rirv938-100p-0ff-rirv938_2517

developer_uid: rirv938

submission_id: rirv938-100p-0ff-rirv938_2517_v1

model_name: rirv938-100p-0ff-rirv938_2517_v1

model_group: rirv938/100p_0ff_rirv938

status: torndown

timestamp: 2025-04-18T22:40:53+00:00

num_battles: 5461

num_wins: 2759

celo_rating: 1292.36

family_friendly_score: 0.49739999999999995

family_friendly_standard_error: 0.007070972210382389

submission_type: basic

model_repo: rirv938/100p_0ff_rirv938_mistral_24b_oai_77698_v2_cp374_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': 0.3729923582962226, 'latency_mean': 2.680920841693878, 'latency_p50': 2.693361520767212, 'latency_p90': 2.975932264328003}, {'batch_size': 2, 'throughput': 0.5844887744120855, 'latency_mean': 3.4122968745231628, 'latency_p50': 3.4143775701522827, 'latency_p90': 3.785744047164917}, {'batch_size': 3, 'throughput': 0.7340210716697951, 'latency_mean': 4.066414880752563, 'latency_p50': 4.067856550216675, 'latency_p90': 4.509465575218201}, {'batch_size': 4, 'throughput': 0.8553512562923143, 'latency_mean': 4.652457309961319, 'latency_p50': 4.6489057540893555, 'latency_p90': 5.119242143630982}, {'batch_size': 5, 'throughput': 0.9331395161638958, 'latency_mean': 5.32635694026947, 'latency_p50': 5.321512460708618, 'latency_p90': 5.932477426528931}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-100p-0ff-rirv938_2517_v1

is_internal_developer: True

language_model: rirv938/100p_0ff_rirv938_mistral_24b_oai_77698_v2_cp374_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 0.66

