developer_uid: rirv938
submission_id: rirv938-0sw-96p-4ff-zon_22472_v1
model_name: rirv938-0sw-96p-4ff-zon_22472_v1
model_group: rirv938/0sw_96p_4ff_zone
status: torndown
timestamp: 2025-03-20T22:13:48+00:00
num_battles: 8705
num_wins: 4285
celo_rating: 1270.26
family_friendly_score: 0.6195999999999999
family_friendly_standard_error: 0.006865796967577762
submission_type: basic
model_repo: rirv938/0sw_96p_4ff_zonemercy_lexical_vira_73487_v18_merge
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.39951189224147643, 'latency_mean': 2.502948405742645, 'latency_p50': 2.4848326444625854, 'latency_p90': 2.789499068260193}, {'batch_size': 3, 'throughput': 0.8249774581266193, 'latency_mean': 3.631919261217117, 'latency_p50': 3.6158400774002075, 'latency_p90': 4.07218873500824}, {'batch_size': 5, 'throughput': 1.0847635969832754, 'latency_mean': 4.598307762145996, 'latency_p50': 4.584321975708008, 'latency_p90': 5.191089534759522}, {'batch_size': 6, 'throughput': 1.1649225655103828, 'latency_mean': 5.122191675901413, 'latency_p50': 5.103221297264099, 'latency_p90': 5.77943434715271}, {'batch_size': 10, 'throughput': 1.3012236070874572, 'latency_mean': 7.624997092485428, 'latency_p50': 7.652299404144287, 'latency_p90': 8.539562392234803}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-0sw-96p-4ff-zon_22472_v1
is_internal_developer: True
language_model: rirv938/0sw_96p_4ff_zonemercy_lexical_vira_73487_v18_merge
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2025-03-20
win_ratio: 0.4922458357265939
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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 rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer
Waiting for job on rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer to finish
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: Downloaded to shared memory in 145.977s
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8rt254yk, device:0
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: quantized model in 51.746s
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: Processed model rirv938/0sw_96p_4ff_zonemercy_lexical_vira_73487_v18_merge in 197.730s
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1/config.json
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1/special_tokens_map.json
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1/tokenizer_config.json
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1/tokenizer.json
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1/flywheel_model.1.safetensors
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-0sw-96p-4ff-zon-22472-v1/flywheel_model.0.safetensors
rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 4/507 [00:00<00:15, 33.23it/s] Loading 0: 2%|▏ | 8/507 [00:00<00:19, 26.20it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:18, 26.24it/s] Loading 0: 3%|▎ | 15/507 [00:00<00:22, 22.18it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:18, 26.04it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:16, 28.74it/s] Loading 0: 5%|▌ | 27/507 [00:01<00:27, 17.30it/s] Loading 0: 6%|▌ | 31/507 [00:01<00:23, 20.46it/s] Loading 0: 7%|▋ | 34/507 [00:01<00:22, 20.92it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:19, 23.75it/s] Loading 0: 8%|▊ | 42/507 [00:01<00:21, 21.80it/s] Loading 0: 9%|▉ | 46/507 [00:01<00:18, 24.94it/s] Loading 0: 10%|▉ | 50/507 [00:02<00:16, 27.39it/s] Loading 0: 10%|█ | 53/507 [00:02<00:22, 19.97it/s] Loading 0: 11%|█ | 56/507 [00:02<00:21, 20.97it/s] Loading 0: 12%|█▏ | 59/507 [00:02<00:24, 17.96it/s] Loading 0: 13%|█▎ | 64/507 [00:02<00:18, 23.71it/s] Loading 0: 13%|█▎ | 67/507 [00:02<00:18, 23.84it/s] Loading 0: 14%|█▍ | 70/507 [00:03<00:18, 23.77it/s] Loading 0: 15%|█▍ | 74/507 [00:03<00:17, 24.06it/s] Loading 0: 15%|█▌ | 78/507 [00:03<00:15, 27.52it/s] Loading 0: 16%|█▌ | 81/507 [00:03<00:21, 19.86it/s] Loading 0: 17%|█▋ | 84/507 [00:03<00:20, 20.55it/s] Loading 0: 17%|█▋ | 88/507 [00:03<00:19, 21.61it/s] Loading 0: 18%|█▊ | 92/507 [00:03<00:16, 25.35it/s] Loading 0: 19%|█▊ | 95/507 [00:04<00:18, 22.05it/s] Loading 0: 20%|█▉ | 99/507 [00:04<00:16, 24.40it/s] Loading 0: 20%|██ | 102/507 [00:04<00:16, 24.30it/s] Loading 0: 21%|██ | 106/507 [00:04<00:19, 20.45it/s] Loading 0: 21%|██▏ | 109/507 [00:04<00:20, 19.08it/s] Loading 0: 22%|██▏ | 112/507 [00:05<00:19, 20.40it/s] Loading 0: 23%|██▎ | 115/507 [00:05<00:18, 21.28it/s] Loading 0: 24%|██▎ | 120/507 [00:05<00:16, 24.16it/s] Loading 0: 24%|██▍ | 123/507 [00:05<00:17, 22.41it/s] Loading 0: 25%|██▌ | 127/507 [00:05<00:14, 25.98it/s] Loading 0: 26%|██▌ | 131/507 [00:05<00:13, 28.36it/s] Loading 0: 26%|██▋ | 134/507 [00:05<00:18, 20.70it/s] Loading 0: 27%|██▋ | 137/507 [00:06<00:17, 21.39it/s] Loading 0: 28%|██▊ | 140/507 [00:06<00:20, 18.20it/s] Loading 0: 29%|██▊ | 145/507 [00:06<00:15, 24.09it/s] Loading 0: 29%|██▉ | 148/507 [00:06<00:15, 23.79it/s] Loading 0: 30%|██▉ | 151/507 [00:06<00:14, 23.81it/s] Loading 0: 31%|███ | 155/507 [00:06<00:14, 23.91it/s] Loading 0: 31%|███▏ | 159/507 [00:06<00:12, 27.47it/s] Loading 0: 32%|███▏ | 162/507 [00:07<00:19, 17.65it/s] Loading 0: 33%|███▎ | 166/507 [00:07<00:16, 20.68it/s] Loading 0: 33%|███▎ | 169/507 [00:07<00:15, 21.37it/s] Loading 0: 34%|███▍ | 172/507 [00:07<00:14, 23.16it/s] Loading 0: 35%|███▍ | 175/507 [00:07<00:14, 23.30it/s] Loading 0: 35%|███▌ | 178/507 [00:07<00:14, 23.44it/s] Loading 0: 36%|███▌ | 182/507 [00:08<00:13, 24.29it/s] Loading 0: 37%|███▋ | 186/507 [00:08<00:11, 27.71it/s] Loading 0: 37%|███▋ | 189/507 [00:08<00:17, 18.08it/s] Loading 0: 38%|███▊ | 193/507 [00:08<00:14, 21.31it/s] Loading 0: 39%|███▊ | 196/507 [00:08<00:14, 21.87it/s] Loading 0: 40%|███▉ | 201/507 [00:08<00:12, 24.77it/s] Loading 0: 40%|████ | 204/507 [00:09<00:13, 22.82it/s] Loading 0: 41%|████ | 208/507 [00:09<00:12, 24.57it/s] Loading 0: 42%|████▏ | 212/507 [00:09<00:11, 26.78it/s] Loading 0: 42%|████▏ | 215/507 [00:09<00:15, 19.30it/s] Loading 0: 43%|████▎ | 218/507 [00:09<00:14, 20.41it/s] Loading 0: 44%|████▎ | 221/507 [00:09<00:16, 17.51it/s] Loading 0: 45%|████▍ | 226/507 [00:10<00:12, 23.09it/s] Loading 0: 45%|████▌ | 229/507 [00:10<00:11, 23.35it/s] Loading 0: 46%|████▌ | 232/507 [00:10<00:11, 24.22it/s] Loading 0: 47%|████▋ | 236/507 [00:10<00:10, 24.89it/s] Loading 0: 47%|████▋ | 240/507 [00:10<00:09, 28.29it/s] Loading 0: 48%|████▊ | 244/507 [00:10<00:12, 20.23it/s] Loading 0: 49%|████▊ | 247/507 [00:10<00:12, 21.20it/s] Loading 0: 49%|████▉ | 250/507 [00:11<00:12, 20.84it/s] Loading 0: 50%|████▉ | 253/507 [00:11<00:11, 22.37it/s] Loading 0: 50%|█████ | 256/507 [00:11<00:10, 22.82it/s] Loading 0: 51%|█████ | 259/507 [00:11<00:10, 22.74it/s] Loading 