Hugging Face's logo

InosLihka
/
rhythm-env-meta-trained-sft-v3

Safetensors
qwen2
Model card Files
xet
 Community
InosLihka commited on
Commit
fbbaa22
·
verified ·
1 Parent(s): 367732c

SFT prime (1 epochs, lora r=16) on teacher trajectories

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +25 -0
  3. chat_template.jinja +54 -0
  4. config.json +67 -0
  5. log_history.json +746 -0
  6. merges.txt +0 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +441 -0
  10. special_tokens_map.json +25 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +217 -0
  13. training_config.json +18 -0
  14. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
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 %}
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "torch_dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
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
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 70,
52
+ "model_type": "qwen2",
53
+ "num_attention_heads": 16,
54
+ "num_hidden_layers": 36,
55
+ "num_key_value_heads": 2,
56
+ "pad_token_id": 151665,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "tie_word_embeddings": true,
62
+ "unsloth_fixed": true,
63
+ "unsloth_version": "2026.4.8",
64
+ "use_cache": true,
65
+ "use_sliding_window": false,
66
+ "vocab_size": 151936
67
+ }
log_history.json ADDED
@@ -0,0 +1,746 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "loss": 2.7697,
4
+ "grad_norm": 7.279645919799805,
5
+ "learning_rate": 1.509433962264151e-05,
6
+ "epoch": 0.009523809523809525,
7
+ "step": 5
8
+ },
9
+ {
10
+ "loss": 2.5772,
11
+ "grad_norm": 1.807359218597412,
12
+ "learning_rate": 3.39622641509434e-05,
13
+ "epoch": 0.01904761904761905,
14
+ "step": 10
15
+ },
16
+ {
17
+ "loss": 2.2646,
18
+ "grad_norm": 1.2268898487091064,
19
+ "learning_rate": 5.283018867924528e-05,
20
+ "epoch": 0.02857142857142857,
21
+ "step": 15
22
+ },
23
+ {
24
+ "loss": 1.9745,
25
+ "grad_norm": 1.018839716911316,
26
+ "learning_rate": 7.169811320754717e-05,
27
+ "epoch": 0.0380952380952381,
28
+ "step": 20
29
+ },
30
+ {
31
+ "loss": 1.6092,
32
+ "grad_norm": 1.1218492984771729,
33
+ "learning_rate": 9.056603773584906e-05,
34
+ "epoch": 0.047619047619047616,
35
+ "step": 25
36
+ },
37
+ {
38
+ "loss": 1.1149,
39
+ "grad_norm": 1.1705206632614136,
40
+ "learning_rate": 0.00010943396226415095,
41
+ "epoch": 0.05714285714285714,
42
+ "step": 30
43
+ },
44
+ {
45
+ "loss": 0.6096,
46
+ "grad_norm": 0.9281210899353027,
47
+ "learning_rate": 0.00012830188679245283,
48
+ "epoch": 0.06666666666666667,
49
+ "step": 35
50
+ },
51
+ {
52
+ "loss": 0.2073,
53
+ "grad_norm": 0.9404050707817078,
54
+ "learning_rate": 0.00014716981132075472,
55
+ "epoch": 0.0761904761904762,
56
+ "step": 40
57
+ },
58
+ {
59
+ "loss": 0.1915,
60
+ "grad_norm": 0.3621023893356323,
61
+ "learning_rate": 0.0001660377358490566,
62
+ "epoch": 0.08571428571428572,
63
+ "step": 45
64
+ },
65
+ {
66
+ "loss": 0.1476,
67
+ "grad_norm": 1.6463737487792969,
68
+ "learning_rate": 0.0001849056603773585,
69
+ "epoch": 0.09523809523809523,
70
+ "step": 50
71
+ },
72
+ {
73
+ "loss": 0.154,
74
