chaiml-rirv938-0sw-96p-_67397

developer_uid: NischayDnk

submission_id: chaiml-rirv938-0sw-96p-_67397_v1

model_name: chaiml-rirv938-0sw-96p-_67397_v1

model_group: ChaiML/rirv938-0sw-96p-4

status: torndown

timestamp: 2025-09-22T06:27:42+00:00

num_battles: 5623

num_wins: 3138

celo_rating: 1300.24

family_friendly_score: 0.48819999999999997

family_friendly_standard_error: 0.007069098386640265

submission_type: basic

model_repo: ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0_mergedv2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 7

max_input_tokens: 1400

max_output_tokens: 70

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6231598759798183, 'latency_mean': 1.604603556394577, 'latency_p50': 1.4496033191680908, 'latency_p90': 2.640387773513794}, {'batch_size': 4, 'throughput': 1.7215617448338159, 'latency_mean': 2.3189334368705747, 'latency_p50': 2.3169071674346924, 'latency_p90': 2.5280405998229982}, {'batch_size': 5, 'throughput': 1.9202912946756336, 'latency_mean': 2.5850472164154055, 'latency_p50': 2.5882625579833984, 'latency_p90': 2.922390413284302}, {'batch_size': 8, 'throughput': 2.283724746990935, 'latency_mean': 3.4692747128009795, 'latency_p50': 3.4770044088363647, 'latency_p90': 3.8953669548034666}, {'batch_size': 10, 'throughput': 2.4497895899204316, 'latency_mean': 4.053625056743622, 'latency_p50': 4.088446855545044, 'latency_p90': 4.714762234687805}, {'batch_size': 12, 'throughput': 2.526372629530428, 'latency_mean': 4.67988815665245, 'latency_p50': 4.68241012096405, 'latency_p90': 5.2734582901000975}, {'batch_size': 15, 'throughput': 2.6581921901414476, 'latency_mean': 5.590400413274765, 'latency_p50': 5.579752683639526, 'latency_p90': 6.382346510887146}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-rirv938-0sw-96p-_67397_v1

ineligible_reason: max_output_tokens!=64

is_internal_developer: False

language_model: ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0_mergedv2

model_size: 13B

ranking_group: single

throughput_3p7s: 2.38

us_pacific_date: 2025-09-21

win_ratio: 0.5580650898097101

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': ['<|im_end|>', 'Bot:', '\n', '<|im_start|>', 'You:', '<|eot_id|>', '</s>', 'User:', '####'], 'max_input_tokens': 1400, 'best_of': 7, 'max_output_tokens': 70}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}

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 chaiml-rirv938-0sw-96p-67397-v1-mkmlizer
Waiting for job on chaiml-rirv938-0sw-96p-67397-v1-mkmlizer to finish
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: Downloaded to shared memory in 24.671s
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: Checking if ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0_mergedv2 already exists in ChaiML
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphtry4dt1, device:0
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: quantized model in 26.389s
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: Processed model ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0_mergedv2 in 51.061s
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-67397-v1/nvidia
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-67397-v1/nvidia/special_tokens_map.json
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-67397-v1/nvidia/config.json
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-67397-v1/nvidia/tokenizer_config.json
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-67397-v1/nvidia/tokenizer.json
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-67397-v1/nvidia/flywheel_model.0.safetensors
chaiml-rirv938-0sw-96p-67397-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:11,  2.86s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:34,  1.30it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.17it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:43,  7.79it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:27, 12.18it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:21, 15.16it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:17, 18.23it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:14, 21.77it/s]
Loading 0:  17%|█▋        | 60/363 [00:06<00:10, 28.72it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:08, 34.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:07<00:07, 40.12it/s]
Loading 0:  24%|██▍       | 87/363 [00:07<00:06, 44.36it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 46.95it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 49.38it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 51.02it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:05, 45.30it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:05, 45.53it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:06, 37.56it/s]
Loading 0:  38%|███▊      | 137/363 [00:08<00:06, 36.22it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:06, 32.12it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:06, 34.26it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:06, 32.35it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:04, 41.17it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:04, 42.65it/s]
Loading 0:  47%|████▋     | 169/363 [00:09<00:04, 43.84it/s]
Loading 0:  48%|████▊     | 176/363 [00:09<00:03, 50.25it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:03, 48.97it/s]
Loading 0:  52%|█████▏    | 188/363 [00:09<00:03, 50.15it/s]
Loading 0:  53%|█████▎    | 194/363 [00:09<00:03, 52.64it/s]
Loading 0:  55%|█████▌    | 200/363 [00:09<00:03, 51.28it/s]
Loading 0:  57%|█████▋    | 206/363 [00:10<00:04, 37.84it/s]
Loading 0:  59%|█████▊    | 213/363 [00:10<00:03, 39.55it/s]
Loading 0:  61%|██████    | 221/363 [00:10<00:02, 47.86it/s]
Loading 0:  63%|██████▎   | 227/363 [00:10<00:02, 47.73it/s]
Loading 0:  64%|██████▍   | 233/363 [00:10<00:02, 49.51it/s]
Loading 0:  66%|██████▌   | 240/363 [00:10<00:02, 47.61it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 54.92it/s]
Loading 0:  70%|██████▉   | 254/363 [00:11<00:02, 52.82it/s]
Loading 0:  72%|███████▏  | 260/363 [00:11<00:01, 52.65it/s]
Loading 0:  74%|███████▎  | 267/363 [00:11<00:01, 49.18it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:01, 56.01it/s]
Loading 0:  77%|███████▋  | 281/363 [00:11<00:01, 53.01it/s]
Loading 0:  79%|███████▉  | 287/363 [00:11<00:01, 39.32it/s]
Loading 0:  81%|████████  | 294/363 [00:12<00:01, 40.53it/s]
Loading 0:  83%|████████▎ | 302/363 [00:12<00:01, 48.36it/s]
Loading 0:  85%|████████▍ | 308/363 [00:12<00:01, 47.52it/s]
Loading 0:  87%|████████▋ | 314/363 [00:12<00:00, 49.51it/s]
Loading 0:  88%|████████▊ | 321/363 [00:12<00:00, 47.23it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:00, 54.30it/s]
Loading 0:  92%|█████████▏| 335/363 [00:12<00:00, 51.24it/s]
Loading 0:  94%|█████████▍| 341/363 [00:12<00:00, 51.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:13<00:00, 49.08it/s]
Loading 0:  98%|█████████▊| 356/363 [00:13<00:00, 55.97it/s]
Loading 0: 100%|█████████▉| 362/363 [00:13<00:00, 53.53it/s]
                                                            
Job chaiml-rirv938-0sw-96p-67397-v1-mkmlizer completed after 113.45s with status: succeeded
Stopping job with name chaiml-rirv938-0sw-96p-67397-v1-mkmlizer
Pipeline stage MKMLizer completed in 113.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-rirv938-0sw-96p-67397-v1
Waiting for inference service chaiml-rirv938-0sw-96p-67397-v1 to be ready
Inference service chaiml-rirv938-0sw-96p-67397-v1 ready after 60.25834321975708s
Pipeline stage MKMLDeployer completed in 60.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3211498260498047s
Received healthy response to inference request in 1.877535343170166s
Received healthy response to inference request in 1.4672267436981201s
Received healthy response to inference request in 1.3489789962768555s
Received healthy response to inference request in 1.6072149276733398s
5 requests
0 failed requests
5th percentile: 1.3267156600952148
10th percentile: 1.332281494140625
20th percentile: 1.3434131622314454
30th percentile: 1.3726285457611085
40th percentile: 1.4199276447296143
50th percentile: 1.4672267436981201
60th percentile: 1.523222017288208
70th percentile: 1.5792172908782958
80th percentile: 1.6612790107727051
90th percentile: 1.7694071769714355
95th percentile: 1.8234712600708007
99th percentile: 1.866722526550293
mean time: 1.5244211673736572
Pipeline stage StressChecker completed in 9.15s
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 0.61s
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 1.07s
Shutdown handler de-registered
chaiml-rirv938-0sw-96p-_67397_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-rirv938-0sw-96p-67397-v1-profiler
Waiting for inference service chaiml-rirv938-0sw-96p-67397-v1-profiler to be ready
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 2204.17s
Shutdown handler de-registered
chaiml-rirv938-0sw-96p-_67397_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-rirv938-0sw-96p-_67397_v1 status is now torndown due to DeploymentManager action