Hugging Face's logo

bk1dr
/
qwen3-8b-code-pkpo

Reinforcement Learning
Safetensors
qwen3
code
pkpo
livecodebench
Model card Files
xet
 Community
bk1dr commited on
Commit
394b215
·
verified ·
1 Parent(s): 607cc24

Upload merged PKPO run

Browse files
Files changed (13) hide show
  1. README.md +3 -3
  2. eval/baseline_results.json +338 -0
  3. eval/eval_subset.json +247 -0
  4. eval/final_results.json +338 -0
  5. eval/sft_log.json +770 -0
  6. eval/training_stage_log.json +2010 -0
  7. generation_config.json +13 -0
  8. model-00001-of-00005.safetensors +3 -0
  9. model-00002-of-00005.safetensors +3 -0
  10. model-00003-of-00005.safetensors +3 -0
  11. model-00004-of-00005.safetensors +3 -0
  12. model-00005-of-00005.safetensors +3 -0
  13. model.safetensors.index.json +406 -0
README.md CHANGED
@@ -27,7 +27,7 @@ coding experiment using the shared tool path in `agent_core.py` and
27
  - Reward: binary hidden-test pass/fail.
28
  - PKPO: `sloo_minus_one` from the paper for `k >= 2`; centered `k=1` rewards for
29
  the first and final stages. No GRPO-style reward normalization is applied.
30
- - Schedule actually run: `pending`.
31
 
32
  The run was intentionally small to fit the free-credit budget and deadline.
33
  Results should be treated as a reproducible experiment, not a leaderboard model.
@@ -40,7 +40,7 @@ for training.
40
 
41
  | model | pass@1 estimate |
42
  |---|---:|
43
- | base before training | 0.0000 |
44
  | final merged model | 0.0000 |
45
 
46
  Raw files:
@@ -65,4 +65,4 @@ python shipped_tool.py --base-url http://127.0.0.1:8000/v1 --model bk1dr/qwen3-8
65
 
66
  ## Run Notes
67
 
68
- Scaffold pushed before GPU training.
 
27
  - Reward: binary hidden-test pass/fail.
28
  - PKPO: `sloo_minus_one` from the paper for `k >= 2`; centered `k=1` rewards for
29
  the first and final stages. No GRPO-style reward normalization is applied.
30
+ - Schedule actually run: `[1, 8, 1]`.
31
 
32
  The run was intentionally small to fit the free-credit budget and deadline.
33
  Results should be treated as a reproducible experiment, not a leaderboard model.
 
40
 
41
  | model | pass@1 estimate |
42
  |---|---:|
43
+ | base before training | 0.1111 |
44
  | final merged model | 0.0000 |
45
 
