406
+ "grad_norm": 1.5529050827026367,
407
+ "learning_rate": 4.9889444017834185e-06,
408
+ "loss": 0.9121,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.31016042780748665,
413
+ "grad_norm": 1.4322819709777832,
414
+ "learning_rate": 4.988546338067078e-06,
415
+ "loss": 0.9703,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.3155080213903743,
420
+ "grad_norm": 2.0150718688964844,
421
+ "learning_rate": 4.988141250712053e-06,
422
+ "loss": 1.1246,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.32085561497326204,
427
+ "grad_norm": 1.3878353834152222,
428
+ "learning_rate": 4.987729140861657e-06,
429
+ "loss": 0.9471,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.32620320855614976,
434
+ "grad_norm": 1.6087543964385986,
435
+ "learning_rate": 4.987310009679023e-06,
436
+ "loss": 0.9886,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.3315508021390374,
441
+ "grad_norm": 1.3640779256820679,
442
+ "learning_rate": 4.986883858347101e-06,
443
+ "loss": 0.8931,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.33689839572192515,
448
+ "grad_norm": 1.624706506729126,
449
+ "learning_rate": 4.986450688068655e-06,
450
+ "loss": 0.6566,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.3422459893048128,
455
+ "grad_norm": 1.3721870183944702,
456
+ "learning_rate": 4.986010500066258e-06,
457
+ "loss": 0.8529,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.34759358288770054,
462
+ "grad_norm": 1.3395642042160034,
463
+ "learning_rate": 4.985563295582292e-06,
464
+ "loss": 0.8009,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.35294117647058826,
469
+ "grad_norm": 2.1208600997924805,
470
+ "learning_rate": 4.98510907587894e-06,
471
+ "loss": 0.9735,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.3582887700534759,
476
+ "grad_norm": 2.461944580078125,
477
+ "learning_rate": 4.984647842238185e-06,
478
+ "loss": 1.2606,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.36363636363636365,
483
+ "grad_norm": 1.5776251554489136,
484
+ "learning_rate": 4.984179595961806e-06,
485
+ "loss": 0.6509,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.3689839572192513,
490
+ "grad_norm": 1.069238543510437,
491
+ "learning_rate": 4.983704338371375e-06,
492
+ "loss": 0.7776,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.37433155080213903,
497
+ "grad_norm": 1.2501965761184692,
498
+ "learning_rate": 4.983222070808255e-06,
499
+ "loss": 0.6613,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.37967914438502676,
504
+ "grad_norm": 1.7865124940872192,
505
+ "learning_rate": 4.982732794633588e-06,
506
+ "loss": 1.0873,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.3850267379679144,
511
+ "grad_norm": 1.2406933307647705,
512
+ "learning_rate": 4.982236511228301e-06,
513
+ "loss": 0.8149,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.39037433155080214,
518
+ "grad_norm": 2.1208770275115967,
519
+ "learning_rate": 4.981733221993099e-06,
520
+ "loss": 1.2344,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.39572192513368987,
525
+ "grad_norm": 2.4793150424957275,
526
+ "learning_rate": 4.981222928348456e-06,
527
+ "loss": 1.036,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.40106951871657753,
532
+ "grad_norm": 1.7698472738265991,
533
+ "learning_rate": 4.98070563173462e-06,
534
+ "loss": 0.9262,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.40641711229946526,
539
+ "grad_norm": 1.6247862577438354,
540
+ "learning_rate": 4.980181333611601e-06,
541
+ "loss": 0.7542,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.4117647058823529,
546
+ "grad_norm": 1.2302203178405762,
547
+ "learning_rate": 4.979650035459171e-06,
548
+ "loss": 0.7295,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.41711229946524064,
553
+ "grad_norm": 1.4345314502716064,
554
+ "learning_rate": 4.9791117387768575e-06,
555
+ "loss": 1.0994,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.42245989304812837,
560
+ "grad_norm": 1.1323312520980835,
561
+ "learning_rate": 4.978566445083942e-06,
562
+ "loss": 0.6173,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.42780748663101603,
567
+ "grad_norm": 1.353563666343689,
568
+ "learning_rate": 4.978014155919455e-06,
569
+ "loss": 0.7334,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.43315508021390375,
574
+ "grad_norm": 1.46320641040802,
575
+ "learning_rate": 4.977454872842169e-06,
576
+ "loss": 0.7971,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.4385026737967914,
581
+ "grad_norm": 1.5818699598312378,
582
+ "learning_rate": 4.976888597430597e-06,
583
+ "loss": 1.0309,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.44385026737967914,
588
+ "grad_norm": 1.5051372051239014,
589
+ "learning_rate": 4.976315331282985e-06,
590
+ "loss": 0.9243,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.44919786096256686,
595
+ "grad_norm": 1.2014626264572144,
596
+ "learning_rate": 4.9757350760173144e-06,
597
+ "loss": 0.7718,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.45454545454545453,
602
+ "grad_norm": 1.6985654830932617,
603
+ "learning_rate": 4.975147833271288e-06,
604
+ "loss": 1.0416,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.45989304812834225,
609
+ "grad_norm": 1.7387703657150269,
610
+ "learning_rate": 4.974553604702332e-06,
611
+ "loss": 0.7641,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.46524064171123,
616
+ "grad_norm": 1.2638602256774902,
617
+ "learning_rate": 4.973952391987589e-06,
618
+ "loss": 0.8637,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.47058823529411764,
623
+ "grad_norm": 1.9693025350570679,
624
+ "learning_rate": 4.9733441968239125e-06,
625
+ "loss": 1.1419,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.47593582887700536,
630
+ "grad_norm": 1.1901171207427979,
631
+ "learning_rate": 4.972729020927866e-06,
632
+ "loss": 0.6641,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.48128342245989303,
637
+ "grad_norm": 1.0939061641693115,
638
+ "learning_rate": 4.97210686603571e-06,
639
+ "loss": 0.8528,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.48663101604278075,
644
+ "grad_norm": 1.5549720525741577,
645
+ "learning_rate": 4.97147773390341e-06,
646
+ "loss": 0.7853,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.4919786096256685,
651
+ "grad_norm": 2.2429018020629883,
652
+ "learning_rate": 4.970841626306617e-06,
653
+ "loss": 0.8976,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.49732620320855614,
658
+ "grad_norm": 1.8647615909576416,
659
+ "learning_rate": 4.970198545040673e-06,
660
+ "loss": 1.0387,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.5026737967914439,
665
+ "grad_norm": 1.7132782936096191,
666
+ "learning_rate": 4.969548491920603e-06,
667
+ "loss": 0.908,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.5080213903743316,
672
+ "grad_norm": 1.5341262817382812,
673
+ "learning_rate": 4.968891468781105e-06,
674
+ "loss": 0.993,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.5133689839572193,
679
+ "grad_norm": 1.376716136932373,
680
+ "learning_rate": 4.968227477476554e-06,
681
+ "loss": 0.8153,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.5187165775401069,
686
+ "grad_norm": 1.637046217918396,
687
+ "learning_rate": 4.9675565198809905e-06,
688
+ "loss": 1.1166,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.5240641711229946,
693
+ "grad_norm": 1.8883839845657349,
694
+ "learning_rate": 4.966878597888114e-06,