+ "grad_norm": 0.15190088748931885,
75
+ "learning_rate": 0.00019999778494686225,
76
+ "epoch": 0.10476190476190476,
77
+ "step": 55
78
+ },
79
+ {
80
+ "loss": 0.1581,
81
+ "grad_norm": 0.1570507138967514,
82
+ "learning_rate": 0.00019992026839012067,
83
+ "epoch": 0.11428571428571428,
84
+ "step": 60
85
+ },
86
+ {
87
+ "loss": 0.1347,
88
+ "grad_norm": 0.15411140024662018,
89
+ "learning_rate": 0.00019973209728616032,
90
+ "epoch": 0.12380952380952381,
91
+ "step": 65
92
+ },
93
+ {
94
+ "loss": 0.1207,
95
+ "grad_norm": 0.1322922706604004,
96
+ "learning_rate": 0.00019943348002101371,
97
+ "epoch": 0.13333333333333333,
98
+ "step": 70
99
+ },
100
+ {
101
+ "loss": 0.1327,
102
+ "grad_norm": 0.22812587022781372,
103
+ "learning_rate": 0.00019902474729193386,
104
+ "epoch": 0.14285714285714285,
105
+ "step": 75
106
+ },
107
+ {
108
+ "loss": 0.1185,
109
+ "grad_norm": 0.156998872756958,
110
+ "learning_rate": 0.00019850635174117033,
111
+ "epoch": 0.1523809523809524,
112
+ "step": 80
113
+ },
114
+ {
115
+ "loss": 0.1122,
116
+ "grad_norm": 0.1560523957014084,
117
+ "learning_rate": 0.00019787886745470065,
118
+ "epoch": 0.1619047619047619,
119
+ "step": 85
120
+ },
121
+ {
122
+ "loss": 0.0999,
123
+ "grad_norm": 0.15414170920848846,
124
+ "learning_rate": 0.00019714298932647098,
125
+ "epoch": 0.17142857142857143,
126
+ "step": 90
127
+ },
128
+ {
129
+ "loss": 0.1028,
130
+ "grad_norm": 0.15751913189888,
131
+ "learning_rate": 0.00019629953228885098,
132
+ "epoch": 0.18095238095238095,
133
+ "step": 95
134
+ },
135
+ {
136
+ "loss": 0.107,
137
+ "grad_norm": 0.14652347564697266,
138
+ "learning_rate": 0.00019534943041015423,
139
+ "epoch": 0.19047619047619047,
140
+ "step": 100
141
+ },
142
+ {
143
+ "loss": 0.1006,
144
+ "grad_norm": 0.10832861065864563,
145
+ "learning_rate": 0.00019429373586022473,
146
+ "epoch": 0.2,
147
+ "step": 105
148
+ },
149
+ {
150
+ "loss": 0.1048,
151
+ "grad_norm": 0.17300932109355927,
152
+ "learning_rate": 0.00019313361774523385,
153
+ "epoch": 0.20952380952380953,
154
+ "step": 110
155
+ },
156
+ {
157
+ "loss": 0.1051,
158
+ "grad_norm": 0.11996150761842728,
159
+ "learning_rate": 0.00019187036081297907,
160
+ "epoch": 0.21904761904761905,
161
+ "step": 115
162
+ },
163
+ {
164
+ "loss": 0.1032,
165
+ "grad_norm": 0.1251075565814972,
166
+ "learning_rate": 0.0001905053640301176,
167
+ "epoch": 0.22857142857142856,
168
+ "step": 120
169
+ },
170
+ {
171
+ "loss": 0.1096,
172
+ "grad_norm": 0.1742381453514099,
173
+ "learning_rate": 0.000189040139032911,
174
+ "epoch": 0.23809523809523808,
175
+ "step": 125
176
+ },
177
+ {
178
+ "loss": 0.0948,
179
+ "grad_norm": 0.124235600233078,
180
+ "learning_rate": 0.00018747630845319612,
181
+ "epoch": 0.24761904761904763,
182
+ "step": 130
183
+ },
184
+ {
185
+ "loss": 0.1104,
186
+ "grad_norm": 0.15166880190372467,
187
+ "learning_rate": 0.00018581560412143661,
188
+ "epoch": 0.2571428571428571,
189
+ "step": 135
190
+ },
191
+ {
192
+ "loss": 0.1017,
193
+ "grad_norm": 0.14957353472709656,
194
+ "learning_rate": 0.00018405986514884434,
195
+ "epoch": 0.26666666666666666,
196
+ "step": 140
197
+ },