0: 52%|█████▏ | 262/507 [00:11<00:10, 24.22it/s] Loading 0: 52%|█████▏ | 266/507 [00:11<00:08, 27.28it/s] Loading 0: 53%|█████▎ | 269/507 [00:11<00:12, 19.22it/s] Loading 0: 54%|█████▎ | 272/507 [00:12<00:11, 20.46it/s] Loading 0: 54%|█████▍ | 275/507 [00:12<00:13, 17.37it/s] Loading 0: 55%|█████▌ | 280/507 [00:12<00:09, 22.84it/s] Loading 0: 56%|█████▌ | 283/507 [00:12<00:09, 22.80it/s] Loading 0: 56%|█████▋ | 286/507 [00:12<00:09, 23.49it/s] Loading 0: 57%|█████▋ | 290/507 [00:12<00:09, 24.05it/s] Loading 0: 58%|█████▊ | 294/507 [00:12<00:07, 27.47it/s] Loading 0: 59%|█████▊ | 297/507 [00:13<00:11, 17.81it/s] Loading 0: 59%|█████▉ | 299/507 [00:28<00:11, 17.81it/s] Loading 0: 59%|█████▉ | 300/507 [00:28<04:44, 1.38s/it] Loading 0: 60%|█████▉ | 302/507 [00:28<03:49, 1.12s/it] Loading 0: 60%|██████ | 306/507 [00:28<02:25, 1.38it/s] Loading 0: 61%|██████ | 309/507 [00:28<01:45, 1.88it/s] Loading 0: 61%|██████▏ | 311/507 [00:28<01:25, 2.28it/s] Loading 0: 62%|██████▏ | 316/507 [00:28<00:49, 3.87it/s] Loading 0: 63%|██████▎ | 320/507 [00:29<00:34, 5.50it/s] Loading 0: 64%|██████▎ | 323/507 [00:29<00:28, 6.36it/s] Loading 0: 64%|██████▍ | 326/507 [00:29<00:22, 7.98it/s] Loading 0: 65%|██████▍ | 329/507 [00:29<00:20, 8.82it/s] Loading 0: 66%|██████▌ | 334/507 [00:29<00:13, 13.01it/s] Loading 0: 66%|██████▋ | 337/507 [00:29<00:11, 14.79it/s] Loading 0: 67%|██████▋ | 340/507 [00:30<00:09, 16.74it/s] Loading 0: 68%|██████▊ | 344/507 [00:30<00:08, 18.62it/s] Loading 0: 69%|██████▉ | 349/507 [00:30<00:08, 19.38it/s] Loading 0: 69%|██████▉ | 352/507 [00:30<00:08, 18.63it/s] Loading 0: 70%|███████ | 355/507 [00:30<00:07, 19.71it/s] Loading 0: 71%|███████ | 358/507 [00:30<00:07, 20.83it/s] Loading 0: 72%|███████▏ | 363/507 [00:31<00:06, 23.99it/s] Loading 0: 72%|███████▏ | 366/507 [00:31<00:06, 21.93it/s] Loading 0: 73%|███████▎ | 370/507 [00:31<00:05, 25.43it/s] Loading 0: 74%|███████▍ | 374/507 [00:31<00:04, 27.89it/s] Loading 0: 74%|███████▍ | 377/507 [00:31<00:06, 20.54it/s] Loading 0: 75%|███████▍ | 380/507 [00:31<00:05, 21.60it/s] Loading 0: 76%|███████▌ | 383/507 [00:32<00:06, 18.42it/s] Loading 0: 77%|███████▋ | 388/507 [00:32<00:04, 24.15it/s] Loading 0: 77%|███████▋ | 391/507 [00:32<00:04, 24.02it/s] Loading 0: 78%|███████▊ | 394/507 [00:32<00:04, 24.15it/s] Loading 0: 79%|███████▊ | 398/507 [00:32<00:04, 24.27it/s] Loading 0: 79%|███████▉ | 403/507 [00:32<00:04, 22.47it/s] Loading 0: 80%|████████ | 406/507 [00:33<00:04, 20.56it/s] Loading 0: 81%|████████ | 409/507 [00:33<00:04, 21.21it/s] Loading 0: 81%|████████▏ | 412/507 [00:33<00:04, 22.23it/s] Loading 0: 82%|████████▏ | 417/507 [00:33<00:03, 25.29it/s] Loading 0: 83%|████████▎ | 420/507 [00:33<00:03, 23.36it/s] Loading 0: 84%|████████▎ | 424/507 [00:33<00:03, 26.64it/s] Loading 0: 84%|████████▍ | 428/507 [00:33<00:02, 28.90it/s] Loading 0: 85%|████████▌ | 432/507 [00:34<00:04, 18.65it/s] Loading 0: 86%|████████▌ | 436/507 [00:34<00:03, 21.54it/s] Loading 0: 87%|████████▋ | 439/507 [00:34<00:03, 22.15it/s] Loading 0: 87%|████████▋ | 442/507 [00:34<00:02, 23.76it/s] Loading 0: 88%|████████▊ | 445/507 [00:34<00:02, 24.03it/s] Loading 0: 88%|████████▊ | 448/507 [00:34<00:02, 24.50it/s] Loading 0: 89%|████████▉ | 452/507 [00:34<00:02, 24.73it/s] Loading 0: 90%|████████▉ | 456/507 [00:35<00:01, 28.26it/s] Loading 