695
+ "loss": 0.9634,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.5294117647058824,
700
+ "grad_norm": 1.2664810419082642,
701
+ "learning_rate": 4.966193713411284e-06,
702
+ "loss": 0.6848,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.5347593582887701,
707
+ "grad_norm": 1.1972209215164185,
708
+ "learning_rate": 4.965501868383507e-06,
709
+ "loss": 0.6721,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.5401069518716578,
714
+ "grad_norm": 1.957922339439392,
715
+ "learning_rate": 4.964803064757438e-06,
716
+ "loss": 0.9653,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.5454545454545454,
721
+ "grad_norm": 1.1878772974014282,
722
+ "learning_rate": 4.964097304505371e-06,
723
+ "loss": 0.779,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.5508021390374331,
728
+ "grad_norm": 1.159286379814148,
729
+ "learning_rate": 4.963384589619233e-06,
730
+ "loss": 0.653,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.5561497326203209,
735
+ "grad_norm": 1.3244158029556274,
736
+ "learning_rate": 4.962664922110581e-06,
737
+ "loss": 0.8696,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.5614973262032086,
742
+ "grad_norm": 1.2110490798950195,
743
+ "learning_rate": 4.9619383040105954e-06,
744
+ "loss": 0.9947,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.5668449197860963,
749
+ "grad_norm": 1.3603569269180298,
750
+ "learning_rate": 4.961204737370071e-06,
751
+ "loss": 0.9075,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.5721925133689839,
756
+ "grad_norm": 2.2284207344055176,
757
+ "learning_rate": 4.960464224259418e-06,
758
+ "loss": 1.1629,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.5775401069518716,
763
+ "grad_norm": 1.107352375984192,
764
+ "learning_rate": 4.95971676676865e-06,
765
+ "loss": 0.5691,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.5828877005347594,
770
+ "grad_norm": 1.0907981395721436,
771
+ "learning_rate": 4.958962367007381e-06,
772
+ "loss": 0.8838,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.5882352941176471,
777
+ "grad_norm": 1.2187764644622803,
778
+ "learning_rate": 4.958201027104818e-06,
779
+ "loss": 0.7349,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.5935828877005348,
784
+ "grad_norm": 7.554049491882324,
785
+ "learning_rate": 4.957432749209755e-06,
786
+ "loss": 0.6896,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.5989304812834224,
791
+ "grad_norm": 1.723722219467163,
792
+ "learning_rate": 4.95665753549057e-06,
793
+ "loss": 0.8566,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.6042780748663101,
798
+ "grad_norm": 1.402064323425293,
799
+ "learning_rate": 4.9558753881352165e-06,
800
+ "loss": 1.2631,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.6096256684491979,
805
+ "grad_norm": 1.4456554651260376,
806
+ "learning_rate": 4.955086309351213e-06,
807
+ "loss": 1.0358,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.6149732620320856,
812
+ "grad_norm": 1.0570646524429321,
813
+ "learning_rate": 4.9542903013656485e-06,
814
+ "loss": 0.567,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.6203208556149733,
819
+ "grad_norm": 1.2498753070831299,
820
+ "learning_rate": 4.953487366425163e-06,
821
+ "loss": 0.7102,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.6256684491978609,
826
+ "grad_norm": 1.1568989753723145,
827
+ "learning_rate": 4.952677506795949e-06,
828
+ "loss": 0.5989,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.6310160427807486,
833
+ "grad_norm": 1.2862508296966553,
834
+ "learning_rate": 4.951860724763743e-06,
835
+ "loss": 0.7446,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.6363636363636364,
840
+ "grad_norm": 1.1460041999816895,
841
+ "learning_rate": 4.95103702263382e-06,
842
+ "loss": 0.7372,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.6417112299465241,
847
+ "grad_norm": 1.2459862232208252,
848
+ "learning_rate": 4.950206402730984e-06,
849
+ "loss": 0.7769,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.6470588235294118,
854
+ "grad_norm": 1.0696263313293457,
855
+ "learning_rate": 4.949368867399567e-06,
856
+ "loss": 0.5383,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.6524064171122995,
861
+ "grad_norm": 1.2742743492126465,
862
+ "learning_rate": 4.948524419003415e-06,
863
+ "loss": 1.185,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.6577540106951871,
868
+ "grad_norm": 1.3774257898330688,
869
+ "learning_rate": 4.947673059925889e-06,
870
+ "loss": 0.8457,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.6631016042780749,
875
+ "grad_norm": 1.0061278343200684,
876
+ "learning_rate": 4.9468147925698525e-06,
877
+ "loss": 0.8931,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.6684491978609626,
882
+ "grad_norm": 1.1825965642929077,
883
+ "learning_rate": 4.945949619357668e-06,
884
+ "loss": 0.6799,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.6737967914438503,
889
+ "grad_norm": 1.1278257369995117,
890
+ "learning_rate": 4.945077542731188e-06,
891
+ "loss": 0.5315,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.679144385026738,
896
+ "grad_norm": 1.335824966430664,
897
+ "learning_rate": 4.94419856515175e-06,
898
+ "loss": 0.8661,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.6844919786096256,
903
+ "grad_norm": 1.157353162765503,
904
+ "learning_rate": 4.943312689100166e-06,
905
+ "loss": 0.85,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.6898395721925134,
910
+ "grad_norm": 1.1066932678222656,
911
+ "learning_rate": 4.942419917076723e-06,
912
+ "loss": 0.6371,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.6951871657754011,
917
+ "grad_norm": 1.1405237913131714,
918
+ "learning_rate": 4.941520251601167e-06,
919
+ "loss": 0.754,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.7005347593582888,
924
+ "grad_norm": 0.9409145712852478,
925
+ "learning_rate": 4.940613695212702e-06,
926
+ "loss": 0.4771,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.7058823529411765,
931
+ "grad_norm": 1.7782841920852661,
932
+ "learning_rate": 4.939700250469979e-06,
933
+ "loss": 1.0409,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.7112299465240641,
938
+ "grad_norm": 1.1810370683670044,
939
+ "learning_rate": 4.938779919951092e-06,
940
+ "loss": 0.8479,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.7165775401069518,
945
+ "grad_norm": 1.3410803079605103,
946
+ "learning_rate": 4.93785270625357e-06,
947
+ "loss": 0.5505,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.7219251336898396,
952
+ "grad_norm": 1.5545536279678345,
953
+ "learning_rate": 4.936918611994368e-06,
954
+ "loss": 0.7061,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.7272727272727273,
959
+ "grad_norm": 1.2099353075027466,
960
+ "learning_rate": 4.935977639809861e-06,
961
+ "loss": 0.8298,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.732620320855615,
966
+ "grad_norm": 1.052022099494934,
967
+ "learning_rate": 4.935029792355834e-06,
968
+ "loss": 0.6414,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.7379679144385026,
973
+ "grad_norm": 1.3165653944015503,
974
+ "learning_rate": 4.934075072307481e-06,
975
+ "loss": 1.0115,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.7433155080213903,
980
+ "grad_norm": 1.1172512769699097,
981
+ "learning_rate": 4.933113482359388e-06,
982
+ "loss": 0.5454,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.7486631016042781,