198
+ {
199
+ "loss": 0.0916,
200
+ "grad_norm": 0.13693228363990784,
201
+ "learning_rate": 0.00018221103589069552,
202
+ "epoch": 0.2761904761904762,
203
+ "step": 145
204
+ },
205
+ {
206
+ "loss": 0.1033,
207
+ "grad_norm": 0.1428951919078827,
208
+ "learning_rate": 0.00018027116379309638,
209
+ "epoch": 0.2857142857142857,
210
+ "step": 150
211
+ },
212
+ {
213
+ "loss": 0.0947,
214
+ "grad_norm": 0.1005215048789978,
215
+ "learning_rate": 0.00017824239712558302,
216
+ "epoch": 0.29523809523809524,
217
+ "step": 155
218
+ },
219
+ {
220
+ "loss": 0.093,
221
+ "grad_norm": 0.10682923346757889,
222
+ "learning_rate": 0.00017612698260206666,
223
+ "epoch": 0.3047619047619048,
224
+ "step": 160
225
+ },
226
+ {
227
+ "loss": 0.0914,
228
+ "grad_norm": 0.13625311851501465,
229
+ "learning_rate": 0.0001739272628927588,
230
+ "epoch": 0.3142857142857143,
231
+ "step": 165
232
+ },
233
+ {
234
+ "loss": 0.0963,
235
+ "grad_norm": 0.14139626920223236,
236
+ "learning_rate": 0.00017164567402983152,
237
+ "epoch": 0.3238095238095238,
238
+ "step": 170
239
+ },
240
+ {
241
+ "loss": 0.0956,
242
+ "grad_norm": 0.10277366638183594,
243
+ "learning_rate": 0.0001692847427096862,
244
+ "epoch": 0.3333333333333333,
245
+ "step": 175
246
+ },
247
+ {
248
+ "loss": 0.0867,
249
+ "grad_norm": 0.10309327393770218,
250
+ "learning_rate": 0.00016684708349481804,
251
+ "epoch": 0.34285714285714286,
252
+ "step": 180
253
+ },
254
+ {
255
+ "loss": 0.0889,
256
+ "grad_norm": 0.12323077768087387,
257
+ "learning_rate": 0.00016433539591837525,
258
+ "epoch": 0.3523809523809524,
259
+ "step": 185
260
+ },
261
+ {
262
+ "loss": 0.0819,
263
+ "grad_norm": 0.10132793337106705,
264
+ "learning_rate": 0.0001617524614946192,
265
+ "epoch": 0.3619047619047619,
266
+ "step": 190
267
+ },
268
+ {
269
+ "loss": 0.0886,
270
+ "grad_norm": 0.10710165649652481,
271
+ "learning_rate": 0.0001591011406385964,
272
+ "epoch": 0.37142857142857144,
273
+ "step": 195
274
+ },
275
+ {
276
+ "loss": 0.0906,
277
+ "grad_norm": 0.11556152999401093,
278
+ "learning_rate": 0.0001563843694984336,
279
+ "epoch": 0.38095238095238093,
280
+ "step": 200
281
+ },
282
+ {
283
+ "loss": 0.0857,
284
+ "grad_norm": 0.09526285529136658,
285
+ "learning_rate": 0.00015360515670376375,
286
+ "epoch": 0.3904761904761905,
287
+ "step": 205
288
+ },
289
+ {
290
+ "loss": 0.0951,
291
+ "grad_norm": 0.13382859528064728,
292
+ "learning_rate": 0.000150766580033884,
293
+ "epoch": 0.4,
294
+ "step": 210
295
+ },
296
+ {
297
+ "loss": 0.1005,
298
+ "grad_norm": 0.14066950976848602,
299
+ "learning_rate": 0.00014787178300933542,
300
+ "epoch": 0.4095238095238095,
301
+ "step": 215
302
+ },
303
+ {
304
+ "loss": 0.0953,
305
+ "grad_norm": 0.10573799908161163,
306
+ "learning_rate": 0.00014492397141067887,
307
+ "epoch": 0.41904761904761906,
308
+ "step": 220
309
+ },
310
+ {
311
+ "loss": 0.0907,
312
+ "grad_norm": 0.10648736357688904,
313
+ "learning_rate": 0.0001419264097283225,
314
+ "epoch": 0.42857142857142855,
315
+ "step": 225
316
+ },
317
+ {
318
+ "loss": 0.0861,
319
+ "grad_norm": 0.13983477652072906,
320
+ "learning_rate": 0.00013888241754733208,
321
+ "epoch": 0.4380952380952381,
322
+ "step": 230
323
+ },
324
+ {
325
+ "loss": 0.0886,
326
+ "grad_norm": 0.11220896244049072,
327
+ "learning_rate": 0.00013579536587122828,
328
+ "epoch": 0.44761904761904764,
329
+ "step": 235
330
+ },
331
+ {
332
+ "loss": 0.0873,
333
+ "grad_norm": 0.15578190982341766,
334
+ "learning_rate": 0.0001326686733888413,
335
+ "epoch": 0.45714285714285713,
336
+ "step": 240
337
+ },
338
+ {
339
+ "loss": 0.0853,
340
+ "grad_norm": 0.10592073202133179,
341
+ "learning_rate": 0.00012950580268835784,
342
+ "epoch": 0.4666666666666667,
343
+ "step": 245
344
+ },
345
+ {
346
+ "loss": 0.0863,
347
+ "grad_norm": 0.11012069135904312,
348
+ "learning_rate": 0.00012631025642275212,
349
+ "epoch": 0.47619047619047616,
350
+ "step": 250
351
+ },
352
+ {
353
+ "loss": 0.0908,
354
+ "grad_norm": 0.1341278851032257,
355
+ "learning_rate": 0.0001230855734308488,
356
+ "epoch": 0.4857142857142857,
357
+ "step": 255
358
+ },
359
+ {
360
+ "loss": 0.0925,
361
+ "grad_norm": 0.10531295835971832,
362
+ "learning_rate": 0.0001198353248183118,
363
+ "epoch": 0.49523809523809526,
364
+ "step": 260
365
+ },
366
+ {
367
+ "loss": 0.0894,
368
+ "grad_norm": 0.12019002437591553,
369
+ "learning_rate": 0.0001165631100029005,
370
+ "epoch": 0.5047619047619047,
371
+ "step": 265
372
+ },
373
+ {
374
+ "loss": 0.0815,
375
+ "grad_norm": 0.11585652828216553,
376
+ "learning_rate": 0.00011327255272837221,
377
+ "epoch": 0.5142857142857142,
378
+ "step": 270
379
+ },
380
+ {
381
+ "loss": 0.087,
382
+ "grad_norm": 0.11940790712833405,
383
+ "learning_rate": 0.0001099672970514451,
384
+ "epoch": 0.5238095238095238,
385
+ "step": 275
386
+ },
387
+ {
388
+ "loss": 0.0817,
389
+ "grad_norm": 0.0971325933933258,
390
+ "learning_rate": 0.00010665100330626625,
391
+ "epoch": 0.5333333333333333,
392
+ "step": 280
393
+ },
394
+ {
395
+ "loss": 0.0937,
396
+ "grad_norm": 0.12433666735887527,
397
+ "learning_rate": 0.00010332734405085342,
398
+ "epoch": 0.5428571428571428,
399
+ "step": 285
400
+ },
401
+ {
402
+ "loss": 0.0912,
403
+ "grad_norm": 0.1293099820613861,
404
+ "learning_rate": 0.0001,
405
+ "epoch": 0.5523809523809524,
406
+ "step": 290
407
+ },
408
+ {
409
+ "loss": 0.0847,
410
+ "grad_norm": 0.11300069838762283,
411
+ "learning_rate": 9.667265594914662e-05,
412
+ "epoch": 0.5619047619047619,
413
+ "step": 295
414
+ },
415
+ {
416
+ "loss": 0.0879,
417
+ "grad_norm": 0.10722248256206512,
418
+ "learning_rate": 9.334899669373379e-05,
419
+ "epoch": 0.5714285714285714,
420
+ "step": 300
421
+ },
422
+ {
423
+ "loss": 0.0883,
424
+ "grad_norm": 0.12601728737354279,
425
+ "learning_rate": 9.003270294855491e-05,
426
+ "epoch": 0.580952380952381,
427
+ "step": 305
428
+ },
429
+ {
430
+ "loss": 0.0839,
431
+ "grad_norm": 0.10425635427236557,
432
+ "learning_rate": 8.672744727162781e-05,
433
+ "epoch": 0.5904761904761905,
434
+ "step": 310
435
+ },
436
+ {
437
+ "loss": 0.0835,
438
+ "grad_norm": 0.09301692992448807,
439
+ "learning_rate": 8.343688999709952e-05,
440
+ "epoch": 0.6,
441
+ "step": 315
442
+ },
443
+ {
444
+ "loss": 0.0879,
445
+ "grad_norm": 0.12155309319496155,
