developer_uid: rirv938
submission_id: rirv938-datamix-v2-cp31_32080_v1
model_name: rirv938-datamix-v2-cp31_32080_v1
model_group: rirv938/datamix_v2_cp312
status: torndown
timestamp: 2025-07-08T15:10:30+00:00
num_battles: 11084
num_wins: 5486
celo_rating: 1294.04
family_friendly_score: 0.5352
family_friendly_standard_error: 0.007053523374881521
submission_type: basic
model_repo: rirv938/datamix_v2_cp312_98ff_b35_r1_reformat_high_quality_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5255933468830307, 'latency_mean': 1.9024880063533782, 'latency_p50': 1.9081422090530396, 'latency_p90': 2.1150619268417357}, {'batch_size': 3, 'throughput': 1.0435336142698397, 'latency_mean': 2.866991364955902, 'latency_p50': 2.8772672414779663, 'latency_p90': 3.1244591236114503}, {'batch_size': 5, 'throughput': 1.3400764282466429, 'latency_mean': 3.7060750913619995, 'latency_p50': 3.7334381341934204, 'latency_p90': 4.069647121429443}, {'batch_size': 6, 'throughput': 1.4291963438955044, 'latency_mean': 4.167553316354752, 'latency_p50': 4.135387420654297, 'latency_p90': 4.682320928573608}, {'batch_size': 8, 'throughput': 1.5645349585785913, 'latency_mean': 5.0595838010311125, 'latency_p50': 5.042710900306702, 'latency_p90': 5.72315742969513}, {'batch_size': 10, 'throughput': 1.6496824067442766, 'latency_mean': 5.992339692115784, 'latency_p50': 5.970590829849243, 'latency_p90': 6.761595392227172}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-datamix-v2-cp31_32080_v1
is_internal_developer: True
language_model: rirv938/datamix_v2_cp312_98ff_b35_r1_reformat_high_quality_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-07-08
win_ratio: 0.49494767232046194
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '</s>', '\n', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rirv938-datamix-v2-cp31-32080-v1-mkmlizer
Waiting for job on rirv938-datamix-v2-cp31-32080-v1-mkmlizer to finish
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: Downloaded to shared memory in 306.294s
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: Checking if rirv938/datamix_v2_cp312_98ff_b35_r1_reformat_high_quality_merged already exists in ChaiML
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: Creating repo ChaiML/datamix_v2_cp312_98ff_b35_r1_reformat_high_quality_merged and uploading /tmp/tmp4lqrau9d to it
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:05<01:54,  5.44s/it]
  9%|▉         | 2/22 [00:13<02:22,  7.14s/it]
 14%|█▎        | 3/22 [00:20<02:12,  6.99s/it]
 18%|█▊        | 4/22 [00:27<02:06,  7.04s/it]
 23%|██▎       | 5/22 [00:36<02:08,  7.54s/it]
 27%|██▋       | 6/22 [00:40<01:42,  6.41s/it]
 32%|███▏      | 7/22 [00:45<01:30,  6.01s/it]
 36%|███▋      | 8/22 [00:53<01:34,  6.76s/it]
 41%|████      | 9/22 [00:57<01:15,  5.78s/it]
 45%|████▌     | 10/22 [01:04<01:13,  6.09s/it]
 50%|█████     | 11/22 [01:11<01:09,  6.34s/it]
 55%|█████▍    | 12/22 [01:15<00:57,  5.78s/it]
 59%|█████▉    | 13/22 [01:23<00:58,  6.51s/it]
 64%|██████▎   | 14/22 [01:32<00:56,  7.00s/it]
 68%|██████▊   | 15/22 [01:39<00:49,  7.04s/it]
 73%|███████▎  | 16/22 [01:44<00:38,  6.41s/it]
 77%|███████▋  | 17/22 [01:49<00:30,  6.10s/it]
 82%|████████▏ | 18/22 [01:54<00:23,  5.87s/it]
 86%|████████▋ | 19/22 [01:58<00:15,  5.24s/it]
 91%|█████████ | 20/22 [02:06<00:12,  6.01s/it]
 95%|█████████▌| 21/22 [02:12<00:06,  6.01s/it]
100%|██████████| 22/22 [02:13<00:00,  4.60s/it]
100%|██████████| 22/22 [02:13<00:00,  6.08s/it]
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4lqrau9d, device:0
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-mistral32-deepse_16364_v2: HTTPConnectionPool(host='chaiml-mistral32-deepse-16364-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: quantized model in 62.768s
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: Processed model rirv938/datamix_v2_cp312_98ff_b35_r1_reformat_high_quality_merged in 595.057s
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia/config.json
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia/special_tokens_map.json
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia/tokenizer_config.json
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia/tokenizer.json
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia/flywheel_model.1.safetensors
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-datamix-v2-cp31-32080-v1/nvidia/flywheel_model.0.safetensors