987
+ "grad_norm": 1.2038301229476929,
988
+ "learning_rate": 4.932145025225535e-06,
989
+ "loss": 0.6953,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.7540106951871658,
994
+ "grad_norm": 1.278849482536316,
995
+ "learning_rate": 4.931169703639282e-06,
996
+ "loss": 0.8666,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.7593582887700535,
1001
+ "grad_norm": 1.2486368417739868,
1002
+ "learning_rate": 4.930187520353363e-06,
1003
+ "loss": 0.7576,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.7647058823529411,
1008
+ "grad_norm": 1.0550994873046875,
1009
+ "learning_rate": 4.929198478139877e-06,
1010
+ "loss": 0.6381,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.7700534759358288,
1015
+ "grad_norm": 1.1743860244750977,
1016
+ "learning_rate": 4.928202579790285e-06,
1017
+ "loss": 0.5925,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.7754010695187166,
1022
+ "grad_norm": 1.119457721710205,
1023
+ "learning_rate": 4.927199828115395e-06,
1024
+ "loss": 0.7164,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.7807486631016043,
1029
+ "grad_norm": 1.2646217346191406,
1030
+ "learning_rate": 4.9261902259453616e-06,
1031
+ "loss": 0.8448,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.786096256684492,
1036
+ "grad_norm": 1.4235252141952515,
1037
+ "learning_rate": 4.925173776129669e-06,
1038
+ "loss": 1.0357,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.7914438502673797,
1043
+ "grad_norm": 0.9110249280929565,
1044
+ "learning_rate": 4.9241504815371346e-06,
1045
+ "loss": 0.488,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.7967914438502673,
1050
+ "grad_norm": 1.1222057342529297,
1051
+ "learning_rate": 4.923120345055887e-06,
1052
+ "loss": 0.7326,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.8021390374331551,
1057
+ "grad_norm": 1.233242392539978,
1058
+ "learning_rate": 4.922083369593372e-06,
1059
+ "loss": 0.6374,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.8074866310160428,
1064
+ "grad_norm": 1.3709094524383545,
1065
+ "learning_rate": 4.921039558076335e-06,
1066
+ "loss": 0.9307,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.8128342245989305,
1071
+ "grad_norm": 1.7019920349121094,
1072
+ "learning_rate": 4.919988913450812e-06,
1073
+ "loss": 0.4521,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.8181818181818182,
1078
+ "grad_norm": 1.4864672422409058,
1079
+ "learning_rate": 4.918931438682132e-06,
1080
+ "loss": 0.8711,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.8235294117647058,
1085
+ "grad_norm": 1.2137510776519775,
1086
+ "learning_rate": 4.917867136754894e-06,
1087
+ "loss": 0.8817,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.8288770053475936,
1092
+ "grad_norm": 1.046115517616272,
1093
+ "learning_rate": 4.916796010672969e-06,
1094
+ "loss": 0.7523,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.8342245989304813,
1099
+ "grad_norm": 1.0783687829971313,
1100
+ "learning_rate": 4.91571806345949e-06,
1101
+ "loss": 0.7799,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.839572192513369,
1106
+ "grad_norm": 1.2369630336761475,
1107
+ "learning_rate": 4.91463329815684e-06,
1108
+ "loss": 0.8074,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.8449197860962567,
1113
+ "grad_norm": 1.1012200117111206,
1114
+ "learning_rate": 4.913541717826645e-06,
1115
+ "loss": 0.5807,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.8502673796791443,
1120
+ "grad_norm": 0.9732352495193481,
1121
+ "learning_rate": 4.912443325549767e-06,
1122
+ "loss": 0.4962,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.8556149732620321,
1127
+ "grad_norm": 1.4297598600387573,
1128
+ "learning_rate": 4.911338124426291e-06,
1129
+ "loss": 0.7422,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.8609625668449198,
1134
+ "grad_norm": 1.1858251094818115,
1135
+ "learning_rate": 4.910226117575525e-06,
1136
+ "loss": 0.8112,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.8663101604278075,
1141
+ "grad_norm": 0.996497392654419,
1142
+ "learning_rate": 4.909107308135978e-06,
1143
+ "loss": 0.5164,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.8716577540106952,
1148
+ "grad_norm": 1.0727980136871338,
1149
+ "learning_rate": 4.907981699265364e-06,
1150
+ "loss": 0.5894,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.8770053475935828,
1155
+ "grad_norm": 2.517244815826416,
1156
+ "learning_rate": 4.906849294140587e-06,
1157
+ "loss": 0.8451,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.8823529411764706,
1162
+ "grad_norm": 1.4754635095596313,
1163
+ "learning_rate": 4.9057100959577285e-06,
1164
+ "loss": 0.6835,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.8877005347593583,
1169
+ "grad_norm": 1.326028823852539,
1170
+ "learning_rate": 4.904564107932048e-06,
1171
+ "loss": 0.9452,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.893048128342246,
1176
+ "grad_norm": 1.3109493255615234,
1177
+ "learning_rate": 4.903411333297966e-06,
1178
+ "loss": 0.8715,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.8983957219251337,
1183
+ "grad_norm": 1.1822558641433716,
1184
+ "learning_rate": 4.902251775309057e-06,
1185
+ "loss": 0.7837,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.9037433155080213,
1190
+ "grad_norm": 2.0237507820129395,
1191
+ "learning_rate": 4.901085437238041e-06,
1192
+ "loss": 0.5641,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.9090909090909091,
1197
+ "grad_norm": 1.146775484085083,
1198
+ "learning_rate": 4.899912322376776e-06,
1199
+ "loss": 0.941,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.9144385026737968,
1204
+ "grad_norm": 5.484114646911621,
1205
+ "learning_rate": 4.8987324340362445e-06,
1206
+ "loss": 0.8631,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.9197860962566845,
1211
+ "grad_norm": 1.1397885084152222,
1212
+ "learning_rate": 4.897545775546545e-06,
1213
+ "loss": 0.7861,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.9251336898395722,
1218
+ "grad_norm": 1.4679510593414307,
1219
+ "learning_rate": 4.8963523502568886e-06,
1220
+ "loss": 1.0241,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.93048128342246,
1225
+ "grad_norm": 1.461098313331604,
1226
+ "learning_rate": 4.895152161535582e-06,
1227
+ "loss": 0.726,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.9358288770053476,
1232
+ "grad_norm": 1.2273950576782227,
1233
+ "learning_rate": 4.893945212770019e-06,
1234
+ "loss": 0.6881,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.9411764705882353,
1239
+ "grad_norm": 1.1804200410842896,
1240
+ "learning_rate": 4.892731507366678e-06,
1241
+ "loss": 0.8014,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.946524064171123,
1246
+ "grad_norm": 1.0605725049972534,
1247
+ "learning_rate": 4.891511048751102e-06,
1248
+ "loss": 0.7123,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.9518716577540107,
1253
+ "grad_norm": 1.1945055723190308,
1254
+ "learning_rate": 4.890283840367898e-06,
1255
+ "loss": 1.1557,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.9572192513368984,
1260
+ "grad_norm": 1.8845665454864502,
1261
+ "learning_rate": 4.889049885680721e-06,
1262
+ "loss": 0.7537,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.9625668449197861,
1267
+ "grad_norm": 1.2743051052093506,
1268
+ "learning_rate": 4.887809188172268e-06,
1269
+ "loss": 0.6832,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.9679144385026738,