446
+ "learning_rate": 8.016467518168821e-05,
447
+ "epoch": 0.6095238095238096,
448
+ "step": 320
449
+ },
450
+ {
451
+ "loss": 0.0828,
452
+ "grad_norm": 0.11660365760326385,
453
+ "learning_rate": 7.69144265691512e-05,
454
+ "epoch": 0.6190476190476191,
455
+ "step": 325
456
+ },
457
+ {
458
+ "loss": 0.0818,
459
+ "grad_norm": 0.10756074637174606,
460
+ "learning_rate": 7.368974357724789e-05,
461
+ "epoch": 0.6285714285714286,
462
+ "step": 330
463
+ },
464
+ {
465
+ "loss": 0.0829,
466
+ "grad_norm": 0.08034606277942657,
467
+ "learning_rate": 7.049419731164221e-05,
468
+ "epoch": 0.638095238095238,
469
+ "step": 335
470
+ },
471
+ {
472
+ "loss": 0.08,
473
+ "grad_norm": 0.08222140371799469,
474
+ "learning_rate": 6.73313266111587e-05,
475
+ "epoch": 0.6476190476190476,
476
+ "step": 340
477
+ },
478
+ {
479
+ "loss": 0.0781,
480
+ "grad_norm": 0.10555204749107361,
481
+ "learning_rate": 6.420463412877176e-05,
482
+ "epoch": 0.6571428571428571,
483
+ "step": 345
484
+ },
485
+ {
486
+ "loss": 0.0849,
487
+ "grad_norm": 0.12122602015733719,
488
+ "learning_rate": 6.111758245266794e-05,
489
+ "epoch": 0.6666666666666666,
490
+ "step": 350
491
+ },
492
+ {
493
+ "loss": 0.0774,
494
+ "grad_norm": 0.09954749792814255,
495
+ "learning_rate": 5.8073590271677536e-05,
496
+ "epoch": 0.6761904761904762,
497
+ "step": 355
498
+ },
499
+ {
500
+ "loss": 0.0855,
501
+ "grad_norm": 0.07693193107843399,
502
+ "learning_rate": 5.507602858932113e-05,
503
+ "epoch": 0.6857142857142857,
504
+ "step": 360
505
+ },
506
+ {
507
+ "loss": 0.0818,
508
+ "grad_norm": 0.1110081821680069,
509
+ "learning_rate": 5.212821699066459e-05,
510
+ "epoch": 0.6952380952380952,
511
+ "step": 365
512
+ },
513
+ {
514
+ "loss": 0.0885,
515
+ "grad_norm": 0.1375397890806198,
516
+ "learning_rate": 4.9233419966116036e-05,
517
+ "epoch": 0.7047619047619048,
518
+ "step": 370
519
+ },
520
+ {
521
+ "loss": 0.0846,
522
+ "grad_norm": 0.09295593947172165,
523
+ "learning_rate": 4.639484329623627e-05,
524
+ "epoch": 0.7142857142857143,
525
+ "step": 375
526
+ },
527
+ {
528
+ "loss": 0.0857,
529
+ "grad_norm": 0.10374521464109421,
530
+ "learning_rate": 4.3615630501566384e-05,
531
+ "epoch": 0.7238095238095238,
532
+ "step": 380
533
+ },
534
+ {
535
+ "loss": 0.0847,
536
+ "grad_norm": 0.12862949073314667,
537
+ "learning_rate": 4.08988593614036e-05,
538
+ "epoch": 0.7333333333333333,
539
+ "step": 385
540
+ },
541
+ {
542
+ "loss": 0.0824,
543
+ "grad_norm": 0.11119960248470306,
544
+ "learning_rate": 3.824753850538082e-05,
545
+ "epoch": 0.7428571428571429,
546
+ "step": 390
547
+ },
548
+ {
549
+ "loss": 0.0775,
550
+ "grad_norm": 0.10405857861042023,
551
+ "learning_rate": 3.5664604081624786e-05,
552
+ "epoch": 0.7523809523809524,
553
+ "step": 395
554
+ },
555
+ {
556
+ "loss": 0.0921,
557
+ "grad_norm": 0.13198421895503998,
558
+ "learning_rate": 3.315291650518197e-05,
559
+ "epoch": 0.7619047619047619,
560
+ "step": 400
561
+ },
562
+ {
563
+ "loss": 0.088,
564
+ "grad_norm": 0.13305306434631348,
565
+ "learning_rate": 3.071525729031384e-05,
566
+ "epoch": 0.7714285714285715,
567
+ "step": 405
568
+ },
569
+ {
570
+ "loss": 0.0783,
571
+ "grad_norm": 0.09370700269937515,
572
+ "learning_rate": 2.8354325970168484e-05,
573
+ "epoch": 0.780952380952381,
574
+ "step": 410
575
+ },
576
+ {
577
+ "loss": 0.0818,
578
+ "grad_norm": 0.10824982076883316,
579
+ "learning_rate": 2.6072737107241208e-05,
580
+ "epoch": 0.7904761904761904,
581
+ "step": 415
582
+ },
583
+ {
584
+ "loss": 0.0768,
585
+ "grad_norm": 0.11371118575334549,
586
+ "learning_rate": 2.3873017397933327e-05,
587
+ "epoch": 0.8,
588
+ "step": 420
589
+ },
590
+ {
591
+ "loss": 0.0779,
592
+ "grad_norm": 0.11898576468229294,
593
+ "learning_rate": 2.1757602874416993e-05,
594
+ "epoch": 0.8095238095238095,
595
+ "step": 425
596
+ },
597
+ {
598
+ "loss": 0.0816,
599
+ "grad_norm": 0.1358272135257721,
600
+ "learning_rate": 1.9728836206903656e-05,
601
+ "epoch": 0.819047619047619,
602
+ "step": 430
603
+ },
604
+ {
605
+ "loss": 0.0843,
606
+ "grad_norm": 0.09827127307653427,
607
+ "learning_rate": 1.7788964109304496e-05,
608
+ "epoch": 0.8285714285714286,
609
+ "step": 435
610
+ },
611
+ {
612
+ "loss": 0.0805,
613
+ "grad_norm": 0.11106231063604355,
614
+ "learning_rate": 1.5940134851155697e-05,
615
+ "epoch": 0.8380952380952381,
616
+ "step": 440
617
+ },
618
+ {
619
+ "loss": 0.0808,
620
+ "grad_norm": 0.11239837855100632,
621
+ "learning_rate": 1.4184395878563395e-05,
622
+ "epoch": 0.8476190476190476,
623
+ "step": 445
624
+ },
625
+ {
626
+ "loss": 0.0782,
627
+ "grad_norm": 0.11788029968738556,
628
+ "learning_rate": 1.2523691546803873e-05,
629
+ "epoch": 0.8571428571428571,
630
+ "step": 450
631
+ },
632
+ {
633
+ "loss": 0.0837,
634
+ "grad_norm": 0.14655092358589172,
635
+ "learning_rate": 1.0959860967089041e-05,
636
+ "epoch": 0.8666666666666667,
637
+ "step": 455
638
+ },
639
+ {
640
+ "loss": 0.0756,
641
+ "grad_norm": 0.11695936322212219,
642
+ "learning_rate": 9.494635969882426e-06,
643
+ "epoch": 0.8761904761904762,
644
+ "step": 460
645
+ },
646
+ {
647
+ "loss": 0.0908,
648
+ "grad_norm": 0.17309154570102692,
649
+ "learning_rate": 8.129639187020954e-06,
650
+ "epoch": 0.8857142857142857,
651
+ "step": 465
652
+ },
653
+ {
654
+ "loss": 0.09,
655
+ "grad_norm": 0.14420992136001587,
656
+ "learning_rate": 6.866382254766157e-06,
657
+ "epoch": 0.8952380952380953,
658
+ "step": 470
659
+ },
660
+ {
661
+ "loss": 0.0862,
662
+ "grad_norm": 0.10915607959032059,
663
+ "learning_rate": 5.706264139775286e-06,
664
+ "epoch": 0.9047619047619048,
665
+ "step": 475
666
+ },
667
+ {
668
+ "loss": 0.081,
669
+ "grad_norm": 0.12303326278924942,
670
+ "learning_rate": 4.6505695898457655e-06,
671
+ "epoch": 0.9142857142857143,
672
+ "step": 480
673
+ },
674
+ {
675
+ "loss": 0.0829,
676
+ "grad_norm": 0.10827255994081497,
677
+ "learning_rate": 3.7004677111490247e-06,
678
+ "epoch": 0.9238095238095239,
679
+ "step": 485
680
+ },
681
+ {
682
+ "loss": 0.0781,
683
+ "grad_norm": 0.13309594988822937,
684
+ "learning_rate": 2.857010673529015e-06,
685
+ "epoch": 0.9333333333333333,
686
+ "step": 490
687
+ },
688
+ {
689
+ "loss": 0.0759,
690
+ "grad_norm": 0.09105637669563293,
691
+ "learning_rate": 2.121132545299376e-06,
692
+ "epoch": 0.9428571428571428,
693
+ "step": 495
694
+ },
695
+ {
696
+ "loss": 0.0798,
697
+ "grad_norm": 0.09017770737409592,
698
+ "learning_rate": 1.493648258829694e-06,
699
+ "epoch": 0.9523809523809523,
700
+ "step": 500
701
+ },
702
+ {
703
+ "loss": 0.0826,
704
+ "grad_norm": 0.11734183877706528,
705
+ "learning_rate": 9.752527080661655e-07,
706
+ "epoch": 0.9619047619047619,
707
+ "step": 505
708
+ },
709
+ {
710
+ "loss": 0.082,
711
+ "grad_norm": 0.11207328736782074,
712
+ "learning_rate": 5.665199789862907e-07,
713
+ "epoch": 0.9714285714285714,
714
+ "step": 510
715
+ },
716
+ {
717
+ "loss": 0.075,
718
+ "grad_norm": 0.09538198262453079,
719
+ "learning_rate": 2.6790271383970723e-07,
720
+ "epoch": 0.9809523809523809,
721
+ "step": 515
722
+ },
723
+ {
724
+ "loss": 0.0812,
725
+ "grad_norm": 0.09621952474117279,
726
+ "learning_rate": 7.973160987931883e-08,
727
+ "epoch": 0.9904761904761905,
728
+ "step": 520
729
+ },
730
+ {
731
+ "loss": 0.0834,
732
+ "grad_norm": 0.1348438411951065,
733
+ "learning_rate": 2.215053137755163e-09,
734
+ "epoch": 1.0,
735
+ "step": 525
736
+ },
737
+ {
738
+ "train_runtime": 1974.3371,
739
+ "train_samples_per_second": 2.127,
740
+ "train_steps_per_second": 0.266,
741
+ "total_flos": 7.149388577287373e+16,
742
+ "train_loss": 0.2107780130704244,
743
+ "epoch": 1.0,
744
+ "step": 525
745
+ }
746
+ ]
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af13ebe39365f9488cba0d708d15203c697025ff2d18096ed7b09f1787f789c
3
+ size 3968658944
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2593a694cd33c072c612073137550eaa19fc9c1dedddba4f44686e595c59cf7e
3
+ size 2203268048
model.safetensors.index.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6171877376
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.norm.weight": "model-00002-of-00002.safetensors"
440
+ }
441
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|PAD_TOKEN|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
+ size 11422086
tokenizer_config.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|PAD_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "clean_up_tokenization_spaces": false,
207
+ "eos_token": "<|im_end|>",
208
+ "errors": "replace",
209
+ "extra_special_tokens": {},
210
+ "model_max_length": 32768,
211
+ "pad_token": "<|PAD_TOKEN|>",
212
+ "padding_side": "left",
213
+ "split_special_tokens": false,
214
+ "tokenizer_class": "Qwen2Tokenizer",
215
+ "unk_token": null,
216
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
217
+ }
training_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "teacher_jsonls": [
3
+ "data/teacher_30ep_validation.jsonl",
4
+ "data/teacher_indist_30_99.jsonl",
5
+ "data/teacher_ood_10000_10049.jsonl"
6
+ ],
7
+ "output_dir": "/tmp/rhythm_env/outputs/rhythm-env-sft-primed",
8
+ "model_name": "unsloth/Qwen2.5-3B-Instruct",
9
+ "epochs": 1,
10
+ "max_steps": -1,
11
+ "lora_rank": 16,
12
+ "learning_rate": 0.0002,
13
+ "max_seq_length": 1024,
14
+ "per_device_batch_size": 1,
15
+ "grad_accum": 8,
16
+ "warmup_ratio": 0.1,
17
+ "save_method": "merged_16bit"
18
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff