danny2507 commited on
Commit
eb6a6e5
·
verified ·
1 Parent(s): 2aaf56b

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. cls_qwen_orderkd_first_l005/checkpoint-200/adapter_config.json +52 -0
  2. cls_qwen_orderkd_first_l005/checkpoint-200/tokenizer_config.json +202 -0
  3. cls_qwen_orderkd_first_l005/checkpoint-400/chat_template.jinja +54 -0
  4. cls_qwen_orderkd_first_l005/checkpoint-400/tokenizer_config.json +202 -0
  5. cls_qwen_orderkd_first_l02/README.md +208 -0
  6. cls_qwen_orderkd_first_l02/adapter_config.json +52 -0
  7. cls_qwen_orderkd_first_l02/chat_template.jinja +54 -0
  8. cls_qwen_orderkd_first_l02/checkpoint-200/README.md +208 -0
  9. cls_qwen_orderkd_first_l02/checkpoint-200/adapter_config.json +52 -0
  10. cls_qwen_orderkd_first_l02/checkpoint-200/chat_template.jinja +54 -0
  11. cls_qwen_orderkd_first_l02/checkpoint-200/tokenizer_config.json +202 -0
  12. cls_qwen_orderkd_first_l02/checkpoint-400/README.md +208 -0
  13. cls_qwen_orderkd_first_l02/checkpoint-400/adapter_config.json +52 -0
  14. cls_qwen_orderkd_first_l02/checkpoint-400/chat_template.jinja +54 -0
  15. cls_qwen_orderkd_first_l02/checkpoint-400/tokenizer_config.json +202 -0
  16. cls_qwen_orderkd_first_l02/tokenizer_config.json +202 -0
  17. cls_qwen_orderkd_first_l02/train_metrics.json +1874 -0
  18. cls_qwen_orderkd_mid_l005/README.md +208 -0
  19. cls_qwen_orderkd_mid_l005/adapter_config.json +52 -0
  20. cls_qwen_orderkd_mid_l005/chat_template.jinja +54 -0
  21. cls_qwen_orderkd_mid_l005/checkpoint-200/README.md +208 -0
  22. cls_qwen_orderkd_mid_l005/checkpoint-200/adapter_config.json +52 -0
  23. cls_qwen_orderkd_mid_l005/checkpoint-200/tokenizer_config.json +202 -0
  24. cls_qwen_orderkd_mid_l005/checkpoint-400/adapter_config.json +52 -0
  25. cls_qwen_orderkd_mid_l005/tokenizer_config.json +202 -0
  26. cls_qwen_orderkd_mid_l005/train_metrics.json +1874 -0
  27. cls_qwen_orderkd_mid_l02/README.md +208 -0
  28. cls_qwen_orderkd_mid_l02/chat_template.jinja +54 -0
  29. cls_smollm2_orderkd_first_l005/README.md +208 -0
  30. cls_smollm2_orderkd_first_l005/adapter_config.json +52 -0
  31. cls_smollm2_orderkd_first_l005/chat_template.jinja +6 -0
  32. cls_smollm2_orderkd_first_l005/checkpoint-200/README.md +208 -0
  33. cls_smollm2_orderkd_first_l005/checkpoint-200/adapter_config.json +52 -0
  34. cls_smollm2_orderkd_first_l005/checkpoint-200/chat_template.jinja +6 -0
  35. cls_smollm2_orderkd_first_l005/checkpoint-200/tokenizer.json +0 -0
  36. cls_smollm2_orderkd_first_l005/checkpoint-200/tokenizer_config.json +155 -0
  37. cls_smollm2_orderkd_first_l005/checkpoint-400/README.md +208 -0
  38. cls_smollm2_orderkd_first_l005/checkpoint-400/adapter_config.json +52 -0
  39. cls_smollm2_orderkd_first_l005/checkpoint-400/chat_template.jinja +6 -0
  40. cls_smollm2_orderkd_first_l005/checkpoint-400/tokenizer.json +0 -0
  41. cls_smollm2_orderkd_first_l005/checkpoint-400/tokenizer_config.json +155 -0
  42. cls_smollm2_orderkd_first_l005/tokenizer.json +0 -0
  43. cls_smollm2_orderkd_first_l005/tokenizer_config.json +155 -0
  44. cls_smollm2_orderkd_first_l005/train_metrics.json +1874 -0
  45. cls_smollm2_orderkd_first_l01/checkpoint-200/tokenizer.json +0 -0
  46. cls_smollm2_orderkd_first_l01/checkpoint-400/adapter_config.json +52 -0
  47. cls_smollm2_orderkd_first_l01/checkpoint-400/chat_template.jinja +6 -0
  48. cls_smollm2_orderkd_first_l01/checkpoint-400/tokenizer.json +0 -0
  49. cls_smollm2_orderkd_first_l01/checkpoint-400/tokenizer_config.json +155 -0
  50. cls_smollm2_orderkd_first_l02/README.md +208 -0
cls_qwen_orderkd_first_l005/checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "k_proj",
38
+ "up_proj",
39
+ "down_proj",
40
+ "gate_proj",
41
+ "q_proj",
42
+ "v_proj",
43
+ "o_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_first_l005/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_first_l005/checkpoint-400/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
cls_qwen_orderkd_first_l005/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_first_l02/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_qwen_orderkd_first_l02/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "k_proj",
38
+ "gate_proj",
39
+ "q_proj",
40
+ "o_proj",
41
+ "up_proj",
42
+ "v_proj",
43
+ "down_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_first_l02/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
cls_qwen_orderkd_first_l02/checkpoint-200/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_qwen_orderkd_first_l02/checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "k_proj",
38
+ "gate_proj",
39
+ "q_proj",
40
+ "o_proj",
41
+ "up_proj",
42
+ "v_proj",
43
+ "down_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_first_l02/checkpoint-200/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
cls_qwen_orderkd_first_l02/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_first_l02/checkpoint-400/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_qwen_orderkd_first_l02/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "k_proj",
38
+ "gate_proj",
39
+ "q_proj",
40
+ "o_proj",
41
+ "up_proj",
42
+ "v_proj",
43
+ "down_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_first_l02/checkpoint-400/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
cls_qwen_orderkd_first_l02/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_first_l02/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_first_l02/train_metrics.json ADDED
@@ -0,0 +1,1874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "loss_log": [
3
+ {
4
+ "global_step": 20,
5
+ "optimizer_step": 2,
6
+ "lr": 4.347826086956522e-06,
7
+ "lm_loss": 1.6699644327163696,
8
+ "order_loss": 0.69140625,
9
+ "ret_loss": 0.0,
10
+ "pretrain_loss": 0.0,
11
+ "total_loss": 1.8086363077163696
12
+ },
13
+ {
14
+ "global_step": 40,
15
+ "optimizer_step": 5,
16
+ "lr": 1.0869565217391305e-05,
17
+ "lm_loss": 0.11095316708087921,
18
+ "order_loss": 0.6875,
19
+ "ret_loss": 0.0,
20
+ "pretrain_loss": 0.0,
21
+ "total_loss": 0.2486484795808792
22
+ },
23
+ {
24
+ "global_step": 60,
25
+ "optimizer_step": 7,
26
+ "lr": 1.5217391304347828e-05,
27
+ "lm_loss": 0.679000198841095,
28
+ "order_loss": 0.68359375,
29
+ "ret_loss": 0.0,
30
+ "pretrain_loss": 0.0,
31
+ "total_loss": 0.815718948841095
32
+ },
33
+ {
34
+ "global_step": 80,
35
+ "optimizer_step": 10,
36
+ "lr": 2.173913043478261e-05,
37
+ "lm_loss": 0.6441856026649475,
38
+ "order_loss": 0.703125,
39
+ "ret_loss": 0.0,
40
+ "pretrain_loss": 0.0,
41
+ "total_loss": 0.7848106026649475
42
+ },
43
+ {
44
+ "global_step": 100,
45
+ "optimizer_step": 12,
46
+ "lr": 2.608695652173913e-05,
47
+ "lm_loss": 0.4895974099636078,
48
+ "order_loss": 0.66796875,
49
+ "ret_loss": 0.0,
50
+ "pretrain_loss": 0.0,
51
+ "total_loss": 0.6233865022659302
52
+ },
53
+ {
54
+ "global_step": 120,
55
+ "optimizer_step": 15,
56
+ "lr": 3.260869565217392e-05,
57
+ "lm_loss": 0.49217724800109863,
58
+ "order_loss": 0.6875,
59
+ "ret_loss": 0.0,
60
+ "pretrain_loss": 0.0,
61
+ "total_loss": 0.6298725605010986
62
+ },
63
+ {
64
+ "global_step": 140,
65
+ "optimizer_step": 17,
66
+ "lr": 3.695652173913043e-05,
67
+ "lm_loss": 0.08086223900318146,
68
+ "order_loss": 0.67578125,
69
+ "ret_loss": 0.0,
70
+ "pretrain_loss": 0.0,
71
+ "total_loss": 0.21562786400318146
72
+ },
73
+ {
74
+ "global_step": 160,
75
+ "optimizer_step": 20,
76
+ "lr": 4.347826086956522e-05,
77
+ "lm_loss": 0.22889940440654755,
78
+ "order_loss": 0.67578125,
79
+ "ret_loss": 0.0,
80
+ "pretrain_loss": 0.0,
81
+ "total_loss": 0.36366504430770874
82
+ },
83
+ {
84
+ "global_step": 180,
85
+ "optimizer_step": 22,
86
+ "lr": 4.782608695652174e-05,
87
+ "lm_loss": 0.026579204946756363,
88
+ "order_loss": 0.66015625,
89
+ "ret_loss": 0.0,
90
+ "pretrain_loss": 0.0,
91
+ "total_loss": 0.15841513872146606
92
+ },
93
+ {
94
+ "global_step": 200,
95
+ "optimizer_step": 25,
96
+ "lr": 4.9997541293989384e-05,
97
+ "lm_loss": 0.13611207902431488,
98
+ "order_loss": 0.6484375,
99
+ "ret_loss": 0.0,
100
+ "pretrain_loss": 0.0,
101
+ "total_loss": 0.2659949064254761
102
+ },
103
+ {
104
+ "global_step": 220,
105
+ "optimizer_step": 27,
106
+ "lr": 4.999016565957633e-05,
107
+ "lm_loss": 0.08699542284011841,
108
+ "order_loss": 0.65234375,
109
+ "ret_loss": 0.0,
110
+ "pretrain_loss": 0.0,
111
+ "total_loss": 0.2178547978401184
112
+ },
113
+ {
114
+ "global_step": 240,
115
+ "optimizer_step": 30,
116
+ "lr": 4.996988640512931e-05,
117
+ "lm_loss": 0.3147357702255249,
118
+ "order_loss": 0.65234375,
119
+ "ret_loss": 0.0,
120
+ "pretrain_loss": 0.0,
121
+ "total_loss": 0.4455951452255249
122
+ },
123
+ {
124
+ "global_step": 260,
125
+ "optimizer_step": 32,
126
+ "lr": 4.995022691166621e-05,
127
+ "lm_loss": 0.20639567077159882,
128
+ "order_loss": 0.69921875,
129
+ "ret_loss": 0.0,
130
+ "pretrain_loss": 0.0,
131
+ "total_loss": 0.34604412317276
132
+ },
133
+ {
134
+ "global_step": 280,
135
+ "optimizer_step": 35,
136
+ "lr": 4.991153735294049e-05,
137
+ "lm_loss": 0.43832501769065857,
138
+ "order_loss": 0.6171875,
139
+ "ret_loss": 0.0,
140
+ "pretrain_loss": 0.0,
141
+ "total_loss": 0.561860203742981
142
+ },
143
+ {
144
+ "global_step": 300,
145
+ "optimizer_step": 37,
146
+ "lr": 4.987961816680492e-05,
147
+ "lm_loss": 0.32394349575042725,
148
+ "order_loss": 0.6875,
149
+ "ret_loss": 0.0,
150
+ "pretrain_loss": 0.0,
151
+ "total_loss": 0.46163880825042725
152
+ },
153
+ {
154
+ "global_step": 320,
155
+ "optimizer_step": 40,
156
+ "lr": 4.9822565862832806e-05,
157
+ "lm_loss": 0.1454029530286789,
158
+ "order_loss": 0.6171875,
159
+ "ret_loss": 0.0,
160
+ "pretrain_loss": 0.0,
161
+ "total_loss": 0.2689381241798401
162
+ },
163
+ {
164
+ "global_step": 340,
165
+ "optimizer_step": 42,
166
+ "lr": 4.9778426220595456e-05,
167
+ "lm_loss": 0.06867104768753052,
168
+ "order_loss": 0.6484375,
169
+ "ret_loss": 0.0,
170
+ "pretrain_loss": 0.0,
171
+ "total_loss": 0.19855386018753052
172
+ },
173
+ {
174
+ "global_step": 360,
175
+ "optimizer_step": 45,
176
+ "lr": 4.970308130276272e-05,
177
+ "lm_loss": 0.22596974670886993,
178
+ "order_loss": 0.640625,
179
+ "ret_loss": 0.0,
180
+ "pretrain_loss": 0.0,
181
+ "total_loss": 0.35389941930770874
182
+ },
183
+ {
184
+ "global_step": 380,
185
+ "optimizer_step": 47,
186
+ "lr": 4.96467754629559e-05,
187
+ "lm_loss": 0.14881941676139832,
188
+ "order_loss": 0.66796875,
189
+ "ret_loss": 0.0,
190
+ "pretrain_loss": 0.0,
191
+ "total_loss": 0.2826084792613983
192
+ },
193
+ {
194
+ "global_step": 400,
195
+ "optimizer_step": 50,
196
+ "lr": 4.955323054879298e-05,
197
+ "lm_loss": 0.1768292784690857,
198
+ "order_loss": 0.6484375,
199
+ "ret_loss": 0.0,
200
+ "pretrain_loss": 0.0,
201
+ "total_loss": 0.3067120909690857
202
+ },
203
+ {
204
+ "global_step": 420,
205
+ "optimizer_step": 52,
206
+ "lr": 4.948482772521345e-05,
207
+ "lm_loss": 0.07656032592058182,
208
+ "order_loss": 0.6015625,
209
+ "ret_loss": 0.0,
210
+ "pretrain_loss": 0.0,
211
+ "total_loss": 0.19667750597000122
212
+ },
213
+ {
214
+ "global_step": 440,
215
+ "optimizer_step": 55,
216
+ "lr": 4.937319780454559e-05,
217
+ "lm_loss": 0.14166221022605896,
218
+ "order_loss": 0.6484375,
219
+ "ret_loss": 0.0,
220
+ "pretrain_loss": 0.0,
221
+ "total_loss": 0.27154502272605896
222
+ },
223
+ {
224
+ "global_step": 460,
225
+ "optimizer_step": 57,
226
+ "lr": 4.929278208117378e-05,
227
+ "lm_loss": 0.1494860202074051,
228
+ "order_loss": 0.66796875,
229
+ "ret_loss": 0.0,
230
+ "pretrain_loss": 0.0,
231
+ "total_loss": 0.2832750678062439
232
+ },
233
+ {
234
+ "global_step": 480,
235
+ "optimizer_step": 60,
236
+ "lr": 4.916320437477008e-05,
237
+ "lm_loss": 0.4734064042568207,
238
+ "order_loss": 0.57421875,
239
+ "ret_loss": 0.0,
240
+ "pretrain_loss": 0.0,
241
+ "total_loss": 0.5881525278091431
242
+ },
243
+ {
244
+ "global_step": 500,
245
+ "optimizer_step": 62,
246
+ "lr": 4.907087460240999e-05,
247
+ "lm_loss": 0.23723165690898895,
248
+ "order_loss": 0.58203125,
249
+ "ret_loss": 0.0,
250
+ "pretrain_loss": 0.0,
251
+ "total_loss": 0.35344260931015015
252
+ },
253
+ {
254
+ "global_step": 520,
255
+ "optimizer_step": 65,
256
+ "lr": 4.892350839330522e-05,
257
+ "lm_loss": 0.029165402054786682,
258
+ "order_loss": 0.55859375,
259
+ "ret_loss": 0.0,
260
+ "pretrain_loss": 0.0,
261
+ "total_loss": 0.14098180830478668
262
+ },
263
+ {
264
+ "global_step": 540,
265
+ "optimizer_step": 67,
266
+ "lr": 4.881937806807241e-05,
267
+ "lm_loss": 0.031027283519506454,
268
+ "order_loss": 0.55078125,
269
+ "ret_loss": 0.0,
270
+ "pretrain_loss": 0.0,
271
+ "total_loss": 0.14137884974479675
272
+ },
273
+ {
274
+ "global_step": 560,
275
+ "optimizer_step": 70,
276
+ "lr": 4.865440450576874e-05,
277
+ "lm_loss": 0.1048983708024025,
278
+ "order_loss": 0.56640625,
279
+ "ret_loss": 0.0,
280
+ "pretrain_loss": 0.0,
281
+ "total_loss": 0.2181796133518219
282
+ },
283
+ {
284
+ "global_step": 580,
285
+ "optimizer_step": 72,
286
+ "lr": 4.853860162957552e-05,
287
+ "lm_loss": 0.622389018535614,
288
+ "order_loss": 0.58203125,
289
+ "ret_loss": 0.0,
290
+ "pretrain_loss": 0.0,
291
+ "total_loss": 0.738599956035614
292
+ },
293
+ {
294
+ "global_step": 600,
295
+ "optimizer_step": 75,
296
+ "lr": 4.8356223507364996e-05,
297
+ "lm_loss": 0.07297493517398834,
298
+ "order_loss": 0.59765625,
299
+ "ret_loss": 0.0,
300
+ "pretrain_loss": 0.0,
301
+ "total_loss": 0.19260384142398834
302
+ },
303
+ {
304
+ "global_step": 620,
305
+ "optimizer_step": 77,
306
+ "lr": 4.822889043057446e-05,
307
+ "lm_loss": 0.3936348259449005,
308
+ "order_loss": 0.67578125,
309
+ "ret_loss": 0.0,
310
+ "pretrain_loss": 0.0,
311
+ "total_loss": 0.5284004211425781
312
+ },
313
+ {
314
+ "global_step": 640,
315
+ "optimizer_step": 80,
316
+ "lr": 4.802933193625593e-05,
317
+ "lm_loss": 0.0912988930940628,
318
+ "order_loss": 0.671875,
319
+ "ret_loss": 0.0,
320
+ "pretrain_loss": 0.0,
321
+ "total_loss": 0.2260645180940628
322
+ },
323
+ {
324
+ "global_step": 660,
325
+ "optimizer_step": 82,
326
+ "lr": 4.789062518269812e-05,
327
+ "lm_loss": 0.32915419340133667,
328
+ "order_loss": 0.6328125,
329
+ "ret_loss": 0.0,
330
+ "pretrain_loss": 0.0,
331
+ "total_loss": 0.45610731840133667
332
+ },
333
+ {
334
+ "global_step": 680,
335
+ "optimizer_step": 85,
336
+ "lr": 4.767413162299501e-05,
337
+ "lm_loss": 0.3757513165473938,
338
+ "order_loss": 0.6953125,
339
+ "ret_loss": 0.0,
340
+ "pretrain_loss": 0.0,
341
+ "total_loss": 0.5144231915473938
342
+ },
343
+ {
344
+ "global_step": 700,
345
+ "optimizer_step": 87,
346
+ "lr": 4.752422169756048e-05,
347
+ "lm_loss": 0.11131633818149567,
348
+ "order_loss": 0.57421875,
349
+ "ret_loss": 0.0,
350
+ "pretrain_loss": 0.0,
351
+ "total_loss": 0.22606243193149567
352
+ },
353
+ {
354
+ "global_step": 720,
355
+ "optimizer_step": 90,
356
+ "lr": 4.729105919657818e-05,
357
+ "lm_loss": 0.003945653326809406,
358
+ "order_loss": 0.58203125,
359
+ "ret_loss": 0.0,
360
+ "pretrain_loss": 0.0,
361
+ "total_loss": 0.12015659362077713
362
+ },
363
+ {
364
+ "global_step": 740,
365
+ "optimizer_step": 92,
366
+ "lr": 4.7130130375625305e-05,
367
+ "lm_loss": 0.2080662101507187,
368
+ "order_loss": 0.67578125,
369
+ "ret_loss": 0.0,
370
+ "pretrain_loss": 0.0,
371
+ "total_loss": 0.3428318500518799
372
+ },
373
+ {
374
+ "global_step": 760,
375
+ "optimizer_step": 95,
376
+ "lr": 4.6880585547718845e-05,
377
+ "lm_loss": 0.0018887391779571772,
378
+ "order_loss": 0.60546875,
379
+ "ret_loss": 0.0,
380
+ "pretrain_loss": 0.0,
381
+ "total_loss": 0.12298248708248138
382
+ },
383
+ {
384
+ "global_step": 780,
385
+ "optimizer_step": 97,
386
+ "lr": 4.670883565255264e-05,
387
+ "lm_loss": 0.35624393820762634,
388
+ "order_loss": 0.59765625,
389
+ "ret_loss": 0.0,
390
+ "pretrain_loss": 0.0,
391
+ "total_loss": 0.47587284445762634
392
+ },
393
+ {
394
+ "global_step": 800,
395
+ "optimizer_step": 100,
396
+ "lr": 4.6443215250006806e-05,
397
+ "lm_loss": 0.3555290997028351,
398
+ "order_loss": 0.60546875,
399
+ "ret_loss": 0.0,
400
+ "pretrain_loss": 0.0,
401
+ "total_loss": 0.4766228497028351
402
+ },
403
+ {
404
+ "global_step": 820,
405
+ "optimizer_step": 102,
406
+ "lr": 4.626085540370762e-05,
407
+ "lm_loss": 0.004661073908209801,
408
+ "order_loss": 0.5234375,
409
+ "ret_loss": 0.0,
410
+ "pretrain_loss": 0.0,
411
+ "total_loss": 0.10915326327085495
412
+ },
413
+ {
414
+ "global_step": 840,
415
+ "optimizer_step": 105,
416
+ "lr": 4.597948593966256e-05,
417
+ "lm_loss": 0.14643071591854095,
418
+ "order_loss": 0.63671875,
419
+ "ret_loss": 0.0,
420
+ "pretrain_loss": 0.0,
421
+ "total_loss": 0.27338385581970215
422
+ },
423
+ {
424
+ "global_step": 860,
425
+ "optimizer_step": 107,
426
+ "lr": 4.5786740307563636e-05,
427
+ "lm_loss": 0.023909086361527443,
428
+ "order_loss": 0.52734375,
429
+ "ret_loss": 0.0,
430
+ "pretrain_loss": 0.0,
431
+ "total_loss": 0.1293778419494629
432
+ },
433
+ {
434
+ "global_step": 880,
435
+ "optimizer_step": 110,
436
+ "lr": 4.5489967654649474e-05,
437
+ "lm_loss": 0.0013749093050137162,
438
+ "order_loss": 0.625,
439
+ "ret_loss": 0.0,
440
+ "pretrain_loss": 0.0,
441
+ "total_loss": 0.12637491524219513
442
+ },
443
+ {
444
+ "global_step": 900,
445
+ "optimizer_step": 112,
446
+ "lr": 4.528707316878232e-05,
447
+ "lm_loss": 0.4079589545726776,
448
+ "order_loss": 0.50390625,
449
+ "ret_loss": 0.0,
450
+ "pretrain_loss": 0.0,
451
+ "total_loss": 0.508544921875
452
+ },
453
+ {
454
+ "global_step": 920,
455
+ "optimizer_step": 115,
456
+ "lr": 4.497526213395623e-05,
457
+ "lm_loss": 0.15249277651309967,
458
+ "order_loss": 0.55078125,
459
+ "ret_loss": 0.0,
460
+ "pretrain_loss": 0.0,
461
+ "total_loss": 0.2628443241119385
462
+ },
463
+ {
464
+ "global_step": 940,
465
+ "optimizer_step": 117,
466
+ "lr": 4.476246820180259e-05,
467
+ "lm_loss": 0.5319370031356812,
468
+ "order_loss": 0.54296875,
469
+ "ret_loss": 0.0,
470
+ "pretrain_loss": 0.0,
471
+ "total_loss": 0.6403354406356812
472
+ },
473
+ {
474
+ "global_step": 960,
475
+ "optimizer_step": 120,
476
+ "lr": 4.443600207791081e-05,
477
+ "lm_loss": 0.04810849949717522,
478
+ "order_loss": 0.62109375,
479
+ "ret_loss": 0.0,
480
+ "pretrain_loss": 0.0,
481
+ "total_loss": 0.17213194072246552
482
+ },
483
+ {
484
+ "global_step": 980,
485
+ "optimizer_step": 122,
486
+ "lr": 4.421357027581921e-05,
487
+ "lm_loss": 0.23312771320343018,
488
+ "order_loss": 0.5703125,
489
+ "ret_loss": 0.0,
490
+ "pretrain_loss": 0.0,
491
+ "total_loss": 0.3473855257034302
492
+ },
493
+ {
494
+ "global_step": 1000,
495
+ "optimizer_step": 125,
496
+ "lr": 4.38728503704354e-05,
497
+ "lm_loss": 0.06427530199289322,
498
+ "order_loss": 0.56640625,
499
+ "ret_loss": 0.0,
500
+ "pretrain_loss": 0.0,
501
+ "total_loss": 0.17755654454231262
502
+ },
503
+ {
504
+ "global_step": 1020,
505
+ "optimizer_step": 127,
506
+ "lr": 4.364105412207914e-05,
507
+ "lm_loss": 0.08760474622249603,
508
+ "order_loss": 0.61328125,
509
+ "ret_loss": 0.0,
510
+ "pretrain_loss": 0.0,
511
+ "total_loss": 0.21016333997249603
512
+ },
513
+ {
514
+ "global_step": 1040,
515
+ "optimizer_step": 130,
516
+ "lr": 4.328649926419819e-05,
517
+ "lm_loss": 0.021755974739789963,
518
+ "order_loss": 0.52734375,
519
+ "ret_loss": 0.0,
520
+ "pretrain_loss": 0.0,
521
+ "total_loss": 0.12722472846508026
522
+ },
523
+ {
524
+ "global_step": 1060,
525
+ "optimizer_step": 132,
526
+ "lr": 4.304562350447008e-05,
527
+ "lm_loss": 0.05028771236538887,
528
+ "order_loss": 0.640625,
529
+ "ret_loss": 0.0,
530
+ "pretrain_loss": 0.0,
531
+ "total_loss": 0.17821739614009857
532
+ },
533
+ {
534
+ "global_step": 1080,
535
+ "optimizer_step": 135,
536
+ "lr": 4.267766952966369e-05,
537
+ "lm_loss": 0.10077612102031708,
538
+ "order_loss": 0.58203125,
539
+ "ret_loss": 0.0,
540
+ "pretrain_loss": 0.0,
541
+ "total_loss": 0.21698705852031708
542
+ },
543
+ {
544
+ "global_step": 1100,
545
+ "optimizer_step": 137,
546
+ "lr": 4.242801035442058e-05,
547
+ "lm_loss": 0.05271952226758003,
548
+ "order_loss": 0.61328125,
549
+ "ret_loss": 0.0,
550
+ "pretrain_loss": 0.0,
551
+ "total_loss": 0.17527811229228973
552
+ },
553
+ {
554
+ "global_step": 1120,
555
+ "optimizer_step": 140,
556
+ "lr": 4.204710956908763e-05,
557
+ "lm_loss": 0.14971713721752167,
558
+ "order_loss": 0.56640625,
559
+ "ret_loss": 0.0,
560
+ "pretrain_loss": 0.0,
561
+ "total_loss": 0.26299840211868286
562
+ },
563
+ {
564
+ "global_step": 1140,
565
+ "optimizer_step": 142,
566
+ "lr": 4.178897387117546e-05,
567
+ "lm_loss": 0.055816471576690674,
568
+ "order_loss": 0.57421875,
569
+ "ret_loss": 0.0,
570
+ "pretrain_loss": 0.0,
571
+ "total_loss": 0.17056256532669067
572
+ },
573
+ {
574
+ "global_step": 1160,
575
+ "optimizer_step": 145,
576
+ "lr": 4.139559449654561e-05,
577
+ "lm_loss": 0.27207791805267334,
578
+ "order_loss": 0.55078125,
579
+ "ret_loss": 0.0,
580
+ "pretrain_loss": 0.0,
581
+ "total_loss": 0.38242948055267334
582
+ },
583
+ {
584
+ "global_step": 1180,
585
+ "optimizer_step": 147,
586
+ "lr": 4.1129299588552193e-05,
587
+ "lm_loss": 0.16886401176452637,
588
+ "order_loss": 0.625,
589
+ "ret_loss": 0.0,
590
+ "pretrain_loss": 0.0,
591
+ "total_loss": 0.29386401176452637
592
+ },
593
+ {
594
+ "global_step": 1200,
595
+ "optimizer_step": 150,
596
+ "lr": 4.072392518512623e-05,
597
+ "lm_loss": 0.051917243748903275,
598
+ "order_loss": 0.375,
599
+ "ret_loss": 0.0,
600
+ "pretrain_loss": 0.0,
601
+ "total_loss": 0.12711255252361298
602
+ },
603
+ {
604
+ "global_step": 1220,
605
+ "optimizer_step": 152,
606
+ "lr": 4.0449798409325665e-05,
607
+ "lm_loss": 0.14206039905548096,
608
+ "order_loss": 0.57421875,
609
+ "ret_loss": 0.0,
610
+ "pretrain_loss": 0.0,
611
+ "total_loss": 0.25680649280548096
612
+ },
613
+ {
614
+ "global_step": 1240,
615
+ "optimizer_step": 155,
616
+ "lr": 4.0032927282460146e-05,
617
+ "lm_loss": 0.0809120163321495,
618
+ "order_loss": 0.57421875,
619
+ "ret_loss": 0.0,
620
+ "pretrain_loss": 0.0,
621
+ "total_loss": 0.1956581175327301
622
+ },
623
+ {
624
+ "global_step": 1260,
625
+ "optimizer_step": 157,
626
+ "lr": 3.9751305608428205e-05,
627
+ "lm_loss": 0.09020818769931793,
628
+ "order_loss": 0.5390625,
629
+ "ret_loss": 0.0,
630
+ "pretrain_loss": 0.0,
631
+ "total_loss": 0.19811834394931793
632
+ },
633
+ {
634
+ "global_step": 1280,
635
+ "optimizer_step": 160,
636
+ "lr": 3.932345019579495e-05,
637
+ "lm_loss": 0.0453609861433506,
638
+ "order_loss": 0.59765625,
639
+ "ret_loss": 0.0,
640
+ "pretrain_loss": 0.0,
641
+ "total_loss": 0.1649898886680603
642
+ },
643
+ {
644
+ "global_step": 1300,
645
+ "optimizer_step": 162,
646
+ "lr": 3.90346798061902e-05,
647
+ "lm_loss": 0.04923363775014877,
648
+ "order_loss": 0.49609375,
649
+ "ret_loss": 0.0,
650
+ "pretrain_loss": 0.0,
651
+ "total_loss": 0.14835473895072937
652
+ },
653
+ {
654
+ "global_step": 1320,
655
+ "optimizer_step": 165,
656
+ "lr": 3.859636604786372e-05,
657
+ "lm_loss": 0.002456007758155465,
658
+ "order_loss": 0.5078125,
659
+ "ret_loss": 0.0,
660
+ "pretrain_loss": 0.0,
661
+ "total_loss": 0.10401850938796997
662
+ },
663
+ {
664
+ "global_step": 1340,
665
+ "optimizer_step": 167,
666
+ "lr": 3.830080191288342e-05,
667
+ "lm_loss": 0.42065590620040894,
668
+ "order_loss": 0.62890625,
669
+ "ret_loss": 0.0,
670
+ "pretrain_loss": 0.0,
671
+ "total_loss": 0.5466324687004089
672
+ },
673
+ {
674
+ "global_step": 1360,
675
+ "optimizer_step": 170,
676
+ "lr": 3.785256860483054e-05,
677
+ "lm_loss": 0.163038969039917,
678
+ "order_loss": 0.494140625,
679
+ "ret_loss": 0.0,
680
+ "pretrain_loss": 0.0,
681
+ "total_loss": 0.261671781539917
682
+ },
683
+ {
684
+ "global_step": 1380,
685
+ "optimizer_step": 172,
686
+ "lr": 3.755057404586455e-05,
687
+ "lm_loss": 0.0022129479330033064,
688
+ "order_loss": 0.64453125,
689
+ "ret_loss": 0.0,
690
+ "pretrain_loss": 0.0,
691
+ "total_loss": 0.13111919164657593
692
+ },
693
+ {
694
+ "global_step": 1400,
695
+ "optimizer_step": 175,
696
+ "lr": 3.7092972177631e-05,
697
+ "lm_loss": 0.006367990281432867,
698
+ "order_loss": 0.6171875,
699
+ "ret_loss": 0.0,
700
+ "pretrain_loss": 0.0,
701
+ "total_loss": 0.1299031525850296
702
+ },
703
+ {
704
+ "global_step": 1420,
705
+ "optimizer_step": 177,
706
+ "lr": 3.678491842064995e-05,
707
+ "lm_loss": 0.05098428949713707,
708
+ "order_loss": 0.5234375,
709
+ "ret_loss": 0.0,
710
+ "pretrain_loss": 0.0,
711
+ "total_loss": 0.15547648072242737
712
+ },
713
+ {
714
+ "global_step": 1440,
715
+ "optimizer_step": 180,
716
+ "lr": 3.631851049805793e-05,
717
+ "lm_loss": 0.18210814893245697,
718
+ "order_loss": 0.498046875,
719
+ "ret_loss": 0.0,
720
+ "pretrain_loss": 0.0,
721
+ "total_loss": 0.28171753883361816
722
+ },
723
+ {
724
+ "global_step": 1460,
725
+ "optimizer_step": 182,
726
+ "lr": 3.600477621728473e-05,
727
+ "lm_loss": 0.026305628940463066,
728
+ "order_loss": 0.5546875,
729
+ "ret_loss": 0.0,
730
+ "pretrain_loss": 0.0,
731
+ "total_loss": 0.13714547455310822
732
+ },
733
+ {
734
+ "global_step": 1480,
735
+ "optimizer_step": 185,
736
+ "lr": 3.5530135570974274e-05,
737
+ "lm_loss": 0.02808750979602337,
738
+ "order_loss": 0.546875,
739
+ "ret_loss": 0.0,
740
+ "pretrain_loss": 0.0,
741
+ "total_loss": 0.13746251165866852
742
+ },
743
+ {
744
+ "global_step": 1500,
745
+ "optimizer_step": 187,
746
+ "lr": 3.521110642339991e-05,
747
+ "lm_loss": 0.010618743486702442,
748
+ "order_loss": 0.51171875,
749
+ "ret_loss": 0.0,
750
+ "pretrain_loss": 0.0,
751
+ "total_loss": 0.11315780878067017
752
+ },
753
+ {
754
+ "global_step": 1520,
755
+ "optimizer_step": 190,
756
+ "lr": 3.4728816504063726e-05,
757
+ "lm_loss": 0.07258732616901398,
758
+ "order_loss": 0.5078125,
759
+ "ret_loss": 0.0,
760
+ "pretrain_loss": 0.0,
761
+ "total_loss": 0.17414982616901398
762
+ },
763
+ {
764
+ "global_step": 1540,
765
+ "optimizer_step": 192,
766
+ "lr": 3.440488465537943e-05,
767
+ "lm_loss": 0.07765470445156097,
768
+ "order_loss": 0.61328125,
769
+ "ret_loss": 0.0,
770
+ "pretrain_loss": 0.0,
771
+ "total_loss": 0.20021329820156097
772
+ },
773
+ {
774
+ "global_step": 1560,
775
+ "optimizer_step": 195,
776
+ "lr": 3.391553831655782e-05,
777
+ "lm_loss": 0.010298844426870346,
778
+ "order_loss": 0.62890625,
779
+ "ret_loss": 0.0,
780
+ "pretrain_loss": 0.0,
781
+ "total_loss": 0.13627541065216064
782
+ },
783
+ {
784
+ "global_step": 1580,
785
+ "optimizer_step": 197,
786
+ "lr": 3.358710195908653e-05,
787
+ "lm_loss": 0.11814656853675842,
788
+ "order_loss": 0.5703125,
789
+ "ret_loss": 0.0,
790
+ "pretrain_loss": 0.0,
791
+ "total_loss": 0.23240438103675842
792
+ },
793
+ {
794
+ "global_step": 1600,
795
+ "optimizer_step": 200,
796
+ "lr": 3.309130072840379e-05,
797
+ "lm_loss": 0.08220347762107849,
798
+ "order_loss": 0.54296875,
799
+ "ret_loss": 0.0,
800
+ "pretrain_loss": 0.0,
801
+ "total_loss": 0.1906019151210785
802
+ },
803
+ {
804
+ "global_step": 1620,
805
+ "optimizer_step": 202,
806
+ "lr": 3.2758763591623295e-05,
807
+ "lm_loss": 0.007858790457248688,
808
+ "order_loss": 0.51171875,
809
+ "ret_loss": 0.0,
810
+ "pretrain_loss": 0.0,
811
+ "total_loss": 0.11039785295724869
812
+ },
813
+ {
814
+ "global_step": 1640,
815
+ "optimizer_step": 205,
816
+ "lr": 3.225711693136156e-05,
817
+ "lm_loss": 0.08243212848901749,
818
+ "order_loss": 0.5078125,
819
+ "ret_loss": 0.0,
820
+ "pretrain_loss": 0.0,
821
+ "total_loss": 0.1839946210384369
822
+ },
823
+ {
824
+ "global_step": 1660,
825
+ "optimizer_step": 207,
826
+ "lr": 3.1920887785621235e-05,
827
+ "lm_loss": 0.2289396971464157,
828
+ "order_loss": 0.56640625,
829
+ "ret_loss": 0.0,
830
+ "pretrain_loss": 0.0,
831
+ "total_loss": 0.3422209620475769
832
+ },
833
+ {
834
+ "global_step": 1680,
835
+ "optimizer_step": 210,
836
+ "lr": 3.141401234354067e-05,
837
+ "lm_loss": 0.0073690032586455345,
838
+ "order_loss": 0.65234375,
839
+ "ret_loss": 0.0,
840
+ "pretrain_loss": 0.0,
841
+ "total_loss": 0.1382283717393875
842
+ },
843
+ {
844
+ "global_step": 1700,
845
+ "optimizer_step": 212,
846
+ "lr": 3.10745044975816e-05,
847
+ "lm_loss": 0.015314987860620022,
848
+ "order_loss": 0.5546875,
849
+ "ret_loss": 0.0,
850
+ "pretrain_loss": 0.0,
851
+ "total_loss": 0.126154825091362
852
+ },
853
+ {
854
+ "global_step": 1720,
855
+ "optimizer_step": 215,
856
+ "lr": 3.056302334890786e-05,
857
+ "lm_loss": 0.37068548798561096,
858
+ "order_loss": 0.59375,
859
+ "ret_loss": 0.0,
860
+ "pretrain_loss": 0.0,
861
+ "total_loss": 0.48933783173561096
862
+ },
863
+ {
864
+ "global_step": 1740,
865
+ "optimizer_step": 217,
866
+ "lr": 3.022065414180425e-05,
867
+ "lm_loss": 0.04771946743130684,
868
+ "order_loss": 0.6171875,
869
+ "ret_loss": 0.0,
870
+ "pretrain_loss": 0.0,
871
+ "total_loss": 0.17125461995601654
872
+ },
873
+ {
874
+ "global_step": 1760,
875
+ "optimizer_step": 220,
876
+ "lr": 2.9705196023315006e-05,
877
+ "lm_loss": 0.12354864180088043,
878
+ "order_loss": 0.66015625,
879
+ "ret_loss": 0.0,
880
+ "pretrain_loss": 0.0,
881
+ "total_loss": 0.25538456439971924
882
+ },
883
+ {
884
+ "global_step": 1780,
885
+ "optimizer_step": 222,
886
+ "lr": 2.9360386311461275e-05,
887
+ "lm_loss": 0.0025185905396938324,
888
+ "order_loss": 0.6953125,
889
+ "ret_loss": 0.0,
890
+ "pretrain_loss": 0.0,
891
+ "total_loss": 0.14119046926498413
892
+ },
893
+ {
894
+ "global_step": 1800,
895
+ "optimizer_step": 225,
896
+ "lr": 2.884158484861325e-05,
897
+ "lm_loss": 0.19057409465312958,
898
+ "order_loss": 0.55078125,
899
+ "ret_loss": 0.0,
900
+ "pretrain_loss": 0.0,
901
+ "total_loss": 0.30092567205429077
902
+ },
903
+ {
904
+ "global_step": 1820,
905
+ "optimizer_step": 227,
906
+ "lr": 2.849475848838749e-05,
907
+ "lm_loss": 0.04037627577781677,
908
+ "order_loss": 0.5859375,
909
+ "ret_loss": 0.0,
910
+ "pretrain_loss": 0.0,
911
+ "total_loss": 0.15756377577781677
912
+ },
913
+ {
914
+ "global_step": 1840,
915
+ "optimizer_step": 230,
916
+ "lr": 2.7973251416434175e-05,
917
+ "lm_loss": 0.13049302995204926,
918
+ "order_loss": 0.6171875,
919
+ "ret_loss": 0.0,
920
+ "pretrain_loss": 0.0,
921
+ "total_loss": 0.25402820110321045
922
+ },
923
+ {
924
+ "global_step": 1860,
925
+ "optimizer_step": 232,
926
+ "lr": 2.7624834743173867e-05,
927
+ "lm_loss": 0.030418887734413147,
928
+ "order_loss": 0.5390625,
929
+ "ret_loss": 0.0,
930
+ "pretrain_loss": 0.0,
931
+ "total_loss": 0.13832904398441315
932
+ },
933
+ {
934
+ "global_step": 1880,
935
+ "optimizer_step": 235,
936
+ "lr": 2.710126312323119e-05,
937
+ "lm_loss": 0.003921869210898876,
938
+ "order_loss": 0.6171875,
939
+ "ret_loss": 0.0,
940
+ "pretrain_loss": 0.0,
941
+ "total_loss": 0.12745702266693115
942
+ },
943
+ {
944
+ "global_step": 1900,
945
+ "optimizer_step": 237,
946
+ "lr": 2.6751684427161683e-05,
947
+ "lm_loss": 0.04966839775443077,
948
+ "order_loss": 0.5703125,
949
+ "ret_loss": 0.0,
950
+ "pretrain_loss": 0.0,
951
+ "total_loss": 0.16392621397972107
952
+ },
953
+ {
954
+ "global_step": 1920,
955
+ "optimizer_step": 240,
956
+ "lr": 2.6226691858185454e-05,
957
+ "lm_loss": 0.0023096452932804823,
958
+ "order_loss": 0.5703125,
959
+ "ret_loss": 0.0,
960
+ "pretrain_loss": 0.0,
961
+ "total_loss": 0.1165674552321434
962
+ },
963
+ {
964
+ "global_step": 1940,
965
+ "optimizer_step": 242,
966
+ "lr": 2.587638085794541e-05,
967
+ "lm_loss": 0.0023053770419210196,
968
+ "order_loss": 0.60546875,
969
+ "ret_loss": 0.0,
970
+ "pretrain_loss": 0.0,
971
+ "total_loss": 0.12339912354946136
972
+ },
973
+ {
974
+ "global_step": 1960,
975
+ "optimizer_step": 245,
976
+ "lr": 2.535061268558906e-05,
977
+ "lm_loss": 0.0028723659925162792,
978
+ "order_loss": 0.458984375,
979
+ "ret_loss": 0.0,
980
+ "pretrain_loss": 0.0,
981
+ "total_loss": 0.09466923773288727
982
+ },
983
+ {
984
+ "global_step": 1980,
985
+ "optimizer_step": 247,
986
+ "lr": 2.5e-05,
987
+ "lm_loss": 0.02799827978014946,
988
+ "order_loss": 0.458984375,
989
+ "ret_loss": 0.0,
990
+ "pretrain_loss": 0.0,
991
+ "total_loss": 0.11979515850543976
992
+ },
993
+ {
994
+ "global_step": 2000,
995
+ "optimizer_step": 250,
996
+ "lr": 2.447410252332528e-05,
997
+ "lm_loss": 0.0008640653104521334,
998
+ "order_loss": 0.609375,
999
+ "ret_loss": 0.0,
1000
+ "pretrain_loss": 0.0,
1001
+ "total_loss": 0.12293437868356705
1002
+ },
1003
+ {
1004
+ "global_step": 2020,
1005
+ "optimizer_step": 252,
1006
+ "lr": 2.4123619142054597e-05,
1007
+ "lm_loss": 0.028730031102895737,
1008
+ "order_loss": 0.60546875,
1009
+ "ret_loss": 0.0,
1010
+ "pretrain_loss": 0.0,
1011
+ "total_loss": 0.14982378482818604
1012
+ },
1013
+ {
1014
+ "global_step": 2040,
1015
+ "optimizer_step": 255,
1016
+ "lr": 2.3598238819070202e-05,
1017
+ "lm_loss": 0.20225244760513306,
1018
+ "order_loss": 0.55859375,
1019
+ "ret_loss": 0.0,
1020
+ "pretrain_loss": 0.0,
1021
+ "total_loss": 0.31406885385513306
1022
+ },
1023
+ {
1024
+ "global_step": 2060,
1025
+ "optimizer_step": 257,
1026
+ "lr": 2.3248315572838316e-05,
1027
+ "lm_loss": 0.4061942398548126,
1028
+ "order_loss": 0.54296875,
1029
+ "ret_loss": 0.0,
1030
+ "pretrain_loss": 0.0,
1031
+ "total_loss": 0.5145926475524902
1032
+ },
1033
+ {
1034
+ "global_step": 2080,
1035
+ "optimizer_step": 260,
1036
+ "lr": 2.272409822584325e-05,
1037
+ "lm_loss": 0.006703692022711039,
1038
+ "order_loss": 0.56640625,
1039
+ "ret_loss": 0.0,
1040
+ "pretrain_loss": 0.0,
1041
+ "total_loss": 0.1199849396944046
1042
+ },
1043
+ {
1044
+ "global_step": 2100,
1045
+ "optimizer_step": 262,
1046
+ "lr": 2.237516525682614e-05,
1047
+ "lm_loss": 0.10825450718402863,
1048
+ "order_loss": 0.640625,
1049
+ "ret_loss": 0.0,
1050
+ "pretrain_loss": 0.0,
1051
+ "total_loss": 0.23618419468402863
1052
+ },
1053
+ {
1054
+ "global_step": 2120,
1055
+ "optimizer_step": 265,
1056
+ "lr": 2.185275527853437e-05,
1057
+ "lm_loss": 0.030753089115023613,
1058
+ "order_loss": 0.5625,
1059
+ "ret_loss": 0.0,
1060
+ "pretrain_loss": 0.0,
1061
+ "total_loss": 0.14305777847766876
1062
+ },
1063
+ {
1064
+ "global_step": 2140,
1065
+ "optimizer_step": 267,
1066
+ "lr": 2.1505241511612522e-05,
1067
+ "lm_loss": 0.004374531097710133,
1068
+ "order_loss": 0.578125,
1069
+ "ret_loss": 0.0,
1070
+ "pretrain_loss": 0.0,
1071
+ "total_loss": 0.12009719014167786
1072
+ },
1073
+ {
1074
+ "global_step": 2160,
1075
+ "optimizer_step": 270,
1076
+ "lr": 2.0985281073035076e-05,
1077
+ "lm_loss": 0.0880327895283699,
1078
+ "order_loss": 0.53515625,
1079
+ "ret_loss": 0.0,
1080
+ "pretrain_loss": 0.0,
1081
+ "total_loss": 0.1949663758277893
1082
+ },
1083
+ {
1084
+ "global_step": 2180,
1085
+ "optimizer_step": 272,
1086
+ "lr": 2.0639613688538734e-05,
1087
+ "lm_loss": 0.1059723049402237,
1088
+ "order_loss": 0.5390625,
1089
+ "ret_loss": 0.0,
1090
+ "pretrain_loss": 0.0,
1091
+ "total_loss": 0.2138824611902237
1092
+ },
1093
+ {
1094
+ "global_step": 2200,
1095
+ "optimizer_step": 275,
1096
+ "lr": 2.0122741949596797e-05,
1097
+ "lm_loss": 0.06937023997306824,
1098
+ "order_loss": 0.5546875,
1099
+ "ret_loss": 0.0,
1100
+ "pretrain_loss": 0.0,
1101
+ "total_loss": 0.18021008372306824
1102
+ },
1103
+ {
1104
+ "global_step": 2220,
1105
+ "optimizer_step": 277,
1106
+ "lr": 1.977934585819576e-05,
1107
+ "lm_loss": 0.03986092284321785,
1108
+ "order_loss": 0.56640625,
1109
+ "ret_loss": 0.0,
1110
+ "pretrain_loss": 0.0,
1111
+ "total_loss": 0.15314216911792755
1112
+ },
1113
+ {
1114
+ "global_step": 2240,
1115
+ "optimizer_step": 280,
1116
+ "lr": 1.9266198182035058e-05,
1117
+ "lm_loss": 0.02938377484679222,
1118
+ "order_loss": 0.6328125,
1119
+ "ret_loss": 0.0,
1120
+ "pretrain_loss": 0.0,
1121
+ "total_loss": 0.15633690357208252
1122
+ },
1123
+ {
1124
+ "global_step": 2260,
1125
+ "optimizer_step": 282,
1126
+ "lr": 1.8925495502418406e-05,
1127
+ "lm_loss": 0.1372852623462677,
1128
+ "order_loss": 0.515625,
1129
+ "ret_loss": 0.0,
1130
+ "pretrain_loss": 0.0,
1131
+ "total_loss": 0.2403126060962677
1132
+ },
1133
+ {
1134
+ "global_step": 2280,
1135
+ "optimizer_step": 285,
1136
+ "lr": 1.841670267439088e-05,
1137
+ "lm_loss": 0.008859424851834774,
1138
+ "order_loss": 0.5859375,
1139
+ "ret_loss": 0.0,
1140
+ "pretrain_loss": 0.0,
1141
+ "total_loss": 0.12604692578315735
1142
+ },
1143
+ {
1144
+ "global_step": 2300,
1145
+ "optimizer_step": 287,
1146
+ "lr": 1.8079112214378768e-05,
1147
+ "lm_loss": 0.13034240901470184,
1148
+ "order_loss": 0.57421875,
1149
+ "ret_loss": 0.0,
1150
+ "pretrain_loss": 0.0,
1151
+ "total_loss": 0.24508850276470184
1152
+ },
1153
+ {
1154
+ "global_step": 2320,
1155
+ "optimizer_step": 290,
1156
+ "lr": 1.757529966665141e-05,
1157
+ "lm_loss": 0.0058040255680680275,
1158
+ "order_loss": 0.5390625,
1159
+ "ret_loss": 0.0,
1160
+ "pretrain_loss": 0.0,
1161
+ "total_loss": 0.11371418088674545
1162
+ },
1163
+ {
1164
+ "global_step": 2340,
1165
+ "optimizer_step": 292,
1166
+ "lr": 1.72412364083767e-05,
1167
+ "lm_loss": 0.14297045767307281,
1168
+ "order_loss": 0.63671875,
1169
+ "ret_loss": 0.0,
1170
+ "pretrain_loss": 0.0,
1171
+ "total_loss": 0.2699235677719116
1172
+ },
1173
+ {
1174
+ "global_step": 2360,
1175
+ "optimizer_step": 295,
1176
+ "lr": 1.6743023451120832e-05,
1177
+ "lm_loss": 0.009616105817258358,
1178
+ "order_loss": 0.53125,
1179
+ "ret_loss": 0.0,
1180
+ "pretrain_loss": 0.0,
1181
+ "total_loss": 0.11606141924858093
1182
+ },
1183
+ {
1184
+ "global_step": 2380,
1185
+ "optimizer_step": 297,
1186
+ "lr": 1.641289804091347e-05,
1187
+ "lm_loss": 0.0023067814763635397,
1188
+ "order_loss": 0.57421875,
1189
+ "ret_loss": 0.0,
1190
+ "pretrain_loss": 0.0,
1191
+ "total_loss": 0.11705287545919418
1192
+ },
1193
+ {
1194
+ "global_step": 2400,
1195
+ "optimizer_step": 300,
1196
+ "lr": 1.5920897101019383e-05,
1197
+ "lm_loss": 0.015196509659290314,
1198
+ "order_loss": 0.59765625,
1199
+ "ret_loss": 0.0,
1200
+ "pretrain_loss": 0.0,
1201
+ "total_loss": 0.13482540845870972
1202
+ },
1203
+ {
1204
+ "global_step": 2420,
1205
+ "optimizer_step": 302,
1206
+ "lr": 1.5595115344620576e-05,
1207
+ "lm_loss": 0.0055085825733840466,
1208
+ "order_loss": 0.4609375,
1209
+ "ret_loss": 0.0,
1210
+ "pretrain_loss": 0.0,
1211
+ "total_loss": 0.09779373556375504
1212
+ },
1213
+ {
1214
+ "global_step": 2440,
1215
+ "optimizer_step": 305,
1216
+ "lr": 1.5109931212873534e-05,
1217
+ "lm_loss": 0.07041700184345245,
1218
+ "order_loss": 0.640625,
1219
+ "ret_loss": 0.0,
1220
+ "pretrain_loss": 0.0,
1221
+ "total_loss": 0.19834668934345245
1222
+ },
1223
+ {
1224
+ "global_step": 2460,
1225
+ "optimizer_step": 307,
1226
+ "lr": 1.4788893576600099e-05,
1227
+ "lm_loss": 0.0008587647462263703,
1228
+ "order_loss": 0.6015625,
1229
+ "ret_loss": 0.0,
1230
+ "pretrain_loss": 0.0,
1231
+ "total_loss": 0.12097594887018204
1232
+ },
1233
+ {
1234
+ "global_step": 2480,
1235
+ "optimizer_step": 310,
1236
+ "lr": 1.4311122664242954e-05,
1237
+ "lm_loss": 0.04767267033457756,
1238
+ "order_loss": 0.56640625,
1239
+ "ret_loss": 0.0,
1240
+ "pretrain_loss": 0.0,
1241
+ "total_loss": 0.16095392405986786
1242
+ },
1243
+ {
1244
+ "global_step": 2500,
1245
+ "optimizer_step": 312,
1246
+ "lr": 1.399522378271527e-05,
1247
+ "lm_loss": 0.10494320094585419,
1248
+ "order_loss": 0.4921875,
1249
+ "ret_loss": 0.0,
1250
+ "pretrain_loss": 0.0,
1251
+ "total_loss": 0.2035760134458542
1252
+ },
1253
+ {
1254
+ "global_step": 2520,
1255
+ "optimizer_step": 315,
1256
+ "lr": 1.3525453388311554e-05,
1257
+ "lm_loss": 0.1248660683631897,
1258
+ "order_loss": 0.62890625,
1259
+ "ret_loss": 0.0,
1260
+ "pretrain_loss": 0.0,
1261
+ "total_loss": 0.2508426308631897
1262
+ },
1263
+ {
1264
+ "global_step": 2540,
1265
+ "optimizer_step": 317,
1266
+ "lr": 1.3215081579350058e-05,
1267
+ "lm_loss": 0.03742207959294319,
1268
+ "order_loss": 0.58203125,
1269
+ "ret_loss": 0.0,
1270
+ "pretrain_loss": 0.0,
1271
+ "total_loss": 0.1536330133676529
1272
+ },
1273
+ {
1274
+ "global_step": 2560,
1275
+ "optimizer_step": 320,
1276
+ "lr": 1.2753889166848909e-05,
1277
+ "lm_loss": 0.04322648048400879,
1278
+ "order_loss": 0.65234375,
1279
+ "ret_loss": 0.0,
1280
+ "pretrain_loss": 0.0,
1281
+ "total_loss": 0.1740858554840088
1282
+ },
1283
+ {
1284
+ "global_step": 2580,
1285
+ "optimizer_step": 322,
1286
+ "lr": 1.2449425954135452e-05,
1287
+ "lm_loss": 0.28463485836982727,
1288
+ "order_loss": 0.478515625,
1289
+ "ret_loss": 0.0,
1290
+ "pretrain_loss": 0.0,
1291
+ "total_loss": 0.38033798336982727
1292
+ },
1293
+ {
1294
+ "global_step": 2600,
1295
+ "optimizer_step": 325,
1296
+ "lr": 1.1997378443025634e-05,
1297
+ "lm_loss": 0.12006889283657074,
1298
+ "order_loss": 0.53515625,
1299
+ "ret_loss": 0.0,
1300
+ "pretrain_loss": 0.0,
1301
+ "total_loss": 0.22700248658657074
1302
+ },
1303
+ {
1304
+ "global_step": 2620,
1305
+ "optimizer_step": 327,
1306
+ "lr": 1.1699198087116589e-05,
1307
+ "lm_loss": 0.041589509695768356,
1308
+ "order_loss": 0.6484375,
1309
+ "ret_loss": 0.0,
1310
+ "pretrain_loss": 0.0,
1311
+ "total_loss": 0.17147232592105865
1312
+ },
1313
+ {
1314
+ "global_step": 2640,
1315
+ "optimizer_step": 330,
1316
+ "lr": 1.1256851155542298e-05,
1317
+ "lm_loss": 0.13465343415737152,
1318
+ "order_loss": 0.8828125,
1319
+ "ret_loss": 0.0,
1320
+ "pretrain_loss": 0.0,
1321
+ "total_loss": 0.3114112615585327
1322
+ },
1323
+ {
1324
+ "global_step": 2660,
1325
+ "optimizer_step": 332,
1326
+ "lr": 1.0965320193809808e-05,
1327
+ "lm_loss": 0.1551741063594818,
1328
+ "order_loss": 0.58984375,
1329
+ "ret_loss": 0.0,
1330
+ "pretrain_loss": 0.0,
1331
+ "total_loss": 0.2733381688594818
1332
+ },
1333
+ {
1334
+ "global_step": 2680,
1335
+ "optimizer_step": 335,
1336
+ "lr": 1.0533217595504858e-05,
1337
+ "lm_loss": 0.21303166449069977,
1338
+ "order_loss": 0.50390625,
1339
+ "ret_loss": 0.0,
1340
+ "pretrain_loss": 0.0,
1341
+ "total_loss": 0.3136175870895386
1342
+ },
1343
+ {
1344
+ "global_step": 2700,
1345
+ "optimizer_step": 337,
1346
+ "lr": 1.0248694391571801e-05,
1347
+ "lm_loss": 0.003032031701877713,
1348
+ "order_loss": 0.478515625,
1349
+ "ret_loss": 0.0,
1350
+ "pretrain_loss": 0.0,
1351
+ "total_loss": 0.09873515367507935
1352
+ },
1353
+ {
1354
+ "global_step": 2720,
1355
+ "optimizer_step": 340,
1356
+ "lr": 9.82736728745186e-06,
1357
+ "lm_loss": 0.011376204900443554,
1358
+ "order_loss": 0.59375,
1359
+ "ret_loss": 0.0,
1360
+ "pretrain_loss": 0.0,
1361
+ "total_loss": 0.13002854585647583
1362
+ },
1363
+ {
1364
+ "global_step": 2740,
1365
+ "optimizer_step": 342,
1366
+ "lr": 9.550201590674343e-06,
1367
+ "lm_loss": 0.02188899554312229,
1368
+ "order_loss": 0.494140625,
1369
+ "ret_loss": 0.0,
1370
+ "pretrain_loss": 0.0,
1371
+ "total_loss": 0.12052180618047714
1372
+ },
1373
+ {
1374
+ "global_step": 2760,
1375
+ "optimizer_step": 345,
1376
+ "lr": 9.140167895908867e-06,
1377
+ "lm_loss": 0.06271595507860184,
1378
+ "order_loss": 0.546875,
1379
+ "ret_loss": 0.0,
1380
+ "pretrain_loss": 0.0,
1381
+ "total_loss": 0.17209094762802124
1382
+ },
1383
+ {
1384
+ "global_step": 2780,
1385
+ "optimizer_step": 347,
1386
+ "lr": 8.870700411447816e-06,
1387
+ "lm_loss": 0.06071629002690315,
1388
+ "order_loss": 0.5703125,
1389
+ "ret_loss": 0.0,
1390
+ "pretrain_loss": 0.0,
1391
+ "total_loss": 0.17497409880161285
1392
+ },
1393
+ {
1394
+ "global_step": 2800,
1395
+ "optimizer_step": 350,
1396
+ "lr": 8.472464158814255e-06,
1397
+ "lm_loss": 0.00121429527644068,
1398
+ "order_loss": 0.58203125,
1399
+ "ret_loss": 0.0,
1400
+ "pretrain_loss": 0.0,
1401
+ "total_loss": 0.11742523312568665
1402
+ },
1403
+ {
1404
+ "global_step": 2820,
1405
+ "optimizer_step": 352,
1406
+ "lr": 8.211026128824539e-06,
1407
+ "lm_loss": 0.15878482162952423,
1408
+ "order_loss": 0.546875,
1409
+ "ret_loss": 0.0,
1410
+ "pretrain_loss": 0.0,
1411
+ "total_loss": 0.26815980672836304
1412
+ },
1413
+ {
1414
+ "global_step": 2840,
1415
+ "optimizer_step": 355,
1416
+ "lr": 7.825076849127458e-06,
1417
+ "lm_loss": 0.02045881561934948,
1418
+ "order_loss": 0.51953125,
1419
+ "ret_loss": 0.0,
1420
+ "pretrain_loss": 0.0,
1421
+ "total_loss": 0.12446272373199463
1422
+ },
1423
+ {
1424
+ "global_step": 2860,
1425
+ "optimizer_step": 357,
1426
+ "lr": 7.571989645579419e-06,
1427
+ "lm_loss": 0.06680122017860413,
1428
+ "order_loss": 0.51171875,
1429
+ "ret_loss": 0.0,
1430
+ "pretrain_loss": 0.0,
1431
+ "total_loss": 0.16934028267860413
1432
+ },
1433
+ {
1434
+ "global_step": 2880,
1435
+ "optimizer_step": 360,
1436
+ "lr": 7.198801765896115e-06,
1437
+ "lm_loss": 0.0058411904610693455,
1438
+ "order_loss": 0.55859375,
1439
+ "ret_loss": 0.0,
1440
+ "pretrain_loss": 0.0,
1441
+ "total_loss": 0.11765759438276291
1442
+ },
1443
+ {
1444
+ "global_step": 2900,
1445
+ "optimizer_step": 362,
1446
+ "lr": 6.9543764955299265e-06,
1447
+ "lm_loss": 0.0028372707311064005,
1448
+ "order_loss": 0.6328125,
1449
+ "ret_loss": 0.0,
1450
+ "pretrain_loss": 0.0,
1451
+ "total_loss": 0.12979039549827576
1452
+ },
1453
+ {
1454
+ "global_step": 2920,
1455
+ "optimizer_step": 365,
1456
+ "lr": 6.594408756022272e-06,
1457
+ "lm_loss": 0.006174637004733086,
1458
+ "order_loss": 0.578125,
1459
+ "ret_loss": 0.0,
1460
+ "pretrain_loss": 0.0,
1461
+ "total_loss": 0.12189729511737823
1462
+ },
1463
+ {
1464
+ "global_step": 2940,
1465
+ "optimizer_step": 367,
1466
+ "lr": 6.358945877920861e-06,
1467
+ "lm_loss": 0.07120844721794128,
1468
+ "order_loss": 0.53515625,
1469
+ "ret_loss": 0.0,
1470
+ "pretrain_loss": 0.0,
1471
+ "total_loss": 0.17814204096794128
1472
+ },
1473
+ {
1474
+ "global_step": 2960,
1475
+ "optimizer_step": 370,
1476
+ "lr": 6.012640767930217e-06,
1477
+ "lm_loss": 0.18083013594150543,
1478
+ "order_loss": 0.5625,
1479
+ "ret_loss": 0.0,
1480
+ "pretrain_loss": 0.0,
1481
+ "total_loss": 0.29313480854034424
1482
+ },
1483
+ {
1484
+ "global_step": 2980,
1485
+ "optimizer_step": 372,
1486
+ "lr": 5.7864297241808e-06,
1487
+ "lm_loss": 0.05748174339532852,
1488
+ "order_loss": 0.55859375,
1489
+ "ret_loss": 0.0,
1490
+ "pretrain_loss": 0.0,
1491
+ "total_loss": 0.16929814219474792
1492
+ },
1493
+ {
1494
+ "global_step": 3000,
1495
+ "optimizer_step": 375,
1496
+ "lr": 5.454212938299255e-06,
1497
+ "lm_loss": 0.05534393712878227,
1498
+ "order_loss": 0.578125,
1499
+ "ret_loss": 0.0,
1500
+ "pretrain_loss": 0.0,
1501
+ "total_loss": 0.17106659710407257
1502
+ },
1503
+ {
1504
+ "global_step": 3020,
1505
+ "optimizer_step": 377,
1506
+ "lr": 5.237531798197415e-06,
1507
+ "lm_loss": 0.05226636677980423,
1508
+ "order_loss": 0.57421875,
1509
+ "ret_loss": 0.0,
1510
+ "pretrain_loss": 0.0,
1511
+ "total_loss": 0.16701245307922363
1512
+ },
1513
+ {
1514
+ "global_step": 3040,
1515
+ "optimizer_step": 380,
1516
+ "lr": 4.91981171298388e-06,
1517
+ "lm_loss": 0.022525141015648842,
1518
+ "order_loss": 0.60546875,
1519
+ "ret_loss": 0.0,
1520
+ "pretrain_loss": 0.0,
1521
+ "total_loss": 0.1436188966035843
1522
+ },
1523
+ {
1524
+ "global_step": 3060,
1525
+ "optimizer_step": 382,
1526
+ "lr": 4.712926831217685e-06,
1527
+ "lm_loss": 0.0219656340777874,
1528
+ "order_loss": 0.59375,
1529
+ "ret_loss": 0.0,
1530
+ "pretrain_loss": 0.0,
1531
+ "total_loss": 0.1406179815530777
1532
+ },
1533
+ {
1534
+ "global_step": 3080,
1535
+ "optimizer_step": 385,
1536
+ "lr": 4.410094003202134e-06,
1537
+ "lm_loss": 0.011890939436852932,
1538
+ "order_loss": 0.6171875,
1539
+ "ret_loss": 0.0,
1540
+ "pretrain_loss": 0.0,
1541
+ "total_loss": 0.1354260891675949
1542
+ },
1543
+ {
1544
+ "global_step": 3100,
1545
+ "optimizer_step": 387,
1546
+ "lr": 4.213259692436367e-06,
1547
+ "lm_loss": 0.04473523795604706,
1548
+ "order_loss": 0.5859375,
1549
+ "ret_loss": 0.0,
1550
+ "pretrain_loss": 0.0,
1551
+ "total_loss": 0.16192273795604706
1552
+ },
1553
+ {
1554
+ "global_step": 3120,
1555
+ "optimizer_step": 390,
1556
+ "lr": 3.925686378029331e-06,
1557
+ "lm_loss": 0.001998218707740307,
1558
+ "order_loss": 0.62109375,
1559
+ "ret_loss": 0.0,
1560
+ "pretrain_loss": 0.0,
1561
+ "total_loss": 0.12602165341377258
1562
+ },
1563
+ {
1564
+ "global_step": 3140,
1565
+ "optimizer_step": 392,
1566
+ "lr": 3.739144596292382e-06,
1567
+ "lm_loss": 0.07612577825784683,
1568
+ "order_loss": 0.5,
1569
+ "ret_loss": 0.0,
1570
+ "pretrain_loss": 0.0,
1571
+ "total_loss": 0.17622342705726624
1572
+ },
1573
+ {
1574
+ "global_step": 3160,
1575
+ "optimizer_step": 395,
1576
+ "lr": 3.4671842941897765e-06,
1577
+ "lm_loss": 0.06267683207988739,
1578
+ "order_loss": 0.69140625,
1579
+ "ret_loss": 0.0,
1580
+ "pretrain_loss": 0.0,
1581
+ "total_loss": 0.2013487070798874
1582
+ },
1583
+ {
1584
+ "global_step": 3180,
1585
+ "optimizer_step": 397,
1586
+ "lr": 3.2911643474473646e-06,
1587
+ "lm_loss": 0.10238153487443924,
1588
+ "order_loss": 0.46484375,
1589
+ "ret_loss": 0.0,
1590
+ "pretrain_loss": 0.0,
1591
+ "total_loss": 0.19515496492385864
1592
+ },
1593
+ {
1594
+ "global_step": 3200,
1595
+ "optimizer_step": 400,
1596
+ "lr": 3.035151364093214e-06,
1597
+ "lm_loss": 0.07949133217334747,
1598
+ "order_loss": 0.625,
1599
+ "ret_loss": 0.0,
1600
+ "pretrain_loss": 0.0,
1601
+ "total_loss": 0.20449133217334747
1602
+ },
1603
+ {
1604
+ "global_step": 3220,
1605
+ "optimizer_step": 402,
1606
+ "lr": 2.869869624374699e-06,
1607
+ "lm_loss": 0.01042896043509245,
1608
+ "order_loss": 0.546875,
1609
+ "ret_loss": 0.0,
1610
+ "pretrain_loss": 0.0,
1611
+ "total_loss": 0.11980395764112473
1612
+ },
1613
+ {
1614
+ "global_step": 3240,
1615
+ "optimizer_step": 405,
1616
+ "lr": 2.6301186630158485e-06,
1617
+ "lm_loss": 0.032333679497241974,
1618
+ "order_loss": 0.5859375,
1619
+ "ret_loss": 0.0,
1620
+ "pretrain_loss": 0.0,
1621
+ "total_loss": 0.14952117204666138
1622
+ },
1623
+ {
1624
+ "global_step": 3260,
1625
+ "optimizer_step": 407,
1626
+ "lr": 2.475778302439524e-06,
1627
+ "lm_loss": 0.04336171969771385,
1628
+ "order_loss": 0.57421875,
1629
+ "ret_loss": 0.0,
1630
+ "pretrain_loss": 0.0,
1631
+ "total_loss": 0.15810781717300415
1632
+ },
1633
+ {
1634
+ "global_step": 3280,
1635
+ "optimizer_step": 410,
1636
+ "lr": 2.2525840762775863e-06,
1637
+ "lm_loss": 0.06556833535432816,
1638
+ "order_loss": 0.62109375,
1639
+ "ret_loss": 0.0,
1640
+ "pretrain_loss": 0.0,
1641
+ "total_loss": 0.18959176540374756
1642
+ },
1643
+ {
1644
+ "global_step": 3300,
1645
+ "optimizer_step": 412,
1646
+ "lr": 2.1093748173018848e-06,
1647
+ "lm_loss": 0.004182081203907728,
1648
+ "order_loss": 0.58203125,
1649
+ "ret_loss": 0.0,
1650
+ "pretrain_loss": 0.0,
1651
+ "total_loss": 0.12039301544427872
1652
+ },
1653
+ {
1654
+ "global_step": 3320,
1655
+ "optimizer_step": 415,
1656
+ "lr": 1.9030116872178316e-06,
1657
+ "lm_loss": 0.008351372554898262,
1658
+ "order_loss": 0.51953125,
1659
+ "ret_loss": 0.0,
1660
+ "pretrain_loss": 0.0,
1661
+ "total_loss": 0.11235527694225311
1662
+ },
1663
+ {
1664
+ "global_step": 3340,
1665
+ "optimizer_step": 417,
1666
+ "lr": 1.771109569425547e-06,
1667
+ "lm_loss": 0.043489690870046616,
1668
+ "order_loss": 0.55078125,
1669
+ "ret_loss": 0.0,
1670
+ "pretrain_loss": 0.0,
1671
+ "total_loss": 0.15384125709533691
1672
+ },
1673
+ {
1674
+ "global_step": 3360,
1675
+ "optimizer_step": 420,
1676
+ "lr": 1.5818312067223672e-06,
1677
+ "lm_loss": 0.0038892761804163456,
1678
+ "order_loss": 0.53125,
1679
+ "ret_loss": 0.0,
1680
+ "pretrain_loss": 0.0,
1681
+ "total_loss": 0.11033459007740021
1682
+ },
1683
+ {
1684
+ "global_step": 3380,
1685
+ "optimizer_step": 422,
1686
+ "lr": 1.4613983704244826e-06,
1687
+ "lm_loss": 0.14987102150917053,
1688
+ "order_loss": 0.5390625,
1689
+ "ret_loss": 0.0,
1690
+ "pretrain_loss": 0.0,
1691
+ "total_loss": 0.25778117775917053
1692
+ },
1693
+ {
1694
+ "global_step": 3400,
1695
+ "optimizer_step": 425,
1696
+ "lr": 1.2894374450024338e-06,
1697
+ "lm_loss": 0.023999933153390884,
1698
+ "order_loss": 0.640625,
1699
+ "ret_loss": 0.0,
1700
+ "pretrain_loss": 0.0,
1701
+ "total_loss": 0.15192961692810059
1702
+ },
1703
+ {
1704
+ "global_step": 3420,
1705
+ "optimizer_step": 427,
1706
+ "lr": 1.180621931927592e-06,
1707
+ "lm_loss": 0.02801506780087948,
1708
+ "order_loss": 0.65625,
1709
+ "ret_loss": 0.0,
1710
+ "pretrain_loss": 0.0,
1711
+ "total_loss": 0.15887443721294403
1712
+ },
1713
+ {
1714
+ "global_step": 3440,
1715
+ "optimizer_step": 430,
1716
+ "lr": 1.0261898262753812e-06,
1717
+ "lm_loss": 0.0042534442618489265,
1718
+ "order_loss": 0.671875,
1719
+ "ret_loss": 0.0,
1720
+ "pretrain_loss": 0.0,
1721
+ "total_loss": 0.13901907205581665
1722
+ },
1723
+ {
1724
+ "global_step": 3460,
1725
+ "optimizer_step": 432,
1726
+ "lr": 9.291253975900139e-07,
1727
+ "lm_loss": 0.03297313675284386,
1728
+ "order_loss": 0.703125,
1729
+ "ret_loss": 0.0,
1730
+ "pretrain_loss": 0.0,
1731
+ "total_loss": 0.17359814047813416
1732
+ },
1733
+ {
1734
+ "global_step": 3480,
1735
+ "optimizer_step": 435,
1736
+ "lr": 7.924119469434665e-07,
1737
+ "lm_loss": 0.03867597132921219,
1738
+ "order_loss": 0.5078125,
1739
+ "ret_loss": 0.0,
1740
+ "pretrain_loss": 0.0,
1741
+ "total_loss": 0.1402384638786316
1742
+ },
1743
+ {
1744
+ "global_step": 3500,
1745
+ "optimizer_step": 437,
1746
+ "lr": 7.072179188262251e-07,
1747
+ "lm_loss": 0.0009399562841281295,
1748
+ "order_loss": 0.515625,
1749
+ "ret_loss": 0.0,
1750
+ "pretrain_loss": 0.0,
1751
+ "total_loss": 0.10396730154752731
1752
+ },
1753
+ {
1754
+ "global_step": 3520,
1755
+ "optimizer_step": 440,
1756
+ "lr": 5.883911778138324e-07,
1757
+ "lm_loss": 0.0024283446837216616,
1758
+ "order_loss": 0.54296875,
1759
+ "ret_loss": 0.0,
1760
+ "pretrain_loss": 0.0,
1761
+ "total_loss": 0.11082678288221359
1762
+ },
1763
+ {
1764
+ "global_step": 3540,
1765
+ "optimizer_step": 442,
1766
+ "lr": 5.151722747865434e-07,
1767
+ "lm_loss": 0.015302804298698902,
1768
+ "order_loss": 0.62890625,
1769
+ "ret_loss": 0.0,
1770
+ "pretrain_loss": 0.0,
1771
+ "total_loss": 0.14127936959266663
1772
+ },
1773
+ {
1774
+ "global_step": 3560,
1775
+ "optimizer_step": 445,
1776
+ "lr": 4.1437831084878974e-07,
1777
+ "lm_loss": 0.0010419447207823396,
1778
+ "order_loss": 0.66015625,
1779
+ "ret_loss": 0.0,
1780
+ "pretrain_loss": 0.0,
1781
+ "total_loss": 0.1328778862953186
1782
+ },
1783
+ {
1784
+ "global_step": 3580,
1785
+ "optimizer_step": 447,
1786
+ "lr": 3.5322453704410286e-07,
1787
+ "lm_loss": 0.5207862854003906,
1788
+ "order_loss": 0.5234375,
1789
+ "ret_loss": 0.0,
1790
+ "pretrain_loss": 0.0,
1791
+ "total_loss": 0.6252784729003906
1792
+ },
1793
+ {
1794
+ "global_step": 3600,
1795
+ "optimizer_step": 450,
1796
+ "lr": 2.705872508804747e-07,
1797
+ "lm_loss": 0.11574822664260864,
1798
+ "order_loss": 0.6328125,
1799
+ "ret_loss": 0.0,
1800
+ "pretrain_loss": 0.0,
1801
+ "total_loss": 0.24270135164260864
1802
+ },
1803
+ {
1804
+ "global_step": 3620,
1805
+ "optimizer_step": 452,
1806
+ "lr": 2.215737794045436e-07,
1807
+ "lm_loss": 0.2073442041873932,
1808
+ "order_loss": 0.5546875,
1809
+ "ret_loss": 0.0,
1810
+ "pretrain_loss": 0.0,
1811
+ "total_loss": 0.3181840479373932
1812
+ },
1813
+ {
1814
+ "global_step": 3640,
1815
+ "optimizer_step": 455,
1816
+ "lr": 1.571947526689349e-07,
1817
+ "lm_loss": 0.6792804598808289,
1818
+ "order_loss": 0.53125,
1819
+ "ret_loss": 0.0,
1820
+ "pretrain_loss": 0.0,
1821
+ "total_loss": 0.7857257723808289
1822
+ },
1823
+ {
1824
+ "global_step": 3660,
1825
+ "optimizer_step": 457,
1826
+ "lr": 1.2038183319507955e-07,
1827
+ "lm_loss": 0.028270093724131584,
1828
+ "order_loss": 0.494140625,
1829
+ "ret_loss": 0.0,
1830
+ "pretrain_loss": 0.0,
1831
+ "total_loss": 0.12690290808677673
1832
+ },
1833
+ {
1834
+ "global_step": 3680,
1835
+ "optimizer_step": 460,
1836
+ "lr": 7.434020362682704e-08,
1837
+ "lm_loss": 0.010708270594477654,
1838
+ "order_loss": 0.6484375,
1839
+ "ret_loss": 0.0,
1840
+ "pretrain_loss": 0.0,
1841
+ "total_loss": 0.1405910849571228
1842
+ },
1843
+ {
1844
+ "global_step": 3700,
1845
+ "optimizer_step": 462,
1846
+ "lr": 4.977308833379324e-08,
1847
+ "lm_loss": 0.006868880707770586,
1848
+ "order_loss": 0.5625,
1849
+ "ret_loss": 0.0,
1850
+ "pretrain_loss": 0.0,
1851
+ "total_loss": 0.1191735714673996
1852
+ },
1853
+ {
1854
+ "global_step": 3720,
1855
+ "optimizer_step": 465,
1856
+ "lr": 2.2125452477828047e-08,
1857
+ "lm_loss": 0.005006551742553711,
1858
+ "order_loss": 0.55078125,
1859
+ "ret_loss": 0.0,
1860
+ "pretrain_loss": 0.0,
1861
+ "total_loss": 0.11535811424255371
1862
+ },
1863
+ {
1864
+ "global_step": 3740,
1865
+ "optimizer_step": 467,
1866
+ "lr": 9.834340423678368e-09,
1867
+ "lm_loss": 0.18168410658836365,
1868
+ "order_loss": 0.58203125,
1869
+ "ret_loss": 0.0,
1870
+ "pretrain_loss": 0.0,
1871
+ "total_loss": 0.29789504408836365
1872
+ }
1873
+ ]
1874
+ }
cls_qwen_orderkd_mid_l005/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_qwen_orderkd_mid_l005/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "down_proj",
39
+ "q_proj",
40
+ "up_proj",
41
+ "o_proj",
42
+ "k_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_mid_l005/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
cls_qwen_orderkd_mid_l005/checkpoint-200/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_qwen_orderkd_mid_l005/checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "down_proj",
39
+ "q_proj",
40
+ "up_proj",
41
+ "o_proj",
42
+ "k_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_mid_l005/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_mid_l005/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "down_proj",
39
+ "q_proj",
40
+ "up_proj",
41
+ "o_proj",
42
+ "k_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_qwen_orderkd_mid_l005/tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "right",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }
cls_qwen_orderkd_mid_l005/train_metrics.json ADDED
@@ -0,0 +1,1874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "loss_log": [
3
+ {
4
+ "global_step": 20,
5
+ "optimizer_step": 2,
6
+ "lr": 4.347826086956522e-06,
7
+ "lm_loss": 1.6705306768417358,
8
+ "order_loss": 10.125,
9
+ "ret_loss": 0.0,
10
+ "pretrain_loss": 0.0,
11
+ "total_loss": 2.1783432960510254
12
+ },
13
+ {
14
+ "global_step": 40,
15
+ "optimizer_step": 5,
16
+ "lr": 1.0869565217391305e-05,
17
+ "lm_loss": 0.10821875184774399,
18
+ "order_loss": 7.53125,
19
+ "ret_loss": 0.0,
20
+ "pretrain_loss": 0.0,
21
+ "total_loss": 0.4851718842983246
22
+ },
23
+ {
24
+ "global_step": 60,
25
+ "optimizer_step": 7,
26
+ "lr": 1.5217391304347828e-05,
27
+ "lm_loss": 0.696049690246582,
28
+ "order_loss": 9.8125,
29
+ "ret_loss": 0.0,
30
+ "pretrain_loss": 0.0,
31
+ "total_loss": 1.186284065246582
32
+ },
33
+ {
34
+ "global_step": 80,
35
+ "optimizer_step": 10,
36
+ "lr": 2.173913043478261e-05,
37
+ "lm_loss": 0.6447479724884033,
38
+ "order_loss": 4.28125,
39
+ "ret_loss": 0.0,
40
+ "pretrain_loss": 0.0,
41
+ "total_loss": 0.8586151599884033
42
+ },
43
+ {
44
+ "global_step": 100,
45
+ "optimizer_step": 12,
46
+ "lr": 2.608695652173913e-05,
47
+ "lm_loss": 0.5031210780143738,
48
+ "order_loss": 2.390625,
49
+ "ret_loss": 0.0,
50
+ "pretrain_loss": 0.0,
51
+ "total_loss": 0.6227499842643738
52
+ },
53
+ {
54
+ "global_step": 120,
55
+ "optimizer_step": 15,
56
+ "lr": 3.260869565217392e-05,
57
+ "lm_loss": 0.4637785255908966,
58
+ "order_loss": 3.921875,
59
+ "ret_loss": 0.0,
60
+ "pretrain_loss": 0.0,
61
+ "total_loss": 0.6600675582885742
62
+ },
63
+ {
64
+ "global_step": 140,
65
+ "optimizer_step": 17,
66
+ "lr": 3.695652173913043e-05,
67
+ "lm_loss": 0.09661665558815002,
68
+ "order_loss": 10.375,
69
+ "ret_loss": 0.0,
70
+ "pretrain_loss": 0.0,
71
+ "total_loss": 0.6161478757858276
72
+ },
73
+ {
74
+ "global_step": 160,
75
+ "optimizer_step": 20,
76
+ "lr": 4.347826086956522e-05,
77
+ "lm_loss": 0.23068878054618835,
78
+ "order_loss": 9.0,
79
+ "ret_loss": 0.0,
80
+ "pretrain_loss": 0.0,
81
+ "total_loss": 0.6799075603485107
82
+ },
83
+ {
84
+ "global_step": 180,
85
+ "optimizer_step": 22,
86
+ "lr": 4.782608695652174e-05,
87
+ "lm_loss": 0.024927427992224693,
88
+ "order_loss": 10.25,
89
+ "ret_loss": 0.0,
90
+ "pretrain_loss": 0.0,
91
+ "total_loss": 0.5366461873054504
92
+ },
93
+ {
94
+ "global_step": 200,
95
+ "optimizer_step": 25,
96
+ "lr": 4.9997541293989384e-05,
97
+ "lm_loss": 0.1361241340637207,
98
+ "order_loss": 0.7109375,
99
+ "ret_loss": 0.0,
100
+ "pretrain_loss": 0.0,
101
+ "total_loss": 0.1717686653137207
102
+ },
103
+ {
104
+ "global_step": 220,
105
+ "optimizer_step": 27,
106
+ "lr": 4.999016565957633e-05,
107
+ "lm_loss": 0.10374148935079575,
108
+ "order_loss": 7.1875,
109
+ "ret_loss": 0.0,
110
+ "pretrain_loss": 0.0,
111
+ "total_loss": 0.46311649680137634
112
+ },
113
+ {
114
+ "global_step": 240,
115
+ "optimizer_step": 30,
116
+ "lr": 4.996988640512931e-05,
117
+ "lm_loss": 0.3016219139099121,
118
+ "order_loss": 6.375,
119
+ "ret_loss": 0.0,
120
+ "pretrain_loss": 0.0,
121
+ "total_loss": 0.6199812889099121
122
+ },
123
+ {
124
+ "global_step": 260,
125
+ "optimizer_step": 32,
126
+ "lr": 4.995022691166621e-05,
127
+ "lm_loss": 0.20621240139007568,
128
+ "order_loss": 11.125,
129
+ "ret_loss": 0.0,
130
+ "pretrain_loss": 0.0,
131
+ "total_loss": 0.7608999013900757
132
+ },
133
+ {
134
+ "global_step": 280,
135
+ "optimizer_step": 35,
136
+ "lr": 4.991153735294049e-05,
137
+ "lm_loss": 0.42221885919570923,
138
+ "order_loss": 0.7734375,
139
+ "ret_loss": 0.0,
140
+ "pretrain_loss": 0.0,
141
+ "total_loss": 0.46079307794570923
142
+ },
143
+ {
144
+ "global_step": 300,
145
+ "optimizer_step": 37,
146
+ "lr": 4.987961816680492e-05,
147
+ "lm_loss": 0.31809934973716736,
148
+ "order_loss": 4.625,
149
+ "ret_loss": 0.0,
150
+ "pretrain_loss": 0.0,
151
+ "total_loss": 0.5495446920394897
152
+ },
153
+ {
154
+ "global_step": 320,
155
+ "optimizer_step": 40,
156
+ "lr": 4.9822565862832806e-05,
157
+ "lm_loss": 0.13736826181411743,
158
+ "order_loss": 0.70703125,
159
+ "ret_loss": 0.0,
160
+ "pretrain_loss": 0.0,
161
+ "total_loss": 0.17276865243911743
162
+ },
163
+ {
164
+ "global_step": 340,
165
+ "optimizer_step": 42,
166
+ "lr": 4.9778426220595456e-05,
167
+ "lm_loss": 0.06809084862470627,
168
+ "order_loss": 4.1875,
169
+ "ret_loss": 0.0,
170
+ "pretrain_loss": 0.0,
171
+ "total_loss": 0.27707523107528687
172
+ },
173
+ {
174
+ "global_step": 360,
175
+ "optimizer_step": 45,
176
+ "lr": 4.970308130276272e-05,
177
+ "lm_loss": 0.19218333065509796,
178
+ "order_loss": 6.84375,
179
+ "ret_loss": 0.0,
180
+ "pretrain_loss": 0.0,
181
+ "total_loss": 0.5339801907539368
182
+ },
183
+ {
184
+ "global_step": 380,
185
+ "optimizer_step": 47,
186
+ "lr": 4.96467754629559e-05,
187
+ "lm_loss": 0.17113624513149261,
188
+ "order_loss": 5.40625,
189
+ "ret_loss": 0.0,
190
+ "pretrain_loss": 0.0,
191
+ "total_loss": 0.4406675100326538
192
+ },
193
+ {
194
+ "global_step": 400,
195
+ "optimizer_step": 50,
196
+ "lr": 4.955323054879298e-05,
197
+ "lm_loss": 0.18644192814826965,
198
+ "order_loss": 7.65625,
199
+ "ret_loss": 0.0,
200
+ "pretrain_loss": 0.0,
201
+ "total_loss": 0.5692543983459473
202
+ },
203
+ {
204
+ "global_step": 420,
205
+ "optimizer_step": 52,
206
+ "lr": 4.948482772521345e-05,
207
+ "lm_loss": 0.0622774176299572,
208
+ "order_loss": 0.66796875,
209
+ "ret_loss": 0.0,
210
+ "pretrain_loss": 0.0,
211
+ "total_loss": 0.0957246869802475
212
+ },
213
+ {
214
+ "global_step": 440,
215
+ "optimizer_step": 55,
216
+ "lr": 4.937319780454559e-05,
217
+ "lm_loss": 0.152618870139122,
218
+ "order_loss": 6.34375,
219
+ "ret_loss": 0.0,
220
+ "pretrain_loss": 0.0,
221
+ "total_loss": 0.4690251350402832
222
+ },
223
+ {
224
+ "global_step": 460,
225
+ "optimizer_step": 57,
226
+ "lr": 4.929278208117378e-05,
227
+ "lm_loss": 0.12415226548910141,
228
+ "order_loss": 6.78125,
229
+ "ret_loss": 0.0,
230
+ "pretrain_loss": 0.0,
231
+ "total_loss": 0.463996022939682
232
+ },
233
+ {
234
+ "global_step": 480,
235
+ "optimizer_step": 60,
236
+ "lr": 4.916320437477008e-05,
237
+ "lm_loss": 0.5055323839187622,
238
+ "order_loss": 8.6875,
239
+ "ret_loss": 0.0,
240
+ "pretrain_loss": 0.0,
241
+ "total_loss": 0.9391261339187622
242
+ },
243
+ {
244
+ "global_step": 500,
245
+ "optimizer_step": 62,
246
+ "lr": 4.907087460240999e-05,
247
+ "lm_loss": 0.25079330801963806,
248
+ "order_loss": 10.625,
249
+ "ret_loss": 0.0,
250
+ "pretrain_loss": 0.0,
251
+ "total_loss": 0.7820433378219604
252
+ },
253
+ {
254
+ "global_step": 520,
255
+ "optimizer_step": 65,
256
+ "lr": 4.892350839330522e-05,
257
+ "lm_loss": 0.026617128401994705,
258
+ "order_loss": 5.09375,
259
+ "ret_loss": 0.0,
260
+ "pretrain_loss": 0.0,
261
+ "total_loss": 0.2805233895778656
262
+ },
263
+ {
264
+ "global_step": 540,
265
+ "optimizer_step": 67,
266
+ "lr": 4.881937806807241e-05,
267
+ "lm_loss": 0.026445936411619186,
268
+ "order_loss": 0.81640625,
269
+ "ret_loss": 0.0,
270
+ "pretrain_loss": 0.0,
271
+ "total_loss": 0.06721742451190948
272
+ },
273
+ {
274
+ "global_step": 560,
275
+ "optimizer_step": 70,
276
+ "lr": 4.865440450576874e-05,
277
+ "lm_loss": 0.10359999537467957,
278
+ "order_loss": 0.76953125,
279
+ "ret_loss": 0.0,
280
+ "pretrain_loss": 0.0,
281
+ "total_loss": 0.14217421412467957
282
+ },
283
+ {
284
+ "global_step": 580,
285
+ "optimizer_step": 72,
286
+ "lr": 4.853860162957552e-05,
287
+ "lm_loss": 0.6062369346618652,
288
+ "order_loss": 5.96875,
289
+ "ret_loss": 0.0,
290
+ "pretrain_loss": 0.0,
291
+ "total_loss": 0.9050650596618652
292
+ },
293
+ {
294
+ "global_step": 600,
295
+ "optimizer_step": 75,
296
+ "lr": 4.8356223507364996e-05,
297
+ "lm_loss": 0.06958272308111191,
298
+ "order_loss": 0.5859375,
299
+ "ret_loss": 0.0,
300
+ "pretrain_loss": 0.0,
301
+ "total_loss": 0.09887959808111191
302
+ },
303
+ {
304
+ "global_step": 620,
305
+ "optimizer_step": 77,
306
+ "lr": 4.822889043057446e-05,
307
+ "lm_loss": 0.36084797978401184,
308
+ "order_loss": 2.5625,
309
+ "ret_loss": 0.0,
310
+ "pretrain_loss": 0.0,
311
+ "total_loss": 0.48877766728401184
312
+ },
313
+ {
314
+ "global_step": 640,
315
+ "optimizer_step": 80,
316
+ "lr": 4.802933193625593e-05,
317
+ "lm_loss": 0.08057578653097153,
318
+ "order_loss": 3.890625,
319
+ "ret_loss": 0.0,
320
+ "pretrain_loss": 0.0,
321
+ "total_loss": 0.2749117314815521
322
+ },
323
+ {
324
+ "global_step": 660,
325
+ "optimizer_step": 82,
326
+ "lr": 4.789062518269812e-05,
327
+ "lm_loss": 0.39295199513435364,
328
+ "order_loss": 0.609375,
329
+ "ret_loss": 0.0,
330
+ "pretrain_loss": 0.0,
331
+ "total_loss": 0.42346957325935364
332
+ },
333
+ {
334
+ "global_step": 680,
335
+ "optimizer_step": 85,
336
+ "lr": 4.767413162299501e-05,
337
+ "lm_loss": 0.2818896174430847,
338
+ "order_loss": 7.40625,
339
+ "ret_loss": 0.0,
340
+ "pretrain_loss": 0.0,
341
+ "total_loss": 0.6529833674430847
342
+ },
343
+ {
344
+ "global_step": 700,
345
+ "optimizer_step": 87,
346
+ "lr": 4.752422169756048e-05,
347
+ "lm_loss": 0.14135967195034027,
348
+ "order_loss": 10.3125,
349
+ "ret_loss": 0.0,
350
+ "pretrain_loss": 0.0,
351
+ "total_loss": 0.6569846868515015
352
+ },
353
+ {
354
+ "global_step": 720,
355
+ "optimizer_step": 90,
356
+ "lr": 4.729105919657818e-05,
357
+ "lm_loss": 0.0027198870666325092,
358
+ "order_loss": 4.15625,
359
+ "ret_loss": 0.0,
360
+ "pretrain_loss": 0.0,
361
+ "total_loss": 0.21072770655155182
362
+ },
363
+ {
364
+ "global_step": 740,
365
+ "optimizer_step": 92,
366
+ "lr": 4.7130130375625305e-05,
367
+ "lm_loss": 0.23343317210674286,
368
+ "order_loss": 0.54296875,
369
+ "ret_loss": 0.0,
370
+ "pretrain_loss": 0.0,
371
+ "total_loss": 0.26053279638290405
372
+ },
373
+ {
374
+ "global_step": 760,
375
+ "optimizer_step": 95,
376
+ "lr": 4.6880585547718845e-05,
377
+ "lm_loss": 0.0029480066150426865,
378
+ "order_loss": 0.5390625,
379
+ "ret_loss": 0.0,
380
+ "pretrain_loss": 0.0,
381
+ "total_loss": 0.029925545677542686
382
+ },
383
+ {
384
+ "global_step": 780,
385
+ "optimizer_step": 97,
386
+ "lr": 4.670883565255264e-05,
387
+ "lm_loss": 0.34151309728622437,
388
+ "order_loss": 6.46875,
389
+ "ret_loss": 0.0,
390
+ "pretrain_loss": 0.0,
391
+ "total_loss": 0.6657318472862244
392
+ },
393
+ {
394
+ "global_step": 800,
395
+ "optimizer_step": 100,
396
+ "lr": 4.6443215250006806e-05,
397
+ "lm_loss": 0.3413035273551941,
398
+ "order_loss": 16.25,
399
+ "ret_loss": 0.0,
400
+ "pretrain_loss": 0.0,
401
+ "total_loss": 1.1538035869598389
402
+ },
403
+ {
404
+ "global_step": 820,
405
+ "optimizer_step": 102,
406
+ "lr": 4.626085540370762e-05,
407
+ "lm_loss": 0.004675194621086121,
408
+ "order_loss": 2.71875,
409
+ "ret_loss": 0.0,
410
+ "pretrain_loss": 0.0,
411
+ "total_loss": 0.14041738212108612
412
+ },
413
+ {
414
+ "global_step": 840,
415
+ "optimizer_step": 105,
416
+ "lr": 4.597948593966256e-05,
417
+ "lm_loss": 0.11196538060903549,
418
+ "order_loss": 11.0625,
419
+ "ret_loss": 0.0,
420
+ "pretrain_loss": 0.0,
421
+ "total_loss": 0.6666528582572937
422
+ },
423
+ {
424
+ "global_step": 860,
425
+ "optimizer_step": 107,
426
+ "lr": 4.5786740307563636e-05,
427
+ "lm_loss": 0.03330649435520172,
428
+ "order_loss": 10.5,
429
+ "ret_loss": 0.0,
430
+ "pretrain_loss": 0.0,
431
+ "total_loss": 0.5567439794540405
432
+ },
433
+ {
434
+ "global_step": 880,
435
+ "optimizer_step": 110,
436
+ "lr": 4.5489967654649474e-05,
437
+ "lm_loss": 0.001231937319971621,
438
+ "order_loss": 1.4140625,
439
+ "ret_loss": 0.0,
440
+ "pretrain_loss": 0.0,
441
+ "total_loss": 0.07203271985054016
442
+ },
443
+ {
444
+ "global_step": 900,
445
+ "optimizer_step": 112,
446
+ "lr": 4.528707316878232e-05,
447
+ "lm_loss": 0.4579201936721802,
448
+ "order_loss": 0.71875,
449
+ "ret_loss": 0.0,
450
+ "pretrain_loss": 0.0,
451
+ "total_loss": 0.4938088655471802
452
+ },
453
+ {
454
+ "global_step": 920,
455
+ "optimizer_step": 115,
456
+ "lr": 4.497526213395623e-05,
457
+ "lm_loss": 0.11886116862297058,
458
+ "order_loss": 4.5625,
459
+ "ret_loss": 0.0,
460
+ "pretrain_loss": 0.0,
461
+ "total_loss": 0.3473767936229706
462
+ },
463
+ {
464
+ "global_step": 940,
465
+ "optimizer_step": 117,
466
+ "lr": 4.476246820180259e-05,
467
+ "lm_loss": 0.5271569490432739,
468
+ "order_loss": 4.40625,
469
+ "ret_loss": 0.0,
470
+ "pretrain_loss": 0.0,
471
+ "total_loss": 0.7478600740432739
472
+ },
473
+ {
474
+ "global_step": 960,
475
+ "optimizer_step": 120,
476
+ "lr": 4.443600207791081e-05,
477
+ "lm_loss": 0.05160878971219063,
478
+ "order_loss": 0.69921875,
479
+ "ret_loss": 0.0,
480
+ "pretrain_loss": 0.0,
481
+ "total_loss": 0.08652089536190033
482
+ },
483
+ {
484
+ "global_step": 980,
485
+ "optimizer_step": 122,
486
+ "lr": 4.421357027581921e-05,
487
+ "lm_loss": 0.2952635884284973,
488
+ "order_loss": 0.55078125,
489
+ "ret_loss": 0.0,
490
+ "pretrain_loss": 0.0,
491
+ "total_loss": 0.3228514790534973
492
+ },
493
+ {
494
+ "global_step": 1000,
495
+ "optimizer_step": 125,
496
+ "lr": 4.38728503704354e-05,
497
+ "lm_loss": 0.04960014671087265,
498
+ "order_loss": 12.0,
499
+ "ret_loss": 0.0,
500
+ "pretrain_loss": 0.0,
501
+ "total_loss": 0.6511626243591309
502
+ },
503
+ {
504
+ "global_step": 1020,
505
+ "optimizer_step": 127,
506
+ "lr": 4.364105412207914e-05,
507
+ "lm_loss": 0.08489231765270233,
508
+ "order_loss": 0.51953125,
509
+ "ret_loss": 0.0,
510
+ "pretrain_loss": 0.0,
511
+ "total_loss": 0.11089329421520233
512
+ },
513
+ {
514
+ "global_step": 1040,
515
+ "optimizer_step": 130,
516
+ "lr": 4.328649926419819e-05,
517
+ "lm_loss": 0.018955232575535774,
518
+ "order_loss": 7.65625,
519
+ "ret_loss": 0.0,
520
+ "pretrain_loss": 0.0,
521
+ "total_loss": 0.4017677307128906
522
+ },
523
+ {
524
+ "global_step": 1060,
525
+ "optimizer_step": 132,
526
+ "lr": 4.304562350447008e-05,
527
+ "lm_loss": 0.05704023316502571,
528
+ "order_loss": 4.0,
529
+ "ret_loss": 0.0,
530
+ "pretrain_loss": 0.0,
531
+ "total_loss": 0.2572355568408966
532
+ },
533
+ {
534
+ "global_step": 1080,
535
+ "optimizer_step": 135,
536
+ "lr": 4.267766952966369e-05,
537
+ "lm_loss": 0.07695232331752777,
538
+ "order_loss": 0.6171875,
539
+ "ret_loss": 0.0,
540
+ "pretrain_loss": 0.0,
541
+ "total_loss": 0.10783611238002777
542
+ },
543
+ {
544
+ "global_step": 1100,
545
+ "optimizer_step": 137,
546
+ "lr": 4.242801035442058e-05,
547
+ "lm_loss": 0.056834254413843155,
548
+ "order_loss": 4.59375,
549
+ "ret_loss": 0.0,
550
+ "pretrain_loss": 0.0,
551
+ "total_loss": 0.28632643818855286
552
+ },
553
+ {
554
+ "global_step": 1120,
555
+ "optimizer_step": 140,
556
+ "lr": 4.204710956908763e-05,
557
+ "lm_loss": 0.13167618215084076,
558
+ "order_loss": 2.71875,
559
+ "ret_loss": 0.0,
560
+ "pretrain_loss": 0.0,
561
+ "total_loss": 0.26741838455200195
562
+ },
563
+ {
564
+ "global_step": 1140,
565
+ "optimizer_step": 142,
566
+ "lr": 4.178897387117546e-05,
567
+ "lm_loss": 0.061770014464855194,
568
+ "order_loss": 3.578125,
569
+ "ret_loss": 0.0,
570
+ "pretrain_loss": 0.0,
571
+ "total_loss": 0.2404809594154358
572
+ },
573
+ {
574
+ "global_step": 1160,
575
+ "optimizer_step": 145,
576
+ "lr": 4.139559449654561e-05,
577
+ "lm_loss": 0.2048301249742508,
578
+ "order_loss": 0.61328125,
579
+ "ret_loss": 0.0,
580
+ "pretrain_loss": 0.0,
581
+ "total_loss": 0.2354697734117508
582
+ },
583
+ {
584
+ "global_step": 1180,
585
+ "optimizer_step": 147,
586
+ "lr": 4.1129299588552193e-05,
587
+ "lm_loss": 0.15212678909301758,
588
+ "order_loss": 8.875,
589
+ "ret_loss": 0.0,
590
+ "pretrain_loss": 0.0,
591
+ "total_loss": 0.5954861640930176
592
+ },
593
+ {
594
+ "global_step": 1200,
595
+ "optimizer_step": 150,
596
+ "lr": 4.072392518512623e-05,
597
+ "lm_loss": 0.044819075614213943,
598
+ "order_loss": 7.6875,
599
+ "ret_loss": 0.0,
600
+ "pretrain_loss": 0.0,
601
+ "total_loss": 0.42958471179008484
602
+ },
603
+ {
604
+ "global_step": 1220,
605
+ "optimizer_step": 152,
606
+ "lr": 4.0449798409325665e-05,
607
+ "lm_loss": 0.12913520634174347,
608
+ "order_loss": 2.53125,
609
+ "ret_loss": 0.0,
610
+ "pretrain_loss": 0.0,
611
+ "total_loss": 0.2560883164405823
612
+ },
613
+ {
614
+ "global_step": 1240,
615
+ "optimizer_step": 155,
616
+ "lr": 4.0032927282460146e-05,
617
+ "lm_loss": 0.0679524838924408,
618
+ "order_loss": 2.4375,
619
+ "ret_loss": 0.0,
620
+ "pretrain_loss": 0.0,
621
+ "total_loss": 0.1900227963924408
622
+ },
623
+ {
624
+ "global_step": 1260,
625
+ "optimizer_step": 157,
626
+ "lr": 3.9751305608428205e-05,
627
+ "lm_loss": 0.09421052038669586,
628
+ "order_loss": 0.4921875,
629
+ "ret_loss": 0.0,
630
+ "pretrain_loss": 0.0,
631
+ "total_loss": 0.11886872351169586
632
+ },
633
+ {
634
+ "global_step": 1280,
635
+ "optimizer_step": 160,
636
+ "lr": 3.932345019579495e-05,
637
+ "lm_loss": 0.06093278527259827,
638
+ "order_loss": 0.9453125,
639
+ "ret_loss": 0.0,
640
+ "pretrain_loss": 0.0,
641
+ "total_loss": 0.10829606652259827
642
+ },
643
+ {
644
+ "global_step": 1300,
645
+ "optimizer_step": 162,
646
+ "lr": 3.90346798061902e-05,
647
+ "lm_loss": 0.04489460960030556,
648
+ "order_loss": 6.6875,
649
+ "ret_loss": 0.0,
650
+ "pretrain_loss": 0.0,
651
+ "total_loss": 0.37887898087501526
652
+ },
653
+ {
654
+ "global_step": 1320,
655
+ "optimizer_step": 165,
656
+ "lr": 3.859636604786372e-05,
657
+ "lm_loss": 0.0032928287982940674,
658
+ "order_loss": 0.69140625,
659
+ "ret_loss": 0.0,
660
+ "pretrain_loss": 0.0,
661
+ "total_loss": 0.03796079754829407
662
+ },
663
+ {
664
+ "global_step": 1340,
665
+ "optimizer_step": 167,
666
+ "lr": 3.830080191288342e-05,
667
+ "lm_loss": 0.4549589157104492,
668
+ "order_loss": 11.4375,
669
+ "ret_loss": 0.0,
670
+ "pretrain_loss": 0.0,
671
+ "total_loss": 1.0252714157104492
672
+ },
673
+ {
674
+ "global_step": 1360,
675
+ "optimizer_step": 170,
676
+ "lr": 3.785256860483054e-05,
677
+ "lm_loss": 0.16511064767837524,
678
+ "order_loss": 0.53125,
679
+ "ret_loss": 0.0,
680
+ "pretrain_loss": 0.0,
681
+ "total_loss": 0.19172197580337524
682
+ },
683
+ {
684
+ "global_step": 1380,
685
+ "optimizer_step": 172,
686
+ "lr": 3.755057404586455e-05,
687
+ "lm_loss": 0.0026866549160331488,
688
+ "order_loss": 0.76953125,
689
+ "ret_loss": 0.0,
690
+ "pretrain_loss": 0.0,
691
+ "total_loss": 0.04126087203621864
692
+ },
693
+ {
694
+ "global_step": 1400,
695
+ "optimizer_step": 175,
696
+ "lr": 3.7092972177631e-05,
697
+ "lm_loss": 0.00660400977358222,
698
+ "order_loss": 6.5,
699
+ "ret_loss": 0.0,
700
+ "pretrain_loss": 0.0,
701
+ "total_loss": 0.33082276582717896
702
+ },
703
+ {
704
+ "global_step": 1420,
705
+ "optimizer_step": 177,
706
+ "lr": 3.678491842064995e-05,
707
+ "lm_loss": 0.04543091356754303,
708
+ "order_loss": 5.8125,
709
+ "ret_loss": 0.0,
710
+ "pretrain_loss": 0.0,
711
+ "total_loss": 0.33644652366638184
712
+ },
713
+ {
714
+ "global_step": 1440,
715
+ "optimizer_step": 180,
716
+ "lr": 3.631851049805793e-05,
717
+ "lm_loss": 0.24766041338443756,
718
+ "order_loss": 16.875,
719
+ "ret_loss": 0.0,
720
+ "pretrain_loss": 0.0,
721
+ "total_loss": 1.0914103984832764
722
+ },
723
+ {
724
+ "global_step": 1460,
725
+ "optimizer_step": 182,
726
+ "lr": 3.600477621728473e-05,
727
+ "lm_loss": 0.01777743175625801,
728
+ "order_loss": 6.375,
729
+ "ret_loss": 0.0,
730
+ "pretrain_loss": 0.0,
731
+ "total_loss": 0.3361368179321289
732
+ },
733
+ {
734
+ "global_step": 1480,
735
+ "optimizer_step": 185,
736
+ "lr": 3.5530135570974274e-05,
737
+ "lm_loss": 0.024640265852212906,
738
+ "order_loss": 5.5625,
739
+ "ret_loss": 0.0,
740
+ "pretrain_loss": 0.0,
741
+ "total_loss": 0.3019840121269226
742
+ },
743
+ {
744
+ "global_step": 1500,
745
+ "optimizer_step": 187,
746
+ "lr": 3.521110642339991e-05,
747
+ "lm_loss": 0.00986605416983366,
748
+ "order_loss": 0.7734375,
749
+ "ret_loss": 0.0,
750
+ "pretrain_loss": 0.0,
751
+ "total_loss": 0.048440273851156235
752
+ },
753
+ {
754
+ "global_step": 1520,
755
+ "optimizer_step": 190,
756
+ "lr": 3.4728816504063726e-05,
757
+ "lm_loss": 0.07523651421070099,
758
+ "order_loss": 2.5625,
759
+ "ret_loss": 0.0,
760
+ "pretrain_loss": 0.0,
761
+ "total_loss": 0.203166201710701
762
+ },
763
+ {
764
+ "global_step": 1540,
765
+ "optimizer_step": 192,
766
+ "lr": 3.440488465537943e-05,
767
+ "lm_loss": 0.07263525575399399,
768
+ "order_loss": 4.09375,
769
+ "ret_loss": 0.0,
770
+ "pretrain_loss": 0.0,
771
+ "total_loss": 0.2777133882045746
772
+ },
773
+ {
774
+ "global_step": 1560,
775
+ "optimizer_step": 195,
776
+ "lr": 3.391553831655782e-05,
777
+ "lm_loss": 0.005979922134429216,
778
+ "order_loss": 18.625,
779
+ "ret_loss": 0.0,
780
+ "pretrain_loss": 0.0,
781
+ "total_loss": 0.9356673955917358
782
+ },
783
+ {
784
+ "global_step": 1580,
785
+ "optimizer_step": 197,
786
+ "lr": 3.358710195908653e-05,
787
+ "lm_loss": 0.11882327497005463,
788
+ "order_loss": 4.90625,
789
+ "ret_loss": 0.0,
790
+ "pretrain_loss": 0.0,
791
+ "total_loss": 0.3639404773712158
792
+ },
793
+ {
794
+ "global_step": 1600,
795
+ "optimizer_step": 200,
796
+ "lr": 3.309130072840379e-05,
797
+ "lm_loss": 0.05646836757659912,
798
+ "order_loss": 7.28125,
799
+ "ret_loss": 0.0,
800
+ "pretrain_loss": 0.0,
801
+ "total_loss": 0.4197496175765991
802
+ },
803
+ {
804
+ "global_step": 1620,
805
+ "optimizer_step": 202,
806
+ "lr": 3.2758763591623295e-05,
807
+ "lm_loss": 0.006530260667204857,
808
+ "order_loss": 0.48828125,
809
+ "ret_loss": 0.0,
810
+ "pretrain_loss": 0.0,
811
+ "total_loss": 0.030944323167204857
812
+ },
813
+ {
814
+ "global_step": 1640,
815
+ "optimizer_step": 205,
816
+ "lr": 3.225711693136156e-05,
817
+ "lm_loss": 0.09345230460166931,
818
+ "order_loss": 4.71875,
819
+ "ret_loss": 0.0,
820
+ "pretrain_loss": 0.0,
821
+ "total_loss": 0.3297804296016693
822
+ },
823
+ {
824
+ "global_step": 1660,
825
+ "optimizer_step": 207,
826
+ "lr": 3.1920887785621235e-05,
827
+ "lm_loss": 0.2289741486310959,
828
+ "order_loss": 0.9921875,
829
+ "ret_loss": 0.0,
830
+ "pretrain_loss": 0.0,
831
+ "total_loss": 0.2785347104072571
832
+ },
833
+ {
834
+ "global_step": 1680,
835
+ "optimizer_step": 210,
836
+ "lr": 3.141401234354067e-05,
837
+ "lm_loss": 0.009529650211334229,
838
+ "order_loss": 2.71875,
839
+ "ret_loss": 0.0,
840
+ "pretrain_loss": 0.0,
841
+ "total_loss": 0.14527183771133423
842
+ },
843
+ {
844
+ "global_step": 1700,
845
+ "optimizer_step": 212,
846
+ "lr": 3.10745044975816e-05,
847
+ "lm_loss": 0.013621973805129528,
848
+ "order_loss": 7.625,
849
+ "ret_loss": 0.0,
850
+ "pretrain_loss": 0.0,
851
+ "total_loss": 0.394481360912323
852
+ },
853
+ {
854
+ "global_step": 1720,
855
+ "optimizer_step": 215,
856
+ "lr": 3.056302334890786e-05,
857
+ "lm_loss": 0.33359622955322266,
858
+ "order_loss": 5.6875,
859
+ "ret_loss": 0.0,
860
+ "pretrain_loss": 0.0,
861
+ "total_loss": 0.6187524795532227
862
+ },
863
+ {
864
+ "global_step": 1740,
865
+ "optimizer_step": 217,
866
+ "lr": 3.022065414180425e-05,
867
+ "lm_loss": 0.05790264904499054,
868
+ "order_loss": 3.296875,
869
+ "ret_loss": 0.0,
870
+ "pretrain_loss": 0.0,
871
+ "total_loss": 0.22294171154499054
872
+ },
873
+ {
874
+ "global_step": 1760,
875
+ "optimizer_step": 220,
876
+ "lr": 2.9705196023315006e-05,
877
+ "lm_loss": 0.09645794332027435,
878
+ "order_loss": 4.46875,
879
+ "ret_loss": 0.0,
880
+ "pretrain_loss": 0.0,
881
+ "total_loss": 0.32009077072143555
882
+ },
883
+ {
884
+ "global_step": 1780,
885
+ "optimizer_step": 222,
886
+ "lr": 2.9360386311461275e-05,
887
+ "lm_loss": 0.0025348321069031954,
888
+ "order_loss": 4.0625,
889
+ "ret_loss": 0.0,
890
+ "pretrain_loss": 0.0,
891
+ "total_loss": 0.20565983653068542
892
+ },
893
+ {
894
+ "global_step": 1800,
895
+ "optimizer_step": 225,
896
+ "lr": 2.884158484861325e-05,
897
+ "lm_loss": 0.14595180749893188,
898
+ "order_loss": 0.62890625,
899
+ "ret_loss": 0.0,
900
+ "pretrain_loss": 0.0,
901
+ "total_loss": 0.17744594812393188
902
+ },
903
+ {
904
+ "global_step": 1820,
905
+ "optimizer_step": 227,
906
+ "lr": 2.849475848838749e-05,
907
+ "lm_loss": 0.03893221169710159,
908
+ "order_loss": 6.375,
909
+ "ret_loss": 0.0,
910
+ "pretrain_loss": 0.0,
911
+ "total_loss": 0.357291579246521
912
+ },
913
+ {
914
+ "global_step": 1840,
915
+ "optimizer_step": 230,
916
+ "lr": 2.7973251416434175e-05,
917
+ "lm_loss": 0.13533219695091248,
918
+ "order_loss": 3.703125,
919
+ "ret_loss": 0.0,
920
+ "pretrain_loss": 0.0,
921
+ "total_loss": 0.3208790719509125
922
+ },
923
+ {
924
+ "global_step": 1860,
925
+ "optimizer_step": 232,
926
+ "lr": 2.7624834743173867e-05,
927
+ "lm_loss": 0.04314413294196129,
928
+ "order_loss": 0.5625,
929
+ "ret_loss": 0.0,
930
+ "pretrain_loss": 0.0,
931
+ "total_loss": 0.07122030854225159
932
+ },
933
+ {
934
+ "global_step": 1880,
935
+ "optimizer_step": 235,
936
+ "lr": 2.710126312323119e-05,
937
+ "lm_loss": 0.0034851201344281435,
938
+ "order_loss": 1.4453125,
939
+ "ret_loss": 0.0,
940
+ "pretrain_loss": 0.0,
941
+ "total_loss": 0.07575074583292007
942
+ },
943
+ {
944
+ "global_step": 1900,
945
+ "optimizer_step": 237,
946
+ "lr": 2.6751684427161683e-05,
947
+ "lm_loss": 0.09201540797948837,
948
+ "order_loss": 1.265625,
949
+ "ret_loss": 0.0,
950
+ "pretrain_loss": 0.0,
951
+ "total_loss": 0.15549197793006897
952
+ },
953
+ {
954
+ "global_step": 1920,
955
+ "optimizer_step": 240,
956
+ "lr": 2.6226691858185454e-05,
957
+ "lm_loss": 0.0035098956432193518,
958
+ "order_loss": 2.9375,
959
+ "ret_loss": 0.0,
960
+ "pretrain_loss": 0.0,
961
+ "total_loss": 0.14999426901340485
962
+ },
963
+ {
964
+ "global_step": 1940,
965
+ "optimizer_step": 242,
966
+ "lr": 2.587638085794541e-05,
967
+ "lm_loss": 0.00286117079667747,
968
+ "order_loss": 3.6875,
969
+ "ret_loss": 0.0,
970
+ "pretrain_loss": 0.0,
971
+ "total_loss": 0.1874314844608307
972
+ },
973
+ {
974
+ "global_step": 1960,
975
+ "optimizer_step": 245,
976
+ "lr": 2.535061268558906e-05,
977
+ "lm_loss": 0.0036227041855454445,
978
+ "order_loss": 0.443359375,
979
+ "ret_loss": 0.0,
980
+ "pretrain_loss": 0.0,
981
+ "total_loss": 0.02583950012922287
982
+ },
983
+ {
984
+ "global_step": 1980,
985
+ "optimizer_step": 247,
986
+ "lr": 2.5e-05,
987
+ "lm_loss": 0.024752845987677574,
988
+ "order_loss": 2.921875,
989
+ "ret_loss": 0.0,
990
+ "pretrain_loss": 0.0,
991
+ "total_loss": 0.17123721539974213
992
+ },
993
+ {
994
+ "global_step": 2000,
995
+ "optimizer_step": 250,
996
+ "lr": 2.447410252332528e-05,
997
+ "lm_loss": 0.0015496063278988004,
998
+ "order_loss": 2.15625,
999
+ "ret_loss": 0.0,
1000
+ "pretrain_loss": 0.0,
1001
+ "total_loss": 0.1094597652554512
1002
+ },
1003
+ {
1004
+ "global_step": 2020,
1005
+ "optimizer_step": 252,
1006
+ "lr": 2.4123619142054597e-05,
1007
+ "lm_loss": 0.03278156742453575,
1008
+ "order_loss": 1.875,
1009
+ "ret_loss": 0.0,
1010
+ "pretrain_loss": 0.0,
1011
+ "total_loss": 0.12653157114982605
1012
+ },
1013
+ {
1014
+ "global_step": 2040,
1015
+ "optimizer_step": 255,
1016
+ "lr": 2.3598238819070202e-05,
1017
+ "lm_loss": 0.17414996027946472,
1018
+ "order_loss": 1.6875,
1019
+ "ret_loss": 0.0,
1020
+ "pretrain_loss": 0.0,
1021
+ "total_loss": 0.2586226165294647
1022
+ },
1023
+ {
1024
+ "global_step": 2060,
1025
+ "optimizer_step": 257,
1026
+ "lr": 2.3248315572838316e-05,
1027
+ "lm_loss": 0.27706393599510193,
1028
+ "order_loss": 0.51171875,
1029
+ "ret_loss": 0.0,
1030
+ "pretrain_loss": 0.0,
1031
+ "total_loss": 0.30269870162010193
1032
+ },
1033
+ {
1034
+ "global_step": 2080,
1035
+ "optimizer_step": 260,
1036
+ "lr": 2.272409822584325e-05,
1037
+ "lm_loss": 0.006486980710178614,
1038
+ "order_loss": 0.49609375,
1039
+ "ret_loss": 0.0,
1040
+ "pretrain_loss": 0.0,
1041
+ "total_loss": 0.031267255544662476
1042
+ },
1043
+ {
1044
+ "global_step": 2100,
1045
+ "optimizer_step": 262,
1046
+ "lr": 2.237516525682614e-05,
1047
+ "lm_loss": 0.07791294157505035,
1048
+ "order_loss": 0.5546875,
1049
+ "ret_loss": 0.0,
1050
+ "pretrain_loss": 0.0,
1051
+ "total_loss": 0.10562290251255035
1052
+ },
1053
+ {
1054
+ "global_step": 2120,
1055
+ "optimizer_step": 265,
1056
+ "lr": 2.185275527853437e-05,
1057
+ "lm_loss": 0.03462192043662071,
1058
+ "order_loss": 0.5,
1059
+ "ret_loss": 0.0,
1060
+ "pretrain_loss": 0.0,
1061
+ "total_loss": 0.05964633449912071
1062
+ },
1063
+ {
1064
+ "global_step": 2140,
1065
+ "optimizer_step": 267,
1066
+ "lr": 2.1505241511612522e-05,
1067
+ "lm_loss": 0.005326329730451107,
1068
+ "order_loss": 1.5859375,
1069
+ "ret_loss": 0.0,
1070
+ "pretrain_loss": 0.0,
1071
+ "total_loss": 0.08442789316177368
1072
+ },
1073
+ {
1074
+ "global_step": 2160,
1075
+ "optimizer_step": 270,
1076
+ "lr": 2.0985281073035076e-05,
1077
+ "lm_loss": 0.08868353068828583,
1078
+ "order_loss": 4.625,
1079
+ "ret_loss": 0.0,
1080
+ "pretrain_loss": 0.0,
1081
+ "total_loss": 0.320128858089447
1082
+ },
1083
+ {
1084
+ "global_step": 2180,
1085
+ "optimizer_step": 272,
1086
+ "lr": 2.0639613688538734e-05,
1087
+ "lm_loss": 0.09814752638339996,
1088
+ "order_loss": 2.34375,
1089
+ "ret_loss": 0.0,
1090
+ "pretrain_loss": 0.0,
1091
+ "total_loss": 0.21533502638339996
1092
+ },
1093
+ {
1094
+ "global_step": 2200,
1095
+ "optimizer_step": 275,
1096
+ "lr": 2.0122741949596797e-05,
1097
+ "lm_loss": 0.07571753859519958,
1098
+ "order_loss": 3.140625,
1099
+ "ret_loss": 0.0,
1100
+ "pretrain_loss": 0.0,
1101
+ "total_loss": 0.23294410109519958
1102
+ },
1103
+ {
1104
+ "global_step": 2220,
1105
+ "optimizer_step": 277,
1106
+ "lr": 1.977934585819576e-05,
1107
+ "lm_loss": 0.04704970493912697,
1108
+ "order_loss": 0.59765625,
1109
+ "ret_loss": 0.0,
1110
+ "pretrain_loss": 0.0,
1111
+ "total_loss": 0.07695692777633667
1112
+ },
1113
+ {
1114
+ "global_step": 2240,
1115
+ "optimizer_step": 280,
1116
+ "lr": 1.9266198182035058e-05,
1117
+ "lm_loss": 0.029621252790093422,
1118
+ "order_loss": 2.90625,
1119
+ "ret_loss": 0.0,
1120
+ "pretrain_loss": 0.0,
1121
+ "total_loss": 0.17512907087802887
1122
+ },
1123
+ {
1124
+ "global_step": 2260,
1125
+ "optimizer_step": 282,
1126
+ "lr": 1.8925495502418406e-05,
1127
+ "lm_loss": 0.12245482951402664,
1128
+ "order_loss": 2.09375,
1129
+ "ret_loss": 0.0,
1130
+ "pretrain_loss": 0.0,
1131
+ "total_loss": 0.22694700956344604
1132
+ },
1133
+ {
1134
+ "global_step": 2280,
1135
+ "optimizer_step": 285,
1136
+ "lr": 1.841670267439088e-05,
1137
+ "lm_loss": 0.008694806136190891,
1138
+ "order_loss": 5.75,
1139
+ "ret_loss": 0.0,
1140
+ "pretrain_loss": 0.0,
1141
+ "total_loss": 0.2958041727542877
1142
+ },
1143
+ {
1144
+ "global_step": 2300,
1145
+ "optimizer_step": 287,
1146
+ "lr": 1.8079112214378768e-05,
1147
+ "lm_loss": 0.12838587164878845,
1148
+ "order_loss": 0.42578125,
1149
+ "ret_loss": 0.0,
1150
+ "pretrain_loss": 0.0,
1151
+ "total_loss": 0.14962610602378845
1152
+ },
1153
+ {
1154
+ "global_step": 2320,
1155
+ "optimizer_step": 290,
1156
+ "lr": 1.757529966665141e-05,
1157
+ "lm_loss": 0.005137450527399778,
1158
+ "order_loss": 0.578125,
1159
+ "ret_loss": 0.0,
1160
+ "pretrain_loss": 0.0,
1161
+ "total_loss": 0.034068115055561066
1162
+ },
1163
+ {
1164
+ "global_step": 2340,
1165
+ "optimizer_step": 292,
1166
+ "lr": 1.72412364083767e-05,
1167
+ "lm_loss": 0.18859940767288208,
1168
+ "order_loss": 6.375,
1169
+ "ret_loss": 0.0,
1170
+ "pretrain_loss": 0.0,
1171
+ "total_loss": 0.5069587826728821
1172
+ },
1173
+ {
1174
+ "global_step": 2360,
1175
+ "optimizer_step": 295,
1176
+ "lr": 1.6743023451120832e-05,
1177
+ "lm_loss": 0.004736732225865126,
1178
+ "order_loss": 0.81640625,
1179
+ "ret_loss": 0.0,
1180
+ "pretrain_loss": 0.0,
1181
+ "total_loss": 0.04550821706652641
1182
+ },
1183
+ {
1184
+ "global_step": 2380,
1185
+ "optimizer_step": 297,
1186
+ "lr": 1.641289804091347e-05,
1187
+ "lm_loss": 0.0014097786042839289,
1188
+ "order_loss": 0.50390625,
1189
+ "ret_loss": 0.0,
1190
+ "pretrain_loss": 0.0,
1191
+ "total_loss": 0.026556262746453285
1192
+ },
1193
+ {
1194
+ "global_step": 2400,
1195
+ "optimizer_step": 300,
1196
+ "lr": 1.5920897101019383e-05,
1197
+ "lm_loss": 0.028016045689582825,
1198
+ "order_loss": 1.8984375,
1199
+ "ret_loss": 0.0,
1200
+ "pretrain_loss": 0.0,
1201
+ "total_loss": 0.12274260818958282
1202
+ },
1203
+ {
1204
+ "global_step": 2420,
1205
+ "optimizer_step": 302,
1206
+ "lr": 1.5595115344620576e-05,
1207
+ "lm_loss": 0.005721462424844503,
1208
+ "order_loss": 7.15625,
1209
+ "ret_loss": 0.0,
1210
+ "pretrain_loss": 0.0,
1211
+ "total_loss": 0.36314332485198975
1212
+ },
1213
+ {
1214
+ "global_step": 2440,
1215
+ "optimizer_step": 305,
1216
+ "lr": 1.5109931212873534e-05,
1217
+ "lm_loss": 0.055272627621889114,
1218
+ "order_loss": 9.3125,
1219
+ "ret_loss": 0.0,
1220
+ "pretrain_loss": 0.0,
1221
+ "total_loss": 0.52011638879776
1222
+ },
1223
+ {
1224
+ "global_step": 2460,
1225
+ "optimizer_step": 307,
1226
+ "lr": 1.4788893576600099e-05,
1227
+ "lm_loss": 0.001077838009223342,
1228
+ "order_loss": 1.5703125,
1229
+ "ret_loss": 0.0,
1230
+ "pretrain_loss": 0.0,
1231
+ "total_loss": 0.07969111949205399
1232
+ },
1233
+ {
1234
+ "global_step": 2480,
1235
+ "optimizer_step": 310,
1236
+ "lr": 1.4311122664242954e-05,
1237
+ "lm_loss": 0.047987036406993866,
1238
+ "order_loss": 7.375,
1239
+ "ret_loss": 0.0,
1240
+ "pretrain_loss": 0.0,
1241
+ "total_loss": 0.41712766885757446
1242
+ },
1243
+ {
1244
+ "global_step": 2500,
1245
+ "optimizer_step": 312,
1246
+ "lr": 1.399522378271527e-05,
1247
+ "lm_loss": 0.1789265125989914,
1248
+ "order_loss": 3.1875,
1249
+ "ret_loss": 0.0,
1250
+ "pretrain_loss": 0.0,
1251
+ "total_loss": 0.3381062150001526
1252
+ },
1253
+ {
1254
+ "global_step": 2520,
1255
+ "optimizer_step": 315,
1256
+ "lr": 1.3525453388311554e-05,
1257
+ "lm_loss": 0.12378852814435959,
1258
+ "order_loss": 2.15625,
1259
+ "ret_loss": 0.0,
1260
+ "pretrain_loss": 0.0,
1261
+ "total_loss": 0.23169869184494019
1262
+ },
1263
+ {
1264
+ "global_step": 2540,
1265
+ "optimizer_step": 317,
1266
+ "lr": 1.3215081579350058e-05,
1267
+ "lm_loss": 0.04076281562447548,
1268
+ "order_loss": 7.4375,
1269
+ "ret_loss": 0.0,
1270
+ "pretrain_loss": 0.0,
1271
+ "total_loss": 0.4118565618991852
1272
+ },
1273
+ {
1274
+ "global_step": 2560,
1275
+ "optimizer_step": 320,
1276
+ "lr": 1.2753889166848909e-05,
1277
+ "lm_loss": 0.03862651810050011,
1278
+ "order_loss": 0.5859375,
1279
+ "ret_loss": 0.0,
1280
+ "pretrain_loss": 0.0,
1281
+ "total_loss": 0.0679233968257904
1282
+ },
1283
+ {
1284
+ "global_step": 2580,
1285
+ "optimizer_step": 322,
1286
+ "lr": 1.2449425954135452e-05,
1287
+ "lm_loss": 0.28010258078575134,
1288
+ "order_loss": 14.3125,
1289
+ "ret_loss": 0.0,
1290
+ "pretrain_loss": 0.0,
1291
+ "total_loss": 0.9949463605880737
1292
+ },
1293
+ {
1294
+ "global_step": 2600,
1295
+ "optimizer_step": 325,
1296
+ "lr": 1.1997378443025634e-05,
1297
+ "lm_loss": 0.11707345396280289,
1298
+ "order_loss": 3.671875,
1299
+ "ret_loss": 0.0,
1300
+ "pretrain_loss": 0.0,
1301
+ "total_loss": 0.3006671965122223
1302
+ },
1303
+ {
1304
+ "global_step": 2620,
1305
+ "optimizer_step": 327,
1306
+ "lr": 1.1699198087116589e-05,
1307
+ "lm_loss": 0.045724671334028244,
1308
+ "order_loss": 6.21875,
1309
+ "ret_loss": 0.0,
1310
+ "pretrain_loss": 0.0,
1311
+ "total_loss": 0.35627153515815735
1312
+ },
1313
+ {
1314
+ "global_step": 2640,
1315
+ "optimizer_step": 330,
1316
+ "lr": 1.1256851155542298e-05,
1317
+ "lm_loss": 0.1456630975008011,
1318
+ "order_loss": 2.125,
1319
+ "ret_loss": 0.0,
1320
+ "pretrain_loss": 0.0,
1321
+ "total_loss": 0.2521083950996399
1322
+ },
1323
+ {
1324
+ "global_step": 2660,
1325
+ "optimizer_step": 332,
1326
+ "lr": 1.0965320193809808e-05,
1327
+ "lm_loss": 0.17638051509857178,
1328
+ "order_loss": 1.8515625,
1329
+ "ret_loss": 0.0,
1330
+ "pretrain_loss": 0.0,
1331
+ "total_loss": 0.2691539525985718
1332
+ },
1333
+ {
1334
+ "global_step": 2680,
1335
+ "optimizer_step": 335,
1336
+ "lr": 1.0533217595504858e-05,
1337
+ "lm_loss": 0.19018177688121796,
1338
+ "order_loss": 0.416015625,
1339
+ "ret_loss": 0.0,
1340
+ "pretrain_loss": 0.0,
1341
+ "total_loss": 0.21093373000621796
1342
+ },
1343
+ {
1344
+ "global_step": 2700,
1345
+ "optimizer_step": 337,
1346
+ "lr": 1.0248694391571801e-05,
1347
+ "lm_loss": 0.006681549362838268,
1348
+ "order_loss": 0.431640625,
1349
+ "ret_loss": 0.0,
1350
+ "pretrain_loss": 0.0,
1351
+ "total_loss": 0.028287995606660843
1352
+ },
1353
+ {
1354
+ "global_step": 2720,
1355
+ "optimizer_step": 340,
1356
+ "lr": 9.82736728745186e-06,
1357
+ "lm_loss": 0.014033184386789799,
1358
+ "order_loss": 0.5234375,
1359
+ "ret_loss": 0.0,
1360
+ "pretrain_loss": 0.0,
1361
+ "total_loss": 0.040156230330467224
1362
+ },
1363
+ {
1364
+ "global_step": 2740,
1365
+ "optimizer_step": 342,
1366
+ "lr": 9.550201590674343e-06,
1367
+ "lm_loss": 0.039739418774843216,
1368
+ "order_loss": 0.52734375,
1369
+ "ret_loss": 0.0,
1370
+ "pretrain_loss": 0.0,
1371
+ "total_loss": 0.06610660254955292
1372
+ },
1373
+ {
1374
+ "global_step": 2760,
1375
+ "optimizer_step": 345,
1376
+ "lr": 9.140167895908867e-06,
1377
+ "lm_loss": 0.0929286926984787,
1378
+ "order_loss": 0.5234375,
1379
+ "ret_loss": 0.0,
1380
+ "pretrain_loss": 0.0,
1381
+ "total_loss": 0.1190517395734787
1382
+ },
1383
+ {
1384
+ "global_step": 2780,
1385
+ "optimizer_step": 347,
1386
+ "lr": 8.870700411447816e-06,
1387
+ "lm_loss": 0.0972345694899559,
1388
+ "order_loss": 2.578125,
1389
+ "ret_loss": 0.0,
1390
+ "pretrain_loss": 0.0,
1391
+ "total_loss": 0.2261408269405365
1392
+ },
1393
+ {
1394
+ "global_step": 2800,
1395
+ "optimizer_step": 350,
1396
+ "lr": 8.472464158814255e-06,
1397
+ "lm_loss": 0.00224293558858335,
1398
+ "order_loss": 0.4609375,
1399
+ "ret_loss": 0.0,
1400
+ "pretrain_loss": 0.0,
1401
+ "total_loss": 0.025314224883913994
1402
+ },
1403
+ {
1404
+ "global_step": 2820,
1405
+ "optimizer_step": 352,
1406
+ "lr": 8.211026128824539e-06,
1407
+ "lm_loss": 0.09758147597312927,
1408
+ "order_loss": 0.46875,
1409
+ "ret_loss": 0.0,
1410
+ "pretrain_loss": 0.0,
1411
+ "total_loss": 0.12101897597312927
1412
+ },
1413
+ {
1414
+ "global_step": 2840,
1415
+ "optimizer_step": 355,
1416
+ "lr": 7.825076849127458e-06,
1417
+ "lm_loss": 0.031101040542125702,
1418
+ "order_loss": 0.474609375,
1419
+ "ret_loss": 0.0,
1420
+ "pretrain_loss": 0.0,
1421
+ "total_loss": 0.0547826811671257
1422
+ },
1423
+ {
1424
+ "global_step": 2860,
1425
+ "optimizer_step": 357,
1426
+ "lr": 7.571989645579419e-06,
1427
+ "lm_loss": 0.0881921648979187,
1428
+ "order_loss": 4.8125,
1429
+ "ret_loss": 0.0,
1430
+ "pretrain_loss": 0.0,
1431
+ "total_loss": 0.3284265398979187
1432
+ },
1433
+ {
1434
+ "global_step": 2880,
1435
+ "optimizer_step": 360,
1436
+ "lr": 7.198801765896115e-06,
1437
+ "lm_loss": 0.008126466535031796,
1438
+ "order_loss": 0.53125,
1439
+ "ret_loss": 0.0,
1440
+ "pretrain_loss": 0.0,
1441
+ "total_loss": 0.03473779559135437
1442
+ },
1443
+ {
1444
+ "global_step": 2900,
1445
+ "optimizer_step": 362,
1446
+ "lr": 6.9543764955299265e-06,
1447
+ "lm_loss": 0.0039254748262465,
1448
+ "order_loss": 2.75,
1449
+ "ret_loss": 0.0,
1450
+ "pretrain_loss": 0.0,
1451
+ "total_loss": 0.14162078499794006
1452
+ },
1453
+ {
1454
+ "global_step": 2920,
1455
+ "optimizer_step": 365,
1456
+ "lr": 6.594408756022272e-06,
1457
+ "lm_loss": 0.00735560804605484,
1458
+ "order_loss": 2.515625,
1459
+ "ret_loss": 0.0,
1460
+ "pretrain_loss": 0.0,
1461
+ "total_loss": 0.13333216309547424
1462
+ },
1463
+ {
1464
+ "global_step": 2940,
1465
+ "optimizer_step": 367,
1466
+ "lr": 6.358945877920861e-06,
1467
+ "lm_loss": 0.058915361762046814,
1468
+ "order_loss": 0.4609375,
1469
+ "ret_loss": 0.0,
1470
+ "pretrain_loss": 0.0,
1471
+ "total_loss": 0.08198665082454681
1472
+ },
1473
+ {
1474
+ "global_step": 2960,
1475
+ "optimizer_step": 370,
1476
+ "lr": 6.012640767930217e-06,
1477
+ "lm_loss": 0.17073313891887665,
1478
+ "order_loss": 6.90625,
1479
+ "ret_loss": 0.0,
1480
+ "pretrain_loss": 0.0,
1481
+ "total_loss": 0.5164362788200378
1482
+ },
1483
+ {
1484
+ "global_step": 2980,
1485
+ "optimizer_step": 372,
1486
+ "lr": 5.7864297241808e-06,
1487
+ "lm_loss": 0.03120318613946438,
1488
+ "order_loss": 2.0625,
1489
+ "ret_loss": 0.0,
1490
+ "pretrain_loss": 0.0,
1491
+ "total_loss": 0.13423052430152893
1492
+ },
1493
+ {
1494
+ "global_step": 3000,
1495
+ "optimizer_step": 375,
1496
+ "lr": 5.454212938299255e-06,
1497
+ "lm_loss": 0.06277970969676971,
1498
+ "order_loss": 0.52734375,
1499
+ "ret_loss": 0.0,
1500
+ "pretrain_loss": 0.0,
1501
+ "total_loss": 0.08914689719676971
1502
+ },
1503
+ {
1504
+ "global_step": 3020,
1505
+ "optimizer_step": 377,
1506
+ "lr": 5.237531798197415e-06,
1507
+ "lm_loss": 0.0592321939766407,
1508
+ "order_loss": 2.421875,
1509
+ "ret_loss": 0.0,
1510
+ "pretrain_loss": 0.0,
1511
+ "total_loss": 0.1803259402513504
1512
+ },
1513
+ {
1514
+ "global_step": 3040,
1515
+ "optimizer_step": 380,
1516
+ "lr": 4.91981171298388e-06,
1517
+ "lm_loss": 0.023755524307489395,
1518
+ "order_loss": 2.125,
1519
+ "ret_loss": 0.0,
1520
+ "pretrain_loss": 0.0,
1521
+ "total_loss": 0.1302008330821991
1522
+ },
1523
+ {
1524
+ "global_step": 3060,
1525
+ "optimizer_step": 382,
1526
+ "lr": 4.712926831217685e-06,
1527
+ "lm_loss": 0.02616839110851288,
1528
+ "order_loss": 2.265625,
1529
+ "ret_loss": 0.0,
1530
+ "pretrain_loss": 0.0,
1531
+ "total_loss": 0.13944964110851288
1532
+ },
1533
+ {
1534
+ "global_step": 3080,
1535
+ "optimizer_step": 385,
1536
+ "lr": 4.410094003202134e-06,
1537
+ "lm_loss": 0.01533004641532898,
1538
+ "order_loss": 2.84375,
1539
+ "ret_loss": 0.0,
1540
+ "pretrain_loss": 0.0,
1541
+ "total_loss": 0.15790817141532898
1542
+ },
1543
+ {
1544
+ "global_step": 3100,
1545
+ "optimizer_step": 387,
1546
+ "lr": 4.213259692436367e-06,
1547
+ "lm_loss": 0.053499478846788406,
1548
+ "order_loss": 0.59765625,
1549
+ "ret_loss": 0.0,
1550
+ "pretrain_loss": 0.0,
1551
+ "total_loss": 0.08340670168399811
1552
+ },
1553
+ {
1554
+ "global_step": 3120,
1555
+ "optimizer_step": 390,
1556
+ "lr": 3.925686378029331e-06,
1557
+ "lm_loss": 0.0032864660024642944,
1558
+ "order_loss": 2.765625,
1559
+ "ret_loss": 0.0,
1560
+ "pretrain_loss": 0.0,
1561
+ "total_loss": 0.1419583410024643
1562
+ },
1563
+ {
1564
+ "global_step": 3140,
1565
+ "optimizer_step": 392,
1566
+ "lr": 3.739144596292382e-06,
1567
+ "lm_loss": 0.07452746480703354,
1568
+ "order_loss": 3.140625,
1569
+ "ret_loss": 0.0,
1570
+ "pretrain_loss": 0.0,
1571
+ "total_loss": 0.23175403475761414
1572
+ },
1573
+ {
1574
+ "global_step": 3160,
1575
+ "optimizer_step": 395,
1576
+ "lr": 3.4671842941897765e-06,
1577
+ "lm_loss": 0.05849137529730797,
1578
+ "order_loss": 4.84375,
1579
+ "ret_loss": 0.0,
1580
+ "pretrain_loss": 0.0,
1581
+ "total_loss": 0.30067887902259827
1582
+ },
1583
+ {
1584
+ "global_step": 3180,
1585
+ "optimizer_step": 397,
1586
+ "lr": 3.2911643474473646e-06,
1587
+ "lm_loss": 0.05900042876601219,
1588
+ "order_loss": 5.1875,
1589
+ "ret_loss": 0.0,
1590
+ "pretrain_loss": 0.0,
1591
+ "total_loss": 0.3187660574913025
1592
+ },
1593
+ {
1594
+ "global_step": 3200,
1595
+ "optimizer_step": 400,
1596
+ "lr": 3.035151364093214e-06,
1597
+ "lm_loss": 0.07281351089477539,
1598
+ "order_loss": 4.5625,
1599
+ "ret_loss": 0.0,
1600
+ "pretrain_loss": 0.0,
1601
+ "total_loss": 0.3013291358947754
1602
+ },
1603
+ {
1604
+ "global_step": 3220,
1605
+ "optimizer_step": 402,
1606
+ "lr": 2.869869624374699e-06,
1607
+ "lm_loss": 0.017012128606438637,
1608
+ "order_loss": 0.53125,
1609
+ "ret_loss": 0.0,
1610
+ "pretrain_loss": 0.0,
1611
+ "total_loss": 0.04362345486879349
1612
+ },
1613
+ {
1614
+ "global_step": 3240,
1615
+ "optimizer_step": 405,
1616
+ "lr": 2.6301186630158485e-06,
1617
+ "lm_loss": 0.04030493646860123,
1618
+ "order_loss": 0.6328125,
1619
+ "ret_loss": 0.0,
1620
+ "pretrain_loss": 0.0,
1621
+ "total_loss": 0.07204321771860123
1622
+ },
1623
+ {
1624
+ "global_step": 3260,
1625
+ "optimizer_step": 407,
1626
+ "lr": 2.475778302439524e-06,
1627
+ "lm_loss": 0.04458524286746979,
1628
+ "order_loss": 5.78125,
1629
+ "ret_loss": 0.0,
1630
+ "pretrain_loss": 0.0,
1631
+ "total_loss": 0.3336477279663086
1632
+ },
1633
+ {
1634
+ "global_step": 3280,
1635
+ "optimizer_step": 410,
1636
+ "lr": 2.2525840762775863e-06,
1637
+ "lm_loss": 0.09504130482673645,
1638
+ "order_loss": 0.56640625,
1639
+ "ret_loss": 0.0,
1640
+ "pretrain_loss": 0.0,
1641
+ "total_loss": 0.12336161732673645
1642
+ },
1643
+ {
1644
+ "global_step": 3300,
1645
+ "optimizer_step": 412,
1646
+ "lr": 2.1093748173018848e-06,
1647
+ "lm_loss": 0.008588898926973343,
1648
+ "order_loss": 2.34375,
1649
+ "ret_loss": 0.0,
1650
+ "pretrain_loss": 0.0,
1651
+ "total_loss": 0.12577639520168304
1652
+ },
1653
+ {
1654
+ "global_step": 3320,
1655
+ "optimizer_step": 415,
1656
+ "lr": 1.9030116872178316e-06,
1657
+ "lm_loss": 0.012238308787345886,
1658
+ "order_loss": 0.5234375,
1659
+ "ret_loss": 0.0,
1660
+ "pretrain_loss": 0.0,
1661
+ "total_loss": 0.038361355662345886
1662
+ },
1663
+ {
1664
+ "global_step": 3340,
1665
+ "optimizer_step": 417,
1666
+ "lr": 1.771109569425547e-06,
1667
+ "lm_loss": 0.06462448090314865,
1668
+ "order_loss": 2.4375,
1669
+ "ret_loss": 0.0,
1670
+ "pretrain_loss": 0.0,
1671
+ "total_loss": 0.18669480085372925
1672
+ },
1673
+ {
1674
+ "global_step": 3360,
1675
+ "optimizer_step": 420,
1676
+ "lr": 1.5818312067223672e-06,
1677
+ "lm_loss": 0.006452600006014109,
1678
+ "order_loss": 1.3984375,
1679
+ "ret_loss": 0.0,
1680
+ "pretrain_loss": 0.0,
1681
+ "total_loss": 0.07627681642770767
1682
+ },
1683
+ {
1684
+ "global_step": 3380,
1685
+ "optimizer_step": 422,
1686
+ "lr": 1.4613983704244826e-06,
1687
+ "lm_loss": 0.13416074216365814,
1688
+ "order_loss": 6.0,
1689
+ "ret_loss": 0.0,
1690
+ "pretrain_loss": 0.0,
1691
+ "total_loss": 0.43494200706481934
1692
+ },
1693
+ {
1694
+ "global_step": 3400,
1695
+ "optimizer_step": 425,
1696
+ "lr": 1.2894374450024338e-06,
1697
+ "lm_loss": 0.03461385890841484,
1698
+ "order_loss": 2.203125,
1699
+ "ret_loss": 0.0,
1700
+ "pretrain_loss": 0.0,
1701
+ "total_loss": 0.14496542513370514
1702
+ },
1703
+ {
1704
+ "global_step": 3420,
1705
+ "optimizer_step": 427,
1706
+ "lr": 1.180621931927592e-06,
1707
+ "lm_loss": 0.06270206719636917,
1708
+ "order_loss": 7.75,
1709
+ "ret_loss": 0.0,
1710
+ "pretrain_loss": 0.0,
1711
+ "total_loss": 0.4494208097457886
1712
+ },
1713
+ {
1714
+ "global_step": 3440,
1715
+ "optimizer_step": 430,
1716
+ "lr": 1.0261898262753812e-06,
1717
+ "lm_loss": 0.007161465007811785,
1718
+ "order_loss": 0.59765625,
1719
+ "ret_loss": 0.0,
1720
+ "pretrain_loss": 0.0,
1721
+ "total_loss": 0.0370686911046505
1722
+ },
1723
+ {
1724
+ "global_step": 3460,
1725
+ "optimizer_step": 432,
1726
+ "lr": 9.291253975900139e-07,
1727
+ "lm_loss": 0.029543619602918625,
1728
+ "order_loss": 9.8125,
1729
+ "ret_loss": 0.0,
1730
+ "pretrain_loss": 0.0,
1731
+ "total_loss": 0.5197780132293701
1732
+ },
1733
+ {
1734
+ "global_step": 3480,
1735
+ "optimizer_step": 435,
1736
+ "lr": 7.924119469434665e-07,
1737
+ "lm_loss": 0.04859507083892822,
1738
+ "order_loss": 5.6875,
1739
+ "ret_loss": 0.0,
1740
+ "pretrain_loss": 0.0,
1741
+ "total_loss": 0.3337513208389282
1742
+ },
1743
+ {
1744
+ "global_step": 3500,
1745
+ "optimizer_step": 437,
1746
+ "lr": 7.072179188262251e-07,
1747
+ "lm_loss": 0.0017518227687105536,
1748
+ "order_loss": 1.140625,
1749
+ "ret_loss": 0.0,
1750
+ "pretrain_loss": 0.0,
1751
+ "total_loss": 0.058880727738142014
1752
+ },
1753
+ {
1754
+ "global_step": 3520,
1755
+ "optimizer_step": 440,
1756
+ "lr": 5.883911778138324e-07,
1757
+ "lm_loss": 0.00409297738224268,
1758
+ "order_loss": 5.96875,
1759
+ "ret_loss": 0.0,
1760
+ "pretrain_loss": 0.0,
1761
+ "total_loss": 0.3029211163520813
1762
+ },
1763
+ {
1764
+ "global_step": 3540,
1765
+ "optimizer_step": 442,
1766
+ "lr": 5.151722747865434e-07,
1767
+ "lm_loss": 0.021804748103022575,
1768
+ "order_loss": 1.0234375,
1769
+ "ret_loss": 0.0,
1770
+ "pretrain_loss": 0.0,
1771
+ "total_loss": 0.07307428121566772
1772
+ },
1773
+ {
1774
+ "global_step": 3560,
1775
+ "optimizer_step": 445,
1776
+ "lr": 4.1437831084878974e-07,
1777
+ "lm_loss": 0.001908239908516407,
1778
+ "order_loss": 1.3203125,
1779
+ "ret_loss": 0.0,
1780
+ "pretrain_loss": 0.0,
1781
+ "total_loss": 0.06782621145248413
1782
+ },
1783
+ {
1784
+ "global_step": 3580,
1785
+ "optimizer_step": 447,
1786
+ "lr": 3.5322453704410286e-07,
1787
+ "lm_loss": 0.4379558861255646,
1788
+ "order_loss": 0.458984375,
1789
+ "ret_loss": 0.0,
1790
+ "pretrain_loss": 0.0,
1791
+ "total_loss": 0.4609051048755646
1792
+ },
1793
+ {
1794
+ "global_step": 3600,
1795
+ "optimizer_step": 450,
1796
+ "lr": 2.705872508804747e-07,
1797
+ "lm_loss": 0.09111914038658142,
1798
+ "order_loss": 2.3125,
1799
+ "ret_loss": 0.0,
1800
+ "pretrain_loss": 0.0,
1801
+ "total_loss": 0.20684179663658142
1802
+ },
1803
+ {
1804
+ "global_step": 3620,
1805
+ "optimizer_step": 452,
1806
+ "lr": 2.215737794045436e-07,
1807
+ "lm_loss": 0.15181221067905426,
1808
+ "order_loss": 0.65234375,
1809
+ "ret_loss": 0.0,
1810
+ "pretrain_loss": 0.0,
1811
+ "total_loss": 0.18452705442905426
1812
+ },
1813
+ {
1814
+ "global_step": 3640,
1815
+ "optimizer_step": 455,
1816
+ "lr": 1.571947526689349e-07,
1817
+ "lm_loss": 0.964504599571228,
1818
+ "order_loss": 0.55859375,
1819
+ "ret_loss": 0.0,
1820
+ "pretrain_loss": 0.0,
1821
+ "total_loss": 0.992458701133728
1822
+ },
1823
+ {
1824
+ "global_step": 3660,
1825
+ "optimizer_step": 457,
1826
+ "lr": 1.2038183319507955e-07,
1827
+ "lm_loss": 0.06842590868473053,
1828
+ "order_loss": 2.296875,
1829
+ "ret_loss": 0.0,
1830
+ "pretrain_loss": 0.0,
1831
+ "total_loss": 0.18317200243473053
1832
+ },
1833
+ {
1834
+ "global_step": 3680,
1835
+ "optimizer_step": 460,
1836
+ "lr": 7.434020362682704e-08,
1837
+ "lm_loss": 0.015211226418614388,
1838
+ "order_loss": 2.5,
1839
+ "ret_loss": 0.0,
1840
+ "pretrain_loss": 0.0,
1841
+ "total_loss": 0.14021122455596924
1842
+ },
1843
+ {
1844
+ "global_step": 3700,
1845
+ "optimizer_step": 462,
1846
+ "lr": 4.977308833379324e-08,
1847
+ "lm_loss": 0.010147752240300179,
1848
+ "order_loss": 0.89453125,
1849
+ "ret_loss": 0.0,
1850
+ "pretrain_loss": 0.0,
1851
+ "total_loss": 0.05482548475265503
1852
+ },
1853
+ {
1854
+ "global_step": 3720,
1855
+ "optimizer_step": 465,
1856
+ "lr": 2.2125452477828047e-08,
1857
+ "lm_loss": 0.007325617130845785,
1858
+ "order_loss": 6.8125,
1859
+ "ret_loss": 0.0,
1860
+ "pretrain_loss": 0.0,
1861
+ "total_loss": 0.3471693694591522
1862
+ },
1863
+ {
1864
+ "global_step": 3740,
1865
+ "optimizer_step": 467,
1866
+ "lr": 9.834340423678368e-09,
1867
+ "lm_loss": 0.22107183933258057,
1868
+ "order_loss": 5.875,
1869
+ "ret_loss": 0.0,
1870
+ "pretrain_loss": 0.0,
1871
+ "total_loss": 0.5140405893325806
1872
+ }
1873
+ ]
1874
+ }
cls_qwen_orderkd_mid_l02/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_qwen_orderkd_mid_l02/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
cls_smollm2_orderkd_first_l005/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM2-1.7B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_smollm2_orderkd_first_l005/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "down_proj",
39
+ "o_proj",
40
+ "up_proj",
41
+ "k_proj",
42
+ "q_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_smollm2_orderkd_first_l005/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
cls_smollm2_orderkd_first_l005/checkpoint-200/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM2-1.7B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_smollm2_orderkd_first_l005/checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "down_proj",
39
+ "o_proj",
40
+ "up_proj",
41
+ "k_proj",
42
+ "q_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_smollm2_orderkd_first_l005/checkpoint-200/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
cls_smollm2_orderkd_first_l005/checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cls_smollm2_orderkd_first_l005/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [],
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "model_max_length": 8192,
12
+ "pad_token": "<|endoftext|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "GPT2Tokenizer",
15
+ "unk_token": "<|endoftext|>",
16
+ "vocab_size": 49152,
17
+ "added_tokens_decoder": {
18
+ "0": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": false,
24
+ "special": true
25
+ },
26
+ "1": {
27
+ "content": "<|im_start|>",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false,
32
+ "special": true
33
+ },
34
+ "2": {
35
+ "content": "<|im_end|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "3": {
43
+ "content": "<repo_name>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "4": {
51
+ "content": "<reponame>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "5": {
59
+ "content": "<file_sep>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "6": {
67
+ "content": "<filename>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "7": {
75
+ "content": "<gh_stars>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "8": {
83
+ "content": "<issue_start>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "9": {
91
+ "content": "<issue_comment>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "10": {
99
+ "content": "<issue_closed>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "11": {
107
+ "content": "<jupyter_start>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "12": {
115
+ "content": "<jupyter_text>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "13": {
123
+ "content": "<jupyter_code>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "14": {
131
+ "content": "<jupyter_output>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "15": {
139
+ "content": "<jupyter_script>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "16": {
147
+ "content": "<empty_output>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": true
153
+ }
154
+ }
155
+ }
cls_smollm2_orderkd_first_l005/checkpoint-400/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM2-1.7B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1
cls_smollm2_orderkd_first_l005/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "down_proj",
39
+ "o_proj",
40
+ "up_proj",
41
+ "k_proj",
42
+ "q_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_smollm2_orderkd_first_l005/checkpoint-400/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
cls_smollm2_orderkd_first_l005/checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cls_smollm2_orderkd_first_l005/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [],
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "model_max_length": 8192,
12
+ "pad_token": "<|endoftext|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "GPT2Tokenizer",
15
+ "unk_token": "<|endoftext|>",
16
+ "vocab_size": 49152,
17
+ "added_tokens_decoder": {
18
+ "0": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": false,
24
+ "special": true
25
+ },
26
+ "1": {
27
+ "content": "<|im_start|>",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false,
32
+ "special": true
33
+ },
34
+ "2": {
35
+ "content": "<|im_end|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "3": {
43
+ "content": "<repo_name>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "4": {
51
+ "content": "<reponame>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "5": {
59
+ "content": "<file_sep>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "6": {
67
+ "content": "<filename>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "7": {
75
+ "content": "<gh_stars>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "8": {
83
+ "content": "<issue_start>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "9": {
91
+ "content": "<issue_comment>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "10": {
99
+ "content": "<issue_closed>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "11": {
107
+ "content": "<jupyter_start>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "12": {
115
+ "content": "<jupyter_text>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "13": {
123
+ "content": "<jupyter_code>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "14": {
131
+ "content": "<jupyter_output>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "15": {
139
+ "content": "<jupyter_script>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "16": {
147
+ "content": "<empty_output>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": true
153
+ }
154
+ }
155
+ }
cls_smollm2_orderkd_first_l005/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cls_smollm2_orderkd_first_l005/tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [],
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "model_max_length": 8192,
12
+ "pad_token": "<|endoftext|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "GPT2Tokenizer",
15
+ "unk_token": "<|endoftext|>",
16
+ "vocab_size": 49152,
17
+ "added_tokens_decoder": {
18
+ "0": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": false,
24
+ "special": true
25
+ },
26
+ "1": {
27
+ "content": "<|im_start|>",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false,
32
+ "special": true
33
+ },
34
+ "2": {
35
+ "content": "<|im_end|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "3": {
43
+ "content": "<repo_name>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "4": {
51
+ "content": "<reponame>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "5": {
59
+ "content": "<file_sep>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "6": {
67
+ "content": "<filename>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "7": {
75
+ "content": "<gh_stars>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "8": {
83
+ "content": "<issue_start>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "9": {
91
+ "content": "<issue_comment>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "10": {
99
+ "content": "<issue_closed>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "11": {
107
+ "content": "<jupyter_start>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "12": {
115
+ "content": "<jupyter_text>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "13": {
123
+ "content": "<jupyter_code>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "14": {
131
+ "content": "<jupyter_output>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "15": {
139
+ "content": "<jupyter_script>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "16": {
147
+ "content": "<empty_output>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": true
153
+ }
154
+ }
155
+ }
cls_smollm2_orderkd_first_l005/train_metrics.json ADDED
@@ -0,0 +1,1874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "loss_log": [
3
+ {
4
+ "global_step": 20,
5
+ "optimizer_step": 2,
6
+ "lr": 4.347826086956522e-06,
7
+ "lm_loss": 1.1238845586776733,
8
+ "order_loss": 1.1484375,
9
+ "ret_loss": 0.0,
10
+ "pretrain_loss": 0.0,
11
+ "total_loss": 1.1812576055526733
12
+ },
13
+ {
14
+ "global_step": 40,
15
+ "optimizer_step": 5,
16
+ "lr": 1.0869565217391305e-05,
17
+ "lm_loss": 2.0878260135650635,
18
+ "order_loss": 0.8828125,
19
+ "ret_loss": 0.0,
20
+ "pretrain_loss": 0.0,
21
+ "total_loss": 2.1320154666900635
22
+ },
23
+ {
24
+ "global_step": 60,
25
+ "optimizer_step": 7,
26
+ "lr": 1.5217391304347828e-05,
27
+ "lm_loss": 1.2100099325180054,
28
+ "order_loss": 0.83203125,
29
+ "ret_loss": 0.0,
30
+ "pretrain_loss": 0.0,
31
+ "total_loss": 1.2515138387680054
32
+ },
33
+ {
34
+ "global_step": 80,
35
+ "optimizer_step": 10,
36
+ "lr": 2.173913043478261e-05,
37
+ "lm_loss": 1.4670660495758057,
38
+ "order_loss": 1.0234375,
39
+ "ret_loss": 0.0,
40
+ "pretrain_loss": 0.0,
41
+ "total_loss": 1.5183355808258057
42
+ },
43
+ {
44
+ "global_step": 100,
45
+ "optimizer_step": 12,
46
+ "lr": 2.608695652173913e-05,
47
+ "lm_loss": 1.3719264268875122,
48
+ "order_loss": 0.7578125,
49
+ "ret_loss": 0.0,
50
+ "pretrain_loss": 0.0,
51
+ "total_loss": 1.4097682237625122
52
+ },
53
+ {
54
+ "global_step": 120,
55
+ "optimizer_step": 15,
56
+ "lr": 3.260869565217392e-05,
57
+ "lm_loss": 4.287930011749268,
58
+ "order_loss": 0.76171875,
59
+ "ret_loss": 0.0,
60
+ "pretrain_loss": 0.0,
61
+ "total_loss": 4.326015949249268
62
+ },
63
+ {
64
+ "global_step": 140,
65
+ "optimizer_step": 17,
66
+ "lr": 3.695652173913043e-05,
67
+ "lm_loss": 0.41322723031044006,
68
+ "order_loss": 0.74609375,
69
+ "ret_loss": 0.0,
70
+ "pretrain_loss": 0.0,
71
+ "total_loss": 0.45058074593544006
72
+ },
73
+ {
74
+ "global_step": 160,
75
+ "optimizer_step": 20,
76
+ "lr": 4.347826086956522e-05,
77
+ "lm_loss": 0.5901991724967957,
78
+ "order_loss": 0.7578125,
79
+ "ret_loss": 0.0,
80
+ "pretrain_loss": 0.0,
81
+ "total_loss": 0.6280409693717957
82
+ },
83
+ {
84
+ "global_step": 180,
85
+ "optimizer_step": 22,
86
+ "lr": 4.782608695652174e-05,
87
+ "lm_loss": 0.41182488203048706,
88
+ "order_loss": 0.64453125,
89
+ "ret_loss": 0.0,
90
+ "pretrain_loss": 0.0,
91
+ "total_loss": 0.44405144453048706
92
+ },
93
+ {
94
+ "global_step": 200,
95
+ "optimizer_step": 25,
96
+ "lr": 4.9997541293989384e-05,
97
+ "lm_loss": 0.11135535687208176,
98
+ "order_loss": 2.59375,
99
+ "ret_loss": 0.0,
100
+ "pretrain_loss": 0.0,
101
+ "total_loss": 0.24123817682266235
102
+ },
103
+ {
104
+ "global_step": 220,
105
+ "optimizer_step": 27,
106
+ "lr": 4.999016565957633e-05,
107
+ "lm_loss": 0.14654971659183502,
108
+ "order_loss": 3.71875,
109
+ "ret_loss": 0.0,
110
+ "pretrain_loss": 0.0,
111
+ "total_loss": 0.33209657669067383
112
+ },
113
+ {
114
+ "global_step": 240,
115
+ "optimizer_step": 30,
116
+ "lr": 4.996988640512931e-05,
117
+ "lm_loss": 0.09418602287769318,
118
+ "order_loss": 0.71875,
119
+ "ret_loss": 0.0,
120
+ "pretrain_loss": 0.0,
121
+ "total_loss": 0.13007469475269318
122
+ },
123
+ {
124
+ "global_step": 260,
125
+ "optimizer_step": 32,
126
+ "lr": 4.995022691166621e-05,
127
+ "lm_loss": 0.33666303753852844,
128
+ "order_loss": 0.6328125,
129
+ "ret_loss": 0.0,
130
+ "pretrain_loss": 0.0,
131
+ "total_loss": 0.36840131878852844
132
+ },
133
+ {
134
+ "global_step": 280,
135
+ "optimizer_step": 35,
136
+ "lr": 4.991153735294049e-05,
137
+ "lm_loss": 0.21148145198822021,
138
+ "order_loss": 0.6328125,
139
+ "ret_loss": 0.0,
140
+ "pretrain_loss": 0.0,
141
+ "total_loss": 0.24321973323822021
142
+ },
143
+ {
144
+ "global_step": 300,
145
+ "optimizer_step": 37,
146
+ "lr": 4.987961816680492e-05,
147
+ "lm_loss": 2.526341438293457,
148
+ "order_loss": 0.6640625,
149
+ "ret_loss": 0.0,
150
+ "pretrain_loss": 0.0,
151
+ "total_loss": 2.559544563293457
152
+ },
153
+ {
154
+ "global_step": 320,
155
+ "optimizer_step": 40,
156
+ "lr": 4.9822565862832806e-05,
157
+ "lm_loss": 3.497163772583008,
158
+ "order_loss": 0.6640625,
159
+ "ret_loss": 0.0,
160
+ "pretrain_loss": 0.0,
161
+ "total_loss": 3.530366897583008
162
+ },
163
+ {
164
+ "global_step": 340,
165
+ "optimizer_step": 42,
166
+ "lr": 4.9778426220595456e-05,
167
+ "lm_loss": 0.20562048256397247,
168
+ "order_loss": 0.734375,
169
+ "ret_loss": 0.0,
170
+ "pretrain_loss": 0.0,
171
+ "total_loss": 0.24224157631397247
172
+ },
173
+ {
174
+ "global_step": 360,
175
+ "optimizer_step": 45,
176
+ "lr": 4.970308130276272e-05,
177
+ "lm_loss": 0.1583261787891388,
178
+ "order_loss": 0.625,
179
+ "ret_loss": 0.0,
180
+ "pretrain_loss": 0.0,
181
+ "total_loss": 0.1895761787891388
182
+ },
183
+ {
184
+ "global_step": 380,
185
+ "optimizer_step": 47,
186
+ "lr": 4.96467754629559e-05,
187
+ "lm_loss": 0.35205933451652527,
188
+ "order_loss": 0.61328125,
189
+ "ret_loss": 0.0,
190
+ "pretrain_loss": 0.0,
191
+ "total_loss": 0.38269898295402527
192
+ },
193
+ {
194
+ "global_step": 400,
195
+ "optimizer_step": 50,
196
+ "lr": 4.955323054879298e-05,
197
+ "lm_loss": 0.12030346691608429,
198
+ "order_loss": 0.67578125,
199
+ "ret_loss": 0.0,
200
+ "pretrain_loss": 0.0,
201
+ "total_loss": 0.1539948731660843
202
+ },
203
+ {
204
+ "global_step": 420,
205
+ "optimizer_step": 52,
206
+ "lr": 4.948482772521345e-05,
207
+ "lm_loss": 0.41500502824783325,
208
+ "order_loss": 0.640625,
209
+ "ret_loss": 0.0,
210
+ "pretrain_loss": 0.0,
211
+ "total_loss": 0.44698745012283325
212
+ },
213
+ {
214
+ "global_step": 440,
215
+ "optimizer_step": 55,
216
+ "lr": 4.937319780454559e-05,
217
+ "lm_loss": 0.3214091956615448,
218
+ "order_loss": 0.5234375,
219
+ "ret_loss": 0.0,
220
+ "pretrain_loss": 0.0,
221
+ "total_loss": 0.3475322425365448
222
+ },
223
+ {
224
+ "global_step": 460,
225
+ "optimizer_step": 57,
226
+ "lr": 4.929278208117378e-05,
227
+ "lm_loss": 0.5990498661994934,
228
+ "order_loss": 0.66015625,
229
+ "ret_loss": 0.0,
230
+ "pretrain_loss": 0.0,
231
+ "total_loss": 0.6320088505744934
232
+ },
233
+ {
234
+ "global_step": 480,
235
+ "optimizer_step": 60,
236
+ "lr": 4.916320437477008e-05,
237
+ "lm_loss": 0.322706401348114,
238
+ "order_loss": 0.6875,
239
+ "ret_loss": 0.0,
240
+ "pretrain_loss": 0.0,
241
+ "total_loss": 0.357130229473114
242
+ },
243
+ {
244
+ "global_step": 500,
245
+ "optimizer_step": 62,
246
+ "lr": 4.907087460240999e-05,
247
+ "lm_loss": 0.06359988451004028,
248
+ "order_loss": 0.65234375,
249
+ "ret_loss": 0.0,
250
+ "pretrain_loss": 0.0,
251
+ "total_loss": 0.09631472826004028
252
+ },
253
+ {
254
+ "global_step": 520,
255
+ "optimizer_step": 65,
256
+ "lr": 4.892350839330522e-05,
257
+ "lm_loss": 0.12247280776500702,
258
+ "order_loss": 0.703125,
259
+ "ret_loss": 0.0,
260
+ "pretrain_loss": 0.0,
261
+ "total_loss": 0.15762905776500702
262
+ },
263
+ {
264
+ "global_step": 540,
265
+ "optimizer_step": 67,
266
+ "lr": 4.881937806807241e-05,
267
+ "lm_loss": 0.2216511368751526,
268
+ "order_loss": 0.6640625,
269
+ "ret_loss": 0.0,
270
+ "pretrain_loss": 0.0,
271
+ "total_loss": 0.2548542618751526
272
+ },
273
+ {
274
+ "global_step": 560,
275
+ "optimizer_step": 70,
276
+ "lr": 4.865440450576874e-05,
277
+ "lm_loss": 0.1668950915336609,
278
+ "order_loss": 0.640625,
279
+ "ret_loss": 0.0,
280
+ "pretrain_loss": 0.0,
281
+ "total_loss": 0.1988775134086609
282
+ },
283
+ {
284
+ "global_step": 580,
285
+ "optimizer_step": 72,
286
+ "lr": 4.853860162957552e-05,
287
+ "lm_loss": 0.037012215703725815,
288
+ "order_loss": 0.62109375,
289
+ "ret_loss": 0.0,
290
+ "pretrain_loss": 0.0,
291
+ "total_loss": 0.06801807880401611
292
+ },
293
+ {
294
+ "global_step": 600,
295
+ "optimizer_step": 75,
296
+ "lr": 4.8356223507364996e-05,
297
+ "lm_loss": 0.17125961184501648,
298
+ "order_loss": 2.640625,
299
+ "ret_loss": 0.0,
300
+ "pretrain_loss": 0.0,
301
+ "total_loss": 0.3030955493450165
302
+ },
303
+ {
304
+ "global_step": 620,
305
+ "optimizer_step": 77,
306
+ "lr": 4.822889043057446e-05,
307
+ "lm_loss": 0.1305747777223587,
308
+ "order_loss": 0.6171875,
309
+ "ret_loss": 0.0,
310
+ "pretrain_loss": 0.0,
311
+ "total_loss": 0.1614585667848587
312
+ },
313
+ {
314
+ "global_step": 640,
315
+ "optimizer_step": 80,
316
+ "lr": 4.802933193625593e-05,
317
+ "lm_loss": 0.30356189608573914,
318
+ "order_loss": 0.671875,
319
+ "ret_loss": 0.0,
320
+ "pretrain_loss": 0.0,
321
+ "total_loss": 0.33725330233573914
322
+ },
323
+ {
324
+ "global_step": 660,
325
+ "optimizer_step": 82,
326
+ "lr": 4.789062518269812e-05,
327
+ "lm_loss": 0.2583479881286621,
328
+ "order_loss": 0.62890625,
329
+ "ret_loss": 0.0,
330
+ "pretrain_loss": 0.0,
331
+ "total_loss": 0.2898421287536621
332
+ },
333
+ {
334
+ "global_step": 680,
335
+ "optimizer_step": 85,
336
+ "lr": 4.767413162299501e-05,
337
+ "lm_loss": 0.531679093837738,
338
+ "order_loss": 0.63671875,
339
+ "ret_loss": 0.0,
340
+ "pretrain_loss": 0.0,
341
+ "total_loss": 0.563417375087738
342
+ },
343
+ {
344
+ "global_step": 700,
345
+ "optimizer_step": 87,
346
+ "lr": 4.752422169756048e-05,
347
+ "lm_loss": 0.46454769372940063,
348
+ "order_loss": 0.6953125,
349
+ "ret_loss": 0.0,
350
+ "pretrain_loss": 0.0,
351
+ "total_loss": 0.49921566247940063
352
+ },
353
+ {
354
+ "global_step": 720,
355
+ "optimizer_step": 90,
356
+ "lr": 4.729105919657818e-05,
357
+ "lm_loss": 0.2914125323295593,
358
+ "order_loss": 0.66796875,
359
+ "ret_loss": 0.0,
360
+ "pretrain_loss": 0.0,
361
+ "total_loss": 0.3248597979545593
362
+ },
363
+ {
364
+ "global_step": 740,
365
+ "optimizer_step": 92,
366
+ "lr": 4.7130130375625305e-05,
367
+ "lm_loss": 0.22330984473228455,
368
+ "order_loss": 0.69921875,
369
+ "ret_loss": 0.0,
370
+ "pretrain_loss": 0.0,
371
+ "total_loss": 0.25822195410728455
372
+ },
373
+ {
374
+ "global_step": 760,
375
+ "optimizer_step": 95,
376
+ "lr": 4.6880585547718845e-05,
377
+ "lm_loss": 0.09557458013296127,
378
+ "order_loss": 0.64453125,
379
+ "ret_loss": 0.0,
380
+ "pretrain_loss": 0.0,
381
+ "total_loss": 0.12780115008354187
382
+ },
383
+ {
384
+ "global_step": 780,
385
+ "optimizer_step": 97,
386
+ "lr": 4.670883565255264e-05,
387
+ "lm_loss": 0.2578425109386444,
388
+ "order_loss": 0.56640625,
389
+ "ret_loss": 0.0,
390
+ "pretrain_loss": 0.0,
391
+ "total_loss": 0.2861628234386444
392
+ },
393
+ {
394
+ "global_step": 800,
395
+ "optimizer_step": 100,
396
+ "lr": 4.6443215250006806e-05,
397
+ "lm_loss": 0.11276813596487045,
398
+ "order_loss": 0.73046875,
399
+ "ret_loss": 0.0,
400
+ "pretrain_loss": 0.0,
401
+ "total_loss": 0.14938923716545105
402
+ },
403
+ {
404
+ "global_step": 820,
405
+ "optimizer_step": 102,
406
+ "lr": 4.626085540370762e-05,
407
+ "lm_loss": 0.25939592719078064,
408
+ "order_loss": 0.58984375,
409
+ "ret_loss": 0.0,
410
+ "pretrain_loss": 0.0,
411
+ "total_loss": 0.28893694281578064
412
+ },
413
+ {
414
+ "global_step": 840,
415
+ "optimizer_step": 105,
416
+ "lr": 4.597948593966256e-05,
417
+ "lm_loss": 0.2961285710334778,
418
+ "order_loss": 0.6875,
419
+ "ret_loss": 0.0,
420
+ "pretrain_loss": 0.0,
421
+ "total_loss": 0.3305523991584778
422
+ },
423
+ {
424
+ "global_step": 860,
425
+ "optimizer_step": 107,
426
+ "lr": 4.5786740307563636e-05,
427
+ "lm_loss": 0.11143630743026733,
428
+ "order_loss": 0.7265625,
429
+ "ret_loss": 0.0,
430
+ "pretrain_loss": 0.0,
431
+ "total_loss": 0.14781326055526733
432
+ },
433
+ {
434
+ "global_step": 880,
435
+ "optimizer_step": 110,
436
+ "lr": 4.5489967654649474e-05,
437
+ "lm_loss": 0.22201621532440186,
438
+ "order_loss": 0.5859375,
439
+ "ret_loss": 0.0,
440
+ "pretrain_loss": 0.0,
441
+ "total_loss": 0.25131309032440186
442
+ },
443
+ {
444
+ "global_step": 900,
445
+ "optimizer_step": 112,
446
+ "lr": 4.528707316878232e-05,
447
+ "lm_loss": 0.09219402074813843,
448
+ "order_loss": 0.546875,
449
+ "ret_loss": 0.0,
450
+ "pretrain_loss": 0.0,
451
+ "total_loss": 0.11953777074813843
452
+ },
453
+ {
454
+ "global_step": 920,
455
+ "optimizer_step": 115,
456
+ "lr": 4.497526213395623e-05,
457
+ "lm_loss": 0.18178370594978333,
458
+ "order_loss": 0.59375,
459
+ "ret_loss": 0.0,
460
+ "pretrain_loss": 0.0,
461
+ "total_loss": 0.21144679188728333
462
+ },
463
+ {
464
+ "global_step": 940,
465
+ "optimizer_step": 117,
466
+ "lr": 4.476246820180259e-05,
467
+ "lm_loss": 0.09260153025388718,
468
+ "order_loss": 0.63671875,
469
+ "ret_loss": 0.0,
470
+ "pretrain_loss": 0.0,
471
+ "total_loss": 0.12433981150388718
472
+ },
473
+ {
474
+ "global_step": 960,
475
+ "optimizer_step": 120,
476
+ "lr": 4.443600207791081e-05,
477
+ "lm_loss": 0.3324756622314453,
478
+ "order_loss": 0.59765625,
479
+ "ret_loss": 0.0,
480
+ "pretrain_loss": 0.0,
481
+ "total_loss": 0.3623828887939453
482
+ },
483
+ {
484
+ "global_step": 980,
485
+ "optimizer_step": 122,
486
+ "lr": 4.421357027581921e-05,
487
+ "lm_loss": 0.22086575627326965,
488
+ "order_loss": 0.55859375,
489
+ "ret_loss": 0.0,
490
+ "pretrain_loss": 0.0,
491
+ "total_loss": 0.24881985783576965
492
+ },
493
+ {
494
+ "global_step": 1000,
495
+ "optimizer_step": 125,
496
+ "lr": 4.38728503704354e-05,
497
+ "lm_loss": 0.24602726101875305,
498
+ "order_loss": 0.58203125,
499
+ "ret_loss": 0.0,
500
+ "pretrain_loss": 0.0,
501
+ "total_loss": 0.27507999539375305
502
+ },
503
+ {
504
+ "global_step": 1020,
505
+ "optimizer_step": 127,
506
+ "lr": 4.364105412207914e-05,
507
+ "lm_loss": 0.36640486121177673,
508
+ "order_loss": 0.56640625,
509
+ "ret_loss": 0.0,
510
+ "pretrain_loss": 0.0,
511
+ "total_loss": 0.39472517371177673
512
+ },
513
+ {
514
+ "global_step": 1040,
515
+ "optimizer_step": 130,
516
+ "lr": 4.328649926419819e-05,
517
+ "lm_loss": 0.4935210645198822,
518
+ "order_loss": 0.69140625,
519
+ "ret_loss": 0.0,
520
+ "pretrain_loss": 0.0,
521
+ "total_loss": 0.5281890630722046
522
+ },
523
+ {
524
+ "global_step": 1060,
525
+ "optimizer_step": 132,
526
+ "lr": 4.304562350447008e-05,
527
+ "lm_loss": 0.08732613176107407,
528
+ "order_loss": 0.5859375,
529
+ "ret_loss": 0.0,
530
+ "pretrain_loss": 0.0,
531
+ "total_loss": 0.11662300676107407
532
+ },
533
+ {
534
+ "global_step": 1080,
535
+ "optimizer_step": 135,
536
+ "lr": 4.267766952966369e-05,
537
+ "lm_loss": 0.04558392986655235,
538
+ "order_loss": 0.70703125,
539
+ "ret_loss": 0.0,
540
+ "pretrain_loss": 0.0,
541
+ "total_loss": 0.08098432421684265
542
+ },
543
+ {
544
+ "global_step": 1100,
545
+ "optimizer_step": 137,
546
+ "lr": 4.242801035442058e-05,
547
+ "lm_loss": 0.21718080341815948,
548
+ "order_loss": 0.625,
549
+ "ret_loss": 0.0,
550
+ "pretrain_loss": 0.0,
551
+ "total_loss": 0.24843080341815948
552
+ },
553
+ {
554
+ "global_step": 1120,
555
+ "optimizer_step": 140,
556
+ "lr": 4.204710956908763e-05,
557
+ "lm_loss": 0.051271308213472366,
558
+ "order_loss": 0.578125,
559
+ "ret_loss": 0.0,
560
+ "pretrain_loss": 0.0,
561
+ "total_loss": 0.08020196855068207
562
+ },
563
+ {
564
+ "global_step": 1140,
565
+ "optimizer_step": 142,
566
+ "lr": 4.178897387117546e-05,
567
+ "lm_loss": 0.1259322613477707,
568
+ "order_loss": 0.61328125,
569
+ "ret_loss": 0.0,
570
+ "pretrain_loss": 0.0,
571
+ "total_loss": 0.1565719097852707
572
+ },
573
+ {
574
+ "global_step": 1160,
575
+ "optimizer_step": 145,
576
+ "lr": 4.139559449654561e-05,
577
+ "lm_loss": 0.3629738390445709,
578
+ "order_loss": 0.6953125,
579
+ "ret_loss": 0.0,
580
+ "pretrain_loss": 0.0,
581
+ "total_loss": 0.3976418077945709
582
+ },
583
+ {
584
+ "global_step": 1180,
585
+ "optimizer_step": 147,
586
+ "lr": 4.1129299588552193e-05,
587
+ "lm_loss": 0.18533805012702942,
588
+ "order_loss": 0.69140625,
589
+ "ret_loss": 0.0,
590
+ "pretrain_loss": 0.0,
591
+ "total_loss": 0.22000601887702942
592
+ },
593
+ {
594
+ "global_step": 1200,
595
+ "optimizer_step": 150,
596
+ "lr": 4.072392518512623e-05,
597
+ "lm_loss": 0.3633327782154083,
598
+ "order_loss": 0.5546875,
599
+ "ret_loss": 0.0,
600
+ "pretrain_loss": 0.0,
601
+ "total_loss": 0.3910427391529083
602
+ },
603
+ {
604
+ "global_step": 1220,
605
+ "optimizer_step": 152,
606
+ "lr": 4.0449798409325665e-05,
607
+ "lm_loss": 0.1945648193359375,
608
+ "order_loss": 0.55078125,
609
+ "ret_loss": 0.0,
610
+ "pretrain_loss": 0.0,
611
+ "total_loss": 0.2221527099609375
612
+ },
613
+ {
614
+ "global_step": 1240,
615
+ "optimizer_step": 155,
616
+ "lr": 4.0032927282460146e-05,
617
+ "lm_loss": 0.2373809516429901,
618
+ "order_loss": 0.62890625,
619
+ "ret_loss": 0.0,
620
+ "pretrain_loss": 0.0,
621
+ "total_loss": 0.2688750922679901
622
+ },
623
+ {
624
+ "global_step": 1260,
625
+ "optimizer_step": 157,
626
+ "lr": 3.9751305608428205e-05,
627
+ "lm_loss": 0.10945524275302887,
628
+ "order_loss": 0.69921875,
629
+ "ret_loss": 0.0,
630
+ "pretrain_loss": 0.0,
631
+ "total_loss": 0.14436735212802887
632
+ },
633
+ {
634
+ "global_step": 1280,
635
+ "optimizer_step": 160,
636
+ "lr": 3.932345019579495e-05,
637
+ "lm_loss": 0.23567743599414825,
638
+ "order_loss": 0.62109375,
639
+ "ret_loss": 0.0,
640
+ "pretrain_loss": 0.0,
641
+ "total_loss": 0.26668328046798706
642
+ },
643
+ {
644
+ "global_step": 1300,
645
+ "optimizer_step": 162,
646
+ "lr": 3.90346798061902e-05,
647
+ "lm_loss": 0.13102228939533234,
648
+ "order_loss": 0.67578125,
649
+ "ret_loss": 0.0,
650
+ "pretrain_loss": 0.0,
651
+ "total_loss": 0.16471369564533234
652
+ },
653
+ {
654
+ "global_step": 1320,
655
+ "optimizer_step": 165,
656
+ "lr": 3.859636604786372e-05,
657
+ "lm_loss": 0.26776665449142456,
658
+ "order_loss": 0.44140625,
659
+ "ret_loss": 0.0,
660
+ "pretrain_loss": 0.0,
661
+ "total_loss": 0.28986138105392456
662
+ },
663
+ {
664
+ "global_step": 1340,
665
+ "optimizer_step": 167,
666
+ "lr": 3.830080191288342e-05,
667
+ "lm_loss": 0.25015050172805786,
668
+ "order_loss": 0.51953125,
669
+ "ret_loss": 0.0,
670
+ "pretrain_loss": 0.0,
671
+ "total_loss": 0.27615147829055786
672
+ },
673
+ {
674
+ "global_step": 1360,
675
+ "optimizer_step": 170,
676
+ "lr": 3.785256860483054e-05,
677
+ "lm_loss": 0.15057191252708435,
678
+ "order_loss": 0.578125,
679
+ "ret_loss": 0.0,
680
+ "pretrain_loss": 0.0,
681
+ "total_loss": 0.17950257658958435
682
+ },
683
+ {
684
+ "global_step": 1380,
685
+ "optimizer_step": 172,
686
+ "lr": 3.755057404586455e-05,
687
+ "lm_loss": 0.2330058515071869,
688
+ "order_loss": 0.6015625,
689
+ "ret_loss": 0.0,
690
+ "pretrain_loss": 0.0,
691
+ "total_loss": 0.2630351483821869
692
+ },
693
+ {
694
+ "global_step": 1400,
695
+ "optimizer_step": 175,
696
+ "lr": 3.7092972177631e-05,
697
+ "lm_loss": 1.2228989601135254,
698
+ "order_loss": 0.69921875,
699
+ "ret_loss": 0.0,
700
+ "pretrain_loss": 0.0,
701
+ "total_loss": 1.2578110694885254
702
+ },
703
+ {
704
+ "global_step": 1420,
705
+ "optimizer_step": 177,
706
+ "lr": 3.678491842064995e-05,
707
+ "lm_loss": 0.17887549102306366,
708
+ "order_loss": 0.5390625,
709
+ "ret_loss": 0.0,
710
+ "pretrain_loss": 0.0,
711
+ "total_loss": 0.20585303008556366
712
+ },
713
+ {
714
+ "global_step": 1440,
715
+ "optimizer_step": 180,
716
+ "lr": 3.631851049805793e-05,
717
+ "lm_loss": 0.044103410094976425,
718
+ "order_loss": 0.69140625,
719
+ "ret_loss": 0.0,
720
+ "pretrain_loss": 0.0,
721
+ "total_loss": 0.07877138257026672
722
+ },
723
+ {
724
+ "global_step": 1460,
725
+ "optimizer_step": 182,
726
+ "lr": 3.600477621728473e-05,
727
+ "lm_loss": 0.6266551613807678,
728
+ "order_loss": 0.5625,
729
+ "ret_loss": 0.0,
730
+ "pretrain_loss": 0.0,
731
+ "total_loss": 0.6547313332557678
732
+ },
733
+ {
734
+ "global_step": 1480,
735
+ "optimizer_step": 185,
736
+ "lr": 3.5530135570974274e-05,
737
+ "lm_loss": 0.3707912266254425,
738
+ "order_loss": 0.5546875,
739
+ "ret_loss": 0.0,
740
+ "pretrain_loss": 0.0,
741
+ "total_loss": 0.3985011875629425
742
+ },
743
+ {
744
+ "global_step": 1500,
745
+ "optimizer_step": 187,
746
+ "lr": 3.521110642339991e-05,
747
+ "lm_loss": 0.31568682193756104,
748
+ "order_loss": 0.64453125,
749
+ "ret_loss": 0.0,
750
+ "pretrain_loss": 0.0,
751
+ "total_loss": 0.34791338443756104
752
+ },
753
+ {
754
+ "global_step": 1520,
755
+ "optimizer_step": 190,
756
+ "lr": 3.4728816504063726e-05,
757
+ "lm_loss": 0.04863154888153076,
758
+ "order_loss": 0.55078125,
759
+ "ret_loss": 0.0,
760
+ "pretrain_loss": 0.0,
761
+ "total_loss": 0.07621943950653076
762
+ },
763
+ {
764
+ "global_step": 1540,
765
+ "optimizer_step": 192,
766
+ "lr": 3.440488465537943e-05,
767
+ "lm_loss": 0.5135523676872253,
768
+ "order_loss": 0.640625,
769
+ "ret_loss": 0.0,
770
+ "pretrain_loss": 0.0,
771
+ "total_loss": 0.5455347895622253
772
+ },
773
+ {
774
+ "global_step": 1560,
775
+ "optimizer_step": 195,
776
+ "lr": 3.391553831655782e-05,
777
+ "lm_loss": 0.2213514894247055,
778
+ "order_loss": 0.6328125,
779
+ "ret_loss": 0.0,
780
+ "pretrain_loss": 0.0,
781
+ "total_loss": 0.2530897855758667
782
+ },
783
+ {
784
+ "global_step": 1580,
785
+ "optimizer_step": 197,
786
+ "lr": 3.358710195908653e-05,
787
+ "lm_loss": 0.11942815780639648,
788
+ "order_loss": 0.50390625,
789
+ "ret_loss": 0.0,
790
+ "pretrain_loss": 0.0,
791
+ "total_loss": 0.14457464218139648
792
+ },
793
+ {
794
+ "global_step": 1600,
795
+ "optimizer_step": 200,
796
+ "lr": 3.309130072840379e-05,
797
+ "lm_loss": 0.06757640093564987,
798
+ "order_loss": 0.62109375,
799
+ "ret_loss": 0.0,
800
+ "pretrain_loss": 0.0,
801
+ "total_loss": 0.09858226031064987
802
+ },
803
+ {
804
+ "global_step": 1620,
805
+ "optimizer_step": 202,
806
+ "lr": 3.2758763591623295e-05,
807
+ "lm_loss": 0.029160860925912857,
808
+ "order_loss": 0.6015625,
809
+ "ret_loss": 0.0,
810
+ "pretrain_loss": 0.0,
811
+ "total_loss": 0.05919015780091286
812
+ },
813
+ {
814
+ "global_step": 1640,
815
+ "optimizer_step": 205,
816
+ "lr": 3.225711693136156e-05,
817
+ "lm_loss": 0.028493866324424744,
818
+ "order_loss": 0.66015625,
819
+ "ret_loss": 0.0,
820
+ "pretrain_loss": 0.0,
821
+ "total_loss": 0.061452850699424744
822
+ },
823
+ {
824
+ "global_step": 1660,
825
+ "optimizer_step": 207,
826
+ "lr": 3.1920887785621235e-05,
827
+ "lm_loss": 0.008012374863028526,
828
+ "order_loss": 0.455078125,
829
+ "ret_loss": 0.0,
830
+ "pretrain_loss": 0.0,
831
+ "total_loss": 0.030717452988028526
832
+ },
833
+ {
834
+ "global_step": 1680,
835
+ "optimizer_step": 210,
836
+ "lr": 3.141401234354067e-05,
837
+ "lm_loss": 0.05485055595636368,
838
+ "order_loss": 0.53125,
839
+ "ret_loss": 0.0,
840
+ "pretrain_loss": 0.0,
841
+ "total_loss": 0.08146188408136368
842
+ },
843
+ {
844
+ "global_step": 1700,
845
+ "optimizer_step": 212,
846
+ "lr": 3.10745044975816e-05,
847
+ "lm_loss": 0.10383021086454391,
848
+ "order_loss": 0.55859375,
849
+ "ret_loss": 0.0,
850
+ "pretrain_loss": 0.0,
851
+ "total_loss": 0.1317843198776245
852
+ },
853
+ {
854
+ "global_step": 1720,
855
+ "optimizer_step": 215,
856
+ "lr": 3.056302334890786e-05,
857
+ "lm_loss": 0.16341173648834229,
858
+ "order_loss": 0.5,
859
+ "ret_loss": 0.0,
860
+ "pretrain_loss": 0.0,
861
+ "total_loss": 0.18843615055084229
862
+ },
863
+ {
864
+ "global_step": 1740,
865
+ "optimizer_step": 217,
866
+ "lr": 3.022065414180425e-05,
867
+ "lm_loss": 0.18171831965446472,
868
+ "order_loss": 0.625,
869
+ "ret_loss": 0.0,
870
+ "pretrain_loss": 0.0,
871
+ "total_loss": 0.21296831965446472
872
+ },
873
+ {
874
+ "global_step": 1760,
875
+ "optimizer_step": 220,
876
+ "lr": 2.9705196023315006e-05,
877
+ "lm_loss": 0.8805843591690063,
878
+ "order_loss": 0.80078125,
879
+ "ret_loss": 0.0,
880
+ "pretrain_loss": 0.0,
881
+ "total_loss": 0.9206234216690063
882
+ },
883
+ {
884
+ "global_step": 1780,
885
+ "optimizer_step": 222,
886
+ "lr": 2.9360386311461275e-05,
887
+ "lm_loss": 0.2869233787059784,
888
+ "order_loss": 0.5625,
889
+ "ret_loss": 0.0,
890
+ "pretrain_loss": 0.0,
891
+ "total_loss": 0.3149995505809784
892
+ },
893
+ {
894
+ "global_step": 1800,
895
+ "optimizer_step": 225,
896
+ "lr": 2.884158484861325e-05,
897
+ "lm_loss": 0.13106697797775269,
898
+ "order_loss": 0.6484375,
899
+ "ret_loss": 0.0,
900
+ "pretrain_loss": 0.0,
901
+ "total_loss": 0.16353768110275269
902
+ },
903
+ {
904
+ "global_step": 1820,
905
+ "optimizer_step": 227,
906
+ "lr": 2.849475848838749e-05,
907
+ "lm_loss": 0.30343306064605713,
908
+ "order_loss": 0.6484375,
909
+ "ret_loss": 0.0,
910
+ "pretrain_loss": 0.0,
911
+ "total_loss": 0.33590376377105713
912
+ },
913
+ {
914
+ "global_step": 1840,
915
+ "optimizer_step": 230,
916
+ "lr": 2.7973251416434175e-05,
917
+ "lm_loss": 0.16127286851406097,
918
+ "order_loss": 0.5703125,
919
+ "ret_loss": 0.0,
920
+ "pretrain_loss": 0.0,
921
+ "total_loss": 0.18983732163906097
922
+ },
923
+ {
924
+ "global_step": 1860,
925
+ "optimizer_step": 232,
926
+ "lr": 2.7624834743173867e-05,
927
+ "lm_loss": 0.8129632472991943,
928
+ "order_loss": 0.53515625,
929
+ "ret_loss": 0.0,
930
+ "pretrain_loss": 0.0,
931
+ "total_loss": 0.8396966457366943
932
+ },
933
+ {
934
+ "global_step": 1880,
935
+ "optimizer_step": 235,
936
+ "lr": 2.710126312323119e-05,
937
+ "lm_loss": 0.36717578768730164,
938
+ "order_loss": 0.5703125,
939
+ "ret_loss": 0.0,
940
+ "pretrain_loss": 0.0,
941
+ "total_loss": 0.39574024081230164
942
+ },
943
+ {
944
+ "global_step": 1900,
945
+ "optimizer_step": 237,
946
+ "lr": 2.6751684427161683e-05,
947
+ "lm_loss": 0.04350918158888817,
948
+ "order_loss": 0.7265625,
949
+ "ret_loss": 0.0,
950
+ "pretrain_loss": 0.0,
951
+ "total_loss": 0.07988613843917847
952
+ },
953
+ {
954
+ "global_step": 1920,
955
+ "optimizer_step": 240,
956
+ "lr": 2.6226691858185454e-05,
957
+ "lm_loss": 0.039855942130088806,
958
+ "order_loss": 0.50390625,
959
+ "ret_loss": 0.0,
960
+ "pretrain_loss": 0.0,
961
+ "total_loss": 0.0650024265050888
962
+ },
963
+ {
964
+ "global_step": 1940,
965
+ "optimizer_step": 242,
966
+ "lr": 2.587638085794541e-05,
967
+ "lm_loss": 0.6905671954154968,
968
+ "order_loss": 0.7109375,
969
+ "ret_loss": 0.0,
970
+ "pretrain_loss": 0.0,
971
+ "total_loss": 0.7262117266654968
972
+ },
973
+ {
974
+ "global_step": 1960,
975
+ "optimizer_step": 245,
976
+ "lr": 2.535061268558906e-05,
977
+ "lm_loss": 0.22763842344284058,
978
+ "order_loss": 0.6171875,
979
+ "ret_loss": 0.0,
980
+ "pretrain_loss": 0.0,
981
+ "total_loss": 0.2585222125053406
982
+ },
983
+ {
984
+ "global_step": 1980,
985
+ "optimizer_step": 247,
986
+ "lr": 2.5e-05,
987
+ "lm_loss": 0.36134329438209534,
988
+ "order_loss": 0.51171875,
989
+ "ret_loss": 0.0,
990
+ "pretrain_loss": 0.0,
991
+ "total_loss": 0.38697806000709534
992
+ },
993
+ {
994
+ "global_step": 2000,
995
+ "optimizer_step": 250,
996
+ "lr": 2.447410252332528e-05,
997
+ "lm_loss": 0.17196257412433624,
998
+ "order_loss": 0.54296875,
999
+ "ret_loss": 0.0,
1000
+ "pretrain_loss": 0.0,
1001
+ "total_loss": 0.19906218349933624
1002
+ },
1003
+ {
1004
+ "global_step": 2020,
1005
+ "optimizer_step": 252,
1006
+ "lr": 2.4123619142054597e-05,
1007
+ "lm_loss": 0.02721952274441719,
1008
+ "order_loss": 0.6640625,
1009
+ "ret_loss": 0.0,
1010
+ "pretrain_loss": 0.0,
1011
+ "total_loss": 0.06042264774441719
1012
+ },
1013
+ {
1014
+ "global_step": 2040,
1015
+ "optimizer_step": 255,
1016
+ "lr": 2.3598238819070202e-05,
1017
+ "lm_loss": 0.5023459792137146,
1018
+ "order_loss": 0.5078125,
1019
+ "ret_loss": 0.0,
1020
+ "pretrain_loss": 0.0,
1021
+ "total_loss": 0.5277366042137146
1022
+ },
1023
+ {
1024
+ "global_step": 2060,
1025
+ "optimizer_step": 257,
1026
+ "lr": 2.3248315572838316e-05,
1027
+ "lm_loss": 0.2271648347377777,
1028
+ "order_loss": 0.66796875,
1029
+ "ret_loss": 0.0,
1030
+ "pretrain_loss": 0.0,
1031
+ "total_loss": 0.2606121003627777
1032
+ },
1033
+ {
1034
+ "global_step": 2080,
1035
+ "optimizer_step": 260,
1036
+ "lr": 2.272409822584325e-05,
1037
+ "lm_loss": 0.3524285852909088,
1038
+ "order_loss": 0.6015625,
1039
+ "ret_loss": 0.0,
1040
+ "pretrain_loss": 0.0,
1041
+ "total_loss": 0.3824578821659088
1042
+ },
1043
+ {
1044
+ "global_step": 2100,
1045
+ "optimizer_step": 262,
1046
+ "lr": 2.237516525682614e-05,
1047
+ "lm_loss": 0.3494965434074402,
1048
+ "order_loss": 0.57421875,
1049
+ "ret_loss": 0.0,
1050
+ "pretrain_loss": 0.0,
1051
+ "total_loss": 0.3781830668449402
1052
+ },
1053
+ {
1054
+ "global_step": 2120,
1055
+ "optimizer_step": 265,
1056
+ "lr": 2.185275527853437e-05,
1057
+ "lm_loss": 0.1902540624141693,
1058
+ "order_loss": 0.61328125,
1059
+ "ret_loss": 0.0,
1060
+ "pretrain_loss": 0.0,
1061
+ "total_loss": 0.2208937108516693
1062
+ },
1063
+ {
1064
+ "global_step": 2140,
1065
+ "optimizer_step": 267,
1066
+ "lr": 2.1505241511612522e-05,
1067
+ "lm_loss": 0.1683250069618225,
1068
+ "order_loss": 0.52734375,
1069
+ "ret_loss": 0.0,
1070
+ "pretrain_loss": 0.0,
1071
+ "total_loss": 0.1946921944618225
1072
+ },
1073
+ {
1074
+ "global_step": 2160,
1075
+ "optimizer_step": 270,
1076
+ "lr": 2.0985281073035076e-05,
1077
+ "lm_loss": 0.22736619412899017,
1078
+ "order_loss": 0.6015625,
1079
+ "ret_loss": 0.0,
1080
+ "pretrain_loss": 0.0,
1081
+ "total_loss": 0.25739550590515137
1082
+ },
1083
+ {
1084
+ "global_step": 2180,
1085
+ "optimizer_step": 272,
1086
+ "lr": 2.0639613688538734e-05,
1087
+ "lm_loss": 0.13654670119285583,
1088
+ "order_loss": 0.55078125,
1089
+ "ret_loss": 0.0,
1090
+ "pretrain_loss": 0.0,
1091
+ "total_loss": 0.16413459181785583
1092
+ },
1093
+ {
1094
+ "global_step": 2200,
1095
+ "optimizer_step": 275,
1096
+ "lr": 2.0122741949596797e-05,
1097
+ "lm_loss": 0.16708070039749146,
1098
+ "order_loss": 0.59375,
1099
+ "ret_loss": 0.0,
1100
+ "pretrain_loss": 0.0,
1101
+ "total_loss": 0.19674378633499146
1102
+ },
1103
+ {
1104
+ "global_step": 2220,
1105
+ "optimizer_step": 277,
1106
+ "lr": 1.977934585819576e-05,
1107
+ "lm_loss": 0.15234331786632538,
1108
+ "order_loss": 0.64453125,
1109
+ "ret_loss": 0.0,
1110
+ "pretrain_loss": 0.0,
1111
+ "total_loss": 0.18456988036632538
1112
+ },
1113
+ {
1114
+ "global_step": 2240,
1115
+ "optimizer_step": 280,
1116
+ "lr": 1.9266198182035058e-05,
1117
+ "lm_loss": 0.008806280791759491,
1118
+ "order_loss": 0.66015625,
1119
+ "ret_loss": 0.0,
1120
+ "pretrain_loss": 0.0,
1121
+ "total_loss": 0.04176526516675949
1122
+ },
1123
+ {
1124
+ "global_step": 2260,
1125
+ "optimizer_step": 282,
1126
+ "lr": 1.8925495502418406e-05,
1127
+ "lm_loss": 0.5242239236831665,
1128
+ "order_loss": 0.609375,
1129
+ "ret_loss": 0.0,
1130
+ "pretrain_loss": 0.0,
1131
+ "total_loss": 0.5547415018081665
1132
+ },
1133
+ {
1134
+ "global_step": 2280,
1135
+ "optimizer_step": 285,
1136
+ "lr": 1.841670267439088e-05,
1137
+ "lm_loss": 0.29609933495521545,
1138
+ "order_loss": 0.55078125,
1139
+ "ret_loss": 0.0,
1140
+ "pretrain_loss": 0.0,
1141
+ "total_loss": 0.32368722558021545
1142
+ },
1143
+ {
1144
+ "global_step": 2300,
1145
+ "optimizer_step": 287,
1146
+ "lr": 1.8079112214378768e-05,
1147
+ "lm_loss": 0.32155320048332214,
1148
+ "order_loss": 3.015625,
1149
+ "ret_loss": 0.0,
1150
+ "pretrain_loss": 0.0,
1151
+ "total_loss": 0.47194382548332214
1152
+ },
1153
+ {
1154
+ "global_step": 2320,
1155
+ "optimizer_step": 290,
1156
+ "lr": 1.757529966665141e-05,
1157
+ "lm_loss": 0.19045846164226532,
1158
+ "order_loss": 0.5078125,
1159
+ "ret_loss": 0.0,
1160
+ "pretrain_loss": 0.0,
1161
+ "total_loss": 0.21584908664226532
1162
+ },
1163
+ {
1164
+ "global_step": 2340,
1165
+ "optimizer_step": 292,
1166
+ "lr": 1.72412364083767e-05,
1167
+ "lm_loss": 0.28408104181289673,
1168
+ "order_loss": 0.609375,
1169
+ "ret_loss": 0.0,
1170
+ "pretrain_loss": 0.0,
1171
+ "total_loss": 0.31459861993789673
1172
+ },
1173
+ {
1174
+ "global_step": 2360,
1175
+ "optimizer_step": 295,
1176
+ "lr": 1.6743023451120832e-05,
1177
+ "lm_loss": 0.09323065727949142,
1178
+ "order_loss": 0.6171875,
1179
+ "ret_loss": 0.0,
1180
+ "pretrain_loss": 0.0,
1181
+ "total_loss": 0.12411444634199142
1182
+ },
1183
+ {
1184
+ "global_step": 2380,
1185
+ "optimizer_step": 297,
1186
+ "lr": 1.641289804091347e-05,
1187
+ "lm_loss": 0.3598926365375519,
1188
+ "order_loss": 0.578125,
1189
+ "ret_loss": 0.0,
1190
+ "pretrain_loss": 0.0,
1191
+ "total_loss": 0.3888233006000519
1192
+ },
1193
+ {
1194
+ "global_step": 2400,
1195
+ "optimizer_step": 300,
1196
+ "lr": 1.5920897101019383e-05,
1197
+ "lm_loss": 0.365915983915329,
1198
+ "order_loss": 1.3515625,
1199
+ "ret_loss": 0.0,
1200
+ "pretrain_loss": 0.0,
1201
+ "total_loss": 0.433298796415329
1202
+ },
1203
+ {
1204
+ "global_step": 2420,
1205
+ "optimizer_step": 302,
1206
+ "lr": 1.5595115344620576e-05,
1207
+ "lm_loss": 0.05704324319958687,
1208
+ "order_loss": 0.61328125,
1209
+ "ret_loss": 0.0,
1210
+ "pretrain_loss": 0.0,
1211
+ "total_loss": 0.08768288791179657
1212
+ },
1213
+ {
1214
+ "global_step": 2440,
1215
+ "optimizer_step": 305,
1216
+ "lr": 1.5109931212873534e-05,
1217
+ "lm_loss": 0.37197041511535645,
1218
+ "order_loss": 0.57421875,
1219
+ "ret_loss": 0.0,
1220
+ "pretrain_loss": 0.0,
1221
+ "total_loss": 0.40065693855285645
1222
+ },
1223
+ {
1224
+ "global_step": 2460,
1225
+ "optimizer_step": 307,
1226
+ "lr": 1.4788893576600099e-05,
1227
+ "lm_loss": 0.1522659957408905,
1228
+ "order_loss": 0.5625,
1229
+ "ret_loss": 0.0,
1230
+ "pretrain_loss": 0.0,
1231
+ "total_loss": 0.1803421676158905
1232
+ },
1233
+ {
1234
+ "global_step": 2480,
1235
+ "optimizer_step": 310,
1236
+ "lr": 1.4311122664242954e-05,
1237
+ "lm_loss": 0.47468554973602295,
1238
+ "order_loss": 0.50390625,
1239
+ "ret_loss": 0.0,
1240
+ "pretrain_loss": 0.0,
1241
+ "total_loss": 0.49983203411102295
1242
+ },
1243
+ {
1244
+ "global_step": 2500,
1245
+ "optimizer_step": 312,
1246
+ "lr": 1.399522378271527e-05,
1247
+ "lm_loss": 0.26292675733566284,
1248
+ "order_loss": 0.62890625,
1249
+ "ret_loss": 0.0,
1250
+ "pretrain_loss": 0.0,
1251
+ "total_loss": 0.29442089796066284
1252
+ },
1253
+ {
1254
+ "global_step": 2520,
1255
+ "optimizer_step": 315,
1256
+ "lr": 1.3525453388311554e-05,
1257
+ "lm_loss": 0.08223970234394073,
1258
+ "order_loss": 0.578125,
1259
+ "ret_loss": 0.0,
1260
+ "pretrain_loss": 0.0,
1261
+ "total_loss": 0.11117036640644073
1262
+ },
1263
+ {
1264
+ "global_step": 2540,
1265
+ "optimizer_step": 317,
1266
+ "lr": 1.3215081579350058e-05,
1267
+ "lm_loss": 0.12066788971424103,
1268
+ "order_loss": 0.7734375,
1269
+ "ret_loss": 0.0,
1270
+ "pretrain_loss": 0.0,
1271
+ "total_loss": 0.15924210846424103
1272
+ },
1273
+ {
1274
+ "global_step": 2560,
1275
+ "optimizer_step": 320,
1276
+ "lr": 1.2753889166848909e-05,
1277
+ "lm_loss": 0.41804543137550354,
1278
+ "order_loss": 0.53515625,
1279
+ "ret_loss": 0.0,
1280
+ "pretrain_loss": 0.0,
1281
+ "total_loss": 0.44477882981300354
1282
+ },
1283
+ {
1284
+ "global_step": 2580,
1285
+ "optimizer_step": 322,
1286
+ "lr": 1.2449425954135452e-05,
1287
+ "lm_loss": 0.20591922104358673,
1288
+ "order_loss": 0.5625,
1289
+ "ret_loss": 0.0,
1290
+ "pretrain_loss": 0.0,
1291
+ "total_loss": 0.23399539291858673
1292
+ },
1293
+ {
1294
+ "global_step": 2600,
1295
+ "optimizer_step": 325,
1296
+ "lr": 1.1997378443025634e-05,
1297
+ "lm_loss": 0.2400602549314499,
1298
+ "order_loss": 0.6171875,
1299
+ "ret_loss": 0.0,
1300
+ "pretrain_loss": 0.0,
1301
+ "total_loss": 0.2709440588951111
1302
+ },
1303
+ {
1304
+ "global_step": 2620,
1305
+ "optimizer_step": 327,
1306
+ "lr": 1.1699198087116589e-05,
1307
+ "lm_loss": 0.015819068998098373,
1308
+ "order_loss": 0.55859375,
1309
+ "ret_loss": 0.0,
1310
+ "pretrain_loss": 0.0,
1311
+ "total_loss": 0.04377317056059837
1312
+ },
1313
+ {
1314
+ "global_step": 2640,
1315
+ "optimizer_step": 330,
1316
+ "lr": 1.1256851155542298e-05,
1317
+ "lm_loss": 0.06032584235072136,
1318
+ "order_loss": 0.671875,
1319
+ "ret_loss": 0.0,
1320
+ "pretrain_loss": 0.0,
1321
+ "total_loss": 0.09401725232601166
1322
+ },
1323
+ {
1324
+ "global_step": 2660,
1325
+ "optimizer_step": 332,
1326
+ "lr": 1.0965320193809808e-05,
1327
+ "lm_loss": 0.100696861743927,
1328
+ "order_loss": 0.6953125,
1329
+ "ret_loss": 0.0,
1330
+ "pretrain_loss": 0.0,
1331
+ "total_loss": 0.135364830493927
1332
+ },
1333
+ {
1334
+ "global_step": 2680,
1335
+ "optimizer_step": 335,
1336
+ "lr": 1.0533217595504858e-05,
1337
+ "lm_loss": 0.3024890720844269,
1338
+ "order_loss": 0.60546875,
1339
+ "ret_loss": 0.0,
1340
+ "pretrain_loss": 0.0,
1341
+ "total_loss": 0.3327625095844269
1342
+ },
1343
+ {
1344
+ "global_step": 2700,
1345
+ "optimizer_step": 337,
1346
+ "lr": 1.0248694391571801e-05,
1347
+ "lm_loss": 0.11295029520988464,
1348
+ "order_loss": 0.58984375,
1349
+ "ret_loss": 0.0,
1350
+ "pretrain_loss": 0.0,
1351
+ "total_loss": 0.14249131083488464
1352
+ },
1353
+ {
1354
+ "global_step": 2720,
1355
+ "optimizer_step": 340,
1356
+ "lr": 9.82736728745186e-06,
1357
+ "lm_loss": 0.24754874408245087,
1358
+ "order_loss": 0.56640625,
1359
+ "ret_loss": 0.0,
1360
+ "pretrain_loss": 0.0,
1361
+ "total_loss": 0.27586907148361206
1362
+ },
1363
+ {
1364
+ "global_step": 2740,
1365
+ "optimizer_step": 342,
1366
+ "lr": 9.550201590674343e-06,
1367
+ "lm_loss": 0.12781944870948792,
1368
+ "order_loss": 0.6484375,
1369
+ "ret_loss": 0.0,
1370
+ "pretrain_loss": 0.0,
1371
+ "total_loss": 0.16029015183448792
1372
+ },
1373
+ {
1374
+ "global_step": 2760,
1375
+ "optimizer_step": 345,
1376
+ "lr": 9.140167895908867e-06,
1377
+ "lm_loss": 0.29023900628089905,
1378
+ "order_loss": 0.58984375,
1379
+ "ret_loss": 0.0,
1380
+ "pretrain_loss": 0.0,
1381
+ "total_loss": 0.31978002190589905
1382
+ },
1383
+ {
1384
+ "global_step": 2780,
1385
+ "optimizer_step": 347,
1386
+ "lr": 8.870700411447816e-06,
1387
+ "lm_loss": 0.038561590015888214,
1388
+ "order_loss": 0.5390625,
1389
+ "ret_loss": 0.0,
1390
+ "pretrain_loss": 0.0,
1391
+ "total_loss": 0.06553912907838821
1392
+ },
1393
+ {
1394
+ "global_step": 2800,
1395
+ "optimizer_step": 350,
1396
+ "lr": 8.472464158814255e-06,
1397
+ "lm_loss": 0.2457677572965622,
1398
+ "order_loss": 0.5,
1399
+ "ret_loss": 0.0,
1400
+ "pretrain_loss": 0.0,
1401
+ "total_loss": 0.2707921862602234
1402
+ },
1403
+ {
1404
+ "global_step": 2820,
1405
+ "optimizer_step": 352,
1406
+ "lr": 8.211026128824539e-06,
1407
+ "lm_loss": 0.08514761924743652,
1408
+ "order_loss": 0.52734375,
1409
+ "ret_loss": 0.0,
1410
+ "pretrain_loss": 0.0,
1411
+ "total_loss": 0.11151480674743652
1412
+ },
1413
+ {
1414
+ "global_step": 2840,
1415
+ "optimizer_step": 355,
1416
+ "lr": 7.825076849127458e-06,
1417
+ "lm_loss": 0.048302918672561646,
1418
+ "order_loss": 0.60546875,
1419
+ "ret_loss": 0.0,
1420
+ "pretrain_loss": 0.0,
1421
+ "total_loss": 0.07857635617256165
1422
+ },
1423
+ {
1424
+ "global_step": 2860,
1425
+ "optimizer_step": 357,
1426
+ "lr": 7.571989645579419e-06,
1427
+ "lm_loss": 0.0022240541875362396,
1428
+ "order_loss": 0.82421875,
1429
+ "ret_loss": 0.0,
1430
+ "pretrain_loss": 0.0,
1431
+ "total_loss": 0.04348381981253624
1432
+ },
1433
+ {
1434
+ "global_step": 2880,
1435
+ "optimizer_step": 360,
1436
+ "lr": 7.198801765896115e-06,
1437
+ "lm_loss": 0.23744088411331177,
1438
+ "order_loss": 0.55859375,
1439
+ "ret_loss": 0.0,
1440
+ "pretrain_loss": 0.0,
1441
+ "total_loss": 0.26539498567581177
1442
+ },
1443
+ {
1444
+ "global_step": 2900,
1445
+ "optimizer_step": 362,
1446
+ "lr": 6.9543764955299265e-06,
1447
+ "lm_loss": 0.38635385036468506,
1448
+ "order_loss": 0.62890625,
1449
+ "ret_loss": 0.0,
1450
+ "pretrain_loss": 0.0,
1451
+ "total_loss": 0.41784799098968506
1452
+ },
1453
+ {
1454
+ "global_step": 2920,
1455
+ "optimizer_step": 365,
1456
+ "lr": 6.594408756022272e-06,
1457
+ "lm_loss": 0.25551310181617737,
1458
+ "order_loss": 0.52734375,
1459
+ "ret_loss": 0.0,
1460
+ "pretrain_loss": 0.0,
1461
+ "total_loss": 0.28188028931617737
1462
+ },
1463
+ {
1464
+ "global_step": 2940,
1465
+ "optimizer_step": 367,
1466
+ "lr": 6.358945877920861e-06,
1467
+ "lm_loss": 0.05681644007563591,
1468
+ "order_loss": 0.59375,
1469
+ "ret_loss": 0.0,
1470
+ "pretrain_loss": 0.0,
1471
+ "total_loss": 0.08647952973842621
1472
+ },
1473
+ {
1474
+ "global_step": 2960,
1475
+ "optimizer_step": 370,
1476
+ "lr": 6.012640767930217e-06,
1477
+ "lm_loss": 0.3008907735347748,
1478
+ "order_loss": 0.74609375,
1479
+ "ret_loss": 0.0,
1480
+ "pretrain_loss": 0.0,
1481
+ "total_loss": 0.3382442891597748
1482
+ },
1483
+ {
1484
+ "global_step": 2980,
1485
+ "optimizer_step": 372,
1486
+ "lr": 5.7864297241808e-06,
1487
+ "lm_loss": 0.21228210628032684,
1488
+ "order_loss": 0.609375,
1489
+ "ret_loss": 0.0,
1490
+ "pretrain_loss": 0.0,
1491
+ "total_loss": 0.24279968440532684
1492
+ },
1493
+ {
1494
+ "global_step": 3000,
1495
+ "optimizer_step": 375,
1496
+ "lr": 5.454212938299255e-06,
1497
+ "lm_loss": 0.34354081749916077,
1498
+ "order_loss": 0.578125,
1499
+ "ret_loss": 0.0,
1500
+ "pretrain_loss": 0.0,
1501
+ "total_loss": 0.37247148156166077
1502
+ },
1503
+ {
1504
+ "global_step": 3020,
1505
+ "optimizer_step": 377,
1506
+ "lr": 5.237531798197415e-06,
1507
+ "lm_loss": 0.25263744592666626,
1508
+ "order_loss": 0.55078125,
1509
+ "ret_loss": 0.0,
1510
+ "pretrain_loss": 0.0,
1511
+ "total_loss": 0.28022533655166626
1512
+ },
1513
+ {
1514
+ "global_step": 3040,
1515
+ "optimizer_step": 380,
1516
+ "lr": 4.91981171298388e-06,
1517
+ "lm_loss": 0.0780947357416153,
1518
+ "order_loss": 0.63671875,
1519
+ "ret_loss": 0.0,
1520
+ "pretrain_loss": 0.0,
1521
+ "total_loss": 0.1098330169916153
1522
+ },
1523
+ {
1524
+ "global_step": 3060,
1525
+ "optimizer_step": 382,
1526
+ "lr": 4.712926831217685e-06,
1527
+ "lm_loss": 0.3715834617614746,
1528
+ "order_loss": 0.69921875,
1529
+ "ret_loss": 0.0,
1530
+ "pretrain_loss": 0.0,
1531
+ "total_loss": 0.4064955711364746
1532
+ },
1533
+ {
1534
+ "global_step": 3080,
1535
+ "optimizer_step": 385,
1536
+ "lr": 4.410094003202134e-06,
1537
+ "lm_loss": 0.007295445539057255,
1538
+ "order_loss": 0.57421875,
1539
+ "ret_loss": 0.0,
1540
+ "pretrain_loss": 0.0,
1541
+ "total_loss": 0.03598196804523468
1542
+ },
1543
+ {
1544
+ "global_step": 3100,
1545
+ "optimizer_step": 387,
1546
+ "lr": 4.213259692436367e-06,
1547
+ "lm_loss": 0.0032686071936041117,
1548
+ "order_loss": 0.55078125,
1549
+ "ret_loss": 0.0,
1550
+ "pretrain_loss": 0.0,
1551
+ "total_loss": 0.030856497585773468
1552
+ },
1553
+ {
1554
+ "global_step": 3120,
1555
+ "optimizer_step": 390,
1556
+ "lr": 3.925686378029331e-06,
1557
+ "lm_loss": 0.06844284385442734,
1558
+ "order_loss": 0.6171875,
1559
+ "ret_loss": 0.0,
1560
+ "pretrain_loss": 0.0,
1561
+ "total_loss": 0.09932663291692734
1562
+ },
1563
+ {
1564
+ "global_step": 3140,
1565
+ "optimizer_step": 392,
1566
+ "lr": 3.739144596292382e-06,
1567
+ "lm_loss": 0.23541045188903809,
1568
+ "order_loss": 0.671875,
1569
+ "ret_loss": 0.0,
1570
+ "pretrain_loss": 0.0,
1571
+ "total_loss": 0.2691018581390381
1572
+ },
1573
+ {
1574
+ "global_step": 3160,
1575
+ "optimizer_step": 395,
1576
+ "lr": 3.4671842941897765e-06,
1577
+ "lm_loss": 0.3603845238685608,
1578
+ "order_loss": 0.66796875,
1579
+ "ret_loss": 0.0,
1580
+ "pretrain_loss": 0.0,
1581
+ "total_loss": 0.3938317894935608
1582
+ },
1583
+ {
1584
+ "global_step": 3180,
1585
+ "optimizer_step": 397,
1586
+ "lr": 3.2911643474473646e-06,
1587
+ "lm_loss": 0.03777855634689331,
1588
+ "order_loss": 0.61328125,
1589
+ "ret_loss": 0.0,
1590
+ "pretrain_loss": 0.0,
1591
+ "total_loss": 0.06841820478439331
1592
+ },
1593
+ {
1594
+ "global_step": 3200,
1595
+ "optimizer_step": 400,
1596
+ "lr": 3.035151364093214e-06,
1597
+ "lm_loss": 0.1275491714477539,
1598
+ "order_loss": 0.57421875,
1599
+ "ret_loss": 0.0,
1600
+ "pretrain_loss": 0.0,
1601
+ "total_loss": 0.1562356948852539
1602
+ },
1603
+ {
1604
+ "global_step": 3220,
1605
+ "optimizer_step": 402,
1606
+ "lr": 2.869869624374699e-06,
1607
+ "lm_loss": 0.25982198119163513,
1608
+ "order_loss": 0.55078125,
1609
+ "ret_loss": 0.0,
1610
+ "pretrain_loss": 0.0,
1611
+ "total_loss": 0.28740987181663513
1612
+ },
1613
+ {
1614
+ "global_step": 3240,
1615
+ "optimizer_step": 405,
1616
+ "lr": 2.6301186630158485e-06,
1617
+ "lm_loss": 0.1199856773018837,
1618
+ "order_loss": 0.59765625,
1619
+ "ret_loss": 0.0,
1620
+ "pretrain_loss": 0.0,
1621
+ "total_loss": 0.1498928964138031
1622
+ },
1623
+ {
1624
+ "global_step": 3260,
1625
+ "optimizer_step": 407,
1626
+ "lr": 2.475778302439524e-06,
1627
+ "lm_loss": 0.1846313774585724,
1628
+ "order_loss": 0.56640625,
1629
+ "ret_loss": 0.0,
1630
+ "pretrain_loss": 0.0,
1631
+ "total_loss": 0.2129516899585724
1632
+ },
1633
+ {
1634
+ "global_step": 3280,
1635
+ "optimizer_step": 410,
1636
+ "lr": 2.2525840762775863e-06,
1637
+ "lm_loss": 0.3496130704879761,
1638
+ "order_loss": 0.5390625,
1639
+ "ret_loss": 0.0,
1640
+ "pretrain_loss": 0.0,
1641
+ "total_loss": 0.3765906095504761
1642
+ },
1643
+ {
1644
+ "global_step": 3300,
1645
+ "optimizer_step": 412,
1646
+ "lr": 2.1093748173018848e-06,
1647
+ "lm_loss": 0.10253337025642395,
1648
+ "order_loss": 0.55859375,
1649
+ "ret_loss": 0.0,
1650
+ "pretrain_loss": 0.0,
1651
+ "total_loss": 0.13048747181892395
1652
+ },
1653
+ {
1654
+ "global_step": 3320,
1655
+ "optimizer_step": 415,
1656
+ "lr": 1.9030116872178316e-06,
1657
+ "lm_loss": 0.031067628413438797,
1658
+ "order_loss": 0.50390625,
1659
+ "ret_loss": 0.0,
1660
+ "pretrain_loss": 0.0,
1661
+ "total_loss": 0.0562141127884388
1662
+ },
1663
+ {
1664
+ "global_step": 3340,
1665
+ "optimizer_step": 417,
1666
+ "lr": 1.771109569425547e-06,
1667
+ "lm_loss": 0.21988312900066376,
1668
+ "order_loss": 0.625,
1669
+ "ret_loss": 0.0,
1670
+ "pretrain_loss": 0.0,
1671
+ "total_loss": 0.25113314390182495
1672
+ },
1673
+ {
1674
+ "global_step": 3360,
1675
+ "optimizer_step": 420,
1676
+ "lr": 1.5818312067223672e-06,
1677
+ "lm_loss": 0.012113655917346478,
1678
+ "order_loss": 0.65625,
1679
+ "ret_loss": 0.0,
1680
+ "pretrain_loss": 0.0,
1681
+ "total_loss": 0.04482850059866905
1682
+ },
1683
+ {
1684
+ "global_step": 3380,
1685
+ "optimizer_step": 422,
1686
+ "lr": 1.4613983704244826e-06,
1687
+ "lm_loss": 0.2473658174276352,
1688
+ "order_loss": 0.5703125,
1689
+ "ret_loss": 0.0,
1690
+ "pretrain_loss": 0.0,
1691
+ "total_loss": 0.2759302854537964
1692
+ },
1693
+ {
1694
+ "global_step": 3400,
1695
+ "optimizer_step": 425,
1696
+ "lr": 1.2894374450024338e-06,
1697
+ "lm_loss": 0.13300944864749908,
1698
+ "order_loss": 0.5078125,
1699
+ "ret_loss": 0.0,
1700
+ "pretrain_loss": 0.0,
1701
+ "total_loss": 0.15840007364749908
1702
+ },
1703
+ {
1704
+ "global_step": 3420,
1705
+ "optimizer_step": 427,
1706
+ "lr": 1.180621931927592e-06,
1707
+ "lm_loss": 0.00670984061434865,
1708
+ "order_loss": 0.498046875,
1709
+ "ret_loss": 0.0,
1710
+ "pretrain_loss": 0.0,
1711
+ "total_loss": 0.03161218389868736
1712
+ },
1713
+ {
1714
+ "global_step": 3440,
1715
+ "optimizer_step": 430,
1716
+ "lr": 1.0261898262753812e-06,
1717
+ "lm_loss": 0.06303583085536957,
1718
+ "order_loss": 0.6796875,
1719
+ "ret_loss": 0.0,
1720
+ "pretrain_loss": 0.0,
1721
+ "total_loss": 0.09697137773036957
1722
+ },
1723
+ {
1724
+ "global_step": 3460,
1725
+ "optimizer_step": 432,
1726
+ "lr": 9.291253975900139e-07,
1727
+ "lm_loss": 0.10441654175519943,
1728
+ "order_loss": 0.62109375,
1729
+ "ret_loss": 0.0,
1730
+ "pretrain_loss": 0.0,
1731
+ "total_loss": 0.13542240858078003
1732
+ },
1733
+ {
1734
+ "global_step": 3480,
1735
+ "optimizer_step": 435,
1736
+ "lr": 7.924119469434665e-07,
1737
+ "lm_loss": 0.4860694110393524,
1738
+ "order_loss": 0.62109375,
1739
+ "ret_loss": 0.0,
1740
+ "pretrain_loss": 0.0,
1741
+ "total_loss": 0.5170753002166748
1742
+ },
1743
+ {
1744
+ "global_step": 3500,
1745
+ "optimizer_step": 437,
1746
+ "lr": 7.072179188262251e-07,
1747
+ "lm_loss": 0.11228866130113602,
1748
+ "order_loss": 0.57421875,
1749
+ "ret_loss": 0.0,
1750
+ "pretrain_loss": 0.0,
1751
+ "total_loss": 0.14097517728805542
1752
+ },
1753
+ {
1754
+ "global_step": 3520,
1755
+ "optimizer_step": 440,
1756
+ "lr": 5.883911778138324e-07,
1757
+ "lm_loss": 0.03569963201880455,
1758
+ "order_loss": 0.6015625,
1759
+ "ret_loss": 0.0,
1760
+ "pretrain_loss": 0.0,
1761
+ "total_loss": 0.06572893261909485
1762
+ },
1763
+ {
1764
+ "global_step": 3540,
1765
+ "optimizer_step": 442,
1766
+ "lr": 5.151722747865434e-07,
1767
+ "lm_loss": 0.34798067808151245,
1768
+ "order_loss": 0.55078125,
1769
+ "ret_loss": 0.0,
1770
+ "pretrain_loss": 0.0,
1771
+ "total_loss": 0.37556856870651245
1772
+ },
1773
+ {
1774
+ "global_step": 3560,
1775
+ "optimizer_step": 445,
1776
+ "lr": 4.1437831084878974e-07,
1777
+ "lm_loss": 0.19142714142799377,
1778
+ "order_loss": 0.59375,
1779
+ "ret_loss": 0.0,
1780
+ "pretrain_loss": 0.0,
1781
+ "total_loss": 0.22109022736549377
1782
+ },
1783
+ {
1784
+ "global_step": 3580,
1785
+ "optimizer_step": 447,
1786
+ "lr": 3.5322453704410286e-07,
1787
+ "lm_loss": 0.13810081779956818,
1788
+ "order_loss": 0.546875,
1789
+ "ret_loss": 0.0,
1790
+ "pretrain_loss": 0.0,
1791
+ "total_loss": 0.16544456779956818
1792
+ },
1793
+ {
1794
+ "global_step": 3600,
1795
+ "optimizer_step": 450,
1796
+ "lr": 2.705872508804747e-07,
1797
+ "lm_loss": 0.04408229887485504,
1798
+ "order_loss": 0.51953125,
1799
+ "ret_loss": 0.0,
1800
+ "pretrain_loss": 0.0,
1801
+ "total_loss": 0.07008327543735504
1802
+ },
1803
+ {
1804
+ "global_step": 3620,
1805
+ "optimizer_step": 452,
1806
+ "lr": 2.215737794045436e-07,
1807
+ "lm_loss": 0.2954983115196228,
1808
+ "order_loss": 0.66796875,
1809
+ "ret_loss": 0.0,
1810
+ "pretrain_loss": 0.0,
1811
+ "total_loss": 0.3289455771446228
1812
+ },
1813
+ {
1814
+ "global_step": 3640,
1815
+ "optimizer_step": 455,
1816
+ "lr": 1.571947526689349e-07,
1817
+ "lm_loss": 0.168072909116745,
1818
+ "order_loss": 0.859375,
1819
+ "ret_loss": 0.0,
1820
+ "pretrain_loss": 0.0,
1821
+ "total_loss": 0.211041659116745
1822
+ },
1823
+ {
1824
+ "global_step": 3660,
1825
+ "optimizer_step": 457,
1826
+ "lr": 1.2038183319507955e-07,
1827
+ "lm_loss": 0.2848998010158539,
1828
+ "order_loss": 0.6171875,
1829
+ "ret_loss": 0.0,
1830
+ "pretrain_loss": 0.0,
1831
+ "total_loss": 0.3157835900783539
1832
+ },
1833
+ {
1834
+ "global_step": 3680,
1835
+ "optimizer_step": 460,
1836
+ "lr": 7.434020362682704e-08,
1837
+ "lm_loss": 0.4838762879371643,
1838
+ "order_loss": 0.5859375,
1839
+ "ret_loss": 0.0,
1840
+ "pretrain_loss": 0.0,
1841
+ "total_loss": 0.5131731629371643
1842
+ },
1843
+ {
1844
+ "global_step": 3700,
1845
+ "optimizer_step": 462,
1846
+ "lr": 4.977308833379324e-08,
1847
+ "lm_loss": 0.1565738171339035,
1848
+ "order_loss": 0.5546875,
1849
+ "ret_loss": 0.0,
1850
+ "pretrain_loss": 0.0,
1851
+ "total_loss": 0.1842837780714035
1852
+ },
1853
+ {
1854
+ "global_step": 3720,
1855
+ "optimizer_step": 465,
1856
+ "lr": 2.2125452477828047e-08,
1857
+ "lm_loss": 0.08877666294574738,
1858
+ "order_loss": 0.4921875,
1859
+ "ret_loss": 0.0,
1860
+ "pretrain_loss": 0.0,
1861
+ "total_loss": 0.11343486607074738
1862
+ },
1863
+ {
1864
+ "global_step": 3740,
1865
+ "optimizer_step": 467,
1866
+ "lr": 9.834340423678368e-09,
1867
+ "lm_loss": 0.5488189458847046,
1868
+ "order_loss": 0.6015625,
1869
+ "ret_loss": 0.0,
1870
+ "pretrain_loss": 0.0,
1871
+ "total_loss": 0.5788482427597046
1872
+ }
1873
+ ]
1874
+ }
cls_smollm2_orderkd_first_l01/checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cls_smollm2_orderkd_first_l01/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 16,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "up_proj",
38
+ "v_proj",
39
+ "k_proj",
40
+ "down_proj",
41
+ "o_proj",
42
+ "q_proj",
43
+ "gate_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
cls_smollm2_orderkd_first_l01/checkpoint-400/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
cls_smollm2_orderkd_first_l01/checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cls_smollm2_orderkd_first_l01/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [],
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "model_max_length": 8192,
12
+ "pad_token": "<|endoftext|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "GPT2Tokenizer",
15
+ "unk_token": "<|endoftext|>",
16
+ "vocab_size": 49152,
17
+ "added_tokens_decoder": {
18
+ "0": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": false,
24
+ "special": true
25
+ },
26
+ "1": {
27
+ "content": "<|im_start|>",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false,
32
+ "special": true
33
+ },
34
+ "2": {
35
+ "content": "<|im_end|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "3": {
43
+ "content": "<repo_name>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "4": {
51
+ "content": "<reponame>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "5": {
59
+ "content": "<file_sep>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "6": {
67
+ "content": "<filename>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "7": {
75
+ "content": "<gh_stars>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "8": {
83
+ "content": "<issue_start>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "9": {
91
+ "content": "<issue_comment>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "10": {
99
+ "content": "<issue_closed>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "11": {
107
+ "content": "<jupyter_start>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "12": {
115
+ "content": "<jupyter_text>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "13": {
123
+ "content": "<jupyter_code>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "14": {
131
+ "content": "<jupyter_output>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "15": {
139
+ "content": "<jupyter_script>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "16": {
147
+ "content": "<empty_output>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": true
153
+ }
154
+ }
155
+ }
cls_smollm2_orderkd_first_l02/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM2-1.7B-Instruct
7
+ - lora
8
+ - transformers
9
+ - unsloth
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.19.1