1274
+ "grad_norm": 1.1513574123382568,
1275
+ "learning_rate": 4.886561751344266e-06,
1276
+ "loss": 0.7828,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.9732620320855615,
1281
+ "grad_norm": 1.2392234802246094,
1282
+ "learning_rate": 4.885307578717464e-06,
1283
+ "loss": 0.7968,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.9786096256684492,
1288
+ "grad_norm": 1.3613368272781372,
1289
+ "learning_rate": 4.8840466738316216e-06,
1290
+ "loss": 0.8377,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.983957219251337,
1295
+ "grad_norm": 1.2968305349349976,
1296
+ "learning_rate": 4.882779040245499e-06,
1297
+ "loss": 0.7362,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.9893048128342246,
1302
+ "grad_norm": 1.0916310548782349,
1303
+ "learning_rate": 4.881504681536847e-06,
1304
+ "loss": 0.5839,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.9946524064171123,
1309
+ "grad_norm": 1.0657607316970825,
1310
+ "learning_rate": 4.880223601302398e-06,
1311
+ "loss": 0.5879,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 1.0,
1316
+ "grad_norm": 1.0571955442428589,
1317
+ "learning_rate": 4.878935803157856e-06,
1318
+ "loss": 0.5795,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 1.0053475935828877,
1323
+ "grad_norm": 1.20957612991333,
1324
+ "learning_rate": 4.8776412907378845e-06,
1325
+ "loss": 0.6837,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 1.0106951871657754,
1330
+ "grad_norm": 1.18942391872406,
1331
+ "learning_rate": 4.876340067696097e-06,
1332
+ "loss": 0.6751,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 1.0160427807486632,
1337
+ "grad_norm": 1.2014987468719482,
1338
+ "learning_rate": 4.875032137705047e-06,
1339
+ "loss": 0.6877,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 1.0213903743315509,
1344
+ "grad_norm": 1.2663947343826294,
1345
+ "learning_rate": 4.873717504456219e-06,
1346
+ "loss": 0.7902,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 1.0267379679144386,
1351
+ "grad_norm": 0.8689743280410767,
1352
+ "learning_rate": 4.872396171660014e-06,
1353
+ "loss": 0.4347,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 1.032085561497326,
1358
+ "grad_norm": 1.0086268186569214,
1359
+ "learning_rate": 4.8710681430457466e-06,
1360
+ "loss": 0.638,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 1.0374331550802138,
1365
+ "grad_norm": 2.1694843769073486,
1366
+ "learning_rate": 4.8697334223616226e-06,
1367
+ "loss": 0.9635,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 1.0427807486631016,
1372
+ "grad_norm": 1.009002923965454,
1373
+ "learning_rate": 4.8683920133747405e-06,
1374
+ "loss": 0.6165,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 1.0481283422459893,
1379
+ "grad_norm": 0.9168912768363953,
1380
+ "learning_rate": 4.867043919871076e-06,
1381
+ "loss": 0.5635,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 1.053475935828877,
1386
+ "grad_norm": 0.9658924341201782,
1387
+ "learning_rate": 4.865689145655467e-06,
1388
+ "loss": 0.6424,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 1.0588235294117647,
1393
+ "grad_norm": 1.0445383787155151,
1394
+ "learning_rate": 4.864327694551612e-06,
1395
+ "loss": 0.6222,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 1.0641711229946524,
1400
+ "grad_norm": 1.4311105012893677,
1401
+ "learning_rate": 4.86295957040205e-06,
1402
+ "loss": 0.9985,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 1.0695187165775402,
1407
+ "grad_norm": 1.4633280038833618,
1408
+ "learning_rate": 4.861584777068154e-06,
1409
+ "loss": 0.7607,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 1.0748663101604279,
1414
+ "grad_norm": 0.9601297974586487,
1415
+ "learning_rate": 4.860203318430126e-06,
1416
+ "loss": 0.3623,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 1.0802139037433156,
1421
+ "grad_norm": 1.2763819694519043,
1422
+ "learning_rate": 4.858815198386973e-06,
1423
+ "loss": 0.686,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 1.085561497326203,
1428
+ "grad_norm": 1.1342650651931763,
1429
+ "learning_rate": 4.8574204208565056e-06,
1430
+ "loss": 0.6218,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 1.0909090909090908,
1435
+ "grad_norm": 0.9920980334281921,
1436
+ "learning_rate": 4.856018989775326e-06,
1437
+ "loss": 0.6106,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 1.0962566844919786,
1442
+ "grad_norm": 1.1050597429275513,
1443
+ "learning_rate": 4.854610909098813e-06,
1444
+ "loss": 0.7119,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 1.1016042780748663,
1449
+ "grad_norm": 1.416072964668274,
1450
+ "learning_rate": 4.853196182801112e-06,
1451
+ "loss": 1.0904,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 1.106951871657754,
1456
+ "grad_norm": 1.2843166589736938,
1457
+ "learning_rate": 4.851774814875131e-06,
1458
+ "loss": 0.7235,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 1.1122994652406417,
1463
+ "grad_norm": 1.048844814300537,
1464
+ "learning_rate": 4.850346809332515e-06,
1465
+ "loss": 0.743,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 1.1176470588235294,
1470
+ "grad_norm": 0.9781081080436707,
1471
+ "learning_rate": 4.8489121702036515e-06,
1472
+ "loss": 0.7786,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 1.1229946524064172,
1477
+ "grad_norm": 1.9083611965179443,
1478
+ "learning_rate": 4.847470901537642e-06,
1479
+ "loss": 0.7338,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 1.1283422459893049,
1484
+ "grad_norm": 1.0221211910247803,
1485
+ "learning_rate": 4.846023007402305e-06,
1486
+ "loss": 0.5435,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 1.1336898395721926,
1491
+ "grad_norm": 1.0517302751541138,
1492
+ "learning_rate": 4.844568491884156e-06,
1493
+ "loss": 0.4034,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 1.1390374331550803,
1498
+ "grad_norm": 1.1334607601165771,
1499
+ "learning_rate": 4.843107359088402e-06,
1500
+ "loss": 0.597,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 1.1443850267379678,
1505
+ "grad_norm": 1.7964959144592285,
1506
+ "learning_rate": 4.84163961313892e-06,
1507
+ "loss": 0.6547,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 1.1497326203208555,
1512
+ "grad_norm": 0.9998727440834045,
1513
+ "learning_rate": 4.840165258178259e-06,
1514
+ "loss": 0.6095,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 1.1550802139037433,
1519
+ "grad_norm": 1.1533814668655396,
1520
+ "learning_rate": 4.838684298367616e-06,
1521
+ "loss": 0.8142,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 1.160427807486631,
1526
+ "grad_norm": 1.0754449367523193,
1527
+ "learning_rate": 4.837196737886834e-06,
1528
+ "loss": 0.84,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 1.1657754010695187,
1533
+ "grad_norm": 1.4141411781311035,
1534
+ "learning_rate": 4.83570258093438e-06,
1535
+ "loss": 0.8648,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 1.1711229946524064,
1540
+ "grad_norm": 1.19698965549469,
1541
+ "learning_rate": 4.834201831727343e-06,
1542
+ "loss": 0.5587,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 1.1764705882352942,
1547
+ "grad_norm": 1.0640945434570312,
1548
+ "learning_rate": 4.832694494501417e-06,
1549
+ "loss": 0.6335,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 1.1818181818181819,
1554
+ "grad_norm": 1.0239144563674927,
1555