us_pacific_date: 2025-04-18

win_ratio: 0.5052188243911372

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['###', '</s>', 'You:', '\n'], 'max_input_tokens': 1024, '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 rirv938-100p-0ff-rirv938-2517-v1-mkmlizer
Waiting for job on rirv938-100p-0ff-rirv938-2517-v1-mkmlizer to finish
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║       /___/                                                         ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: Downloaded to shared memory in 162.565s
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4peymio0, device:0
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: quantized model in 76.230s
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: Processed model rirv938/100p_0ff_rirv938_mistral_24b_oai_77698_v2_cp374_merged in 238.795s
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1/special_tokens_map.json
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1/config.json
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1/tokenizer_config.json
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1/tokenizer.json
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1/flywheel_model.1.safetensors
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv938-2517-v1/flywheel_model.0.safetensors
rirv938-100p-0ff-rirv938-2517-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 27.53it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 12.82it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.21it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.80it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:33, 10.37it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.68it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:24, 13.64it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:26, 12.56it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:20, 16.02it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:17, 18.56it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:26, 12.18it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:29, 11.23it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:26, 12.16it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:33,  9.72it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:21, 14.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:18, 17.23it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:25, 12.07it/s]
Loading 0:  15%|█▌        | 55/363 [00:04<00:26, 11.69it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:24, 12.55it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:29, 10.17it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:19, 15.04it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:16, 17.93it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:24, 12.07it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:25, 11.32it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:23, 12.27it/s]
Loading 0:  21%|██        | 77/363 [00:06<00:28,  9.88it/s]
Loading 0:  23%|██▎       | 82/363 [00:06<00:18, 14.97it/s]
Loading 0:  24%|██▎       | 86/363 [00:06<00:15, 17.99it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:21, 12.95it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.54it/s]
Loading 0:  26%|██▌       | 95/363 [00:07<00:16, 16.42it/s]
Loading 0:  27%|██▋       | 99/363 [00:07<00:13, 19.65it/s]
Loading 0:  28%|██▊       | 102/363 [00:07<00:14, 18.14it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.44it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:21, 12.08it/s]
Loading 0:  31%|███       | 111/363 [00:08<00:19, 13.04it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:23, 10.53it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:15, 16.03it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 19.14it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:18, 12.92it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:19, 11.87it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:18, 12.48it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:23,  9.86it/s]
Loading 0:  37%|███▋      | 136/363 [00:10<00:15, 14.58it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:12, 17.49it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:18, 12.14it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:18, 11.69it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:17, 12.49it/s]
Loading 0:  41%|████      | 149/363 [00:11<00:21, 10.05it/s]
Loading 0:  42%|████▏     | 154/363 [00:11<00:13, 14.94it/s]
Loading 0:  44%|████▎     | 158/363 [00:11<00:11, 17.21it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:16, 12.00it/s]
Loading 0:  45%|████▍     | 163/363 [00:12<00:17, 11.49it/s]
Loading 0:  45%|████▌     | 165/363 [00:12<00:16, 12.29it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:19, 10.17it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:12, 15.00it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:10, 17.64it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:15, 11.74it/s]
Loading 0:  50%|████▉     | 181/363 [00:13<00:16, 11.06it/s]
Loading 0:  50%|█████     | 183/363 [00:13<00:15, 11.78it/s]
Loading 0:  51%|█████     | 185/363 [00:14<00:18,  9.60it/s]
Loading 0:  52%|█████▏    | 190/363 [00:14<00:11, 14.63it/s]
Loading 0:  53%|█████▎    | 194/363 [00:14<00:09, 18.01it/s]
Loading 0:  54%|█████▍    | 197/363 [00:14<00:12, 13.61it/s]
Loading 0:  55%|█████▍    | 199/363 [00:14<00:12, 13.19it/s]
Loading 0:  55%|█████▌    | 200/363 [00:31<00:12, 13.19it/s]
Loading 0:  55%|█████▌    | 201/363 [00:31<05:17,  1.96s/it]
Loading 0:  56%|█████▌    | 202/363 [00:31<04:33,  1.70s/it]
Loading 0:  56%|█████▌    | 204/363 [00:32<03:20,  1.26s/it]
Loading 0:  57%|█████▋    | 207/363 [00:32<02:04,  1.26it/s]
Loading 0:  58%|█████▊    | 209/363 [00:32<01:32,  1.66it/s]
Loading 0:  58%|█████▊    | 212/363 [00:32<01:00,  2.50it/s]
Loading 0:  59%|█████▉    | 214/363 [00:32<00:50,  2.94it/s]
Loading 0:  60%|█████▉    | 216/363 [00:33<00:42,  3.43it/s]
Loading 0:  60%|██████    | 219/363 [00:33<00:28,  5.01it/s]
Loading 0:  61%|██████    | 221/363 [00:33<00:27,  5.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:33<00:15,  8.70it/s]
Loading 0:  63%|██████▎   | 230/363 [00:33<00:11, 11.33it/s]
Loading 0:  64%|██████▍   | 233/363 [00:34<00:13,  9.53it/s]
Loading 0:  65%|██████▍   | 235/363 [00:34<00:13,  9.54it/s]
Loading 0:  65%|██████▌   | 237/363 [00:34<00:12, 10.43it/s]
Loading 0:  66%|██████▌   | 239/363 [00:35<00:14,  8.52it/s]
Loading 0:  67%|██████▋   | 244/363 [00:35<00:09, 12.45it/s]
Loading 0:  68%|██████▊   | 248/363 [00:35<00:07, 14.94it/s]
Loading 0:  69%|██████▉   | 250/363 [00:35<00:09, 11.72it/s]
Loading 0:  69%|██████▉   | 252/363 [00:36<00:11,  9.52it/s]
Loading 0:  70%|███████   | 255/363 [00:36<00:09, 11.72it/s]
Loading 0:  71%|███████   | 257/363 [00:36<00:11,  9.52it/s]
Loading 0:  72%|███████▏  | 262/363 [00:36<00:07, 14.17it/s]
Loading 0:  73%|███████▎  | 266/363 [00:36<00:05, 16.94it/s]
Loading 0:  74%|███████▍  | 269/363 [00:37<00:07, 12.31it/s]
Loading 0:  75%|███████▍  | 271/363 [00:37<00:07, 11.84it/s]
Loading 0:  75%|███████▌  | 273/363 [00:37<00:07, 12.53it/s]
Loading 0:  76%|███████▌  | 275/363 [00:37<00:08, 10.22it/s]
Loading 0:  77%|███████▋  | 280/363 [00:38<00:05, 15.19it/s]
Loading 0:  78%|███████▊  | 284/363 [00:38<00:04, 18.28it/s]
Loading 0:  79%|███████▉  | 287/363 [00:38<00:05, 12.80it/s]
Loading 0:  80%|███████▉  | 289/363 [00:38<00:06, 12.02it/s]
Loading 0:  80%|████████  | 291/363 [00:38<00:05, 12.68it/s]
Loading 0:  81%|████████  | 293/363 [00:39<00:06, 10.16it/s]
Loading 0:  82%|████████▏ | 298/363 [00:39<00:04, 15.11it/s]
Loading 0:  83%|████████▎ | 302/363 [00:39<00:03, 17.56it/s]
Loading 0:  84%|████████▍ | 305/363 [00:40<00:04, 12.19it/s]
Loading 0:  85%|████████▍ | 307/363 [00:40<00:04, 11.46it/s]
Loading 0:  85%|████████▌ | 309/363 [00:40<00:04, 12.05it/s]
Loading 0:  86%|████████▌ | 311/363 [00:40<00:05,  9.50it/s]
Loading 0:  87%|████████▋ | 316/363 [00:40<00:03, 14.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:41<00:02, 16.90it/s]
Loading 0:  89%|████████▉ | 323/363 [00:41<00:03, 12.28it/s]
Loading 0:  90%|████████▉ | 325/363 [00:41<00:03, 11.34it/s]
Loading 0:  90%|█████████ | 327/363 [00:41<00:03, 11.95it/s]
Loading 0:  91%|█████████ | 329/363 [00:42<00:03,  9.54it/s]
Loading 0:  92%|█████████▏| 334/363 [00:42<00:02, 14.01it/s]
Loading 0:  93%|█████████▎| 338/363 [00:42<00:01, 16.21it/s]
Loading 0:  94%|█████████▎| 340/363 [00:42<00:02, 11.33it/s]
Loading 0:  94%|█████████▍| 342/363 [00:43<00:02,  9.69it/s]
Loading 0:  95%|█████████▌| 345/363 [00:43<00:01, 12.23it/s]
Loading 0:  96%|█████████▌| 347/363 [00:43<00:01,  9.89it/s]
Loading 0:  97%|█████████▋| 352/363 [00:43<00:00, 14.85it/s]
Loading 0:  98%|█████████▊| 356/363 [00:43<00:00, 18.00it/s]
Loading 0:  99%|█████████▉| 359/363 [00:51<00:03,  1.32it/s]
Loading 0:  99%|█████████▉| 361/363 [00:52<00:01,  1.55it/s]
                                                            
Job rirv938-100p-0ff-rirv938-2517-v1-mkmlizer completed after 439.77s with status: succeeded
Stopping job with name rirv938-100p-0ff-rirv938-2517-v1-mkmlizer
Pipeline stage MKMLizer completed in 440.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-100p-0ff-rirv938-2517-v1
Waiting for inference service rirv938-100p-0ff-rirv938-2517-v1 to be ready
Inference service rirv938-100p-0ff-rirv938-2517-v1 ready after 130.55315351486206s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.131746292114258s
Received healthy response to inference request in 2.5259323120117188s
Received healthy response to inference request in 2.037437915802002s
Received healthy response to inference request in 2.6798336505889893s
Received healthy response to inference request in 2.4770712852478027s
5 requests
0 failed requests
5th percentile: 2.125364589691162
10th percentile: 2.2132912635803224
20th percentile: 2.3891446113586428
30th percentile: 2.486843490600586
40th percentile: 2.5063879013061525
50th percentile: 2.5259323120117188
60th percentile: 2.587492847442627
70th percentile: 2.649053382873535
80th percentile: 2.770216178894043
90th percentile: 2.9509812355041505
95th percentile: 3.041363763809204
99th percentile: 3.113669786453247
mean time: 2.570404291152954
Pipeline stage StressChecker completed in 14.14s
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 1.02s
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 0.61s
Shutdown handler de-registered
rirv938-100p-0ff-rirv938_2517_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 3063.01s
Shutdown handler de-registered
rirv938-100p-0ff-rirv938_2517_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-100p-0ff-rirv938_2517_v1 status is now torndown due to DeploymentManager action