0: 91%|█████████ | 460/507 [00:35<00:02, 19.95it/s] Loading 0: 91%|█████████▏| 463/507 [00:35<00:02, 20.79it/s] Loading 0: 92%|█████████▏| 466/507 [00:35<00:01, 21.81it/s] Loading 0: 93%|█████████▎| 471/507 [00:35<00:01, 25.21it/s] Loading 0: 93%|█████████▎| 474/507 [00:35<00:01, 22.65it/s] Loading 0: 94%|█████████▍| 478/507 [00:36<00:01, 24.89it/s] Loading 0: 95%|█████████▌| 482/507 [00:36<00:00, 27.41it/s] Loading 0: 96%|█████████▌| 485/507 [00:38<00:04, 4.51it/s] Loading 0: 96%|█████████▋| 488/507 [00:38<00:03, 5.60it/s] Loading 0: 97%|█████████▋| 491/507 [00:38<00:02, 7.13it/s] Loading 0: 97%|█████████▋| 494/507 [00:38<00:01, 8.97it/s] Loading 0: 98%|█████████▊| 499/507 [00:39<00:00, 12.55it/s] Loading 0: 99%|█████████▉| 502/507 [00:39<00:00, 13.61it/s] Loading 0: 100%|█████████▉| 506/507 [00:39<00:00, 17.30it/s]
Job rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer completed after 225.3s with status: succeeded
Stopping job with name rirv938-0sw-96p-4ff-zon-22472-v1-mkmlizer
Pipeline stage MKMLizer completed in 225.86s
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 rirv938-0sw-96p-4ff-zon-22472-v1
Waiting for inference service rirv938-0sw-96p-4ff-zon-22472-v1 to be ready
Inference service rirv938-0sw-96p-4ff-zon-22472-v1 ready after 90.47448015213013s
Pipeline stage MKMLDeployer completed in 91.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9833428859710693s
Received healthy response to inference request in 2.425351619720459s
Received healthy response to inference request in 2.4731788635253906s
Received healthy response to inference request in 2.338006019592285s
Received healthy response to inference request in 2.532351016998291s
5 requests
0 failed requests
5th percentile: 2.35547513961792
10th percentile: 2.3729442596435546
20th percentile: 2.407882499694824
30th percentile: 2.4349170684814454
40th percentile: 2.454047966003418
50th percentile: 2.4731788635253906
60th percentile: 2.496847724914551
70th percentile: 2.520516586303711
80th percentile: 2.6225493907928468
90th percentile: 2.802946138381958
95th percentile: 2.8931445121765136
99th percentile: 2.965303211212158
mean time: 2.550446081161499
Pipeline stage StressChecker completed in 14.30s
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 0.76s
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
rirv938-0sw-96p-4ff-zon_22472_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-0sw-96p-4ff-zon-22472-v1-profiler
Waiting for inference service rirv938-0sw-96p-4ff-zon-22472-v1-profiler to be ready
Inference service rirv938-0sw-96p-4ff-zon-22472-v1-profiler ready after 80.23686075210571s
Pipeline stage MKMLProfilerDeployer completed in 80.57s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-0sw-96p-4ff-bf20d26bade241bb8692487b5d48c89e-deplofjndv:/code/chaiverse_profiler_1742509291 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-0sw-96p-4ff-bf20d26bade241bb8692487b5d48c89e-deplofjndv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1742509291 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1742509291/summary.json'
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 2801.26s
Shutdown handler de-registered
rirv938-0sw-96p-4ff-zon_22472_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-0sw-96p-4ff-zon_22472_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1