+ "learning_rate": 4.83118057351089e-06,
1556
+ "loss": 0.4245,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 1.1871657754010696,
1561
+ "grad_norm": 1.04526686668396,
1562
+ "learning_rate": 4.829660073028631e-06,
1563
+ "loss": 0.5714,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 1.192513368983957,
1568
+ "grad_norm": 1.2421259880065918,
1569
+ "learning_rate": 4.82813299734608e-06,
1570
+ "loss": 0.5515,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 1.1978609625668448,
1575
+ "grad_norm": 1.1532832384109497,
1576
+ "learning_rate": 4.826599350773234e-06,
1577
+ "loss": 0.4792,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 1.2032085561497325,
1582
+ "grad_norm": 1.4684878587722778,
1583
+ "learning_rate": 4.825059137638636e-06,
1584
+ "loss": 0.8759,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 1.2085561497326203,
1589
+ "grad_norm": 1.275098204612732,
1590
+ "learning_rate": 4.823512362289362e-06,
1591
+ "loss": 0.6575,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 1.213903743315508,
1596
+ "grad_norm": 1.0070858001708984,
1597
+ "learning_rate": 4.821959029091009e-06,
1598
+ "loss": 0.6332,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 1.2192513368983957,
1603
+ "grad_norm": 1.2541303634643555,
1604
+ "learning_rate": 4.820399142427684e-06,
1605
+ "loss": 0.6189,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 1.2245989304812834,
1610
+ "grad_norm": 0.9502724409103394,
1611
+ "learning_rate": 4.818832706701989e-06,
1612
+ "loss": 0.5039,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 1.2299465240641712,
1617
+ "grad_norm": 1.229194164276123,
1618
+ "learning_rate": 4.817259726335009e-06,
1619
+ "loss": 0.9031,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 1.2352941176470589,
1624
+ "grad_norm": 1.2500348091125488,
1625
+ "learning_rate": 4.815680205766304e-06,
1626
+ "loss": 0.8338,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 1.2406417112299466,
1631
+ "grad_norm": 0.7873129844665527,
1632
+ "learning_rate": 4.814094149453891e-06,
1633
+ "loss": 0.4355,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 1.2459893048128343,
1638
+ "grad_norm": 1.2361822128295898,
1639
+ "learning_rate": 4.812501561874232e-06,
1640
+ "loss": 0.7375,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 1.251336898395722,
1645
+ "grad_norm": 1.3732285499572754,
1646
+ "learning_rate": 4.8109024475222255e-06,
1647
+ "loss": 0.7582,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 1.2566844919786098,
1652
+ "grad_norm": 1.1772031784057617,
1653
+ "learning_rate": 4.809296810911188e-06,
1654
+ "loss": 0.8901,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 1.2620320855614973,
1659
+ "grad_norm": 1.221704363822937,
1660
+ "learning_rate": 4.8076846565728475e-06,
1661
+ "loss": 0.9178,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 1.267379679144385,
1666
+ "grad_norm": 1.0428493022918701,
1667
+ "learning_rate": 4.806065989057326e-06,
1668
+ "loss": 0.6723,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 1.2727272727272727,
1673
+ "grad_norm": 1.0525826215744019,
1674
+ "learning_rate": 4.8044408129331266e-06,
1675
+ "loss": 0.4761,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 1.2780748663101604,
1680
+ "grad_norm": 1.0145494937896729,
1681
+ "learning_rate": 4.802809132787125e-06,
1682
+ "loss": 0.6633,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 1.2834224598930482,
1687
+ "grad_norm": 1.0016582012176514,
1688
+ "learning_rate": 4.801170953224554e-06,
1689
+ "loss": 0.799,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 1.2887700534759359,
1694
+ "grad_norm": 0.8688123226165771,
1695
+ "learning_rate": 4.7995262788689865e-06,
1696
+ "loss": 0.466,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 1.2941176470588236,
1701
+ "grad_norm": 1.2246720790863037,
1702
+ "learning_rate": 4.797875114362331e-06,
1703
+ "loss": 0.589,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 1.299465240641711,
1708
+ "grad_norm": 1.197195291519165,
1709
+ "learning_rate": 4.796217464364808e-06,
1710
+ "loss": 0.7172,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 1.3048128342245988,
1715
+ "grad_norm": 1.5257734060287476,
1716
+ "learning_rate": 4.794553333554949e-06,
1717
+ "loss": 0.7422,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 1.3101604278074865,
1722
+ "grad_norm": 1.0605517625808716,
1723
+ "learning_rate": 4.792882726629572e-06,
1724
+ "loss": 0.6162,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 1.3155080213903743,
1729
+ "grad_norm": 1.5351297855377197,
1730
+ "learning_rate": 4.791205648303775e-06,
1731
+ "loss": 0.9099,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 1.320855614973262,
1736
+ "grad_norm": 1.2023025751113892,
1737
+ "learning_rate": 4.789522103310922e-06,
1738
+ "loss": 0.644,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 1.3262032085561497,
1743
+ "grad_norm": 0.9756056070327759,
1744
+ "learning_rate": 4.787832096402626e-06,
1745
+ "loss": 0.6793,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 1.3315508021390374,
1750
+ "grad_norm": 1.6098637580871582,
1751
+ "learning_rate": 4.786135632348738e-06,
1752
+ "loss": 0.7011,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 1.3368983957219251,
1757
+ "grad_norm": 1.0160528421401978,
1758
+ "learning_rate": 4.7844327159373365e-06,
1759
+ "loss": 0.8866,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 1.3422459893048129,
1764
+ "grad_norm": 0.9334290623664856,
1765
+ "learning_rate": 4.782723351974708e-06,
1766
+ "loss": 0.5706,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 1.3475935828877006,
1771
+ "grad_norm": 1.0337231159210205,
1772
+ "learning_rate": 4.7810075452853385e-06,
1773
+ "loss": 0.7292,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 1.3529411764705883,
1778
+ "grad_norm": 1.0874898433685303,
1779
+ "learning_rate": 4.779285300711897e-06,
1780
+ "loss": 0.6961,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 1.358288770053476,
1785
+ "grad_norm": 0.9048140645027161,
1786
+ "learning_rate": 4.7775566231152216e-06,
1787
+ "loss": 0.3912,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 1.3636363636363638,
1792
+ "grad_norm": 1.0958999395370483,
1793
+ "learning_rate": 4.775821517374308e-06,
1794
+ "loss": 0.9101,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 1.3689839572192513,
1799
+ "grad_norm": 0.8642525672912598,
1800
+ "learning_rate": 4.7740799883862966e-06,
1801
+ "loss": 0.5143,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 1.374331550802139,
1806
+ "grad_norm": 0.9413106441497803,
1807
+ "learning_rate": 4.772332041066452e-06,
1808
+ "loss": 0.4793,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 1.3796791443850267,
1813
+ "grad_norm": 1.3453179597854614,
1814
+ "learning_rate": 4.770577680348159e-06,
1815
+ "loss": 0.9241,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 1.3850267379679144,
1820
+ "grad_norm": 1.1179924011230469,
1821
+ "learning_rate": 4.768816911182899e-06,
1822
+ "loss": 0.4698,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 1.3903743315508021,
1827
+ "grad_norm": 1.1064088344573975,
1828
+ "learning_rate": 4.767049738540244e-06,
1829
+ "loss": 0.572,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 1.3957219251336899,
1834
+ "grad_norm": 0.9627691507339478,
1835
+ "learning_rate": 4.765276167407836e-06,
1836
+ "loss": 0.4432,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 1.4010695187165776,
1841
+ "grad_norm": 1.1974354982376099,
1842
+ "learning_rate": 4.7634962027913784e-06,
1843
+ "loss": 0.8065,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 1.4064171122994653,
1848
+ "grad_norm": 0.9519065022468567,
1849
+ "learning_rate": 4.761709849714619e-06,
1850
+ "loss": 0.6041,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 1.4117647058823528,
1855
+ "grad_norm": 1.1260693073272705,
1856
+ "learning_rate": 4.7599171132193355e-06,
1857
+ "loss": 0.7201,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 1.4171122994652405,
1862
+ "grad_norm": 1.038185715675354,
1863
+ "learning_rate": 4.7581179983653224e-06,
1864
+ "loss": 0.6769,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 1.4224598930481283,
1869
+ "grad_norm": 0.9998167753219604,
1870
+ "learning_rate": 4.756312510230377e-06,
1871
+ "loss": 0.4137,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 1.427807486631016,
1876
+ "grad_norm": 1.2673780918121338,
1877
+ "learning_rate": 4.754500653910284e-06,
1878
+ "loss": 0.6252,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 1.4331550802139037,
1883
+ "grad_norm": 1.008988380432129,
1884
+ "learning_rate": 4.752682434518801e-06,
1885
+ "loss": 0.636,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 1.4385026737967914,
1890
+ "grad_norm": 1.099381685256958,
1891
+ "learning_rate": 4.750857857187645e-06,
1892
+ "loss": 0.4901,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 1.4438502673796791,
1897
+ "grad_norm": 1.0696007013320923,
1898
+ "learning_rate": 4.749026927066479e-06,
1899
+ "loss": 0.8305,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 1.4491978609625669,
1904
+ "grad_norm": 0.8355650901794434,
1905
+ "learning_rate": 4.747189649322894e-06,
1906
+ "loss": 0.5531,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 1.4545454545454546,
1911
+ "grad_norm": 1.1239508390426636,
1912
+ "learning_rate": 4.745346029142397e-06,
1913
+ "loss": 0.6902,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 1.4598930481283423,
1918
+ "grad_norm": 0.9494181275367737,
1919
+ "learning_rate": 4.743496071728396e-06,
1920
+ "loss": 0.6843,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 1.46524064171123,
1925
+ "grad_norm": 1.0402284860610962,
1926
+ "learning_rate": 4.741639782302187e-06,
1927
+ "loss": 0.4734,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 1.4705882352941178,
1932
+ "grad_norm": 0.9741571545600891,
1933
+ "learning_rate": 4.739777166102933e-06,
1934
+ "loss": 0.5365,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 1.4759358288770055,
1939
+ "grad_norm": 1.13914155960083,
1940
+ "learning_rate": 4.737908228387656e-06,
1941
+ "loss": 0.6126,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 1.481283422459893,
1946
+ "grad_norm": 0.9242702722549438,
1947
+ "learning_rate": 4.736032974431222e-06,
1948
+ "loss": 0.53,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 1.4866310160427807,
1953
+ "grad_norm": 0.8968143463134766,
1954
+ "learning_rate": 4.7341514095263214e-06,
1955
+ "loss": 0.5028,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 1.4919786096256684,
1960
+ "grad_norm": 1.134374976158142,
1961
+ "learning_rate": 4.732263538983456e-06,
1962
+ "loss": 0.6472,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 1.4973262032085561,
1967
+ "grad_norm": 1.2837514877319336,
1968
+ "learning_rate": 4.730369368130925e-06,
1969
+ "loss": 0.6933,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 1.5026737967914439,
1974
+ "grad_norm": 1.6060264110565186,
1975
+ "learning_rate": 4.728468902314811e-06,
1976
+ "loss": 1.3412,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 1.5080213903743316,
1981
+ "grad_norm": 0.9336663484573364,
1982
+ "learning_rate": 4.726562146898963e-06,
1983
+ "loss": 0.6967,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 1.5133689839572193,
1988
+ "grad_norm": 1.1355899572372437,
1989
+ "learning_rate": 4.72464910726498e-06,
1990
+ "loss": 0.5342,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 1.5187165775401068,
1995
+ "grad_norm": 1.3025175333023071,
1996
+ "learning_rate": 4.7227297888121985e-06,
1997
+ "loss": 0.8124,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 1.5240641711229945,
2002
+ "grad_norm": 1.0148515701293945,
2003
+ "learning_rate": 4.720804196957676e-06,
2004
+ "loss": 0.6428,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 1.5294117647058822,
2009
+ "grad_norm": 1.13893723487854,
2010
+ "learning_rate": 4.718872337136176e-06,
2011
+ "loss": 0.8569,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 1.53475935828877,
2016
+ "grad_norm": 1.080116868019104,
2017
+ "learning_rate": 4.716934214800155e-06,
2018
+ "loss": 1.0755,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 1.5401069518716577,
2023
+ "grad_norm": 1.0785784721374512,
2024
+ "learning_rate": 4.714989835419741e-06,
2025
+ "loss": 0.6449,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 1.5454545454545454,
2030
+ "grad_norm": 1.1317613124847412,
2031
+ "learning_rate": 4.713039204482723e-06,
2032
+ "loss": 0.5227,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 1.5508021390374331,
2037
+ "grad_norm": 1.0730540752410889,
2038
+ "learning_rate": 4.711082327494536e-06,
2039
+ "loss": 0.7847,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 1.5561497326203209,
2044
+ "grad_norm": 1.2158780097961426,
2045
+ "learning_rate": 4.709119209978242e-06,
2046
+ "loss": 0.5319,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 1.5614973262032086,
2051
+ "grad_norm": 0.8821747899055481,
2052
+ "learning_rate": 4.707149857474516e-06,
2053
+ "loss": 0.435,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 1.5668449197860963,
2058
+ "grad_norm": 0.9107806086540222,
2059
+ "learning_rate": 4.705174275541632e-06,
2060
+ "loss": 0.5626,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 1.572192513368984,
2065
+ "grad_norm": 0.9523131251335144,
2066
+ "learning_rate": 4.703192469755444e-06,
2067
+ "loss": 0.6647,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 1.5775401069518717,
2072
+ "grad_norm": 1.1997532844543457,
2073
+ "learning_rate": 4.701204445709375e-06,
2074
+ "loss": 0.6932,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 1.5828877005347595,
2079
+ "grad_norm": 1.0278339385986328,
2080
+ "learning_rate": 4.699210209014394e-06,
2081
+ "loss": 0.7149,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 1.5882352941176472,
2086
+ "grad_norm": 1.1402068138122559,
2087
+ "learning_rate": 4.69720976529901e-06,
2088
+ "loss": 0.5502,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 1.593582887700535,
2093
+ "grad_norm": 0.9727303385734558,
2094
+ "learning_rate": 4.695203120209245e-06,
2095
+ "loss": 0.5037,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 1.5989304812834224,
2100
+ "grad_norm": 1.1070572137832642,
2101
+ "learning_rate": 4.693190279408628e-06,
2102
+ "loss": 0.4887,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 1.6042780748663101,
2107
+ "grad_norm": 1.1652781963348389,
2108
+ "learning_rate": 4.691171248578172e-06,
2109
+ "loss": 0.5242,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 1.6096256684491979,
2114
+ "grad_norm": 0.9106811285018921,
2115
+ "learning_rate": 4.689146033416362e-06,
2116
+ "loss": 0.7305,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 1.6149732620320856,
2121
+ "grad_norm": 1.1986925601959229,