46
  Raw files:
 
65
 
66
  ## Run Notes
67
 
68
+ Modal H100 pipeline elapsed 42.1 minutes. Run id pkpo_20260709T184830Z; eval subset size 6, samples/problem 6, rollouts/group 12; verified Python-3 SFT examples 96. Raw rollout traces remain in the private Modal work volume and are not published.
eval/baseline_results.json ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "details": [
3
+ {
4
+ "difficulty": "hard",
5
+ "problem_id": "arc196_a",
6
+ "samples": [
7
+ {
8
+ "code_chars": 380,
9
+ "completion_chars": 2880,
10
+ "end": "wrong_answer",
11
+ "passed": false,
12
+ "stop_seen": true,
13
+ "tool_type": "final"
14
+ },
15
+ {
16
+ "code_chars": 327,
17
+ "completion_chars": 4333,
18
+ "end": "runtime_error",
19
+ "passed": false,
20
+ "stop_seen": true,
21
+ "tool_type": "final"
22
+ },
23
+ {
24
+ "code_chars": 0,
25
+ "completion_chars": 5950,
26
+ "end": "format_error: final",
27
+ "passed": false,
28
+ "stop_seen": false,
29
+ "tool_type": "final"
30
+ },
31
+ {
32
+ "code_chars": 318,
33
+ "completion_chars": 5576,
34
+ "end": "wrong_answer",
35
+ "passed": false,
36
+ "stop_seen": true,
37
+ "tool_type": "final"
38
+ },
39
+ {
40
+ "code_chars": 316,
41
+ "completion_chars": 6824,
42
+ "end": "wrong_answer",
43
+ "passed": false,
44
+ "stop_seen": true,
45
+ "tool_type": "final"
46
+ },
47
+ {
48
+ "code_chars": 540,
49
+ "completion_chars": 3408,
50
+ "end": "runtime_error",
51
+ "passed": false,
52
+ "stop_seen": true,
53
+ "tool_type": "final"
54
+ }
55
+ ]
56
+ },
57
+ {
58
+ "difficulty": "hard",
59
+ "problem_id": "abc398_f",
60
+ "samples": [
61
+ {
62
+ "code_chars": 332,
63
+ "completion_chars": 5783,
64
+ "end": "wrong_answer",
65
+ "passed": false,
66
+ "stop_seen": true,
67
+ "tool_type": "final"
68
+ },
69
+ {
70
+ "code_chars": 325,
71
+ "completion_chars": 4684,
72
+ "end": "wrong_answer",
73
+ "passed": false,
74
+ "stop_seen": true,
75
+ "tool_type": "final"
76
+ },
77
+ {
78
+ "code_chars": 351,
79
+ "completion_chars": 2437,
80
+ "end": "wrong_answer",
81
+ "passed": false,
82
+ "stop_seen": true,
83
+ "tool_type": "final"
84
+ },
85
+ {
86
+ "code_chars": 194,
87
+ "completion_chars": 4745,
88
+ "end": "runtime_error",
89
+ "passed": false,
90
+ "stop_seen": true,
91
+ "tool_type": "final"
92
+ },
93
+ {
94
+ "code_chars": 360,
95
+ "completion_chars": 3907,
96
+ "end": "ok",
97
+ "passed": true,
98
+ "stop_seen": true,
99
+ "tool_type": "final"
100
+ },
101
+ {
102
+ "code_chars": 0,
103
+ "completion_chars": 6143,
104
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
105
+ "passed": false,
106
+ "stop_seen": false,
107
+ "tool_type": null
108
+ }
109
+ ]
110
+ },
111
+ {
112
+ "difficulty": "easy",
113
+ "problem_id": "abc400_a",
114
+ "samples": [
115
+ {
116
+ "code_chars": 180,
117
+ "completion_chars": 982,
118
+ "end": "ok",
119
+ "passed": true,
120
+ "stop_seen": true,
121
+ "tool_type": "final"
122
+ },
123
+ {
124
+ "code_chars": 0,
125
+ "completion_chars": 1062,
126
+ "end": "format_error: final",
127
+ "passed": false,
128
+ "stop_seen": false,
129
+ "tool_type": "final"
130
+ },
131
+ {
132
+ "code_chars": 285,
133
+ "completion_chars": 1636,
134
+ "end": "runtime_error",
135
+ "passed": false,
136
+ "stop_seen": true,
137
+ "tool_type": "final"
138
+ },
139
+ {
140
+ "code_chars": 264,
141
+ "completion_chars": 1539,
142
+ "end": "runtime_error",
143
+ "passed": false,
144
+ "stop_seen": true,
145
+ "tool_type": "final"
146
+ },
147
+ {
148
+ "code_chars": 165,
149
+ "completion_chars": 886,
150
+ "end": "ok",
151
+ "passed": true,
152
+ "stop_seen": true,
153
+ "tool_type": "final"
154
+ },
155
+ {
156
+ "code_chars": 175,
157
+ "completion_chars": 940,
158
+ "end": "ok",
159
+ "passed": true,
160
+ "stop_seen": true,
161
+ "tool_type": "final"
162
+ }
163
+ ]
164
+ },
165
+ {
166
+ "difficulty": "hard",
167
+ "problem_id": "arc196_c",
168
+ "samples": [
169
+ {
170
+ "code_chars": 0,
171
+ "completion_chars": 9181,
172
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
173
+ "passed": false,
174
+ "stop_seen": true,
175
+ "tool_type": null
176
+ },
177
+ {
178
+ "code_chars": 601,
179
+ "completion_chars": 7205,
180
+ "end": "wrong_answer",
181
+ "passed": false,
182
+ "stop_seen": true,
183
+ "tool_type": "final"
184
+ },
185
+ {
186
+ "code_chars": 371,
187
+ "completion_chars": 3946,
188
+ "end": "runtime_error",
189
+ "passed": false,
190
+ "stop_seen": true,
191
+ "tool_type": "final"
192
+ },
193
+ {
194
+ "code_chars": 1489,
195
+ "completion_chars": 8048,
196
+ "end": "runtime_error",
197
+ "passed": false,
198
+ "stop_seen": true,
199
+ "tool_type": "final"
200
+ },
201
+ {
202
+ "code_chars": 0,
203
+ "completion_chars": 5614,
204
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
205
+ "passed": false,
206
+ "stop_seen": false,
207
+ "tool_type": null
208
+ },
209
+ {
210
+ "code_chars": 125,
211
+ "completion_chars": 7651,
212
+ "end": "wrong_answer",
213
+ "passed": false,
214
+ "stop_seen": true,
215
+ "tool_type": "final"
216
+ }
217
+ ]
218
+ },
219
+ {
220
+ "difficulty": "medium",
221
+ "problem_id": "abc400_d",
222
+ "samples": [
223
+ {
224
+ "code_chars": 2468,
225
+ "completion_chars": 5103,
226
+ "end": "timeout",
227
+ "passed": false,
228
+ "stop_seen": true,
229
+ "tool_type": "final"
230
+ },
231
+ {
232
+ "code_chars": 0,
233
+ "completion_chars": 3814,
234
+ "end": "format_error: final",
235
+ "passed": false,
236
+ "stop_seen": false,
237
+ "tool_type": "final"
238
+ },
239
+ {
240
+ "code_chars": 1121,
241
+ "completion_chars": 9244,
242
+ "end": "wrong_answer",
243
+ "passed": false,
244
+ "stop_seen": true,
245
+ "tool_type": "final"
246
+ },
247
+ {
248
+ "code_chars": 0,
249
+ "completion_chars": 3572,
250
+ "end": "format_error: final",
251
+ "passed": false,
252
+ "stop_seen": false,
253
+ "tool_type": "final"
254
+ },
255
+ {
256
+ "code_chars": 1874,
257
+ "completion_chars": 4560,
258
+ "end": "wrong_answer",
259
+ "passed": false,
260
+ "stop_seen": true,
261
+ "tool_type": "final"
262
+ },
263
+ {
264
+ "code_chars": 0,
265
+ "completion_chars": 3678,
266
+ "end": "format_error: final",
267
+ "passed": false,
268
+ "stop_seen": false,
269
+ "tool_type": "final"
270
+ }
271
+ ]
272
+ },
273
+ {
274
+ "difficulty": "hard",
275
+ "problem_id": "abc398_g",
276
+ "samples": [
277
+ {
278
+ "code_chars": 820,
279
+ "completion_chars": 3243,
280
+ "end": "runtime_error",
281
+ "passed": false,
282
+ "stop_seen": true,
283
+ "tool_type": "final"
284
+ },
285
+ {
286
+ "code_chars": 1127,
287
+ "completion_chars": 5958,
288
+ "end": "runtime_error",
289
+ "passed": false,
290
+ "stop_seen": true,
291
+ "tool_type": "final"
292
+ },
293
+ {
294
+ "code_chars": 842,
295
+ "completion_chars": 6255,
296
+ "end": "wrong_answer",
297
+ "passed": false,
298
+ "stop_seen": true,
299
+ "tool_type": "final"
300
+ },
301
+ {
302
+ "code_chars": 326,
303
+ "completion_chars": 6262,
304
+ "end": "wrong_answer",
305
+ "passed": false,
306
+ "stop_seen": true,
307
+ "tool_type": "final"
308
+ },
309
+ {
310
+ "code_chars": 869,
311
+ "completion_chars": 4210,
312
+ "end": "runtime_error",
313
+ "passed": false,
314
+ "stop_seen": true,
315
+ "tool_type": "final"
316
+ },
317
+ {
318
+ "code_chars": 0,
319
+ "completion_chars": 3812,
320
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
321
+ "passed": false,
322
+ "stop_seen": false,
323
+ "tool_type": null
324
+ }
325
+ ]
326
+ }
327
+ ],
328
+ "eval_limit": 6,
329
+ "max_new_tokens": 1024,
330
+ "pass_at_1": 0.1111111111111111,
331
+ "passed_samples": 4,
332
+ "samples_per_problem": 6,
333
+ "tag": "baseline",
334
+ "temperature": 1.0,
335
+ "tool_turn_limit": 1,
336
+ "top_p": 0.95,
337
+ "total_samples": 36
338
+ }
eval/eval_subset.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "contest_date": "2025-04-06T00:00:00",
4
+ "difficulty": "hard",
5
+ "hidden_tests": [
6
+ {
7
+ "input": "4564\n253140288 293305612 750791934 354530934 444237786 846682985 925663544 35056",
8
+ "output_len": 14
9
+ },
10
+ {
11
+ "input": "63\n55449 10966 48278 28854 34199 76708 21835 56522 25159 46992 15075 8370 92014 ",
12
+ "output_len": 8
13
+ },
14
+ {
15
+ "input": "52\n68827 19447 33671 78983 20435 49677 76409 38586 94127 92586 61661 8698 11095 ",
16
+ "output_len": 8
17
+ }
18
+ ],
19
+ "problem_id": "arc196_a",
20
+ "public_tests": [
21
+ {
22
+ "input": "4\n1 2 5 3",
23
+ "output": "5",
24
+ "testtype": "stdin"
25
+ },
26
+ {
27
+ "input": "7\n3 1 4 1 5 9 2",
28
+ "output": "14",
29
+ "testtype": "stdin"
30
+ },
31
+ {
32
+ "input": "5\n1 1 1 1 1",
33
+ "output": "0",
34
+ "testtype": "stdin"
35
+ }
36
+ ],
37
+ "source": "livecodebench/code_generation_lite:v6",
38
+ "starter_code": "",
39
+ "statement": "You are given a length-N sequence A = (A_1, A_2, \\ldots, A_N).\nYou will repeatedly perform the following operation until the sequence has length at most 1: choose two adjacent numbers and remove both from the sequence.\nThe score obtained in one operation is the absolute difference of the two chosen numbers.\nFind the maximum possible total score obtained.\n\nInput\n\nThe input is given from Standard Input in the following format:\nN\nA_1 A_2 \\ldots A_N\n\nOutput\n\nPrint the maximum possible total score ob",
40
+ "title": "Adjacent Delete"
41
+ },
42
+ {
43
+ "contest_date": "2025-03-22T00:00:00",
44
+ "difficulty": "hard",
45
+ "hidden_tests": [
46
+ {
47
+ "input": "ZGBZMOLYGOLZUCBBPIAQVSSGHCYUYQWQNQJDENSNCDNCDNYEXAZONVNAPKXICLCDLWALLFAHLCTEGAGV",
48
+ "output_len": 166
49
+ },
50
+ {
51
+ "input": "UOMWVSNBMWSNYVWBFOCIWFOQPRTYABPKJOBZZNGRUCXEAMVNKAGAWYAVQTDGDTUG",
52
+ "output_len": 128
53
+ },
54
+ {
55
+ "input": "XCU",
56
+ "output_len": 6
57
+ }
58
+ ],
59
+ "problem_id": "abc398_f",
60
+ "public_tests": [
61
+ {
62
+ "input": "ABC",
63
+ "output": "ABCBA",
64
+ "testtype": "stdin"
65
+ },
66
+ {
67
+ "input": "Z",
68
+ "output": "Z",
69
+ "testtype": "stdin"
70
+ },
71
+ {
72
+ "input": "TREE",
73
+ "output": "TREERT",
74
+ "testtype": "stdin"
75
+ }
76
+ ],
77
+ "source": "livecodebench/code_generation_lite:v6",
78
+ "starter_code": "",
79
+ "statement": "Find one shortest palindrome that has S as its prefix.\n\nInput\n\nThe input is given from Standard Input in the following format:\nS\n\nOutput\n\nPrint the answer.\r\nIf multiple solutions exist, any of them is accepted.\n\nConstraints\n\n\n- S is a string of length between 1 and 500000, inclusive, consisting of uppercase English letters.\n\nSample Input 1\n\nABC\n\nSample Output 1\n\nABCBA\r\n\nABCBA is a shortest palindrome that has S= ABC as its prefix.\n\nSample Input 2\n\nZ\n\nSample Output 2\n\nZ\r\n\nZ is a shortest palindro",
80
+ "title": "ABCBA"
81
+ },
82
+ {
83
+ "contest_date": "2025-04-05T00:00:00",
84
+ "difficulty": "easy",
85
+ "hidden_tests": [
86
+ {
87
+ "input": "286",
88
+ "output_len": 3
89
+ },
90
+ {
91
+ "input": "20",
92
+ "output_len": 3
93
+ },
94
+ {
95
+ "input": "26",
96
+ "output_len": 3
97
+ }
98
+ ],
99
+ "problem_id": "abc400_a",
100
+ "public_tests": [
101
+ {
102
+ "input": "10",
103
+ "output": "40",
104
+ "testtype": "stdin"
105
+ },
106
+ {
107
+ "input": "11",
108
+ "output": "-1",
109
+ "testtype": "stdin"
110
+ },
111
+ {
112
+ "input": "400",
113
+ "output": "1",
114
+ "testtype": "stdin"
115
+ }
116
+ ],
117
+ "source": "livecodebench/code_generation_lite:v6",
118
+ "starter_code": "",
119
+ "statement": "In the ceremony commemorating ABC400, we want to arrange 400 people in a rectangular formation of A rows and B columns without any gaps.\nYou are given a positive integer A. Print the value of a positive integer B for which such an arrangement is possible. If there is no such positive integer B, print -1.\n\nInput\n\nThe input is given from Standard Input in the following format:\nA\n\nOutput\n\nPrint the value of B or -1 as specified by the problem statement.\n\nConstraints\n\n\n- A is an integer between 1 an",
120
+ "title": "ABC400 Party"
121
+ },
122
+ {
123
+ "contest_date": "2025-04-06T00:00:00",
124
+ "difficulty": "hard",
125
+ "hidden_tests": [
126
+ {
127
+ "input": "118\nWWWWBWBWWBWBWWWWWWWBWBWWBBBBBBBWBBWBBWBWBWBWBWWWBBBWBWBWBWWBWWWWWWBBWWBBWBWB",
128
+ "output_len": 2
129
+ },
130
+ {
131
+ "input": "108\nBBBWWBWBWWBWBBWWBWWBWBWWBWWWWBWWWBWBWBWWWBBWWWBBWWWBWBBBWWWWBBWBWBBBWBWWWBWB",
132
+ "output_len": 2
133
+ },
134
+ {
135
+ "input": "8\nWWBWBWWBWBBBWWBB",
136
+ "output_len": 2
137
+ }
138
+ ],
139
+ "problem_id": "arc196_c",
140
+ "public_tests": [
141
+ {
142
+ "input": "2\nBWBW",
143
+ "output": "1",
144
+ "testtype": "stdin"
145
+ },
146
+ {
147
+ "input": "4\nBWWBWBWB",
148
+ "output": "0",
149
+ "testtype": "stdin"
150
+ },
151
+ {
152
+ "input": "9\nBWWBWBBBWWBWBBWWBW",
153
+ "output": "240792",
154
+ "testtype": "stdin"
155
+ }
156
+ ],
157
+ "source": "livecodebench/code_generation_lite:v6",
158
+ "starter_code": "",
159
+ "statement": "There is a directed graph with 2N vertices and 2N-1 edges.\r\nThe vertices are numbered 1, 2, \\ldots, 2N, and the i-th edge is a directed edge from vertex i to vertex i+1.\nYou are given a length-2N string S = S_1 S_2 \\ldots S_{2N} consisting of N Ws and N Bs.\r\nVertex i is colored white if S_i is W, and black if S_i is B.\nYou will perform the following series of operations:\n\n- Partition the 2N vertices into N pairs, each consisting of one white vertex and one black vertex.\n- For each pair, add a di",
160
+ "title": "Strongly Connected"
161
+ },
162
+ {
163
+ "contest_date": "2025-04-05T00:00:00",
164
+ "difficulty": "medium",
165
+ "hidden_tests": [
166
+ {
167
+ "input": "2 2\n..\n..\n2 2 2 1",
168
+ "output_len": 2
169
+ },
170
+ {
171
+ "input": "8 5\n....#\n...#.\n.##.#\n###.#\n##...\n###.#\n.#..#\n.##..\n4 4 2 5",
172
+ "output_len": 2
173
+ },
174
+ {
175
+ "input": "6 4\n..##\n...#\n##..\n.#..\n..#.\n...#\n4 1 1 1",
176
+ "output_len": 2
177
+ }
178
+ ],
179
+ "problem_id": "abc400_d",
180
+ "public_tests": [
181
+ {
182
+ "input": "10 10\n..........\n#########.\n#.......#.\n#..####.#.\n##....#.#.\n#####.#.#.\n.##.#.#.#.\n###.#.#.#.\n###.#.#.#.\n#.....#...\n1 1 7 1",
183
+ "output": "1",
184
+ "testtype": "stdin"
185
+ },
186
+ {
187
+ "input": "2 2\n.#\n#.\n1 1 2 2",
188
+ "output": "1",
189
+ "testtype": "stdin"
190
+ },
191
+ {
192
+ "input": "1 3\n.#.\n1 1 1 3",
193
+ "output": "1",
194
+ "testtype": "stdin"
195
+ },
196
+ {
197
+ "input": "20 20\n####################\n##...##....###...###\n#.....#.....#.....##\n#..#..#..#..#..#..##\n#..#..#....##..#####\n#.....#.....#..#####\n#.....#..#..#..#..##\n#..#..#.....#.....##\n#..#..#....###...###\n####################\n####################\n##..#..##...###...##\n##..#..#.....#.....#\n##..#..#..#..#..#..#\n##..#..#..#..#..#..#\n##.....#..#..#..#..#\n###....#..#..#..#..#\n#####..#.....#.....#\n#####..##...###...##\n####################\n3 3 18 18",
198
+ "output": "3",
199
+ "testtype": "stdin"
200
+ }
201
+ ],
202
+ "source": "livecodebench/code_generation_lite:v6",
203
+ "starter_code": "",
204
+ "statement": "Takahashi is about to go buy eel at a fish shop.\nThe town where he lives is divided into a grid of H rows and W columns. Each cell is either a road or a wall.\r\nLet us denote the cell at the i-th row from the top (1\\leq i \\leq H) and the j-th column from the left (1\\leq j \\leq W) as cell (i,j).\r\nInformation about each cell is given by H strings S_1,S_2,\\ldots,S_H, each of length W. Specifically, if the j-th character of S_i (1\\leq i \\leq H,1\\leq j\\leq W) is ., cell (i,j) is a road; if it is #, ce",
205
+ "title": "Takahashi the Wall Breaker"
206
+ },
207
+ {
208
+ "contest_date": "2025-03-22T00:00:00",
209
+ "difficulty": "hard",
210
+ "hidden_tests": [
211
+ {
212
+ "input": "5 4\n1 2\n1 3\n1 4\n1 5",
213
+ "output_len": 10
214
+ },
215
+ {
216
+ "input": "128 2871\n1 68\n24 62\n13 107\n21 41\n6 89\n10 106\n24 88\n25 53\n21 44\n2 72\n2 95\n29 79\n1",
217
+ "output_len": 10
218
+ },
219
+ {
220
+ "input": "6 5\n1 6\n3 6\n2 6\n4 6\n5 6",
221
+ "output_len": 10
222
+ }
223
+ ],
224
+ "problem_id": "abc398_g",
225
+ "public_tests": [
226
+ {
227
+ "input": "4 3\n1 2\n2 3\n3 4",
228
+ "output": "Aoki",
229
+ "testtype": "stdin"
230
+ },
231
+ {
232
+ "input": "4 2\n1 2\n3 4",
233
+ "output": "Takahashi",
234
+ "testtype": "stdin"
235
+ },
236
+ {
237
+ "input": "9 5\n2 9\n2 3\n4 6\n5 7\n1 8",
238
+ "output": "Aoki",
239
+ "testtype": "stdin"
240
+ }
241
+ ],
242
+ "source": "livecodebench/code_generation_lite:v6",
243
+ "starter_code": "",
244
+ "statement": "You are given a simple undirected graph with N vertices and M edges, with vertices labeled 1 to N and edges labeled 1 to M. The i-th edge connects vertices U_i and V_i. Initially, G does not contain an odd cycle.\nTakahashi and Aoki will play a game using this graph G. With Aoki going first, they take turns performing the following operation:\n\n- Choose a pair of integers (i,j) with 1 \\leq i < j \\leq N that satisfies both of the following conditions, then add an edge connecting vertices i and j to",
245
+ "title": "Not Only Tree Game"
246
+ }
247
+ ]
eval/final_results.json ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "details": [
3
+ {
4
+ "difficulty": "hard",
5
+ "problem_id": "arc196_a",
6
+ "samples": [
7
+ {
8
+ "code_chars": 719,
9
+ "completion_chars": 828,
10
+ "end": "runtime_error",
11
+ "passed": false,
12
+ "stop_seen": true,
13
+ "tool_type": "final"
14
+ },
15
+ {
16
+ "code_chars": 115,
17
+ "completion_chars": 2707,
18
+ "end": "wrong_answer",
19
+ "passed": false,
20
+ "stop_seen": true,
21
+ "tool_type": "final"
22
+ },
23
+ {
24
+ "code_chars": 389,
25
+ "completion_chars": 1655,
26
+ "end": "timeout",
27
+ "passed": false,
28
+ "stop_seen": true,
29
+ "tool_type": "final"
30
+ },
31
+ {
32
+ "code_chars": 214,
33
+ "completion_chars": 2386,
34
+ "end": "runtime_error",
35
+ "passed": false,
36
+ "stop_seen": true,
37
+ "tool_type": "final"
38
+ },
39
+ {
40
+ "code_chars": 282,
41
+ "completion_chars": 2263,
42
+ "end": "runtime_error",
43
+ "passed": false,
44
+ "stop_seen": true,
45
+ "tool_type": "final"
46
+ },
47
+ {
48
+ "code_chars": 303,
49
+ "completion_chars": 2072,
50
+ "end": "wrong_answer",
51
+ "passed": false,
52
+ "stop_seen": true,
53
+ "tool_type": "final"
54
+ }
55
+ ]
56
+ },
57
+ {
58
+ "difficulty": "hard",
59
+ "problem_id": "abc398_f",
60
+ "samples": [
61
+ {
62
+ "code_chars": 165,
63
+ "completion_chars": 3251,
64
+ "end": "wrong_answer",
65
+ "passed": false,
66
+ "stop_seen": true,
67
+ "tool_type": "final"
68
+ },
69
+ {
70
+ "code_chars": 160,
71
+ "completion_chars": 3358,
72
+ "end": "wrong_answer",
73
+ "passed": false,
74
+ "stop_seen": true,
75
+ "tool_type": "final"
76
+ },
77
+ {
78
+ "code_chars": 877,
79
+ "completion_chars": 985,
80
+ "end": "runtime_error",
81
+ "passed": false,
82
+ "stop_seen": true,
83
+ "tool_type": "final"
84
+ },
85
+ {
86
+ "code_chars": 499,
87
+ "completion_chars": 2528,
88
+ "end": "wrong_answer",
89
+ "passed": false,
90
+ "stop_seen": true,
91
+ "tool_type": "final"
92
+ },
93
+ {
94
+ "code_chars": 396,
95
+ "completion_chars": 2252,
96
+ "end": "wrong_answer",
97
+ "passed": false,
98
+ "stop_seen": true,
99
+ "tool_type": "final"
100
+ },
101
+ {
102
+ "code_chars": 327,
103
+ "completion_chars": 2724,
104
+ "end": "runtime_error",
105
+ "passed": false,
106
+ "stop_seen": true,
107
+ "tool_type": "final"
108
+ }
109
+ ]
110
+ },
111
+ {
112
+ "difficulty": "easy",
113
+ "problem_id": "abc400_a",
114
+ "samples": [
115
+ {
116
+ "code_chars": 125,
117
+ "completion_chars": 12597,
118
+ "end": "wrong_answer",
119
+ "passed": false,
120
+ "stop_seen": true,
121
+ "tool_type": "final"
122
+ },
123
+ {
124
+ "code_chars": 88,
125
+ "completion_chars": 12702,
126
+ "end": "wrong_answer",
127
+ "passed": false,
128
+ "stop_seen": true,
129
+ "tool_type": "final"
130
+ },
131
+ {
132
+ "code_chars": 143,
133
+ "completion_chars": 12602,
134
+ "end": "wrong_answer",
135
+ "passed": false,
136
+ "stop_seen": true,
137
+ "tool_type": "final"
138
+ },
139
+ {
140
+ "code_chars": 103,
141
+ "completion_chars": 12689,
142
+ "end": "wrong_answer",
143
+ "passed": false,
144
+ "stop_seen": true,
145
+ "tool_type": "final"
146
+ },
147
+ {
148
+ "code_chars": 30,
149
+ "completion_chars": 12918,
150
+ "end": "wrong_answer",
151
+ "passed": false,
152
+ "stop_seen": true,
153
+ "tool_type": "final"
154
+ },
155
+ {
156
+ "code_chars": 0,
157
+ "completion_chars": 2353,
158
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
159
+ "passed": false,
160
+ "stop_seen": false,
161
+ "tool_type": null
162
+ }
163
+ ]
164
+ },
165
+ {
166
+ "difficulty": "hard",
167
+ "problem_id": "arc196_c",
168
+ "samples": [
169
+ {
170
+ "code_chars": 111,
171
+ "completion_chars": 3537,
172
+ "end": "runtime_error",
173
+ "passed": false,
174
+ "stop_seen": true,
175
+ "tool_type": "final"
176
+ },
177
+ {
178
+ "code_chars": 231,
179
+ "completion_chars": 2460,
180
+ "end": "wrong_answer",
181
+ "passed": false,
182
+ "stop_seen": true,
183
+ "tool_type": "final"
184
+ },
185
+ {
186
+ "code_chars": 233,
187
+ "completion_chars": 3048,
188
+ "end": "wrong_answer",
189
+ "passed": false,
190
+ "stop_seen": true,
191
+ "tool_type": "final"
192
+ },
193
+ {
194
+ "code_chars": 132,
195
+ "completion_chars": 3325,
196
+ "end": "wrong_answer",
197
+ "passed": false,
198
+ "stop_seen": true,
199
+ "tool_type": "final"
200
+ },
201
+ {
202
+ "code_chars": 870,
203
+ "completion_chars": 979,
204
+ "end": "wrong_answer",
205
+ "passed": false,
206
+ "stop_seen": true,
207
+ "tool_type": "final"
208
+ },
209
+ {
210
+ "code_chars": 389,
211
+ "completion_chars": 2591,
212
+ "end": "wrong_answer",
213
+ "passed": false,
214
+ "stop_seen": true,
215
+ "tool_type": "final"
216
+ }
217
+ ]
218
+ },
219
+ {
220
+ "difficulty": "medium",
221
+ "problem_id": "abc400_d",
222
+ "samples": [
223
+ {
224
+ "code_chars": 733,
225
+ "completion_chars": 9798,
226
+ "end": "wrong_answer",
227
+ "passed": false,
228
+ "stop_seen": true,
229
+ "tool_type": "final"
230
+ },
231
+ {
232
+ "code_chars": 0,
233
+ "completion_chars": 9689,
234
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
235
+ "passed": false,
236
+ "stop_seen": false,
237
+ "tool_type": null
238
+ },
239
+ {
240
+ "code_chars": 1866,
241
+ "completion_chars": 7054,
242
+ "end": "runtime_error",
243
+ "passed": false,
244
+ "stop_seen": true,
245
+ "tool_type": "final"
246
+ },
247
+ {
248
+ "code_chars": 1347,
249
+ "completion_chars": 8086,
250
+ "end": "runtime_error",
251
+ "passed": false,
252
+ "stop_seen": true,
253
+ "tool_type": "final"
254
+ },
255
+ {
256
+ "code_chars": 0,
257
+ "completion_chars": 2217,
258
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
259
+ "passed": false,
260
+ "stop_seen": false,
261
+ "tool_type": null
262
+ },
263
+ {
264
+ "code_chars": 1162,
265
+ "completion_chars": 8951,
266
+ "end": "runtime_error",
267
+ "passed": false,
268
+ "stop_seen": true,
269
+ "tool_type": "final"
270
+ }
271
+ ]
272
+ },
273
+ {
274
+ "difficulty": "hard",
275
+ "problem_id": "abc398_g",
276
+ "samples": [
277
+ {
278
+ "code_chars": 0,
279
+ "completion_chars": 4543,
280
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
281
+ "passed": false,
282
+ "stop_seen": false,
283
+ "tool_type": null
284
+ },
285
+ {
286
+ "code_chars": 2840,
287
+ "completion_chars": 3882,
288
+ "end": "timeout",
289
+ "passed": false,
290
+ "stop_seen": true,
291
+ "tool_type": "final"
292
+ },
293
+ {
294
+ "code_chars": 347,
295
+ "completion_chars": 11776,
296
+ "end": "wrong_answer",
297
+ "passed": false,
298
+ "stop_seen": true,
299
+ "tool_type": "final"
300
+ },
301
+ {
302
+ "code_chars": 0,
303
+ "completion_chars": 5113,
304
+ "end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
305
+ "passed": false,
306
+ "stop_seen": false,
307
+ "tool_type": null
308
+ },
309
+ {
310
+ "code_chars": 791,
311
+ "completion_chars": 11156,
312
+ "end": "runtime_error",
313
+ "passed": false,
314
+ "stop_seen": true,
315
+ "tool_type": "final"
316
+ },
317
+ {
318
+ "code_chars": 1219,
319
+ "completion_chars": 10183,
320
+ "end": "runtime_error",
321
+ "passed": false,
322
+ "stop_seen": true,
323
+ "tool_type": "final"
324
+ }
325
+ ]
326
+ }
327
+ ],
328
+ "eval_limit": 6,
329
+ "max_new_tokens": 1024,
330
+ "pass_at_1": 0.0,
331
+ "passed_samples": 0,
332
+ "samples_per_problem": 6,
333
+ "tag": "final",
334
+ "temperature": 1.0,
335
+ "tool_turn_limit": 1,
336
+ "top_p": 0.95,
337
+ "total_samples": 36
338
+ }
eval/sft_log.json ADDED
@@ -0,0 +1,770 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "grad_norm": 1.040154218673706,
4
+ "index": 1,
5
+ "loss": 0.48266512155532837,
6
+ "nll": 0.48266512155532837,
7
+ "problem_id": "438_A. The Child and Toy",
8
+ "skipped": null
9
+ },
10
+ {
11
+ "grad_norm": 1.1882520914077759,
12
+ "index": 2,
13
+ "loss": 0.5828834176063538,
14
+ "nll": 0.5828834176063538,
15
+ "problem_id": "300_A. Array",
16
+ "skipped": null
17
+ },
18
+ {
19
+ "grad_norm": 1.9626847505569458,
20
+ "index": 3,
21
+ "loss": 1.1390048265457153,
22
+ "nll": 1.1390048265457153,
23
+ "problem_id": "478_A. Initial Bet",
24
+ "skipped": null
25
+ },
26
+ {
27
+ "grad_norm": 1.5171997547149658,
28
+ "index": 4,
29
+ "loss": 0.9680904150009155,
30
+ "nll": 0.9680904150009155,
31
+ "problem_id": "676_A. Nicholas and Permutation",
32
+ "skipped": null
33
+ },
34
+ {
35
+ "grad_norm": 0.3860478699207306,
36
+ "index": 5,
37
+ "loss": 0.39563682675361633,
38
+ "nll": 0.39563682675361633,
39
+ "problem_id": "1031_B. Curiosity Has No Limits",
40
+ "skipped": null
41
+ },
42
+ {
43
+ "grad_norm": 1.020121455192566,
44
+ "index": 6,
45
+ "loss": 0.8472175002098083,
46
+ "nll": 0.8472175002098083,
47
+ "problem_id": "940_A. Points on the line",
48
+ "skipped": null
49
+ },
50
+ {
51
+ "grad_norm": 0.4967013895511627,
52
+ "index": 7,
53
+ "loss": 0.5509471893310547,
54
+ "nll": 0.5509471893310547,
55
+ "problem_id": "1080_C. Masha and two friends",
56
+ "skipped": null
57
+ },
58
+ {
59
+ "grad_norm": 1.479300856590271,
60
+ "index": 8,
61
+ "loss": 0.8386653661727905,
62
+ "nll": 0.8386653661727905,
63
+ "problem_id": "38_C. Blinds",
64
+ "skipped": null
65
+ },
66
+ {
67
+ "grad_norm": 0.8893219828605652,
68
+ "index": 9,
69
+ "loss": 0.3628019392490387,
70
+ "nll": 0.3628019392490387,
71
+ "problem_id": "489_B. BerSU Ball",
72
+ "skipped": null
73
+ },
74
+ {
75
+ "grad_norm": 1.4400527477264404,
76
+ "index": 10,
77
+ "loss": 0.9306145310401917,
78
+ "nll": 0.9306145310401917,
79
+ "problem_id": "787_A. The Monster",
80
+ "skipped": null
81
+ },
82
+ {
83
+ "grad_norm": 1.0569334030151367,
84
+ "index": 11,
85
+ "loss": 0.6781665086746216,
86
+ "nll": 0.6781665086746216,
87
+ "problem_id": "1070_D. Garbage Disposal",
88
+ "skipped": null
89
+ },
90
+ {
91
+ "grad_norm": 1.9829460382461548,
92
+ "index": 12,
93
+ "loss": 1.084402322769165,
94
+ "nll": 1.084402322769165,
95
+ "problem_id": "805_A. Fake NP",
96
+ "skipped": null
97
+ },
98
+ {
99
+ "grad_norm": 0.910430908203125,
100
+ "index": 13,
101
+ "loss": 0.7472644448280334,
102
+ "nll": 0.7472644448280334,
103
+ "problem_id": "1305_B. Kuroni and Simple Strings",
104
+ "skipped": null
105
+ },
106
+ {
107
+ "grad_norm": 0.8546664714813232,
108
+ "index": 14,
109
+ "loss": 0.4409652650356293,
110
+ "nll": 0.4409652650356293,
111
+ "problem_id": "742_A. Arpa\u2019s hard exam and Mehrdad\u2019s naive cheat",
112
+ "skipped": null
113
+ },
114
+ {
115
+ "grad_norm": 1.0713262557983398,
116
+ "index": 15,
117
+ "loss": 0.9237834215164185,
118
+ "nll": 0.9237834215164185,
119
+ "problem_id": "358_B. Dima and Text Messages",
120
+ "skipped": null
121
+ },
122
+ {
123
+ "grad_norm": 1.3963273763656616,
124
+ "index": 16,
125
+ "loss": 0.7768023610115051,
126
+ "nll": 0.7768023610115051,
127
+ "problem_id": "1443_A. Kids Seating",
128
+ "skipped": null
129
+ },
130
+ {
131
+ "grad_norm": 1.0952928066253662,
132
+ "index": 17,
133
+ "loss": 0.8175995945930481,
134
+ "nll": 0.8175995945930481,
135
+ "problem_id": "604_B. More Cowbell",
136
+ "skipped": null
137
+ },
138
+ {
139
+ "grad_norm": 1.6387556791305542,
140
+ "index": 18,
141
+ "loss": 1.1116256713867188,
142
+ "nll": 1.1116256713867188,
143
+ "problem_id": "1043_A. Elections",
144
+ "skipped": null
145
+ },
146
+ {
147
+ "grad_norm": 0.9755963683128357,
148
+ "index": 19,
149
+ "loss": 0.7564535737037659,
150
+ "nll": 0.7564535737037659,
151
+ "problem_id": "1054_B. Appending Mex",
152
+ "skipped": null
153
+ },
154
+ {
155
+ "grad_norm": 0.8682615756988525,
156
+ "index": 20,
157
+ "loss": 0.785297691822052,
158
+ "nll": 0.785297691822052,
159
+ "problem_id": "248_B. Chilly Willy",
160
+ "skipped": null
161
+ },
162
+ {
163
+ "grad_norm": 0.7661585807800293,
164
+ "index": 21,
165
+ "loss": 0.6494926810264587,
166
+ "nll": 0.6494926810264587,
167
+ "problem_id": "985_A. Chess Placing",
168
+ "skipped": null
169
+ },
170
+ {
171
+ "grad_norm": 2.292353630065918,
172
+ "index": 22,
173
+ "loss": 0.8781017065048218,
174
+ "nll": 0.8781017065048218,
175
+ "problem_id": "110_B. Lucky String",
176
+ "skipped": null
177
+ },
178
+ {
179
+ "grad_norm": 0.833644449710846,
180
+ "index": 23,
181
+ "loss": 0.504396378993988,
182
+ "nll": 0.504396378993988,
183
+ "problem_id": "519_B. A and B and Compilation Errors",
184
+ "skipped": null
185
+ },
186
+ {
187
+ "grad_norm": 0.9993244409561157,
188
+ "index": 24,
189
+ "loss": 0.8234552145004272,
190
+ "nll": 0.8234552145004272,
191
+ "problem_id": "615_A. Bulbs",
192
+ "skipped": null
193
+ },
194
+ {
195
+ "grad_norm": 1.3748852014541626,
196
+ "index": 25,
197
+ "loss": 0.5862762928009033,
198
+ "nll": 0.5862762928009033,
199
+ "problem_id": "270_B. Multithreading",
200
+ "skipped": null
201
+ },
202
+ {
203
+ "grad_norm": 1.3495038747787476,
204
+ "index": 26,
205
+ "loss": 1.5716842412948608,
206
+ "nll": 1.5716842412948608,
207
+ "problem_id": "272_C. Dima and Staircase",
208
+ "skipped": null
209
+ },
210
+ {
211
+ "grad_norm": 0.9883641600608826,
212
+ "index": 27,
213
+ "loss": 0.5327346324920654,
214
+ "nll": 0.5327346324920654,
215
+ "problem_id": "5_A. Chat Server's Outgoing Traffic",
216
+ "skipped": null
217
+ },
218
+ {
219
+ "grad_norm": 0.7346091270446777,
220
+ "index": 28,
221
+ "loss": 0.721221923828125,
222
+ "nll": 0.721221923828125,
223
+ "problem_id": "1408_B. Arrays Sum",
224
+ "skipped": null
225
+ },
226
+ {
227
+ "grad_norm": 1.3178147077560425,
228
+ "index": 29,
229
+ "loss": 0.7296963334083557,
230
+ "nll": 0.7296963334083557,
231
+ "problem_id": "177_D1. Encrypting Messages",
232
+ "skipped": null
233
+ },
234
+ {
235
+ "grad_norm": 1.020062804222107,
236
+ "index": 30,
237
+ "loss": 0.5247489213943481,
238
+ "nll": 0.5247489213943481,
239
+ "problem_id": "282_B. Painting Eggs",
240
+ "skipped": null
241
+ },
242
+ {
243
+ "grad_norm": 0.8763545155525208,
244
+ "index": 31,
245
+ "loss": 0.5632577538490295,
246
+ "nll": 0.5632577538490295,
247
+ "problem_id": "1334_A. Level Statistics",
248
+ "skipped": null
249
+ },
250
+ {
251
+ "grad_norm": 0.9953303337097168,
252
+ "index": 32,
253
+ "loss": 0.3932126760482788,
254
+ "nll": 0.3932126760482788,
255
+ "problem_id": "630_A. Again Twenty Five!",
256
+ "skipped": null
257
+ },
258
+ {
259
+ "grad_norm": 1.3474981784820557,
260
+ "index": 33,
261
+ "loss": 0.514382004737854,
262
+ "nll": 0.514382004737854,
263
+ "problem_id": "1366_A. Shovels and Swords",
264
+ "skipped": null
265
+ },
266
+ {
267
+ "grad_norm": 0.7742969393730164,
268
+ "index": 34,
269
+ "loss": 0.5816912055015564,
270
+ "nll": 0.5816912055015564,
271
+ "problem_id": "448_B. Suffix Structures",
272
+ "skipped": null
273
+ },
274
+ {
275
+ "grad_norm": 1.562877893447876,
276
+ "index": 35,
277
+ "loss": 0.8283543586730957,
278
+ "nll": 0.8283543586730957,
279
+ "problem_id": "1353_C. Board Moves",
280
+ "skipped": null
281
+ },
282
+ {
283
+ "grad_norm": 0.783785343170166,
284
+ "index": 36,
285
+ "loss": 0.3817444145679474,
286
+ "nll": 0.3817444145679474,
287
+ "problem_id": "259_B. Little Elephant and Magic Square",
288
+ "skipped": null
289
+ },
290
+ {
291
+ "grad_norm": 0.7053418755531311,
292
+ "index": 37,
293
+ "loss": 0.4648408889770508,
294
+ "nll": 0.4648408889770508,
295
+ "problem_id": "687_A. NP-Hard Problem",
296
+ "skipped": null
297
+ },
298
+ {
299
+ "grad_norm": 0.8954440355300903,
300
+ "index": 38,
301
+ "loss": 0.5581481456756592,
302
+ "nll": 0.5581481456756592,
303
+ "problem_id": "1121_A. Technogoblet of Fire",
304
+ "skipped": null
305
+ },
306
+ {
307
+ "grad_norm": 1.3505918979644775,
308
+ "index": 39,
309
+ "loss": 0.5477667450904846,
310
+ "nll": 0.5477667450904846,
311
+ "problem_id": "918_A. Eleven",
312
+ "skipped": null
313
+ },
314
+ {
315
+ "grad_norm": 1.0709880590438843,
316
+ "index": 40,
317
+ "loss": 0.7576397657394409,
318
+ "nll": 0.7576397657394409,
319
+ "problem_id": "1084_C. The Fair Nut and String",
320
+ "skipped": null
321
+ },
322
+ {
323
+ "grad_norm": 1.2410813570022583,
324
+ "index": 41,
325
+ "loss": 0.981418788433075,
326
+ "nll": 0.981418788433075,
327
+ "problem_id": "545_C. Woodcutters",
328
+ "skipped": null
329
+ },
330
+ {
331
+ "grad_norm": 0.44853660464286804,
332
+ "index": 42,
333
+ "loss": 0.20538830757141113,
334
+ "nll": 0.20538830757141113,
335
+ "problem_id": "1152_A. Neko Finds Grapes",
336
+ "skipped": null
337
+ },
338
+ {
339
+ "grad_norm": 0.7902032732963562,
340
+ "index": 43,
341
+ "loss": 0.43099430203437805,
342
+ "nll": 0.43099430203437805,
343
+ "problem_id": "385_A. Bear and Raspberry",
344
+ "skipped": null
345
+ },
346
+ {
347
+ "grad_norm": 0.8370153307914734,
348
+ "index": 44,
349
+ "loss": 0.5004207491874695,
350
+ "nll": 0.5004207491874695,
351
+ "problem_id": "1392_B. Omkar and Infinity Clock",
352
+ "skipped": null
353
+ },
354
+ {
355
+ "grad_norm": 0.6053890585899353,
356
+ "index": 45,
357
+ "loss": 0.527194082736969,
358
+ "nll": 0.527194082736969,
359
+ "problem_id": "1301_B. Motarack's Birthday",
360
+ "skipped": null
361
+ },
362
+ {
363
+ "grad_norm": 1.0937732458114624,
364
+ "index": 46,
365
+ "loss": 0.703790545463562,
366
+ "nll": 0.703790545463562,
367
+ "problem_id": "494_A. Treasure",
368
+ "skipped": null
369
+ },
370
+ {
371
+ "grad_norm": 0.902428150177002,
372
+ "index": 47,
373
+ "loss": 0.42323175072669983,
374
+ "nll": 0.42323175072669983,
375
+ "problem_id": "1366_B. Shuffle",
376
+ "skipped": null
377
+ },
378
+ {
379
+ "grad_norm": 0.6949153542518616,
380
+ "index": 48,
381
+ "loss": 0.37455669045448303,
382
+ "nll": 0.37455669045448303,
383
+ "problem_id": "69_A. Young Physicist",
384
+ "skipped": null
385
+ },
386
+ {
387
+ "grad_norm": 1.3904484510421753,
388
+ "index": 49,
389
+ "loss": 0.7064117193222046,
390
+ "nll": 0.7064117193222046,
391
+ "problem_id": "125_A. Measuring Lengths in Baden",
392
+ "skipped": null
393
+ },
394
+ {
395
+ "grad_norm": 1.2604994773864746,
396
+ "index": 50,
397
+ "loss": 0.6908637285232544,
398
+ "nll": 0.6908637285232544,
399
+ "problem_id": "45_I. TCMCF+++",
400
+ "skipped": null
401
+ },
402
+ {
403
+ "grad_norm": 1.3847407102584839,
404
+ "index": 51,
405
+ "loss": 0.6546027660369873,
406
+ "nll": 0.6546027660369873,
407
+ "problem_id": "740_B. Alyona and flowers",
408
+ "skipped": null
409
+ },
410
+ {
411
+ "grad_norm": 1.031480073928833,
412
+ "index": 52,
413
+ "loss": 0.6020389795303345,
414
+ "nll": 0.6020389795303345,
415
+ "problem_id": "136_B. Ternary Logic",
416
+ "skipped": null
417
+ },
418
+ {
419
+ "grad_norm": 0.9329264760017395,
420
+ "index": 53,
421
+ "loss": 0.766955554485321,
422
+ "nll": 0.766955554485321,
423
+ "problem_id": "1139_C. Edgy Trees",
424
+ "skipped": null
425
+ },
426
+ {
427
+ "grad_norm": 0.34977203607559204,
428
+ "index": 54,
429
+ "loss": 0.44151249527931213,
430
+ "nll": 0.44151249527931213,
431
+ "problem_id": "1481_B. New Colony",
432
+ "skipped": null
433
+ },
434
+ {
435
+ "grad_norm": 0.8771538734436035,
436
+ "index": 55,
437
+ "loss": 0.7079184055328369,
438
+ "nll": 0.7079184055328369,
439
+ "problem_id": "1382_A. Common Subsequence",
440
+ "skipped": null
441
+ },
442
+ {
443
+ "grad_norm": 1.0364067554473877,
444
+ "index": 56,
445
+ "loss": 0.8011530637741089,
446
+ "nll": 0.8011530637741089,
447
+ "problem_id": "248_A. Cupboards",
448
+ "skipped": null
449
+ },
450
+ {
451
+ "grad_norm": 0.8864939212799072,
452
+ "index": 57,
453
+ "loss": 0.5355629324913025,
454
+ "nll": 0.5355629324913025,
455
+ "problem_id": "268_A. Games",
456
+ "skipped": null
457
+ },
458
+ {
459
+ "grad_norm": 0.47688010334968567,
460
+ "index": 58,
461
+ "loss": 0.509407639503479,
462
+ "nll": 0.509407639503479,
463
+ "problem_id": "618_B. Guess the Permutation",
464
+ "skipped": null
465
+ },
466
+ {
467
+ "grad_norm": 1.1146557331085205,
468
+ "index": 59,
469
+ "loss": 0.9011950492858887,
470
+ "nll": 0.9011950492858887,
471
+ "problem_id": "1181_A. Chunga-Changa",
472
+ "skipped": null
473
+ },
474
+ {
475
+ "grad_norm": 0.5178598761558533,
476
+ "index": 60,
477
+ "loss": 0.2951464056968689,
478
+ "nll": 0.2951464056968689,
479
+ "problem_id": "1421_B. Putting Bricks in the Wall",
480
+ "skipped": null
481
+ },
482
+ {
483
+ "grad_norm": 0.9971789121627808,
484
+ "index": 61,
485
+ "loss": 0.5864426493644714,
486
+ "nll": 0.5864426493644714,
487
+ "problem_id": "554_C. Kyoya and Colored Balls",
488
+ "skipped": null
489
+ },
490
+ {
491
+ "grad_norm": 0.699429452419281,
492
+ "index": 62,
493
+ "loss": 0.4205191731452942,
494
+ "nll": 0.4205191731452942,
495
+ "problem_id": "1203_A. Circle of Students",
496
+ "skipped": null
497
+ },
498
+ {
499
+ "grad_norm": 0.7046372294425964,
500
+ "index": 63,
501
+ "loss": 0.8773186206817627,
502
+ "nll": 0.8773186206817627,
503
+ "problem_id": "1427_B. Chess Cheater",
504
+ "skipped": null
505
+ },
506
+ {
507
+ "grad_norm": 1.2316917181015015,
508
+ "index": 64,
509
+ "loss": 0.7916744351387024,
510
+ "nll": 0.7916744351387024,
511
+ "problem_id": "670_B. Game of Robots",
512
+ "skipped": null
513
+ },
514
+ {
515
+ "grad_norm": 0.7533033490180969,
516
+ "index": 65,
517
+ "loss": 0.5084953308105469,
518
+ "nll": 0.5084953308105469,
519
+ "problem_id": "1000_A. Codehorses T-shirts",
520
+ "skipped": null
521
+ },
522
+ {
523
+ "grad_norm": 0.4042784869670868,
524
+ "index": 66,
525
+ "loss": 0.3695657253265381,
526
+ "nll": 0.3695657253265381,
527
+ "problem_id": "1264_A. Beautiful Regional Contest",
528
+ "skipped": null
529
+ },
530
+ {
531
+ "grad_norm": 1.0112096071243286,
532
+ "index": 67,
533
+ "loss": 0.8849809169769287,
534
+ "nll": 0.8849809169769287,
535
+ "problem_id": "538_B. Quasi Binary",
536
+ "skipped": null
537
+ },
538
+ {
539
+ "grad_norm": 0.7484896183013916,
540
+ "index": 68,
541
+ "loss": 0.5725398659706116,
542
+ "nll": 0.5725398659706116,
543
+ "problem_id": "868_A. Bark to Unlock",
544
+ "skipped": null
545
+ },
546
+ {
547
+ "grad_norm": 0.4507679045200348,
548
+ "index": 69,
549
+ "loss": 0.40581223368644714,
550
+ "nll": 0.40581223368644714,
551
+ "problem_id": "99_B. Help Chef Gerasim",
552
+ "skipped": null
553
+ },
554
+ {
555
+ "grad_norm": 0.6510177850723267,
556
+ "index": 70,
557
+ "loss": 0.5508701205253601,
558
+ "nll": 0.5508701205253601,
559
+ "problem_id": "931_A. Friends Meeting",
560
+ "skipped": null
561
+ },
562
+ {
563
+ "grad_norm": 0.9200932383537292,
564
+ "index": 71,
565
+ "loss": 0.6416708827018738,
566
+ "nll": 0.6416708827018738,
567
+ "problem_id": "870_A. Search for Pretty Integers",
568
+ "skipped": null
569
+ },
570
+ {
571
+ "grad_norm": 0.8513489365577698,
572
+ "index": 72,
573
+ "loss": 1.0005862712860107,
574
+ "nll": 1.0005862712860107,
575
+ "problem_id": "1191_C. Tokitsukaze and Discard Items",
576
+ "skipped": null
577
+ },
578
+ {
579
+ "grad_norm": 0.4327949285507202,
580
+ "index": 73,
581
+ "loss": 0.5023372173309326,
582
+ "nll": 0.5023372173309326,
583
+ "problem_id": "505_B. Mr. Kitayuta's Colorful Graph",
584
+ "skipped": null
585
+ },
586
+ {
587
+ "grad_norm": 0.6228141784667969,
588
+ "index": 74,
589
+ "loss": 0.482375830411911,
590
+ "nll": 0.482375830411911,
591
+ "problem_id": "365_A. Good Number",
592
+ "skipped": null
593
+ },
594
+ {
595
+ "grad_norm": 0.9539189338684082,
596
+ "index": 75,
597
+ "loss": 0.5643600225448608,
598
+ "nll": 0.5643600225448608,
599
+ "problem_id": "513_A. Game",
600
+ "skipped": null
601
+ },
602
+ {
603
+ "grad_norm": 0.8559263944625854,
604
+ "index": 76,
605
+ "loss": 1.1494770050048828,
606
+ "nll": 1.1494770050048828,
607
+ "problem_id": "1159_A. A pile of stones",
608
+ "skipped": null
609
+ },
610
+ {
611
+ "grad_norm": 0.9862070083618164,
612
+ "index": 77,
613
+ "loss": 1.1389682292938232,
614
+ "nll": 1.1389682292938232,
615
+ "problem_id": "1398_A. Bad Triangle",
616
+ "skipped": null
617
+ },
618
+ {
619
+ "grad_norm": 1.9144845008850098,
620
+ "index": 78,
621
+ "loss": 0.7307466268539429,
622
+ "nll": 0.7307466268539429,
623
+ "problem_id": "483_C. Diverse Permutation",
624
+ "skipped": null
625
+ },
626
+ {
627
+ "grad_norm": 1.0251142978668213,
628
+ "index": 79,
629
+ "loss": 0.7849968075752258,
630
+ "nll": 0.7849968075752258,
631
+ "problem_id": "673_A. Bear and Game",
632
+ "skipped": null
633
+ },
634
+ {
635
+ "grad_norm": 1.3851652145385742,
636
+ "index": 80,
637
+ "loss": 0.9004217386245728,
638
+ "nll": 0.9004217386245728,
639
+ "problem_id": "604_A. Uncowed Forces",
640
+ "skipped": null
641
+ },
642
+ {
643
+ "grad_norm": 0.8206305503845215,
644
+ "index": 81,
645
+ "loss": 0.513279914855957,
646
+ "nll": 0.513279914855957,
647
+ "problem_id": "1059_A. Cashier",
648
+ "skipped": null
649
+ },
650
+ {
651
+ "grad_norm": 0.4920770823955536,
652
+ "index": 82,
653
+ "loss": 0.2822416424751282,
654
+ "nll": 0.2822416424751282,
655
+ "problem_id": "835_A. Key races",
656
+ "skipped": null
657
+ },
658
+ {
659
+ "grad_norm": 0.789677083492279,
660
+ "index": 83,
661
+ "loss": 0.6259894967079163,
662
+ "nll": 0.6259894967079163,
663
+ "problem_id": "1490_D. Permutation Transformation",
664
+ "skipped": null
665
+ },
666
+ {
667
+ "grad_norm": 0.9807916879653931,
668
+ "index": 84,
669
+ "loss": 0.98895663022995,
670
+ "nll": 0.98895663022995,
671
+ "problem_id": "443_B. Kolya and Tandem Repeat",
672
+ "skipped": null
673
+ },
674
+ {
675
+ "grad_norm": 0.6448408365249634,
676
+ "index": 85,
677
+ "loss": 0.4732319116592407,
678
+ "nll": 0.4732319116592407,
679
+ "problem_id": "580_B. Kefa and Company",
680
+ "skipped": null
681
+ },
682
+ {
683
+ "grad_norm": 0.6379855871200562,
684
+ "index": 86,
685
+ "loss": 0.470840722322464,
686
+ "nll": 0.470840722322464,
687
+ "problem_id": "143_A. Help Vasilisa the Wise 2",
688
+ "skipped": null
689
+ },
690
+ {
691
+ "grad_norm": 0.816592276096344,
692
+ "index": 87,
693
+ "loss": 0.8404387831687927,
694
+ "nll": 0.8404387831687927,
695
+ "problem_id": "1011_A. Stages",
696
+ "skipped": null
697
+ },
698
+ {
699
+ "grad_norm": 0.6529431343078613,
700
+ "index": 88,
701
+ "loss": 0.6879411935806274,
702
+ "nll": 0.6879411935806274,
703
+ "problem_id": "1269_B. Modulo Equality",
704
+ "skipped": null
705
+ },
706
+ {
707
+ "grad_norm": 0.6517459154129028,
708
+ "index": 89,
709
+ "loss": 0.5100618004798889,
710
+ "nll": 0.5100618004798889,
711
+ "problem_id": "1543_B. Customising the Track",
712
+ "skipped": null
713
+ },
714
+ {
715
+ "grad_norm": 0.5063552260398865,
716
+ "index": 90,
717
+ "loss": 0.49379613995552063,
718
+ "nll": 0.49379613995552063,
719
+ "problem_id": "177_C1. Party",
720
+ "skipped": null
721
+ },
722
+ {
723
+ "grad_norm": 1.0049214363098145,
724
+ "index": 91,
725
+ "loss": 0.4494905471801758,
726
+ "nll": 0.4494905471801758,
727
+ "problem_id": "379_A. New Year Candles",
728
+ "skipped": null
729
+ },
730
+ {
731
+ "grad_norm": 0.5677995681762695,
732
+ "index": 92,
733
+ "loss": 0.5990645885467529,
734
+ "nll": 0.5990645885467529,
735
+ "problem_id": "1474_B. Different Divisors",
736
+ "skipped": null
737
+ },
738
+ {
739
+ "grad_norm": 0.9032794237136841,
740
+ "index": 93,
741
+ "loss": 0.5278613567352295,
742
+ "nll": 0.5278613567352295,
743
+ "problem_id": "155_A. I_love_%username%",
744
+ "skipped": null
745
+ },
746
+ {
747
+ "grad_norm": 0.44249868392944336,
748
+ "index": 94,
749
+ "loss": 0.372690349817276,
750
+ "nll": 0.372690349817276,
751
+ "problem_id": "673_C. Bear and Colors",
752
+ "skipped": null
753
+ },
754
+ {
755
+ "grad_norm": 0.7681690454483032,
756
+ "index": 95,
757
+ "loss": 0.7501130104064941,
758
+ "nll": 0.7501130104064941,
759
+ "problem_id": "381_A. Sereja and Dima",
760
+ "skipped": null
761
+ },
762
+ {
763
+ "grad_norm": 1.172059416770935,
764
+ "index": 96,
765
+ "loss": 0.8275896310806274,
766
+ "nll": 0.8275896310806274,
767
+ "problem_id": "39_H. Multiplication Table",
768
+ "skipped": null
769
+ }
770
+ ]
eval/training_stage_log.json ADDED
@@ -0,0 +1,2010 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "advantages": [
4
+ -0.16666666666666666,
5
+ -0.16666666666666666,
6
+ 0.8333333333333334,
7
+ -0.16666666666666666,
8
+ -0.16666666666666666,
9
+ -0.16666666666666666,
10
+ 0.8333333333333334,
11
+ -0.16666666666666666,
12
+ -0.16666666666666666,
13
+ -0.16666666666666666,
14
+ -0.16666666666666666,
15
+ -0.16666666666666666
16
+ ],
17
+ "candidate_attempts": [
18
+ {
19
+ "advantages": [
20
+ -0.16666666666666666,
21
+ -0.16666666666666666,
22
+ 0.8333333333333334,
23
+ -0.16666666666666666,
24
+ -0.16666666666666666,
25
+ -0.16666666666666666,
26
+ 0.8333333333333334,
27
+ -0.16666666666666666,
28
+ -0.16666666666666666,
29
+ -0.16666666666666666,
30
+ -0.16666666666666666,
31
+ -0.16666666666666666
32
+ ],
33
+ "eligible": true,
34
+ "passes": 2,
35
+ "problem_id": "1090_M. The Pleasant Walk",
36
+ "rewards": [
37
+ 0.0,
38
+ 0.0,
39
+ 1.0,
40
+ 0.0,
41
+ 0.0,
42
+ 0.0,
43
+ 1.0,
44
+ 0.0,
45
+ 0.0,
46
+ 0.0,
47
+ 0.0,
48
+ 0.0
49
+ ]
50
+ }
51
+ ],
52
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage0_group0",
53
+ "grad_norm": 0.15402822196483612,
54
+ "group": 0,
55
+ "k": 1,
56
+ "losses": [
57
+ 0.0,
58
+ -0.0062665618024766445,
59
+ 0.01790863275527954,
60
+ 0.0,
61
+ -0.005659318529069424,
62
+ -0.009413816966116428,
63
+ 0.022304832935333252,
64
+ -0.006309435237199068,
65
+ -0.006303392816334963,
66
+ 0.0,
67
+ -0.005746547598391771,
68
+ -0.012491217814385891
69
+ ],
70
+ "nlls": [
71
+ null,
72
+ 0.4511924386024475,
73
+ 0.25788429379463196,
74
+ null,
75
+ 0.4074709415435791,
76
+ 0.6777948141098022,
77
+ 0.3211895823478699,
78
+ 0.4542793333530426,
79
+ 0.453844279050827,
80
+ null,
81
+ 0.41375142335891724,
82
+ 0.8993676900863647
83
+ ],
84
+ "problem_id": "1090_M. The Pleasant Walk",
85
+ "rewards": [
86
+ 0.0,
87
+ 0.0,
88
+ 1.0,
89
+ 0.0,
90
+ 0.0,
91
+ 0.0,
92
+ 1.0,
93
+ 0.0,
94
+ 0.0,
95
+ 0.0,
96
+ 0.0,
97
+ 0.0
98
+ ],
99
+ "skipped_samples": [
100
+ {
101
+ "reason": "invalid_final",
102
+ "sample": 0
103
+ },
104
+ {
105
+ "reason": "invalid_final",
106
+ "sample": 3
107
+ },
108
+ {
109
+ "reason": "invalid_final",
110
+ "sample": 9
111
+ }
112
+ ],
113
+ "stage": 0
114
+ },
115
+ {
116
+ "advantages": [
117
+ -0.16666666666666666,
118
+ -0.16666666666666666,
119
+ 0.8333333333333334,
120
+ -0.16666666666666666,
121
+ -0.16666666666666666,
122
+ -0.16666666666666666,
123
+ -0.16666666666666666,
124
+ -0.16666666666666666,
125
+ 0.8333333333333334,
126
+ -0.16666666666666666,
127
+ -0.16666666666666666,
128
+ -0.16666666666666666
129
+ ],
130
+ "candidate_attempts": [
131
+ {
132
+ "advantages": [
133
+ 0.0,
134
+ 0.0,
135
+ 0.0,
136
+ 0.0,
137
+ 0.0,
138
+ 0.0,
139
+ 0.0,
140
+ 0.0,
141
+ 0.0,
142
+ 0.0,
143
+ 0.0,
144
+ 0.0
145
+ ],
146
+ "eligible": false,
147
+ "passes": 0,
148
+ "problem_id": "38_B. Chess",
149
+ "rewards": [
150
+ 0.0,
151
+ 0.0,
152
+ 0.0,
153
+ 0.0,
154
+ 0.0,
155
+ 0.0,
156
+ 0.0,
157
+ 0.0,
158
+ 0.0,
159
+ 0.0,
160
+ 0.0,
161
+ 0.0
162
+ ]
163
+ },
164
+ {
165
+ "advantages": [
166
+ 0.0,
167
+ 0.0,
168
+ 0.0,
169
+ 0.0,
170
+ 0.0,
171
+ 0.0,
172
+ 0.0,
173
+ 0.0,
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0
178
+ ],
179
+ "eligible": false,
180
+ "passes": 0,
181
+ "problem_id": "749_B. Parallelogram is Back",
182
+ "rewards": [
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0,
190
+ 0.0,
191
+ 0.0,
192
+ 0.0,
193
+ 0.0,
194
+ 0.0
195
+ ]
196
+ },
197
+ {
198
+ "advantages": [
199
+ 0.0,
200
+ 0.0,
201
+ 0.0,
202
+ 0.0,
203
+ 0.0,
204
+ 0.0,
205
+ 0.0,
206
+ 0.0,
207
+ 0.0,
208
+ 0.0,
209
+ 0.0,
210
+ 0.0
211
+ ],
212
+ "eligible": false,
213
+ "passes": 0,
214
+ "problem_id": "1451_B. Non-Substring Subsequence",
215
+ "rewards": [
216
+ 0.0,
217
+ 0.0,
218
+ 0.0,
219
+ 0.0,
220
+ 0.0,
221
+ 0.0,
222
+ 0.0,
223
+ 0.0,
224
+ 0.0,
225
+ 0.0,
226
+ 0.0,
227
+ 0.0
228
+ ]
229
+ },
230
+ {
231
+ "advantages": [
232
+ 0.0,
233
+ 0.0,
234
+ 0.0,
235
+ 0.0,
236
+ 0.0,
237
+ 0.0,
238
+ 0.0,
239
+ 0.0,
240
+ 0.0,
241
+ 0.0,
242
+ 0.0,
243
+ 0.0
244
+ ],
245
+ "eligible": false,
246
+ "passes": 0,
247
+ "problem_id": "622_A. Infinite Sequence",
248
+ "rewards": [
249
+ 0.0,
250
+ 0.0,
251
+ 0.0,
252
+ 0.0,
253
+ 0.0,
254
+ 0.0,
255
+ 0.0,
256
+ 0.0,
257
+ 0.0,
258
+ 0.0,
259
+ 0.0,
260
+ 0.0
261
+ ]
262
+ },
263
+ {
264
+ "advantages": [
265
+ -0.16666666666666666,
266
+ -0.16666666666666666,
267
+ 0.8333333333333334,
268
+ -0.16666666666666666,
269
+ -0.16666666666666666,
270
+ -0.16666666666666666,
271
+ -0.16666666666666666,
272
+ -0.16666666666666666,
273
+ 0.8333333333333334,
274
+ -0.16666666666666666,
275
+ -0.16666666666666666,
276
+ -0.16666666666666666
277
+ ],
278
+ "eligible": true,
279
+ "passes": 2,
280
+ "problem_id": "266_B. Queue at the School",
281
+ "rewards": [
282
+ 0.0,
283
+ 0.0,
284
+ 1.0,
285
+ 0.0,
286
+ 0.0,
287
+ 0.0,
288
+ 0.0,
289
+ 0.0,
290
+ 1.0,
291
+ 0.0,
292
+ 0.0,
293
+ 0.0
294
+ ]
295
+ }
296
+ ],
297
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage0_group1",
298
+ "grad_norm": 0.25454211235046387,
299
+ "group": 1,
300
+ "k": 1,
301
+ "losses": [
302
+ 0.0,
303
+ -0.0036656493321061134,
304
+ 0.03466184437274933,
305
+ -0.004902771208435297,
306
+ 0.0,
307
+ -0.005019296891987324,
308
+ -0.006813161075115204,
309
+ -0.011760557070374489,
310
+ 0.022579248994588852,
311
+ 0.0,
312
+ 0.0,
313
+ 0.0
314
+ ],
315
+ "nlls": [
316
+ null,
317
+ 0.26392674446105957,
318
+ 0.4991305470466614,
319
+ 0.3529995381832123,
320
+ null,
321
+ 0.3613893687725067,
322
+ 0.4905475974082947,
323
+ 0.846760094165802,
324
+ 0.32514116168022156,
325
+ null,
326
+ null,
327
+ null
328
+ ],
329
+ "problem_id": "266_B. Queue at the School",
330
+ "rewards": [
331
+ 0.0,
332
+ 0.0,
333
+ 1.0,
334
+ 0.0,
335
+ 0.0,
336
+ 0.0,
337
+ 0.0,
338
+ 0.0,
339
+ 1.0,
340
+ 0.0,
341
+ 0.0,
342
+ 0.0
343
+ ],
344
+ "skipped_samples": [
345
+ {
346
+ "reason": "invalid_final",
347
+ "sample": 0
348
+ },
349
+ {
350
+ "reason": "invalid_final",
351
+ "sample": 4
352
+ },
353
+ {
354
+ "reason": "invalid_final",
355
+ "sample": 9
356
+ },
357
+ {
358
+ "reason": "invalid_final",
359
+ "sample": 10
360
+ },
361
+ {
362
+ "reason": "invalid_final",
363
+ "sample": 11
364
+ }
365
+ ],
366
+ "stage": 0
367
+ },
368
+ {
369
+ "advantages": [
370
+ -0.08333333333333333,
371
+ -0.08333333333333333,
372
+ -0.08333333333333333,
373
+ -0.08333333333333333,
374
+ -0.08333333333333333,
375
+ -0.08333333333333333,
376
+ -0.08333333333333333,
377
+ -0.08333333333333333,
378
+ 0.9166666666666665,
379
+ -0.08333333333333333,
380
+ -0.08333333333333333,
381
+ -0.08333333333333333
382
+ ],
383
+ "candidate_attempts": [
384
+ {
385
+ "advantages": [
386
+ -0.08333333333333333,
387
+ -0.08333333333333333,
388
+ -0.08333333333333333,
389
+ -0.08333333333333333,
390
+ -0.08333333333333333,
391
+ -0.08333333333333333,
392
+ -0.08333333333333333,
393
+ -0.08333333333333333,
394
+ 0.9166666666666665,
395
+ -0.08333333333333333,
396
+ -0.08333333333333333,
397
+ -0.08333333333333333
398
+ ],
399
+ "eligible": true,
400
+ "passes": 1,
401
+ "problem_id": "549_A. Face Detection",
402
+ "rewards": [
403
+ 0.0,
404
+ 0.0,
405
+ 0.0,
406
+ 0.0,
407
+ 0.0,
408
+ 0.0,
409
+ 0.0,
410
+ 0.0,
411
+ 1.0,
412
+ 0.0,
413
+ 0.0,
414
+ 0.0
415
+ ]
416
+ }
417
+ ],
418
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage0_group2",
419
+ "grad_norm": 0.04858814924955368,
420
+ "group": 2,
421
+ "k": 1,
422
+ "losses": [
423
+ -0.0012184502556920052,
424
+ 0.0,
425
+ -0.0016815627459436655,
426
+ -0.002285321243107319,
427
+ -0.001479756785556674,
428
+ 0.0,
429
+ -0.002193969674408436,
430
+ 0.0,
431
+ 0.025543252006173134,
432
+ -0.0022434527054429054,
433
+ -0.0023422008380293846,
434
+ -0.0018333798507228494
435
+ ],
436
+ "nlls": [
437
+ 0.17545683681964874,
438
+ null,
439
+ 0.24214503169059753,
440
+ 0.3290862441062927,
441
+ 0.21308498084545135,
442
+ null,
443
+ 0.31593161821365356,
444
+ null,
445
+ 0.33438438177108765,
446
+ 0.3230571746826172,
447
+ 0.3372769057750702,
448
+ 0.26400670409202576
449
+ ],
450
+ "problem_id": "549_A. Face Detection",
451
+ "rewards": [
452
+ 0.0,
453
+ 0.0,
454
+ 0.0,
455
+ 0.0,
456
+ 0.0,
457
+ 0.0,
458
+ 0.0,
459
+ 0.0,
460
+ 1.0,
461
+ 0.0,
462
+ 0.0,
463
+ 0.0
464
+ ],
465
+ "skipped_samples": [
466
+ {
467
+ "reason": "invalid_final",
468
+ "sample": 1
469
+ },
470
+ {
471
+ "reason": "invalid_final",
472
+ "sample": 5
473
+ },
474
+ {
475
+ "reason": "invalid_final",
476
+ "sample": 7
477
+ }
478
+ ],
479
+ "stage": 0
480
+ },
481
+ {
482
+ "candidate_attempts": [
483
+ {
484
+ "advantages": [
485
+ 0.0,
486
+ 0.0,
487
+ 0.0,
488
+ 0.0,
489
+ 0.0,
490
+ 0.0,
491
+ 0.0,
492
+ 0.0,
493
+ 0.0,
494
+ 0.0,
495
+ 0.0,
496
+ 0.0
497
+ ],
498
+ "eligible": false,
499
+ "passes": 0,
500
+ "problem_id": "1184_A1. Heidi Learns Hashing (Easy)",
501
+ "rewards": [
502
+ 0.0,
503
+ 0.0,
504
+ 0.0,
505
+ 0.0,
506
+ 0.0,
507
+ 0.0,
508
+ 0.0,
509
+ 0.0,
510
+ 0.0,
511
+ 0.0,
512
+ 0.0,
513
+ 0.0
514
+ ]
515
+ },
516
+ {
517
+ "advantages": [
518
+ 0.0,
519
+ 0.0,
520
+ 0.0,
521
+ 0.0,
522
+ 0.0,
523
+ 0.0,
524
+ 0.0,
525
+ 0.0,
526
+ 0.0,
527
+ 0.0,
528
+ 0.0,
529
+ 0.0
530
+ ],
531
+ "eligible": false,
532
+ "passes": 0,
533
+ "problem_id": "1267_B. Balls of Buma",
534
+ "rewards": [
535
+ 0.0,
536
+ 0.0,
537
+ 0.0,
538
+ 0.0,
539
+ 0.0,
540
+ 0.0,
541
+ 0.0,
542
+ 0.0,
543
+ 0.0,
544
+ 0.0,
545
+ 0.0,
546
+ 0.0
547
+ ]
548
+ },
549
+ {
550
+ "advantages": [
551
+ 0.0,
552
+ 0.0,
553
+ 0.0,
554
+ 0.0,
555
+ 0.0,
556
+ 0.0,
557
+ 0.0,
558
+ 0.0,
559
+ 0.0,
560
+ 0.0,
561
+ 0.0,
562
+ 0.0
563
+ ],
564
+ "eligible": false,
565
+ "passes": 0,
566
+ "problem_id": "389_A. Fox and Number Game",
567
+ "rewards": [
568
+ 0.0,
569
+ 0.0,
570
+ 0.0,
571
+ 0.0,
572
+ 0.0,
573
+ 0.0,
574
+ 0.0,
575
+ 0.0,
576
+ 0.0,
577
+ 0.0,
578
+ 0.0,
579
+ 0.0
580
+ ]
581
+ },
582
+ {
583
+ "advantages": [
584
+ 0.0,
585
+ 0.0,
586
+ 0.0,
587
+ 0.0,
588
+ 0.0,
589
+ 0.0,
590
+ 0.0,
591
+ 0.0,
592
+ 0.0,
593
+ 0.0,
594
+ 0.0,
595
+ 0.0
596
+ ],
597
+ "eligible": false,
598
+ "passes": 0,
599
+ "problem_id": "1476_A. K-divisible Sum",
600
+ "rewards": [
601
+ 0.0,
602
+ 0.0,
603
+ 0.0,
604
+ 0.0,
605
+ 0.0,
606
+ 0.0,
607
+ 0.0,
608
+ 0.0,
609
+ 0.0,
610
+ 0.0,
611
+ 0.0,
612
+ 0.0
613
+ ]
614
+ },
615
+ {
616
+ "advantages": [
617
+ 0.0,
618
+ 0.0,
619
+ 0.0,
620
+ 0.0,
621
+ 0.0,
622
+ 0.0,
623
+ 0.0,
624
+ 0.0,
625
+ 0.0,
626
+ 0.0,
627
+ 0.0,
628
+ 0.0
629
+ ],
630
+ "eligible": false,
631
+ "passes": 0,
632
+ "problem_id": "124_C. Prime Permutation",
633
+ "rewards": [
634
+ 0.0,
635
+ 0.0,
636
+ 0.0,
637
+ 0.0,
638
+ 0.0,
639
+ 0.0,
640
+ 0.0,
641
+ 0.0,
642
+ 0.0,
643
+ 0.0,
644
+ 0.0,
645
+ 0.0
646
+ ]
647
+ }
648
+ ],
649
+ "group": 3,
650
+ "k": 1,
651
+ "skipped": "no_pkpo_eligible_group",
652
+ "stage": 0
653
+ },
654
+ {
655
+ "advantages": [
656
+ 6.661338147750939e-16,
657
+ 6.661338147750939e-16,
658
+ 6.661338147750939e-16,
659
+ 6.661338147750939e-16,
660
+ 6.661338147750939e-16,
661
+ 6.661338147750939e-16,
662
+ 6.661338147750939e-16,
663
+ 6.661338147750939e-16,
664
+ 8.0,
665
+ 6.661338147750939e-16,
666
+ 6.661338147750939e-16,
667
+ 6.661338147750939e-16
668
+ ],
669
+ "candidate_attempts": [
670
+ {
671
+ "advantages": [
672
+ 0.0,
673
+ 0.0,
674
+ 0.0,
675
+ 0.0,
676
+ 0.0,
677
+ 0.0,
678
+ 0.0,
679
+ 0.0,
680
+ 0.0,
681
+ 0.0,
682
+ 0.0,
683
+ 0.0
684
+ ],
685
+ "eligible": false,
686
+ "passes": 0,
687
+ "problem_id": "1191_A. Tokitsukaze and Enhancement",
688
+ "rewards": [
689
+ 0.0,
690
+ 0.0,
691
+ 0.0,
692
+ 0.0,
693
+ 0.0,
694
+ 0.0,
695
+ 0.0,
696
+ 0.0,
697
+ 0.0,
698
+ 0.0,
699
+ 0.0,
700
+ 0.0
701
+ ]
702
+ },
703
+ {
704
+ "advantages": [
705
+ 0.0,
706
+ 0.0,
707
+ 0.0,
708
+ 0.0,
709
+ 0.0,
710
+ 0.0,
711
+ 0.0,
712
+ 0.0,
713
+ 0.0,
714
+ 0.0,
715
+ 0.0,
716
+ 0.0
717
+ ],
718
+ "eligible": false,
719
+ "passes": 0,
720
+ "problem_id": "1278_A. Shuffle Hashing",
721
+ "rewards": [
722
+ 0.0,
723
+ 0.0,
724
+ 0.0,
725
+ 0.0,
726
+ 0.0,
727
+ 0.0,
728
+ 0.0,
729
+ 0.0,
730
+ 0.0,
731
+ 0.0,
732
+ 0.0,
733
+ 0.0
734
+ ]
735
+ },
736
+ {
737
+ "advantages": [
738
+ 0.0,
739
+ 0.0,
740
+ 0.0,
741
+ 0.0,
742
+ 0.0,
743
+ 0.0,
744
+ 0.0,
745
+ 0.0,
746
+ 0.0,
747
+ 0.0,
748
+ 0.0,
749
+ 0.0
750
+ ],
751
+ "eligible": false,
752
+ "passes": 0,
753
+ "problem_id": "1064_B. Equations of Mathematical Magic",
754
+ "rewards": [
755
+ 0.0,
756
+ 0.0,
757
+ 0.0,
758
+ 0.0,
759
+ 0.0,
760
+ 0.0,
761
+ 0.0,
762
+ 0.0,
763
+ 0.0,
764
+ 0.0,
765
+ 0.0,
766
+ 0.0
767
+ ]
768
+ },
769
+ {
770
+ "advantages": [
771
+ 0.0,
772
+ 0.0,
773
+ 0.0,
774
+ 0.0,
775
+ 0.0,
776
+ 0.0,
777
+ 0.0,
778
+ 0.0,
779
+ 0.0,
780
+ 0.0,
781
+ 0.0,
782
+ 0.0
783
+ ],
784
+ "eligible": false,
785
+ "passes": 0,
786
+ "problem_id": "624_B. Making a String",
787
+ "rewards": [
788
+ 0.0,
789
+ 0.0,
790
+ 0.0,
791
+ 0.0,
792
+ 0.0,
793
+ 0.0,
794
+ 0.0,
795
+ 0.0,
796
+ 0.0,
797
+ 0.0,
798
+ 0.0,
799
+ 0.0
800
+ ]
801
+ },
802
+ {
803
+ "advantages": [
804
+ 6.661338147750939e-16,
805
+ 6.661338147750939e-16,
806
+ 6.661338147750939e-16,
807
+ 6.661338147750939e-16,
808
+ 6.661338147750939e-16,
809
+ 6.661338147750939e-16,
810
+ 6.661338147750939e-16,
811
+ 6.661338147750939e-16,
812
+ 8.0,
813
+ 6.661338147750939e-16,
814
+ 6.661338147750939e-16,
815
+ 6.661338147750939e-16
816
+ ],
817
+ "eligible": true,
818
+ "passes": 1,
819
+ "problem_id": "488_A. Giga Tower",
820
+ "rewards": [
821
+ 0.0,
822
+ 0.0,
823
+ 0.0,
824
+ 0.0,
825
+ 0.0,
826
+ 0.0,
827
+ 0.0,
828
+ 0.0,
829
+ 1.0,
830
+ 0.0,
831
+ 0.0,
832
+ 0.0
833
+ ]
834
+ }
835
+ ],
836
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage1_group0",
837
+ "grad_norm": 2.4634461402893066,
838
+ "group": 0,
839
+ "k": 8,
840
+ "losses": [
841
+ 0.0,
842
+ 0.0,
843
+ 0.0,
844
+ 0.0,
845
+ 0.0,
846
+ 0.0,
847
+ 0.0,
848
+ 0.0,
849
+ 0.31233516335487366,
850
+ 0.0,
851
+ 0.0,
852
+ 0.0
853
+ ],
854
+ "nlls": [
855
+ null,
856
+ null,
857
+ null,
858
+ null,
859
+ null,
860
+ null,
861
+ null,
862
+ null,
863
+ 0.4685027301311493,
864
+ null,
865
+ null,
866
+ null
867
+ ],
868
+ "problem_id": "488_A. Giga Tower",
869
+ "rewards": [
870
+ 0.0,
871
+ 0.0,
872
+ 0.0,
873
+ 0.0,
874
+ 0.0,
875
+ 0.0,
876
+ 0.0,
877
+ 0.0,
878
+ 1.0,
879
+ 0.0,
880
+ 0.0,
881
+ 0.0
882
+ ],
883
+ "skipped_samples": [
884
+ {
885
+ "reason": "invalid_final",
886
+ "sample": 1
887
+ },
888
+ {
889
+ "reason": "invalid_final",
890
+ "sample": 3
891
+ },
892
+ {
893
+ "reason": "invalid_final",
894
+ "sample": 6
895
+ },
896
+ {
897
+ "reason": "invalid_final",
898
+ "sample": 7
899
+ },
900
+ {
901
+ "reason": "invalid_final",
902
+ "sample": 11
903
+ }
904
+ ],
905
+ "stage": 1
906
+ },
907
+ {
908
+ "advantages": [
909
+ 6.661338147750939e-16,
910
+ 6.661338147750939e-16,
911
+ 6.661338147750939e-16,
912
+ 8.0,
913
+ 6.661338147750939e-16,
914
+ 6.661338147750939e-16,
915
+ 6.661338147750939e-16,
916
+ 6.661338147750939e-16,
917
+ 6.661338147750939e-16,
918
+ 6.661338147750939e-16,
919
+ 6.661338147750939e-16,
920
+ 6.661338147750939e-16
921
+ ],
922
+ "candidate_attempts": [
923
+ {
924
+ "advantages": [
925
+ 0.0,
926
+ 0.0,
927
+ 0.0,
928
+ 0.0,
929
+ 0.0,
930
+ 0.0,
931
+ 0.0,
932
+ 0.0,
933
+ 0.0,
934
+ 0.0,
935
+ 0.0,
936
+ 0.0
937
+ ],
938
+ "eligible": false,
939
+ "passes": 0,
940
+ "problem_id": "1220_C. Substring Game in the Lesson",
941
+ "rewards": [
942
+ 0.0,
943
+ 0.0,
944
+ 0.0,
945
+ 0.0,
946
+ 0.0,
947
+ 0.0,
948
+ 0.0,
949
+ 0.0,
950
+ 0.0,
951
+ 0.0,
952
+ 0.0,
953
+ 0.0
954
+ ]
955
+ },
956
+ {
957
+ "advantages": [
958
+ 0.0,
959
+ 0.0,
960
+ 0.0,
961
+ 0.0,
962
+ 0.0,
963
+ 0.0,
964
+ 0.0,
965
+ 0.0,
966
+ 0.0,
967
+ 0.0,
968
+ 0.0,
969
+ 0.0
970
+ ],
971
+ "eligible": false,
972
+ "passes": 0,
973
+ "problem_id": "870_B. Maximum of Maximums of Minimums",
974
+ "rewards": [
975
+ 0.0,
976
+ 0.0,
977
+ 0.0,
978
+ 0.0,
979
+ 0.0,
980
+ 0.0,
981
+ 0.0,
982
+ 0.0,
983
+ 0.0,
984
+ 0.0,
985
+ 0.0,
986
+ 0.0
987
+ ]
988
+ },
989
+ {
990
+ "advantages": [
991
+ 0.0,
992
+ 0.0,
993
+ 0.0,
994
+ 0.0,
995
+ 0.0,
996
+ 0.0,
997
+ 0.0,
998
+ 0.0,
999
+ 0.0,
1000
+ 0.0,
1001
+ 0.0,
1002
+ 0.0
1003
+ ],
1004
+ "eligible": false,
1005
+ "passes": 0,
1006
+ "problem_id": "1100_C. NN and the Optical Illusion",
1007
+ "rewards": [
1008
+ 0.0,
1009
+ 0.0,
1010
+ 0.0,
1011
+ 0.0,
1012
+ 0.0,
1013
+ 0.0,
1014
+ 0.0,
1015
+ 0.0,
1016
+ 0.0,
1017
+ 0.0,
1018
+ 0.0,
1019
+ 0.0
1020
+ ]
1021
+ },
1022
+ {
1023
+ "advantages": [
1024
+ 6.661338147750939e-16,
1025
+ 6.661338147750939e-16,
1026
+ 6.661338147750939e-16,
1027
+ 8.0,
1028
+ 6.661338147750939e-16,
1029
+ 6.661338147750939e-16,
1030
+ 6.661338147750939e-16,
1031
+ 6.661338147750939e-16,
1032
+ 6.661338147750939e-16,
1033
+ 6.661338147750939e-16,
1034
+ 6.661338147750939e-16,
1035
+ 6.661338147750939e-16
1036
+ ],
1037
+ "eligible": true,
1038
+ "passes": 1,
1039
+ "problem_id": "1436_A. Reorder",
1040
+ "rewards": [
1041
+ 0.0,
1042
+ 0.0,
1043
+ 0.0,
1044
+ 1.0,
1045
+ 0.0,
1046
+ 0.0,
1047
+ 0.0,
1048
+ 0.0,
1049
+ 0.0,
1050
+ 0.0,
1051
+ 0.0,
1052
+ 0.0
1053
+ ]
1054
+ }
1055
+ ],
1056
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage1_group1",
1057
+ "grad_norm": 0.9941281080245972,
1058
+ "group": 1,
1059
+ "k": 8,
1060
+ "losses": [
1061
+ 0.0,
1062
+ 0.0,
1063
+ 0.0,
1064
+ 0.23788821697235107,
1065
+ 0.0,
1066
+ 0.0,
1067
+ 0.0,
1068
+ 0.0,
1069
+ 0.0,
1070
+ 0.0,
1071
+ 0.0,
1072
+ 0.0
1073
+ ],
1074
+ "nlls": [
1075
+ null,
1076
+ null,
1077
+ null,
1078
+ 0.3568323254585266,
1079
+ null,
1080
+ null,
1081
+ null,
1082
+ null,
1083
+ null,
1084
+ null,
1085
+ null,
1086
+ null
1087
+ ],
1088
+ "problem_id": "1436_A. Reorder",
1089
+ "rewards": [
1090
+ 0.0,
1091
+ 0.0,
1092
+ 0.0,
1093
+ 1.0,
1094
+ 0.0,
1095
+ 0.0,
1096
+ 0.0,
1097
+ 0.0,
1098
+ 0.0,
1099
+ 0.0,
1100
+ 0.0,
1101
+ 0.0
1102
+ ],
1103
+ "skipped_samples": [
1104
+ {
1105
+ "reason": "invalid_final",
1106
+ "sample": 1
1107
+ },
1108
+ {
1109
+ "reason": "invalid_final",
1110
+ "sample": 2
1111
+ },
1112
+ {
1113
+ "reason": "invalid_final",
1114
+ "sample": 4
1115
+ },
1116
+ {
1117
+ "reason": "invalid_final",
1118
+ "sample": 5
1119
+ },
1120
+ {
1121
+ "reason": "invalid_final",
1122
+ "sample": 6
1123
+ },
1124
+ {
1125
+ "reason": "invalid_final",
1126
+ "sample": 10
1127
+ }
1128
+ ],
1129
+ "stage": 1
1130
+ },
1131
+ {
1132
+ "advantages": [
1133
+ 6.661338147750939e-16,
1134
+ 6.661338147750939e-16,
1135
+ 6.661338147750939e-16,
1136
+ 6.661338147750939e-16,
1137
+ 6.661338147750939e-16,
1138
+ 8.0,
1139
+ 6.661338147750939e-16,
1140
+ 6.661338147750939e-16,
1141
+ 6.661338147750939e-16,
1142
+ 6.661338147750939e-16,
1143
+ 6.661338147750939e-16,
1144
+ 6.661338147750939e-16
1145
+ ],
1146
+ "candidate_attempts": [
1147
+ {
1148
+ "advantages": [
1149
+ 6.661338147750939e-16,
1150
+ 6.661338147750939e-16,
1151
+ 6.661338147750939e-16,
1152
+ 6.661338147750939e-16,
1153
+ 6.661338147750939e-16,
1154
+ 8.0,
1155
+ 6.661338147750939e-16,
1156
+ 6.661338147750939e-16,
1157
+ 6.661338147750939e-16,
1158
+ 6.661338147750939e-16,
1159
+ 6.661338147750939e-16,
1160
+ 6.661338147750939e-16
1161
+ ],
1162
+ "eligible": true,
1163
+ "passes": 1,
1164
+ "problem_id": "721_A. One-dimensional Japanese Crossword",
1165
+ "rewards": [
1166
+ 0.0,
1167
+ 0.0,
1168
+ 0.0,
1169
+ 0.0,
1170
+ 0.0,
1171
+ 1.0,
1172
+ 0.0,
1173
+ 0.0,
1174
+ 0.0,
1175
+ 0.0,
1176
+ 0.0,
1177
+ 0.0
1178
+ ]
1179
+ }
1180
+ ],
1181
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage1_group2",
1182
+ "grad_norm": 1.1130837202072144,
1183
+ "group": 2,
1184
+ "k": 8,
1185
+ "losses": [
1186
+ 0.0,
1187
+ 0.0,
1188
+ 0.0,
1189
+ 0.0,
1190
+ 0.0,
1191
+ 0.2609608769416809,
1192
+ 0.0,
1193
+ 0.0,
1194
+ 0.0,
1195
+ 0.0,
1196
+ 0.0,
1197
+ 0.0
1198
+ ],
1199
+ "nlls": [
1200
+ null,
1201
+ null,
1202
+ null,
1203
+ null,
1204
+ null,
1205
+ 0.391441285610199,
1206
+ null,
1207
+ null,
1208
+ null,
1209
+ null,
1210
+ null,
1211
+ null
1212
+ ],
1213
+ "problem_id": "721_A. One-dimensional Japanese Crossword",
1214
+ "rewards": [
1215
+ 0.0,
1216
+ 0.0,
1217
+ 0.0,
1218
+ 0.0,
1219
+ 0.0,
1220
+ 1.0,
1221
+ 0.0,
1222
+ 0.0,
1223
+ 0.0,
1224
+ 0.0,
1225
+ 0.0,
1226
+ 0.0
1227
+ ],
1228
+ "skipped_samples": [
1229
+ {
1230
+ "reason": "invalid_final",
1231
+ "sample": 2
1232
+ },
1233
+ {
1234
+ "reason": "invalid_final",
1235
+ "sample": 3
1236
+ },
1237
+ {
1238
+ "reason": "invalid_final",
1239
+ "sample": 4
1240
+ },
1241
+ {
1242
+ "reason": "invalid_final",
1243
+ "sample": 6
1244
+ },
1245
+ {
1246
+ "reason": "invalid_final",
1247
+ "sample": 8
1248
+ },
1249
+ {
1250
+ "reason": "invalid_final",
1251
+ "sample": 9
1252
+ },
1253
+ {
1254
+ "reason": "invalid_final",
1255
+ "sample": 10
1256
+ }
1257
+ ],
1258
+ "stage": 1
1259
+ },
1260
+ {
1261
+ "advantages": [
1262
+ 8.0,
1263
+ 6.661338147750939e-16,
1264
+ 6.661338147750939e-16,
1265
+ 6.661338147750939e-16,
1266
+ 6.661338147750939e-16,
1267
+ 6.661338147750939e-16,
1268
+ 6.661338147750939e-16,
1269
+ 6.661338147750939e-16,
1270
+ 6.661338147750939e-16,
1271
+ 6.661338147750939e-16,
1272
+ 6.661338147750939e-16,
1273
+ 6.661338147750939e-16
1274
+ ],
1275
+ "candidate_attempts": [
1276
+ {
1277
+ "advantages": [
1278
+ 8.0,
1279
+ 6.661338147750939e-16,
1280
+ 6.661338147750939e-16,
1281
+ 6.661338147750939e-16,
1282
+ 6.661338147750939e-16,
1283
+ 6.661338147750939e-16,
1284
+ 6.661338147750939e-16,
1285
+ 6.661338147750939e-16,
1286
+ 6.661338147750939e-16,
1287
+ 6.661338147750939e-16,
1288
+ 6.661338147750939e-16,
1289
+ 6.661338147750939e-16
1290
+ ],
1291
+ "eligible": true,
1292
+ "passes": 1,
1293
+ "problem_id": "483_A. Counterexample ",
1294
+ "rewards": [
1295
+ 1.0,
1296
+ 0.0,
1297
+ 0.0,
1298
+ 0.0,
1299
+ 0.0,
1300
+ 0.0,
1301
+ 0.0,
1302
+ 0.0,
1303
+ 0.0,
1304
+ 0.0,
1305
+ 0.0,
1306
+ 0.0
1307
+ ]
1308
+ }
1309
+ ],
1310
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage1_group3",
1311
+ "grad_norm": 0.8771262764930725,
1312
+ "group": 3,
1313
+ "k": 8,
1314
+ "losses": [
1315
+ 0.23838478326797485,
1316
+ 0.0,
1317
+ 0.0,
1318
+ 0.0,
1319
+ 0.0,
1320
+ 0.0,
1321
+ 0.0,
1322
+ 0.0,
1323
+ 0.0,
1324
+ 0.0,
1325
+ 0.0,
1326
+ 0.0
1327
+ ],
1328
+ "nlls": [
1329
+ 0.3575771749019623,
1330
+ null,
1331
+ null,
1332
+ null,
1333
+ null,
1334
+ null,
1335
+ null,
1336
+ null,
1337
+ null,
1338
+ null,
1339
+ null,
1340
+ null
1341
+ ],
1342
+ "problem_id": "483_A. Counterexample ",
1343
+ "rewards": [
1344
+ 1.0,
1345
+ 0.0,
1346
+ 0.0,
1347
+ 0.0,
1348
+ 0.0,
1349
+ 0.0,
1350
+ 0.0,
1351
+ 0.0,
1352
+ 0.0,
1353
+ 0.0,
1354
+ 0.0,
1355
+ 0.0
1356
+ ],
1357
+ "skipped_samples": [
1358
+ {
1359
+ "reason": "invalid_final",
1360
+ "sample": 3
1361
+ },
1362
+ {
1363
+ "reason": "invalid_final",
1364
+ "sample": 5
1365
+ },
1366
+ {
1367
+ "reason": "invalid_final",
1368
+ "sample": 6
1369
+ },
1370
+ {
1371
+ "reason": "invalid_final",
1372
+ "sample": 7
1373
+ },
1374
+ {
1375
+ "reason": "invalid_final",
1376
+ "sample": 9
1377
+ },
1378
+ {
1379
+ "reason": "invalid_final",
1380
+ "sample": 11
1381
+ }
1382
+ ],
1383
+ "stage": 1
1384
+ },
1385
+ {
1386
+ "advantages": [
1387
+ 0.5,
1388
+ 0.5,
1389
+ 0.5,
1390
+ 0.5,
1391
+ -0.5,
1392
+ 0.5,
1393
+ -0.5,
1394
+ -0.5,
1395
+ -0.5,
1396
+ -0.5,
1397
+ 0.5,
1398
+ -0.5
1399
+ ],
1400
+ "candidate_attempts": [
1401
+ {
1402
+ "advantages": [
1403
+ 0.0,
1404
+ 0.0,
1405
+ 0.0,
1406
+ 0.0,
1407
+ 0.0,
1408
+ 0.0,
1409
+ 0.0,
1410
+ 0.0,
1411
+ 0.0,
1412
+ 0.0,
1413
+ 0.0,
1414
+ 0.0
1415
+ ],
1416
+ "eligible": false,
1417
+ "passes": 0,
1418
+ "problem_id": "831_A. Unimodal Array",
1419
+ "rewards": [
1420
+ 0.0,
1421
+ 0.0,
1422
+ 0.0,
1423
+ 0.0,
1424
+ 0.0,
1425
+ 0.0,
1426
+ 0.0,
1427
+ 0.0,
1428
+ 0.0,
1429
+ 0.0,
1430
+ 0.0,
1431
+ 0.0
1432
+ ]
1433
+ },
1434
+ {
1435
+ "advantages": [
1436
+ 0.0,
1437
+ 0.0,
1438
+ 0.0,
1439
+ 0.0,
1440
+ 0.0,
1441
+ 0.0,
1442
+ 0.0,
1443
+ 0.0,
1444
+ 0.0,
1445
+ 0.0,
1446
+ 0.0,
1447
+ 0.0
1448
+ ],
1449
+ "eligible": false,
1450
+ "passes": 0,
1451
+ "problem_id": "27_B. Tournament",
1452
+ "rewards": [
1453
+ 0.0,
1454
+ 0.0,
1455
+ 0.0,
1456
+ 0.0,
1457
+ 0.0,
1458
+ 0.0,
1459
+ 0.0,
1460
+ 0.0,
1461
+ 0.0,
1462
+ 0.0,
1463
+ 0.0,
1464
+ 0.0
1465
+ ]
1466
+ },
1467
+ {
1468
+ "advantages": [
1469
+ 0.0,
1470
+ 0.0,
1471
+ 0.0,
1472
+ 0.0,
1473
+ 0.0,
1474
+ 0.0,
1475
+ 0.0,
1476
+ 0.0,
1477
+ 0.0,
1478
+ 0.0,
1479
+ 0.0,
1480
+ 0.0
1481
+ ],
1482
+ "eligible": false,
1483
+ "passes": 0,
1484
+ "problem_id": "722_B. Verse Pattern",
1485
+ "rewards": [
1486
+ 0.0,
1487
+ 0.0,
1488
+ 0.0,
1489
+ 0.0,
1490
+ 0.0,
1491
+ 0.0,
1492
+ 0.0,
1493
+ 0.0,
1494
+ 0.0,
1495
+ 0.0,
1496
+ 0.0,
1497
+ 0.0
1498
+ ]
1499
+ },
1500
+ {
1501
+ "advantages": [
1502
+ 0.5,
1503
+ 0.5,
1504
+ 0.5,
1505
+ 0.5,
1506
+ -0.5,
1507
+ 0.5,
1508
+ -0.5,
1509
+ -0.5,
1510
+ -0.5,
1511
+ -0.5,
1512
+ 0.5,
1513
+ -0.5
1514
+ ],
1515
+ "eligible": true,
1516
+ "passes": 6,
1517
+ "problem_id": "888_A. Local Extrema",
1518
+ "rewards": [
1519
+ 1.0,
1520
+ 1.0,
1521
+ 1.0,
1522
+ 1.0,
1523
+ 0.0,
1524
+ 1.0,
1525
+ 0.0,
1526
+ 0.0,
1527
+ 0.0,
1528
+ 0.0,
1529
+ 1.0,
1530
+ 0.0
1531
+ ]
1532
+ }
1533
+ ],
1534
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage2_group0",
1535
+ "grad_norm": 0.25151196122169495,
1536
+ "group": 0,
1537
+ "k": 1,
1538
+ "losses": [
1539
+ 0.015174690634012222,
1540
+ 0.011867734603583813,
1541
+ 0.008792450651526451,
1542
+ 0.05844135582447052,
1543
+ 0.0,
1544
+ 0.014020396396517754,
1545
+ 0.0,
1546
+ 0.0,
1547
+ -0.013643275946378708,
1548
+ -0.0162839163094759,
1549
+ 0.01361892931163311,
1550
+ 0.0
1551
+ ],
1552
+ "nlls": [
1553
+ 0.36419257521629333,
1554
+ 0.2848256230354309,
1555
+ 0.21101881563663483,
1556
+ 1.4025925397872925,
1557
+ null,
1558
+ 0.3364894986152649,
1559
+ null,
1560
+ null,
1561
+ 0.327438622713089,
1562
+ 0.3908139765262604,
1563
+ 0.32685428857803345,
1564
+ null
1565
+ ],
1566
+ "problem_id": "888_A. Local Extrema",
1567
+ "rewards": [
1568
+ 1.0,
1569
+ 1.0,
1570
+ 1.0,
1571
+ 1.0,
1572
+ 0.0,
1573
+ 1.0,
1574
+ 0.0,
1575
+ 0.0,
1576
+ 0.0,
1577
+ 0.0,
1578
+ 1.0,
1579
+ 0.0
1580
+ ],
1581
+ "skipped_samples": [
1582
+ {
1583
+ "reason": "invalid_final",
1584
+ "sample": 4
1585
+ },
1586
+ {
1587
+ "reason": "invalid_final",
1588
+ "sample": 6
1589
+ },
1590
+ {
1591
+ "reason": "invalid_final",
1592
+ "sample": 7
1593
+ },
1594
+ {
1595
+ "reason": "invalid_final",
1596
+ "sample": 11
1597
+ }
1598
+ ],
1599
+ "stage": 2
1600
+ },
1601
+ {
1602
+ "advantages": [
1603
+ -0.25,
1604
+ -0.25,
1605
+ -0.25,
1606
+ -0.25,
1607
+ -0.25,
1608
+ -0.25,
1609
+ -0.25,
1610
+ 0.75,
1611
+ -0.25,
1612
+ -0.25,
1613
+ 0.75,
1614
+ 0.75
1615
+ ],
1616
+ "candidate_attempts": [
1617
+ {
1618
+ "advantages": [
1619
+ 0.0,
1620
+ 0.0,
1621
+ 0.0,
1622
+ 0.0,
1623
+ 0.0,
1624
+ 0.0,
1625
+ 0.0,
1626
+ 0.0,
1627
+ 0.0,
1628
+ 0.0,
1629
+ 0.0,
1630
+ 0.0
1631
+ ],
1632
+ "eligible": false,
1633
+ "passes": 0,
1634
+ "problem_id": "820_A. Mister B and Book Reading",
1635
+ "rewards": [
1636
+ 0.0,
1637
+ 0.0,
1638
+ 0.0,
1639
+ 0.0,
1640
+ 0.0,
1641
+ 0.0,
1642
+ 0.0,
1643
+ 0.0,
1644
+ 0.0,
1645
+ 0.0,
1646
+ 0.0,
1647
+ 0.0
1648
+ ]
1649
+ },
1650
+ {
1651
+ "advantages": [
1652
+ 0.0,
1653
+ 0.0,
1654
+ 0.0,
1655
+ 0.0,
1656
+ 0.0,
1657
+ 0.0,
1658
+ 0.0,
1659
+ 0.0,
1660
+ 0.0,
1661
+ 0.0,
1662
+ 0.0,
1663
+ 0.0
1664
+ ],
1665
+ "eligible": false,
1666
+ "passes": 0,
1667
+ "problem_id": "276_B. Little Girl and Game",
1668
+ "rewards": [
1669
+ 0.0,
1670
+ 0.0,
1671
+ 0.0,
1672
+ 0.0,
1673
+ 0.0,
1674
+ 0.0,
1675
+ 0.0,
1676
+ 0.0,
1677
+ 0.0,
1678
+ 0.0,
1679
+ 0.0,
1680
+ 0.0
1681
+ ]
1682
+ },
1683
+ {
1684
+ "advantages": [
1685
+ -0.25,
1686
+ -0.25,
1687
+ -0.25,
1688
+ -0.25,
1689
+ -0.25,
1690
+ -0.25,
1691
+ -0.25,
1692
+ 0.75,
1693
+ -0.25,
1694
+ -0.25,
1695
+ 0.75,
1696
+ 0.75
1697
+ ],
1698
+ "eligible": true,
1699
+ "passes": 3,
1700
+ "problem_id": "802_G. Fake News (easy)",
1701
+ "rewards": [
1702
+ 0.0,
1703
+ 0.0,
1704
+ 0.0,
1705
+ 0.0,
1706
+ 0.0,
1707
+ 0.0,
1708
+ 0.0,
1709
+ 1.0,
1710
+ 0.0,
1711
+ 0.0,
1712
+ 1.0,
1713
+ 1.0
1714
+ ]
1715
+ }
1716
+ ],
1717
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage2_group1",
1718
+ "grad_norm": 0.18021968007087708,
1719
+ "group": 1,
1720
+ "k": 1,
1721
+ "losses": [
1722
+ -0.007747136987745762,
1723
+ -0.012813568115234375,
1724
+ -0.004977892152965069,
1725
+ -0.003978469409048557,
1726
+ 0.0,
1727
+ -0.006662151776254177,
1728
+ -0.005627603270113468,
1729
+ 0.02030503936111927,
1730
+ -0.004221352748572826,
1731
+ 0.0,
1732
+ 0.027963481843471527,
1733
+ 0.021282752975821495
1734
+ ],
1735
+ "nlls": [
1736
+ 0.3718625605106354,
1737
+ 0.61505126953125,
1738
+ 0.2389388084411621,
1739
+ 0.19096651673316956,
1740
+ null,
1741
+ 0.3197832703590393,
1742
+ 0.2701249420642853,
1743
+ 0.3248806297779083,
1744
+ 0.20262493193149567,
1745
+ null,
1746
+ 0.44741570949554443,
1747
+ 0.3405240476131439
1748
+ ],
1749
+ "problem_id": "802_G. Fake News (easy)",
1750
+ "rewards": [
1751
+ 0.0,
1752
+ 0.0,
1753
+ 0.0,
1754
+ 0.0,
1755
+ 0.0,
1756
+ 0.0,
1757
+ 0.0,
1758
+ 1.0,
1759
+ 0.0,
1760
+ 0.0,
1761
+ 1.0,
1762
+ 1.0
1763
+ ],
1764
+ "skipped_samples": [
1765
+ {
1766
+ "reason": "invalid_final",
1767
+ "sample": 4
1768
+ },
1769
+ {
1770
+ "reason": "invalid_final",
1771
+ "sample": 9
1772
+ }
1773
+ ],
1774
+ "stage": 2
1775
+ },
1776
+ {
1777
+ "advantages": [
1778
+ 0.9166666666666665,
1779
+ -0.08333333333333333,
1780
+ -0.08333333333333333,
1781
+ -0.08333333333333333,
1782
+ -0.08333333333333333,
1783
+ -0.08333333333333333,
1784
+ -0.08333333333333333,
1785
+ -0.08333333333333333,
1786
+ -0.08333333333333333,
1787
+ -0.08333333333333333,
1788
+ -0.08333333333333333,
1789
+ -0.08333333333333333
1790
+ ],
1791
+ "candidate_attempts": [
1792
+ {
1793
+ "advantages": [
1794
+ 0.9166666666666665,
1795
+ -0.08333333333333333,
1796
+ -0.08333333333333333,
1797
+ -0.08333333333333333,
1798
+ -0.08333333333333333,
1799
+ -0.08333333333333333,
1800
+ -0.08333333333333333,
1801
+ -0.08333333333333333,
1802
+ -0.08333333333333333,
1803
+ -0.08333333333333333,
1804
+ -0.08333333333333333,
1805
+ -0.08333333333333333
1806
+ ],
1807
+ "eligible": true,
1808
+ "passes": 1,
1809
+ "problem_id": "1155_C. Alarm Clocks Everywhere",
1810
+ "rewards": [
1811
+ 1.0,
1812
+ 0.0,
1813
+ 0.0,
1814
+ 0.0,
1815
+ 0.0,
1816
+ 0.0,
1817
+ 0.0,
1818
+ 0.0,
1819
+ 0.0,
1820
+ 0.0,
1821
+ 0.0,
1822
+ 0.0
1823
+ ]
1824
+ }
1825
+ ],
1826
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage2_group2",
1827
+ "grad_norm": 0.08956214785575867,
1828
+ "group": 2,
1829
+ "k": 1,
1830
+ "losses": [
1831
+ 0.03524526581168175,
1832
+ 0.0,
1833
+ -0.003468739567324519,
1834
+ -0.0037891429383307695,
1835
+ -0.0029842720832675695,
1836
+ 0.0,
1837
+ 0.0,
1838
+ -0.003300668438896537,
1839
+ -0.002671028720214963,
1840
+ -0.0039009505417197943,
1841
+ 0.0,
1842
+ 0.0
1843
+ ],
1844
+ "nlls": [
1845
+ 0.4613925516605377,
1846
+ null,
1847
+ 0.49949848651885986,
1848
+ 0.5456365942955017,
1849
+ 0.4297351837158203,
1850
+ null,
1851
+ null,
1852
+ 0.4752962589263916,
1853
+ 0.38462814688682556,
1854
+ 0.5617368817329407,
1855
+ null,
1856
+ null
1857
+ ],
1858
+ "problem_id": "1155_C. Alarm Clocks Everywhere",
1859
+ "rewards": [
1860
+ 1.0,
1861
+ 0.0,
1862
+ 0.0,
1863
+ 0.0,
1864
+ 0.0,
1865
+ 0.0,
1866
+ 0.0,
1867
+ 0.0,
1868
+ 0.0,
1869
+ 0.0,
1870
+ 0.0,
1871
+ 0.0
1872
+ ],
1873
+ "skipped_samples": [
1874
+ {
1875
+ "reason": "invalid_final",
1876
+ "sample": 1
1877
+ },
1878
+ {
1879
+ "reason": "invalid_final",
1880
+ "sample": 5
1881
+ },
1882
+ {
1883
+ "reason": "invalid_final",
1884
+ "sample": 6
1885
+ },
1886
+ {
1887
+ "reason": "invalid_final",
1888
+ "sample": 10
1889
+ },
1890
+ {
1891
+ "reason": "invalid_final",
1892
+ "sample": 11
1893
+ }
1894
+ ],
1895
+ "stage": 2
1896
+ },
1897
+ {
1898
+ "advantages": [
1899
+ 0.4166666666666667,
1900
+ -0.5833333333333333,
1901
+ 0.4166666666666667,
1902
+ -0.5833333333333333,
1903
+ 0.4166666666666667,
1904
+ 0.4166666666666667,
1905
+ 0.4166666666666667,
1906
+ -0.5833333333333333,
1907
+ -0.5833333333333333,
1908
+ 0.4166666666666667,
1909
+ 0.4166666666666667,
1910
+ -0.5833333333333333
1911
+ ],
1912
+ "candidate_attempts": [
1913
+ {
1914
+ "advantages": [
1915
+ 0.4166666666666667,
1916
+ -0.5833333333333333,
1917
+ 0.4166666666666667,
1918
+ -0.5833333333333333,
1919
+ 0.4166666666666667,
1920
+ 0.4166666666666667,
1921
+ 0.4166666666666667,
1922
+ -0.5833333333333333,
1923
+ -0.5833333333333333,
1924
+ 0.4166666666666667,
1925
+ 0.4166666666666667,
1926
+ -0.5833333333333333
1927
+ ],
1928
+ "eligible": true,
1929
+ "passes": 7,
1930
+ "problem_id": "431_A. Black Square",
1931
+ "rewards": [
1932
+ 1.0,
1933
+ 0.0,
1934
+ 1.0,
1935
+ 0.0,
1936
+ 1.0,
1937
+ 1.0,
1938
+ 1.0,
1939
+ 0.0,
1940
+ 0.0,
1941
+ 1.0,
1942
+ 1.0,
1943
+ 0.0
1944
+ ]
1945
+ }
1946
+ ],
1947
+ "checkpoint": "/work/checkpoints/pkpo_20260709T184830Z/stage2_group3",
1948
+ "grad_norm": 0.16979184746742249,
1949
+ "group": 3,
1950
+ "k": 1,
1951
+ "losses": [
1952
+ 0.008487503975629807,
1953
+ -0.01556235272437334,
1954
+ 0.013701685704290867,
1955
+ -0.01810634136199951,
1956
+ 0.005909562110900879,
1957
+ 0.013518122024834156,
1958
+ 0.011939951218664646,
1959
+ 0.0,
1960
+ 0.0,
1961
+ 0.010004074312746525,
1962
+ 0.007014663424342871,
1963
+ 0.0
1964
+ ],
1965
+ "nlls": [
1966
+ 0.24444009363651276,
1967
+ 0.3201398253440857,
1968
+ 0.3946085274219513,
1969
+ 0.3724732995033264,
1970
+ 0.17019538581371307,
1971
+ 0.389321893453598,
1972
+ 0.3438705801963806,
1973
+ null,
1974
+ null,
1975
+ 0.28811731934547424,
1976
+ 0.20202229917049408,
1977
+ null
1978
+ ],
1979
+ "problem_id": "431_A. Black Square",
1980
+ "rewards": [
1981
+ 1.0,
1982
+ 0.0,
1983
+ 1.0,
1984
+ 0.0,
1985
+ 1.0,
1986
+ 1.0,
1987
+ 1.0,
1988
+ 0.0,
1989
+ 0.0,
1990
+ 1.0,
1991
+ 1.0,
1992
+ 0.0
1993
+ ],
1994
+ "skipped_samples": [
1995
+ {
1996
+ "reason": "invalid_final",
1997
+ "sample": 7
1998
+ },
1999
+ {
2000
+ "reason": "invalid_final",
2001
+ "sample": 8
2002
+ },
2003
+ {
2004
+ "reason": "invalid_final",
2005
+ "sample": 11
2006
+ }
2007
+ ],
2008
+ "stage": 2
2009
+ }
2010
+ ]
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "max_new_tokens": 1024,
7
+ "pad_token_id": 151643,
8
+ "stop_strings": [
9
+ "</answer>"
10
+ ],
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.52.4"
13
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b06ec9c40da54a65f0a1361550b8aed8e99d8e69ffc9e840e1ac173184bda4e
3
+ size 3996250744
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc13d82303e4fc318e6b59f23b4050ca4c1fab1717f680f5d1ed7ec6bf8f2422
3
+ size 3993160032
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c954616bdd6d8693b74acc9cab3e505d8912e93da77fa72c814d72291302bc96
3
+ size 3959604768
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d884a3675577809505194b814cb4cc0810978d86846de4246a18b071cb06a98
3
+ size 3187841392
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf24915d47ea030bb68ab0b9488f4515a907185baa6dc26837c9c3f2326a550
3
+ size 1244659840
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16381470720
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
404
+ "model.norm.weight": "model-00004-of-00005.safetensors"
405
+ }
406
+ }