sirui6011 commited on
Commit
a714680
·
verified ·
1 Parent(s): 8a4bc09

add checkpoints/sft1.5b_lr1e5_bs32

Browse files
Files changed (24) hide show
  1. .gitattributes +3 -0
  2. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/added_tokens.json +35 -0
  3. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/chat_template.jinja +54 -0
  4. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/config.json +58 -0
  5. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/generation_config.json +8 -0
  6. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/merges.txt +0 -0
  7. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/model.safetensors +3 -0
  8. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/special_tokens_map.json +31 -0
  9. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer.json +3 -0
  10. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer_config.json +295 -0
  11. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/trainer_state.json +0 -0
  12. checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/vocab.json +0 -0
  13. checkpoints/sft1.5b_lr1e5_bs32/wandb/debug-internal.log +15 -0
  14. checkpoints/sft1.5b_lr1e5_bs32/wandb/debug.log +24 -0
  15. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/files/requirements.txt +222 -0
  16. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-core.log +6 -0
  17. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-internal.log +11 -0
  18. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug.log +22 -0
  19. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/run-8u6a9bbf.wandb +3 -0
  20. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/files/requirements.txt +222 -0
  21. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-core.log +15 -0
  22. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log +15 -0
  23. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log +24 -0
  24. checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/run-f7zbl5g6.wandb +3 -0
.gitattributes CHANGED
@@ -119,3 +119,6 @@ checkpoints/codi-single-3b/checkpoint-3000/tokenizer.json filter=lfs diff=lfs me
119
  checkpoints/codi-single-3b/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
120
  checkpoints/codi-single-3b/wandb/offline-run-20260624_140152-pm1zc3bt/run-pm1zc3bt.wandb filter=lfs diff=lfs merge=lfs -text
121
  checkpoints/codi-single-3b/wandb/offline-run-20260624_191509-pzchjc4v/run-pzchjc4v.wandb filter=lfs diff=lfs merge=lfs -text
 
 
 
 
119
  checkpoints/codi-single-3b/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
120
  checkpoints/codi-single-3b/wandb/offline-run-20260624_140152-pm1zc3bt/run-pm1zc3bt.wandb filter=lfs diff=lfs merge=lfs -text
121
  checkpoints/codi-single-3b/wandb/offline-run-20260624_191509-pzchjc4v/run-pzchjc4v.wandb filter=lfs diff=lfs merge=lfs -text
122
+ checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer.json filter=lfs diff=lfs merge=lfs -text
123
+ checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/run-8u6a9bbf.wandb filter=lfs diff=lfs merge=lfs -text
124
+ checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/run-f7zbl5g6.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/added_tokens.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|action_sep|>": 151670,
5
+ "<|arg_sep|>": 151671,
6
+ "<|box_end|>": 151649,
7
+ "<|box_start|>": 151648,
8
+ "<|call_sep|>": 151666,
9
+ "<|end_of_text|>": 151673,
10
+ "<|endoftext|>": 151643,
11
+ "<|exception_sep|>": 151669,
12
+ "<|file_sep|>": 151664,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|frame_sep|>": 151672,
18
+ "<|im_end|>": 151645,
19
+ "<|im_start|>": 151644,
20
+ "<|image_pad|>": 151655,
21
+ "<|latent_end|>": 151675,
22
+ "<|latent_start|>": 151674,
23
+ "<|line_sep|>": 151667,
24
+ "<|object_ref_end|>": 151647,
25
+ "<|object_ref_start|>": 151646,
26
+ "<|quad_end|>": 151651,
27
+ "<|quad_start|>": 151650,
28
+ "<|repo_name|>": 151663,
29
+ "<|return_sep|>": 151668,
30
+ "<|trace_context_start|>": 151665,
31
+ "<|video_pad|>": 151656,
32
+ "<|vision_end|>": 151653,
33
+ "<|vision_pad|>": 151654,
34
+ "<|vision_start|>": 151652
35
+ }
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/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 %}
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 2,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
54
+ "transformers_version": "4.57.6",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 151676
58
+ }
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643
4
+ ],
5
+ "max_new_tokens": 2048,
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "4.57.6"
8
+ }
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a60852ffe133303364862403563d33d286ad15a6aaa795590f35383ec6f9b1
3
+ size 3086668424
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a790d654474f5dfe225f889afd0210313eb1083f942671f2c4b8e95a1c922b
3
+ size 11424004
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer_config.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|trace_context_start|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|call_sep|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|line_sep|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<|return_sep|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<|exception_sep|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|action_sep|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|arg_sep|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<|frame_sep|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<|end_of_text|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<|latent_start|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|latent_end|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ }
269
+ },
270
+ "additional_special_tokens": [
271
+ "<|im_start|>",
272
+ "<|im_end|>",
273
+ "<|object_ref_start|>",
274
+ "<|object_ref_end|>",
275
+ "<|box_start|>",
276
+ "<|box_end|>",
277
+ "<|quad_start|>",
278
+ "<|quad_end|>",
279
+ "<|vision_start|>",
280
+ "<|vision_end|>",
281
+ "<|vision_pad|>",
282
+ "<|image_pad|>",
283
+ "<|video_pad|>"
284
+ ],
285
+ "bos_token": null,
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|endoftext|>",
288
+ "errors": "replace",
289
+ "extra_special_tokens": {},
290
+ "model_max_length": 32768,
291
+ "pad_token": "<|endoftext|>",
292
+ "split_special_tokens": false,
293
+ "tokenizer_class": "Qwen2Tokenizer",
294
+ "unk_token": null
295
+ }
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/sft1.5b_lr1e5_bs32/wandb/debug-internal.log ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-06-19T14:15:27.495513616+02:00","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-06-19T14:15:27.495530857+02:00","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
3
+ {"time":"2026-06-19T14:15:27.616112226+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
4
+ {"time":"2026-06-19T14:15:27.616134112+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
5
+ {"time":"2026-06-19T14:15:27.616150216+02:00","level":"INFO","msg":"stream: created new stream","id":"f7zbl5g6"}
6
+ {"time":"2026-06-19T14:15:27.616287718+02:00","level":"INFO","msg":"handler: started"}
7
+ {"time":"2026-06-19T14:15:27.618163388+02:00","level":"INFO","msg":"stream: started"}
8
+ {"time":"2026-06-19T14:15:27.618208304+02:00","level":"INFO","msg":"writer: started","stream_id":"f7zbl5g6"}
9
+ {"time":"2026-06-19T14:15:27.618225281+02:00","level":"INFO","msg":"sender: started"}
10
+ {"time":"2026-06-19T14:15:27.632535917+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
11
+ {"time":"2026-06-19T14:15:27.632547267+02:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
12
+ {"time":"2026-06-19T17:06:21.280675611+02:00","level":"INFO","msg":"stream: finishing up"}
13
+ {"time":"2026-06-19T17:06:21.281207168+02:00","level":"INFO","msg":"handler: closed"}
14
+ {"time":"2026-06-19T17:06:21.28217981+02:00","level":"INFO","msg":"sender: closed"}
15
+ {"time":"2026-06-19T17:06:21.282191245+02:00","level":"INFO","msg":"stream: all finished"}
checkpoints/sft1.5b_lr1e5_bs32/wandb/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-06-19 14:15:27,122 INFO MainThread:599607 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
2
+ 2026-06-19 14:15:27,122 INFO MainThread:599607 [wandb_setup.py:_flush():81] Configure stats pid to 599607
3
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_setup.py:_flush():81] Loading settings from environment variables
4
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log
5
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log
6
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:init():766] calling init triggers
7
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
8
+ config: {'model': 'model_weights/qwen2.5-coder-1.5b', 'output_dir': 'model_weights/sft-coder-1.5b', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'epochs': 4.0, 'lr': 2e-05, 'batch_size': 1, 'grad_accum': 8, 'max_steps': -1, 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/sft_train', '_wandb': {}}
9
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:init():814] starting backend
10
+ 2026-06-19 14:15:27,485 INFO MainThread:599607 [wandb_init.py:init():829] sending inform_init request
11
+ 2026-06-19 14:15:27,618 INFO MainThread:599607 [wandb_init.py:init():834] backend started and connected
12
+ 2026-06-19 14:15:27,620 INFO MainThread:599607 [wandb_init.py:init():904] updated telemetry
13
+ 2026-06-19 14:15:27,630 INFO MainThread:599607 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
14
+ 2026-06-19 14:15:27,633 INFO MainThread:599607 [wandb_init.py:init():972] starting run threads in backend
15
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_console_start():2523] atexit reg
16
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_redirect():2373] redirect: wrap_raw
17
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_redirect():2442] Wrapping output streams.
18
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_redirect():2465] Redirects installed.
19
+ 2026-06-19 14:15:27,928 INFO MainThread:599607 [wandb_init.py:init():1010] run started, returning control to user process
20
+ 2026-06-19 14:15:33,043 INFO MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb None None {'vocab_size': 151676, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'bfloat16', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 151643, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'model_weights/qwen2.5-coder-1.5b', 'transformers_version': '4.57.6', 'model_type': 'qwen2', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'model_weights/sft-coder-1.5b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/sft-coder-1.5b/runs/Jun19_14-15-27_alvis4-37', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
21
+ 2026-06-19 14:15:33,047 INFO MainThread:599607 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1543314944 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x145bcdaf6ad0>>
22
+ 2026-06-19 14:15:33,047 INFO MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1543314944 None
23
+ 2026-06-19 17:06:21,276 INFO wandb-AsyncioManager-main:599607 [service_client.py:_forward_responses():122] Reached EOF.
24
+ 2026-06-19 17:06:21,276 INFO wandb-AsyncioManager-main:599607 [mailbox.py:close():154] Closing mailbox, abandoning 0 handles.
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/files/requirements.txt ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wheel==0.47.0
2
+ triton==3.3.1
3
+ ptyprocess==0.7.0
4
+ pyzmq==27.1.0
5
+ nvidia-cublas-cu12==12.6.4.1
6
+ python-dateutil==2.9.0.post0
7
+ rfc3339-validator==0.1.4
8
+ pluggy==1.6.0
9
+ grpclib==0.4.9
10
+ attrs==26.1.0
11
+ urllib3==2.7.0
12
+ cffi==2.0.0
13
+ openai==1.86.0
14
+ async-lru==2.3.0
15
+ cfgv==3.5.0
16
+ httpcore==1.0.9
17
+ bitsandbytes==0.49.2
18
+ iniconfig==2.3.0
19
+ nvidia-cuda-runtime-cu12==12.6.77
20
+ jupyterlab_server==2.28.0
21
+ latex2sympy2_extended==1.11.0
22
+ jupyter-events==0.12.1
23
+ docker==7.1.0
24
+ ipywidgets==8.1.8
25
+ blinker==1.9.0
26
+ cbor2==6.1.2
27
+ nvidia-cufft-cu12==11.3.0.4
28
+ nvidia-cusolver-cu12==11.7.1.2
29
+ multiprocess==0.70.16
30
+ anyio==4.14.0
31
+ itsdangerous==2.2.0
32
+ widgetsnbextension==4.0.15
33
+ watchfiles==1.2.0
34
+ swebench==4.1.0
35
+ blobfile==3.2.0
36
+ jupyter==1.1.1
37
+ certifi==2026.6.17
38
+ argon2-cffi==25.1.0
39
+ argon2-cffi-bindings==25.1.0
40
+ overrides==7.7.0
41
+ propcache==0.5.2
42
+ ipython==8.33.0
43
+ nbconvert==7.17.1
44
+ rich==15.0.0
45
+ asttokens==3.0.1
46
+ tokenizers==0.22.2
47
+ synchronicity==0.12.4
48
+ tqdm==4.68.3
49
+ nvidia-nvjitlink-cu12==12.6.85
50
+ nvidia-nvtx-cu12==12.6.77
51
+ jsonschema-specifications==2025.9.1
52
+ jupyterlab==4.5.8
53
+ pure_eval==0.2.3
54
+ uri-template==1.3.0
55
+ sentry-sdk==2.63.0
56
+ pycryptodomex==3.23.0
57
+ yarl==1.24.2
58
+ h2==4.3.0
59
+ h11==0.16.0
60
+ requests==2.34.2
61
+ Jinja2==3.1.6
62
+ xformers==0.0.31.post1
63
+ rfc3987-syntax==1.1.0
64
+ antlr4-python3-runtime==4.11.0
65
+ nvidia-cusparselt-cu12==0.6.3
66
+ safetensors==0.8.0
67
+ notebook_shim==0.2.4
68
+ Pygments==2.20.0
69
+ python-json-logger==4.1.0
70
+ isoduration==20.11.0
71
+ smmap==5.0.3
72
+ click==8.3.3
73
+ transformers==4.57.6
74
+ aiohappyeyeballs==2.6.2
75
+ regex==2026.5.9
76
+ jsonpointer==3.1.1
77
+ fqdn==1.5.1
78
+ jupyter-lsp==2.3.1
79
+ rfc3986-validator==0.1.1
80
+ prometheus_client==0.25.0
81
+ mistune==3.2.1
82
+ sentencepiece==0.2.1
83
+ types-toml==0.10.8.20260518
84
+ wcwidth==0.8.1
85
+ identify==2.6.19
86
+ protobuf==6.33.6
87
+ datasets==3.6.0
88
+ accelerate==1.14.0
89
+ networkx==3.6.1
90
+ pydantic==2.13.4
91
+ multidict==6.7.1
92
+ chardet==7.4.3
93
+ pytest==9.1.0
94
+ babel==2.18.0
95
+ pip==26.1.2
96
+ dill==0.3.8
97
+ referencing==0.37.0
98
+ pre_commit==4.6.0
99
+ numpy==2.4.6
100
+ math-verify==0.9.0
101
+ traitlets==5.15.1
102
+ nvidia-curand-cu12==10.3.7.77
103
+ websocket-client==1.9.0
104
+ hf-xet==1.5.1
105
+ unidiff==0.7.5
106
+ nest-asyncio2==1.7.2
107
+ typing_extensions==4.15.0
108
+ platformdirs==4.10.0
109
+ torch==2.7.1
110
+ tblib==3.2.2
111
+ sqlfluff==4.2.2
112
+ modal==1.5.0
113
+ ipykernel==7.3.0
114
+ msgspec==0.21.1
115
+ virtualenv==21.5.1
116
+ json5==0.14.0
117
+ pathlib_abc==0.5.2
118
+ aiosignal==1.4.0
119
+ moodist==0.5.1
120
+ rpds-py==2026.5.1
121
+ webencodings==0.5.1
122
+ sniffio==1.3.1
123
+ annotated-types==0.7.0
124
+ python-discovery==1.4.2
125
+ scipy==1.17.1
126
+ GitPython==3.1.50
127
+ defusedxml==0.7.1
128
+ nvidia-cufile-cu12==1.11.1.6
129
+ nvidia-nccl-cu12==2.26.2
130
+ sympy==1.14.0
131
+ tinycss2==1.5.1
132
+ soupsieve==2.8.4
133
+ ninja==1.13.0
134
+ python-dotenv==1.2.2
135
+ ghapi==1.0.13
136
+ jupyter_server_terminals==0.5.4
137
+ markdown-it-py==4.2.0
138
+ nbclient==0.11.0
139
+ mpmath==1.3.0
140
+ frozenlist==1.8.0
141
+ Werkzeug==3.1.8
142
+ executing==2.2.1
143
+ gitdb==4.0.12
144
+ setuptools==82.0.1
145
+ Flask==3.1.1
146
+ MarkupSafe==3.0.3
147
+ notebook==7.5.7
148
+ jupyter_core==5.9.1
149
+ jedi==0.20.0
150
+ mdurl==0.1.2
151
+ lark==1.3.1
152
+ bleach==6.4.0
153
+ hpack==4.1.0
154
+ google-re2==1.1.20240702
155
+ beautifulsoup4==4.15.0
156
+ jsonschema==4.26.0
157
+ psutil==7.2.2
158
+ nvidia-cuda-nvrtc-cu12==12.6.77
159
+ narwhals==2.22.1
160
+ lxml==6.1.1
161
+ fastjsonschema==2.21.2
162
+ tornado==6.5.7
163
+ nodeenv==1.10.0
164
+ typing-inspection==0.4.2
165
+ httpx==0.28.1
166
+ distro==1.9.0
167
+ colorama==0.4.6
168
+ jupyter-console==6.6.3
169
+ jupyterlab_widgets==3.0.16
170
+ PyYAML==6.0.3
171
+ fsspec==2025.3.0
172
+ hyperframe==6.1.0
173
+ nvidia-cuda-cupti-cu12==12.6.80
174
+ charset-normalizer==3.4.7
175
+ wandb==0.27.2
176
+ nbformat==5.10.4
177
+ nvidia-cudnn-cu12==9.5.1.17
178
+ peft==0.19.1
179
+ pathspec==1.1.1
180
+ matplotlib-inline==0.2.2
181
+ huggingface_hub==0.36.2
182
+ pyarrow==24.0.0
183
+ nvidia-cusparse-cu12==12.5.4.2
184
+ cwm==0.0.1
185
+ prompt_toolkit==3.0.52
186
+ omegaconf==2.4.0.dev4
187
+ tiktoken==0.13.0
188
+ comm==0.2.3
189
+ threadpoolctl==3.6.0
190
+ pydantic_core==2.46.4
191
+ tenacity==9.1.4
192
+ parso==0.8.7
193
+ pandas==3.0.3
194
+ webcolors==25.10.0
195
+ idna==3.18
196
+ terminado==0.18.1
197
+ pandocfilters==1.5.1
198
+ aiohttp==3.14.1
199
+ arrow==1.4.0
200
+ packaging==26.2
201
+ tzdata==2026.2
202
+ distlib==0.4.3
203
+ Send2Trash==2.1.0
204
+ jupyterlab_pygments==0.3.0
205
+ decorator==5.3.1
206
+ jupyter_server==2.20.0
207
+ scikit-learn==1.9.0
208
+ six==1.17.0
209
+ diff_cover==10.3.0
210
+ pycparser==3.0
211
+ types-certifi==2021.10.8.3
212
+ toml==0.10.2
213
+ stack-data==0.6.3
214
+ fastcore==1.13.5
215
+ filelock==3.29.4
216
+ xxhash==3.7.0
217
+ pexpect==4.9.0
218
+ jupyter_client==8.9.1
219
+ jiter==0.15.0
220
+ debugpy==1.8.21
221
+ universal_pathlib==0.3.10
222
+ joblib==1.5.3
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-core.log ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {"time":"2026-06-19T13:52:53.756446026+02:00","level":"INFO","msg":"main: starting server","port-filename":"/local/tmp.6767576/tmpq69h57wa/port-5604.txt","pid":5604,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2026-06-19T13:52:53.756834913+02:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/local/tmp.6767576/wandb-5604-5808-4086320459/socket","Net":"unix"}}
3
+ {"time":"2026-06-19T13:52:53.756910259+02:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":5604}
4
+ {"time":"2026-06-19T13:52:53.937561818+02:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2026-06-19T13:52:53.951667135+02:00","level":"INFO","msg":"handleInformInit: received","streamId":"8u6a9bbf","id":"1(@)"}
6
+ {"time":"2026-06-19T13:52:54.084559321+02:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u6a9bbf","id":"1(@)"}
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-internal.log ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-06-19T13:52:53.954447401+02:00","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-06-19T13:52:53.954460021+02:00","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
3
+ {"time":"2026-06-19T13:52:54.076642955+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
4
+ {"time":"2026-06-19T13:52:54.076659633+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
5
+ {"time":"2026-06-19T13:52:54.07667716+02:00","level":"INFO","msg":"stream: created new stream","id":"8u6a9bbf"}
6
+ {"time":"2026-06-19T13:52:54.0767048+02:00","level":"INFO","msg":"handler: started"}
7
+ {"time":"2026-06-19T13:52:54.084549674+02:00","level":"INFO","msg":"stream: started"}
8
+ {"time":"2026-06-19T13:52:54.084679246+02:00","level":"INFO","msg":"writer: started","stream_id":"8u6a9bbf"}
9
+ {"time":"2026-06-19T13:52:54.084703599+02:00","level":"INFO","msg":"sender: started"}
10
+ {"time":"2026-06-19T13:52:54.093460106+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
11
+ {"time":"2026-06-19T13:52:54.09346915+02:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug.log ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
2
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_setup.py:_flush():81] Configure stats pid to 5604
3
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_setup.py:_flush():81] Loading settings from environment variables
4
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug.log
5
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-internal.log
6
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_init.py:init():766] calling init triggers
7
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
8
+ config: {'model': 'model_weights/qwen2.5-coder-1.5b', 'output_dir': 'model_weights/sft-coder-1.5b', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'epochs': 4.0, 'lr': 2e-05, 'batch_size': 2, 'grad_accum': 4, 'max_steps': -1, 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/sft_train', '_wandb': {}}
9
+ 2026-06-19 13:52:53,411 INFO MainThread:5604 [wandb_init.py:init():814] starting backend
10
+ 2026-06-19 13:52:53,937 INFO MainThread:5604 [wandb_init.py:init():829] sending inform_init request
11
+ 2026-06-19 13:52:54,085 INFO MainThread:5604 [wandb_init.py:init():834] backend started and connected
12
+ 2026-06-19 13:52:54,086 INFO MainThread:5604 [wandb_init.py:init():904] updated telemetry
13
+ 2026-06-19 13:52:54,092 INFO MainThread:5604 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
14
+ 2026-06-19 13:52:54,094 INFO MainThread:5604 [wandb_init.py:init():972] starting run threads in backend
15
+ 2026-06-19 13:52:54,689 INFO MainThread:5604 [wandb_run.py:_console_start():2523] atexit reg
16
+ 2026-06-19 13:52:54,690 INFO MainThread:5604 [wandb_run.py:_redirect():2373] redirect: wrap_raw
17
+ 2026-06-19 13:52:54,690 INFO MainThread:5604 [wandb_run.py:_redirect():2442] Wrapping output streams.
18
+ 2026-06-19 13:52:54,690 INFO MainThread:5604 [wandb_run.py:_redirect():2465] Redirects installed.
19
+ 2026-06-19 13:52:54,697 INFO MainThread:5604 [wandb_init.py:init():1010] run started, returning control to user process
20
+ 2026-06-19 13:53:00,144 INFO MainThread:5604 [wandb_run.py:_config_callback():1346] config_cb None None {'vocab_size': 151676, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'bfloat16', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151643, 'pad_token_id': None, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'model_weights/qwen2.5-coder-1.5b', 'transformers_version': '4.57.6', 'model_type': 'qwen2', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'model_weights/sft-coder-1.5b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/sft-coder-1.5b/runs/Jun19_13-52-54_alvis5-11', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
21
+ 2026-06-19 13:53:00,148 INFO MainThread:5604 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1543314944 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x149ca8701290>>
22
+ 2026-06-19 13:53:00,148 INFO MainThread:5604 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1543314944 None
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/run-8u6a9bbf.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be7899520edde22ffd32cd4b72c17ce18b0c6943d96c82e20e96b86766b7099
3
+ size 196608
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/files/requirements.txt ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wheel==0.47.0
2
+ triton==3.3.1
3
+ ptyprocess==0.7.0
4
+ pyzmq==27.1.0
5
+ nvidia-cublas-cu12==12.6.4.1
6
+ python-dateutil==2.9.0.post0
7
+ rfc3339-validator==0.1.4
8
+ pluggy==1.6.0
9
+ grpclib==0.4.9
10
+ attrs==26.1.0
11
+ urllib3==2.7.0
12
+ cffi==2.0.0
13
+ openai==1.86.0
14
+ async-lru==2.3.0
15
+ cfgv==3.5.0
16
+ httpcore==1.0.9
17
+ bitsandbytes==0.49.2
18
+ iniconfig==2.3.0
19
+ nvidia-cuda-runtime-cu12==12.6.77
20
+ jupyterlab_server==2.28.0
21
+ latex2sympy2_extended==1.11.0
22
+ jupyter-events==0.12.1
23
+ docker==7.1.0
24
+ ipywidgets==8.1.8
25
+ blinker==1.9.0
26
+ cbor2==6.1.2
27
+ nvidia-cufft-cu12==11.3.0.4
28
+ nvidia-cusolver-cu12==11.7.1.2
29
+ multiprocess==0.70.16
30
+ anyio==4.14.0
31
+ itsdangerous==2.2.0
32
+ widgetsnbextension==4.0.15
33
+ watchfiles==1.2.0
34
+ swebench==4.1.0
35
+ blobfile==3.2.0
36
+ jupyter==1.1.1
37
+ certifi==2026.6.17
38
+ argon2-cffi==25.1.0
39
+ argon2-cffi-bindings==25.1.0
40
+ overrides==7.7.0
41
+ propcache==0.5.2
42
+ ipython==8.33.0
43
+ nbconvert==7.17.1
44
+ rich==15.0.0
45
+ asttokens==3.0.1
46
+ tokenizers==0.22.2
47
+ synchronicity==0.12.4
48
+ tqdm==4.68.3
49
+ nvidia-nvjitlink-cu12==12.6.85
50
+ nvidia-nvtx-cu12==12.6.77
51
+ jsonschema-specifications==2025.9.1
52
+ jupyterlab==4.5.8
53
+ pure_eval==0.2.3
54
+ uri-template==1.3.0
55
+ sentry-sdk==2.63.0
56
+ pycryptodomex==3.23.0
57
+ yarl==1.24.2
58
+ h2==4.3.0
59
+ h11==0.16.0
60
+ requests==2.34.2
61
+ Jinja2==3.1.6
62
+ xformers==0.0.31.post1
63
+ rfc3987-syntax==1.1.0
64
+ antlr4-python3-runtime==4.11.0
65
+ nvidia-cusparselt-cu12==0.6.3
66
+ safetensors==0.8.0
67
+ notebook_shim==0.2.4
68
+ Pygments==2.20.0
69
+ python-json-logger==4.1.0
70
+ isoduration==20.11.0
71
+ smmap==5.0.3
72
+ click==8.3.3
73
+ transformers==4.57.6
74
+ aiohappyeyeballs==2.6.2
75
+ regex==2026.5.9
76
+ jsonpointer==3.1.1
77
+ fqdn==1.5.1
78
+ jupyter-lsp==2.3.1
79
+ rfc3986-validator==0.1.1
80
+ prometheus_client==0.25.0
81
+ mistune==3.2.1
82
+ sentencepiece==0.2.1
83
+ types-toml==0.10.8.20260518
84
+ wcwidth==0.8.1
85
+ identify==2.6.19
86
+ protobuf==6.33.6
87
+ datasets==3.6.0
88
+ accelerate==1.14.0
89
+ networkx==3.6.1
90
+ pydantic==2.13.4
91
+ multidict==6.7.1
92
+ chardet==7.4.3
93
+ pytest==9.1.0
94
+ babel==2.18.0
95
+ pip==26.1.2
96
+ dill==0.3.8
97
+ referencing==0.37.0
98
+ pre_commit==4.6.0
99
+ numpy==2.4.6
100
+ math-verify==0.9.0
101
+ traitlets==5.15.1
102
+ nvidia-curand-cu12==10.3.7.77
103
+ websocket-client==1.9.0
104
+ hf-xet==1.5.1
105
+ unidiff==0.7.5
106
+ nest-asyncio2==1.7.2
107
+ typing_extensions==4.15.0
108
+ platformdirs==4.10.0
109
+ torch==2.7.1
110
+ tblib==3.2.2
111
+ sqlfluff==4.2.2
112
+ modal==1.5.0
113
+ ipykernel==7.3.0
114
+ msgspec==0.21.1
115
+ virtualenv==21.5.1
116
+ json5==0.14.0
117
+ pathlib_abc==0.5.2
118
+ aiosignal==1.4.0
119
+ moodist==0.5.1
120
+ rpds-py==2026.5.1
121
+ webencodings==0.5.1
122
+ sniffio==1.3.1
123
+ annotated-types==0.7.0
124
+ python-discovery==1.4.2
125
+ scipy==1.17.1
126
+ GitPython==3.1.50
127
+ defusedxml==0.7.1
128
+ nvidia-cufile-cu12==1.11.1.6
129
+ nvidia-nccl-cu12==2.26.2
130
+ sympy==1.14.0
131
+ tinycss2==1.5.1
132
+ soupsieve==2.8.4
133
+ ninja==1.13.0
134
+ python-dotenv==1.2.2
135
+ ghapi==1.0.13
136
+ jupyter_server_terminals==0.5.4
137
+ markdown-it-py==4.2.0
138
+ nbclient==0.11.0
139
+ mpmath==1.3.0
140
+ frozenlist==1.8.0
141
+ Werkzeug==3.1.8
142
+ executing==2.2.1
143
+ gitdb==4.0.12
144
+ setuptools==82.0.1
145
+ Flask==3.1.1
146
+ MarkupSafe==3.0.3
147
+ notebook==7.5.7
148
+ jupyter_core==5.9.1
149
+ jedi==0.20.0
150
+ mdurl==0.1.2
151
+ lark==1.3.1
152
+ bleach==6.4.0
153
+ hpack==4.1.0
154
+ google-re2==1.1.20240702
155
+ beautifulsoup4==4.15.0
156
+ jsonschema==4.26.0
157
+ psutil==7.2.2
158
+ nvidia-cuda-nvrtc-cu12==12.6.77
159
+ narwhals==2.22.1
160
+ lxml==6.1.1
161
+ fastjsonschema==2.21.2
162
+ tornado==6.5.7
163
+ nodeenv==1.10.0
164
+ typing-inspection==0.4.2
165
+ httpx==0.28.1
166
+ distro==1.9.0
167
+ colorama==0.4.6
168
+ jupyter-console==6.6.3
169
+ jupyterlab_widgets==3.0.16
170
+ PyYAML==6.0.3
171
+ fsspec==2025.3.0
172
+ hyperframe==6.1.0
173
+ nvidia-cuda-cupti-cu12==12.6.80
174
+ charset-normalizer==3.4.7
175
+ wandb==0.27.2
176
+ nbformat==5.10.4
177
+ nvidia-cudnn-cu12==9.5.1.17
178
+ peft==0.19.1
179
+ pathspec==1.1.1
180
+ matplotlib-inline==0.2.2
181
+ huggingface_hub==0.36.2
182
+ pyarrow==24.0.0
183
+ nvidia-cusparse-cu12==12.5.4.2
184
+ cwm==0.0.1
185
+ prompt_toolkit==3.0.52
186
+ omegaconf==2.4.0.dev4
187
+ tiktoken==0.13.0
188
+ comm==0.2.3
189
+ threadpoolctl==3.6.0
190
+ pydantic_core==2.46.4
191
+ tenacity==9.1.4
192
+ parso==0.8.7
193
+ pandas==3.0.3
194
+ webcolors==25.10.0
195
+ idna==3.18
196
+ terminado==0.18.1
197
+ pandocfilters==1.5.1
198
+ aiohttp==3.14.1
199
+ arrow==1.4.0
200
+ packaging==26.2
201
+ tzdata==2026.2
202
+ distlib==0.4.3
203
+ Send2Trash==2.1.0
204
+ jupyterlab_pygments==0.3.0
205
+ decorator==5.3.1
206
+ jupyter_server==2.20.0
207
+ scikit-learn==1.9.0
208
+ six==1.17.0
209
+ diff_cover==10.3.0
210
+ pycparser==3.0
211
+ types-certifi==2021.10.8.3
212
+ toml==0.10.2
213
+ stack-data==0.6.3
214
+ fastcore==1.13.5
215
+ filelock==3.29.4
216
+ xxhash==3.7.0
217
+ pexpect==4.9.0
218
+ jupyter_client==8.9.1
219
+ jiter==0.15.0
220
+ debugpy==1.8.21
221
+ universal_pathlib==0.3.10
222
+ joblib==1.5.3
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-core.log ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-06-19T14:15:27.301398896+02:00","level":"INFO","msg":"main: starting server","port-filename":"/local/tmp.6767617/tmpgyti6bop/port-599607.txt","pid":599607,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2026-06-19T14:15:27.302028933+02:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":599607}
3
+ {"time":"2026-06-19T14:15:27.301999053+02:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/local/tmp.6767617/wandb-599607-599718-3625508308/socket","Net":"unix"}}
4
+ {"time":"2026-06-19T14:15:27.485481018+02:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2026-06-19T14:15:27.49441811+02:00","level":"INFO","msg":"handleInformInit: received","streamId":"f7zbl5g6","id":"1(@)"}
6
+ {"time":"2026-06-19T14:15:27.618170162+02:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"f7zbl5g6","id":"1(@)"}
7
+ {"time":"2026-06-19T17:06:21.276182437+02:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
8
+ {"time":"2026-06-19T17:06:21.28047003+02:00","level":"INFO","msg":"server is shutting down"}
9
+ {"time":"2026-06-19T17:06:21.280507216+02:00","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
10
+ {"time":"2026-06-19T17:06:21.280596484+02:00","level":"INFO","msg":"server: listener closed","addr":{"Name":"/local/tmp.6767617/wandb-599607-599718-3625508308/socket","Net":"unix"}}
11
+ {"time":"2026-06-19T17:06:21.280545814+02:00","level":"INFO","msg":"connection: closing","id":"1(@)"}
12
+ {"time":"2026-06-19T17:06:21.281790311+02:00","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
13
+ {"time":"2026-06-19T17:06:21.282648474+02:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
14
+ {"time":"2026-06-19T17:06:21.282654653+02:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
15
+ {"time":"2026-06-19T17:06:21.282659444+02:00","level":"INFO","msg":"server is closed"}
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-06-19T14:15:27.495513616+02:00","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-06-19T14:15:27.495530857+02:00","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
3
+ {"time":"2026-06-19T14:15:27.616112226+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
4
+ {"time":"2026-06-19T14:15:27.616134112+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
5
+ {"time":"2026-06-19T14:15:27.616150216+02:00","level":"INFO","msg":"stream: created new stream","id":"f7zbl5g6"}
6
+ {"time":"2026-06-19T14:15:27.616287718+02:00","level":"INFO","msg":"handler: started"}
7
+ {"time":"2026-06-19T14:15:27.618163388+02:00","level":"INFO","msg":"stream: started"}
8
+ {"time":"2026-06-19T14:15:27.618208304+02:00","level":"INFO","msg":"writer: started","stream_id":"f7zbl5g6"}
9
+ {"time":"2026-06-19T14:15:27.618225281+02:00","level":"INFO","msg":"sender: started"}
10
+ {"time":"2026-06-19T14:15:27.632535917+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
11
+ {"time":"2026-06-19T14:15:27.632547267+02:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
12
+ {"time":"2026-06-19T17:06:21.280675611+02:00","level":"INFO","msg":"stream: finishing up"}
13
+ {"time":"2026-06-19T17:06:21.281207168+02:00","level":"INFO","msg":"handler: closed"}
14
+ {"time":"2026-06-19T17:06:21.28217981+02:00","level":"INFO","msg":"sender: closed"}
15
+ {"time":"2026-06-19T17:06:21.282191245+02:00","level":"INFO","msg":"stream: all finished"}
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-06-19 14:15:27,122 INFO MainThread:599607 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
2
+ 2026-06-19 14:15:27,122 INFO MainThread:599607 [wandb_setup.py:_flush():81] Configure stats pid to 599607
3
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_setup.py:_flush():81] Loading settings from environment variables
4
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log
5
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log
6
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:init():766] calling init triggers
7
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
8
+ config: {'model': 'model_weights/qwen2.5-coder-1.5b', 'output_dir': 'model_weights/sft-coder-1.5b', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'epochs': 4.0, 'lr': 2e-05, 'batch_size': 1, 'grad_accum': 8, 'max_steps': -1, 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/sft_train', '_wandb': {}}
9
+ 2026-06-19 14:15:27,123 INFO MainThread:599607 [wandb_init.py:init():814] starting backend
10
+ 2026-06-19 14:15:27,485 INFO MainThread:599607 [wandb_init.py:init():829] sending inform_init request
11
+ 2026-06-19 14:15:27,618 INFO MainThread:599607 [wandb_init.py:init():834] backend started and connected
12
+ 2026-06-19 14:15:27,620 INFO MainThread:599607 [wandb_init.py:init():904] updated telemetry
13
+ 2026-06-19 14:15:27,630 INFO MainThread:599607 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
14
+ 2026-06-19 14:15:27,633 INFO MainThread:599607 [wandb_init.py:init():972] starting run threads in backend
15
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_console_start():2523] atexit reg
16
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_redirect():2373] redirect: wrap_raw
17
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_redirect():2442] Wrapping output streams.
18
+ 2026-06-19 14:15:27,924 INFO MainThread:599607 [wandb_run.py:_redirect():2465] Redirects installed.
19
+ 2026-06-19 14:15:27,928 INFO MainThread:599607 [wandb_init.py:init():1010] run started, returning control to user process
20
+ 2026-06-19 14:15:33,043 INFO MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb None None {'vocab_size': 151676, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'bfloat16', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 151643, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'model_weights/qwen2.5-coder-1.5b', 'transformers_version': '4.57.6', 'model_type': 'qwen2', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'model_weights/sft-coder-1.5b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/sft-coder-1.5b/runs/Jun19_14-15-27_alvis4-37', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
21
+ 2026-06-19 14:15:33,047 INFO MainThread:599607 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1543314944 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x145bcdaf6ad0>>
22
+ 2026-06-19 14:15:33,047 INFO MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1543314944 None
23
+ 2026-06-19 17:06:21,276 INFO wandb-AsyncioManager-main:599607 [service_client.py:_forward_responses():122] Reached EOF.
24
+ 2026-06-19 17:06:21,276 INFO wandb-AsyncioManager-main:599607 [mailbox.py:close():154] Closing mailbox, abandoning 0 handles.
checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/run-f7zbl5g6.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b29b895bc295fe58e4fb463eb712323f657e88d5e5fe462466c7c703fc01c0
3
+ size 3637022