2122
+ "learning_rate": 4.687114639639136e-06,
2123
+ "loss": 0.4518,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 1.6203208556149733,
2128
+ "grad_norm": 1.102372646331787,
2129
+ "learning_rate": 4.685077072979874e-06,
2130
+ "loss": 0.48,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 1.6256684491978608,
2135
+ "grad_norm": 1.047916293144226,
2136
+ "learning_rate": 4.683033339189375e-06,
2137
+ "loss": 0.4871,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 1.6310160427807485,
2142
+ "grad_norm": 1.2392176389694214,
2143
+ "learning_rate": 4.680983444035843e-06,
2144
+ "loss": 0.7791,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 1.6363636363636362,
2149
+ "grad_norm": 1.0462485551834106,
2150
+ "learning_rate": 4.678927393304877e-06,
2151
+ "loss": 0.3736,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 1.641711229946524,
2156
+ "grad_norm": 0.9711524248123169,
2157
+ "learning_rate": 4.676865192799443e-06,
2158
+ "loss": 0.4959,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 1.6470588235294117,
2163
+ "grad_norm": 1.1203721761703491,
2164
+ "learning_rate": 4.6747968483398695e-06,
2165
+ "loss": 0.8252,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 1.6524064171122994,
2170
+ "grad_norm": 0.8006160855293274,
2171
+ "learning_rate": 4.672722365763821e-06,
2172
+ "loss": 0.3834,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 1.6577540106951871,
2177
+ "grad_norm": 1.0191600322723389,
2178
+ "learning_rate": 4.6706417509262905e-06,
2179
+ "loss": 0.5832,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 1.6631016042780749,
2184
+ "grad_norm": 1.0450992584228516,
2185
+ "learning_rate": 4.668555009699575e-06,
2186
+ "loss": 0.5214,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 1.6684491978609626,
2191
+ "grad_norm": 1.0037814378738403,
2192
+ "learning_rate": 4.666462147973264e-06,
2193
+ "loss": 0.6614,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 1.6737967914438503,
2198
+ "grad_norm": 1.360205888748169,
2199
+ "learning_rate": 4.664363171654223e-06,
2200
+ "loss": 0.7079,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 1.679144385026738,
2205
+ "grad_norm": 1.6256295442581177,
2206
+ "learning_rate": 4.662258086666571e-06,
2207
+ "loss": 0.9379,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 1.6844919786096257,
2212
+ "grad_norm": 1.2857729196548462,
2213
+ "learning_rate": 4.660146898951674e-06,
2214
+ "loss": 0.878,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 1.6898395721925135,
2219
+ "grad_norm": 1.1930155754089355,
2220
+ "learning_rate": 4.6580296144681155e-06,
2221
+ "loss": 0.7534,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 1.6951871657754012,
2226
+ "grad_norm": 1.2688080072402954,
2227
+ "learning_rate": 4.655906239191693e-06,
2228
+ "loss": 0.7914,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 1.700534759358289,
2233
+ "grad_norm": 0.9058023691177368,
2234
+ "learning_rate": 4.653776779115389e-06,
2235
+ "loss": 0.6896,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 1.7058823529411766,
2240
+ "grad_norm": 1.2911888360977173,
2241
+ "learning_rate": 4.651641240249364e-06,
2242
+ "loss": 0.4868,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 1.7112299465240641,
2247
+ "grad_norm": 1.0514754056930542,
2248
+ "learning_rate": 4.649499628620931e-06,
2249
+ "loss": 0.422,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 1.7165775401069518,
2254
+ "grad_norm": 0.9909546375274658,
2255
+ "learning_rate": 4.647351950274548e-06,
2256
+ "loss": 0.6655,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 1.7219251336898396,
2261
+ "grad_norm": 1.012528419494629,
2262
+ "learning_rate": 4.6451982112717896e-06,
2263
+ "loss": 0.6941,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 1.7272727272727273,
2268
+ "grad_norm": 1.0260202884674072,
2269
+ "learning_rate": 4.643038417691341e-06,
2270
+ "loss": 0.5326,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 1.732620320855615,
2275
+ "grad_norm": 0.8661928772926331,
2276
+ "learning_rate": 4.640872575628973e-06,
2277
+ "loss": 0.4679,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 1.7379679144385025,
2282
+ "grad_norm": 1.0018043518066406,
2283
+ "learning_rate": 4.6387006911975275e-06,
2284
+ "loss": 0.7368,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 1.7433155080213902,
2289
+ "grad_norm": 0.9654306769371033,
2290
+ "learning_rate": 4.6365227705269026e-06,
2291
+ "loss": 0.7109,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 1.748663101604278,
2296
+ "grad_norm": 1.4752485752105713,
2297
+ "learning_rate": 4.634338819764029e-06,
2298
+ "loss": 0.6031,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 1.7540106951871657,
2303
+ "grad_norm": 1.0305147171020508,
2304
+ "learning_rate": 4.632148845072861e-06,
2305
+ "loss": 0.5183,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 1.7593582887700534,
2310
+ "grad_norm": 1.0311737060546875,
2311
+ "learning_rate": 4.6299528526343525e-06,
2312
+ "loss": 0.599,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 1.7647058823529411,
2317
+ "grad_norm": 1.6055175065994263,
2318
+ "learning_rate": 4.627750848646443e-06,
2319
+ "loss": 0.9565,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 1.7700534759358288,
2324
+ "grad_norm": 1.1404913663864136,
2325
+ "learning_rate": 4.625542839324036e-06,
2326
+ "loss": 0.6204,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 1.7754010695187166,
2331
+ "grad_norm": 1.0448116064071655,
2332
+ "learning_rate": 4.6233288308989874e-06,
2333
+ "loss": 0.4278,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 1.7807486631016043,
2338
+ "grad_norm": 0.9623430371284485,
2339
+ "learning_rate": 4.6211088296200834e-06,
2340
+ "loss": 0.4501,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 1.786096256684492,
2345
+ "grad_norm": 0.8799414038658142,
2346
+ "learning_rate": 4.618882841753026e-06,
2347
+ "loss": 0.6616,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 1.7914438502673797,
2352
+ "grad_norm": 0.9244107007980347,
2353
+ "learning_rate": 4.616650873580411e-06,
2354
+ "loss": 0.6467,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 1.7967914438502675,
2359
+ "grad_norm": 0.8985466361045837,
2360
+ "learning_rate": 4.614412931401715e-06,
2361
+ "loss": 0.5621,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 1.8021390374331552,
2366
+ "grad_norm": 0.9541940093040466,
2367
+ "learning_rate": 4.612169021533276e-06,
2368
+ "loss": 0.5175,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 1.807486631016043,
2373
+ "grad_norm": 1.0680545568466187,
2374
+ "learning_rate": 4.609919150308273e-06,
2375
+ "loss": 0.6331,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 1.8128342245989306,
2380
+ "grad_norm": 1.0528939962387085,
2381
+ "learning_rate": 4.607663324076711e-06,
2382
+ "loss": 0.5435,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 1.8181818181818183,
2387
+ "grad_norm": 1.0774506330490112,
2388
+ "learning_rate": 4.605401549205404e-06,
2389
+ "loss": 0.7387,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 1.8235294117647058,
2394
+ "grad_norm": 1.2670179605484009,
2395
+ "learning_rate": 4.603133832077953e-06,
2396
+ "loss": 0.6235,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 1.8288770053475936,
2401
+ "grad_norm": 1.0826292037963867,
2402
+ "learning_rate": 4.600860179094732e-06,
2403