rirv938-datamix-v2-cp31-32080-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.13it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 13.10it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.26it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.96it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.69it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.28it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.77it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.64it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.75it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.06it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 14.17it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.46it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.24it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:27, 11.54it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:18, 17.04it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.21it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.43it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.69it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 14.71it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:25, 11.93it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.71it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.95it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.15it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.49it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:20, 13.89it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.09it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.13it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.28it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 13.82it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.71it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.40it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.33it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:15, 17.31it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:21, 12.26it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 11.70it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:22, 11.36it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:20, 12.51it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.49it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:15, 16.09it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 19.35it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.80it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.17it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 13.97it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:20, 11.33it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.65it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.87it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.02it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 13.21it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:15, 13.94it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.31it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.97it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 19.74it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 13.93it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:15, 13.04it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 13.97it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.44it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.94it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 19.96it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:13, 14.01it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.27it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 14.15it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.38it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 17.13it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.08it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.11it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<05:03,  1.88s/it]
Loading 0:  56%|█████▌    | 202/363 [00:29<04:22,  1.63s/it]
Loading 0:  56%|█████▌    | 204/363 [00:29<03:10,  1.20s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<01:58,  1.32it/s]
Loading 0:  58%|█████▊    | 209/363 [00:30<01:28,  1.75it/s]
Loading 0:  58%|█████▊    | 212/363 [00:30<00:57,  2.61it/s]
Loading 0:  59%|█████▉    | 214/363 [00:30<00:48,  3.08it/s]
Loading 0:  60%|█████▉    | 216/363 [00:30<00:40,  3.60it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:27,  5.23it/s]
Loading 0:  61%|██████    | 221/363 [00:31<00:25,  5.53it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:14,  9.40it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:10, 12.48it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:12, 10.58it/s]
Loading 0:  65%|██████▍   | 235/363 [00:32<00:12, 10.50it/s]
Loading 0:  65%|██████▌   | 237/363 [00:32<00:10, 11.58it/s]
Loading 0:  66%|██████▌   | 239/363 [00:32<00:12,  9.88it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:07, 14.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:06, 17.97it/s]
Loading 0:  69%|██████▉   | 251/363 [00:33<00:08, 12.92it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:08, 12.44it/s]
Loading 0:  70%|███████   | 255/363 [00:33<00:08, 13.23it/s]
Loading 0:  71%|███████   | 257/363 [00:33<00:10, 10.36it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:06, 15.65it/s]
Loading 0:  73%|███████▎  | 266/363 [00:34<00:05, 18.74it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 13.50it/s]
Loading 0:  75%|███████▍  | 271/363 [00:34<00:07, 12.85it/s]
Loading 0:  75%|███████▌  | 273/363 [00:34<00:06, 13.60it/s]
Loading 0:  76%|███████▌  | 275/363 [00:35<00:08, 10.99it/s]
Loading 0:  77%|███████▋  | 280/363 [00:35<00:05, 16.20it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:04, 19.22it/s]
Loading 0:  79%|███████▉  | 287/363 [00:35<00:05, 13.54it/s]
Loading 0:  80%|███████▉  | 289/363 [00:35<00:05, 12.91it/s]
Loading 0:  80%|████████  | 291/363 [00:36<00:05, 13.61it/s]
Loading 0:  81%|████████  | 293/363 [00:36<00:06, 11.08it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:03, 16.38it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:03, 19.27it/s]
Loading 0:  84%|████████▍ | 305/363 [00:37<00:04, 13.39it/s]
Loading 0:  85%|████████▍ | 307/363 [00:37<00:04, 12.85it/s]
Loading 0:  85%|████████▌ | 309/363 [00:37<00:03, 13.59it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 10.90it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 16.10it/s]
Loading 0:  88%|████████▊ | 320/363 [00:37<00:02, 19.08it/s]
Loading 0:  89%|████████▉ | 323/363 [00:38<00:03, 12.82it/s]
Loading 0:  90%|████████▉ | 325/363 [00:38<00:03, 12.21it/s]
Loading 0:  90%|█████████ | 327/363 [00:38<00:02, 12.89it/s]
Loading 0:  91%|█████████ | 329/363 [00:38<00:03, 10.34it/s]
Loading 0:  92%|█████████▏| 334/363 [00:39<00:01, 15.37it/s]
Loading 0:  93%|█████████▎| 338/363 [00:39<00:01, 18.25it/s]
Loading 0:  94%|█████████▍| 341/363 [00:39<00:01, 12.19it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 11.84it/s]
Loading 0:  95%|█████████▌| 345/363 [00:40<00:01, 12.72it/s]
Loading 0:  96%|█████████▌| 347/363 [00:40<00:01, 10.54it/s]
Loading 0:  97%|█████████▋| 352/363 [00:40<00:00, 15.49it/s]
Loading 0:  98%|█████████▊| 356/363 [00:40<00:00, 18.17it/s]
Loading 0:  99%|█████████▉| 359/363 [00:41<00:00,  9.55it/s]
Loading 0:  99%|█████████▉| 361/363 [00:41<00:00,  8.88it/s]
                                                            

Job rirv938-datamix-v2-cp31-32080-v1-mkmlizer completed after 631.84s with status: succeeded
Stopping job with name rirv938-datamix-v2-cp31-32080-v1-mkmlizer
Pipeline stage MKMLizer completed in 632.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-datamix-v2-cp31-32080-v1
Waiting for inference service rirv938-datamix-v2-cp31-32080-v1 to be ready
Inference service rirv938-datamix-v2-cp31-32080-v1 ready after 202.11275577545166s
Pipeline stage MKMLDeployer completed in 203.30s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.508415460586548s
Received healthy response to inference request in 2.784400701522827s
Received healthy response to inference request in 2.044431686401367s
Received healthy response to inference request in 2.1027190685272217s
5 requests
1 failed requests
5th percentile: 2.056089162826538
10th percentile: 2.067746639251709
20th percentile: 2.091061592102051
30th percentile: 2.2390553951263428
40th percentile: 2.511728048324585
50th percentile: 2.784400701522827
60th percentile: 3.0740066051483153
70th percentile: 3.3636125087738034
80th percentile: 6.888476276397708
90th percentile: 13.64859790802002
95th percentile: 17.028658723831175
99th percentile: 19.732707376480104
mean time: 6.16973729133606
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9187588691711426s
Received healthy response to inference request in 2.4414119720458984s
Received healthy response to inference request in 2.0945491790771484s
Received healthy response to inference request in 2.367521047592163s
Received healthy response to inference request in 1.9725227355957031s
5 requests
0 failed requests
5th percentile: 1.9295116424560548
10th percentile: 1.9402644157409668
20th percentile: 1.961769962310791
30th percentile: 1.9969280242919922
40th percentile: 2.0457386016845702
50th percentile: 2.0945491790771484
60th percentile: 2.2037379264831545
70th percentile: 2.31292667388916
80th percentile: 2.38229923248291
90th percentile: 2.411855602264404
95th percentile: 2.4266337871551515
99th percentile: 2.438456335067749
mean time: 2.158952760696411
Pipeline stage StressChecker completed in 46.40s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.66s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.72s
Shutdown handler de-registered
rirv938-datamix-v2-cp31_32080_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3394.37s
Shutdown handler de-registered
rirv938-datamix-v2-cp31_32080_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-datamix-v2-cp31_32080_v1 status is now torndown due to DeploymentManager action