+ "loss": 0.6937,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 1.8342245989304813,
2408
+ "grad_norm": 1.0795179605484009,
2409
+ "learning_rate": 4.5985805966728675e-06,
2410
+ "loss": 0.6641,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 1.839572192513369,
2415
+ "grad_norm": 0.9684019088745117,
2416
+ "learning_rate": 4.596295091246221e-06,
2417
+ "loss": 0.5393,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 1.8449197860962567,
2422
+ "grad_norm": 1.0225133895874023,
2423
+ "learning_rate": 4.594003669265371e-06,
2424
+ "loss": 0.607,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 1.8502673796791442,
2429
+ "grad_norm": 1.2203558683395386,
2430
+ "learning_rate": 4.591706337197597e-06,
2431
+ "loss": 0.6652,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 1.855614973262032,
2436
+ "grad_norm": 0.9773402810096741,
2437
+ "learning_rate": 4.589403101526854e-06,
2438
+ "loss": 0.4763,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 1.8609625668449197,
2443
+ "grad_norm": 1.0512480735778809,
2444
+ "learning_rate": 4.587093968753765e-06,
2445
+ "loss": 0.678,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 1.8663101604278074,
2450
+ "grad_norm": 0.9488521814346313,
2451
+ "learning_rate": 4.584778945395594e-06,
2452
+ "loss": 0.4685,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 1.8716577540106951,
2457
+ "grad_norm": 1.2795664072036743,
2458
+ "learning_rate": 4.582458037986231e-06,
2459
+ "loss": 0.6796,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 1.8770053475935828,
2464
+ "grad_norm": 1.4291759729385376,
2465
+ "learning_rate": 4.580131253076171e-06,
2466
+ "loss": 0.9619,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 1.8823529411764706,
2471
+ "grad_norm": 1.4512319564819336,
2472
+ "learning_rate": 4.5777985972325016e-06,
2473
+ "loss": 0.622,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 1.8877005347593583,
2478
+ "grad_norm": 0.8678804636001587,
2479
+ "learning_rate": 4.575460077038877e-06,
2480
+ "loss": 0.4037,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 1.893048128342246,
2485
+ "grad_norm": 1.6955478191375732,
2486
+ "learning_rate": 4.573115699095505e-06,
2487
+ "loss": 0.9417,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 1.8983957219251337,
2492
+ "grad_norm": 0.9945119619369507,
2493
+ "learning_rate": 4.570765470019125e-06,
2494
+ "loss": 0.4733,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 1.9037433155080214,
2499
+ "grad_norm": 1.2008395195007324,
2500
+ "learning_rate": 4.5684093964429906e-06,
2501
+ "loss": 0.642,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 1.9090909090909092,
2506
+ "grad_norm": 0.9995360970497131,
2507
+ "learning_rate": 4.566047485016853e-06,
2508
+ "loss": 0.4843,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 1.914438502673797,
2513
+ "grad_norm": 1.633129358291626,
2514
+ "learning_rate": 4.563679742406935e-06,
2515
+ "loss": 0.6759,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 1.9197860962566846,
2520
+ "grad_norm": 1.164298176765442,
2521
+ "learning_rate": 4.5613061752959236e-06,
2522
+ "loss": 1.1817,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 1.9251336898395723,
2527
+ "grad_norm": 1.0954480171203613,
2528
+ "learning_rate": 4.558926790382941e-06,
2529
+ "loss": 0.935,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 1.93048128342246,
2534
+ "grad_norm": 1.215140700340271,
2535
+ "learning_rate": 4.556541594383528e-06,
2536
+ "loss": 0.6227,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 1.9358288770053476,
2541
+ "grad_norm": 0.7756662368774414,
2542
+ "learning_rate": 4.554150594029631e-06,
2543
+ "loss": 0.3146,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 1.9411764705882353,
2548
+ "grad_norm": 1.15339994430542,
2549
+ "learning_rate": 4.551753796069577e-06,
2550
+ "loss": 0.6296,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 1.946524064171123,
2555
+ "grad_norm": 0.9783138632774353,
2556
+ "learning_rate": 4.5493512072680535e-06,
2557
+ "loss": 0.6297,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 1.9518716577540107,
2562
+ "grad_norm": 1.1024492979049683,
2563
+ "learning_rate": 4.546942834406094e-06,
2564
+ "loss": 0.7985,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 1.9572192513368984,
2569
+ "grad_norm": 1.4505765438079834,
2570
+ "learning_rate": 4.544528684281056e-06,
2571
+ "loss": 0.4953,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 1.962566844919786,
2576
+ "grad_norm": 1.0261201858520508,
2577
+ "learning_rate": 4.5421087637066065e-06,
2578
+ "loss": 0.4941,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 1.9679144385026737,
2583
+ "grad_norm": 0.8985170722007751,
2584
+ "learning_rate": 4.539683079512692e-06,
2585
+ "loss": 0.7235,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 1.9732620320855614,
2590
+ "grad_norm": 1.1936858892440796,
2591
+ "learning_rate": 4.537251638545532e-06,
2592
+ "loss": 0.5973,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 1.9786096256684491,
2597
+ "grad_norm": 0.9097899794578552,
2598
+ "learning_rate": 4.534814447667591e-06,
2599
+ "loss": 0.3087,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 1.9839572192513368,
2604
+ "grad_norm": 0.8672341108322144,
2605
+ "learning_rate": 4.532371513757564e-06,
2606
+ "loss": 0.5131,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 1.9893048128342246,
2611
+ "grad_norm": 1.1601113080978394,
2612
+ "learning_rate": 4.529922843710354e-06,
2613
+ "loss": 0.6784,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 1.9946524064171123,
2618
+ "grad_norm": 2.197719097137451,
2619
+ "learning_rate": 4.52746844443705e-06,
2620
+ "loss": 0.6617,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 2.0,
2625
+ "grad_norm": 0.9790298342704773,
2626
+ "learning_rate": 4.525008322864917e-06,
2627
+ "loss": 0.6739,
2628
+ "step": 374
2629
+ }
2630
+ ],
2631
+ "logging_steps": 1,
2632
+ "max_steps": 1870,
2633
+ "num_input_tokens_seen": 0,
2634
+ "num_train_epochs": 10,
2635
+ "save_steps": 208,
2636
+ "stateful_callbacks": {
2637
+ "TrainerControl": {
2638
+ "args": {
2639
+ "should_epoch_stop": false,
2640
+ "should_evaluate": false,
2641
+ "should_log": false,
2642
+ "should_save": true,
2643
+ "should_training_stop": false
2644
+ },
2645
+ "attributes": {}
2646
+ }
2647
+ },
2648
+ "total_flos": 1.023726260846592e+17,
2649
+ "train_batch_size": 1,
2650
+ "trial_name": null,
2651
+ "trial_params": null
2652
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-374/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/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 %}
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 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": 10000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "4.55.0"
9
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-561/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/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 %}
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 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": 10000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "4.55.0"
9
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/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
+ }
qwen_2_5_7b_math_instruct/limo_filtered_combined/checkpoint-935/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff