chaiml-rirv938-0sw-96p_18713

developer_uid: NischayDnk

submission_id: chaiml-rirv938-0sw-96p_18713_v14

model_name: chaiml-rirv938-0sw-96p_18713_v14

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

status: torndown

timestamp: 2025-09-22T06:27:03+00:00

num_battles: 5714

num_wins: 3096

celo_rating: 1284.8

family_friendly_score: 0.47519999999999996

family_friendly_standard_error: 0.007062364476575816

submission_type: basic

model_repo: ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0

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': 0.7002885761198547, 'latency_mean': 1.4278620707988738, 'latency_p50': 1.4199604988098145, 'latency_p90': 1.5843047380447388}, {'batch_size': 4, 'throughput': 1.7116810857184037, 'latency_mean': 2.3209771502017973, 'latency_p50': 2.345521926879883, 'latency_p90': 2.568841743469238}, {'batch_size': 5, 'throughput': 1.9137783950946397, 'latency_mean': 2.5948744082450865, 'latency_p50': 2.5830140113830566, 'latency_p90': 2.88828330039978}, {'batch_size': 8, 'throughput': 2.287176589119023, 'latency_mean': 3.473472819328308, 'latency_p50': 3.452087163925171, 'latency_p90': 3.8672605991363525}, {'batch_size': 10, 'throughput': 2.4108059273478064, 'latency_mean': 4.0944978511333465, 'latency_p50': 4.129755020141602, 'latency_p90': 4.676011562347412}, {'batch_size': 12, 'throughput': 2.5102025395112495, 'latency_mean': 4.719025480747223, 'latency_p50': 4.751242995262146, 'latency_p90': 5.43874077796936}, {'batch_size': 15, 'throughput': 2.618013159855698, 'latency_mean': 5.657151284217835, 'latency_p50': 5.698646664619446, 'latency_p90': 6.473129177093505}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-rirv938-0sw-96p_18713_v14

ineligible_reason: max_output_tokens!=64

is_internal_developer: False

language_model: ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0

model_size: 13B

ranking_group: single

throughput_3p7s: 2.36

us_pacific_date: 2025-09-21

win_ratio: 0.5418270913545677

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|>', '####', '\n', 'Bot:', '</s>', 'User:', 'You:', '<|eot_id|>', '<|im_start|>'], '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-18713-v14-mkmlizer
Waiting for job on chaiml-rirv938-0sw-96p-18713-v14-mkmlizer to finish
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  belonging to:                                                      ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: Downloaded to shared memory in 22.437s
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: Checking if ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0 already exists in ChaiML
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz2r9onoy, device:0
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: quantized model in 29.052s
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: Processed model ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0 in 51.490s
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v14/nvidia
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v14/nvidia/config.json
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v14/nvidia/special_tokens_map.json
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v14/nvidia/tokenizer_config.json
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v14/nvidia/tokenizer.json
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v14/nvidia/flywheel_model.0.safetensors
chaiml-rirv938-0sw-96p-18713-v14-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:07<24:03,  4.00s/it]
Loading 0:   2%|▏         | 6/363 [00:08<06:20,  1.07s/it]
Loading 0:   4%|▍         | 14/363 [00:08<02:02,  2.84it/s]
Loading 0:   6%|▌         | 20/363 [00:08<01:13,  4.70it/s]
Loading 0:   7%|▋         | 25/363 [00:08<00:50,  6.72it/s]
Loading 0:   9%|▉         | 32/363 [00:08<00:31, 10.52it/s]
Loading 0:  10%|█         | 38/363 [00:08<00:22, 14.15it/s]
Loading 0:  12%|█▏        | 44/363 [00:08<00:17, 18.52it/s]
Loading 0:  14%|█▍        | 51/363 [00:09<00:13, 22.94it/s]
Loading 0:  16%|█▋        | 59/363 [00:09<00:10, 30.12it/s]
Loading 0:  18%|█▊        | 65/363 [00:09<00:12, 24.77it/s]
Loading 0:  19%|█▉        | 70/363 [00:09<00:11, 25.11it/s]
Loading 0:  21%|██        | 77/363 [00:09<00:09, 31.59it/s]
Loading 0:  23%|██▎       | 83/363 [00:09<00:08, 34.77it/s]
Loading 0:  24%|██▍       | 88/363 [00:10<00:07, 37.09it/s]
Loading 0:  26%|██▌       | 95/363 [00:10<00:06, 43.89it/s]
Loading 0:  28%|██▊       | 101/363 [00:10<00:05, 44.52it/s]
Loading 0:  29%|██▉       | 107/363 [00:10<00:05, 46.92it/s]
Loading 0:  31%|███▏      | 114/363 [00:10<00:05, 45.36it/s]
Loading 0:  34%|███▎      | 122/363 [00:10<00:04, 53.28it/s]
Loading 0:  35%|███▌      | 128/363 [00:10<00:04, 51.71it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:07, 30.62it/s]
Loading 0:  39%|███▉      | 141/363 [00:11<00:06, 33.32it/s]
Loading 0:  41%|████      | 149/363 [00:11<00:05, 41.29it/s]
Loading 0:  43%|████▎     | 155/363 [00:11<00:04, 42.39it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:04, 45.38it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:04, 44.50it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:03, 51.97it/s]
Loading 0:  50%|█████     | 182/363 [00:12<00:03, 50.75it/s]
Loading 0:  52%|█████▏    | 188/363 [00:12<00:03, 51.01it/s]
Loading 0:  54%|█████▎    | 195/363 [00:12<00:03, 48.20it/s]
Loading 0:  56%|█████▌    | 204/363 [00:12<00:03, 50.63it/s]
Loading 0:  58%|█████▊    | 212/363 [00:12<00:02, 56.57it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:02, 53.61it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:02, 53.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:02, 54.92it/s]
Loading 0:  65%|██████▌   | 236/363 [00:13<00:02, 52.04it/s]
Loading 0:  67%|██████▋   | 242/363 [00:13<00:02, 52.36it/s]
Loading 0:  69%|██████▊   | 249/363 [00:13<00:02, 48.82it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:01, 55.86it/s]
Loading 0:  72%|███████▏  | 263/363 [00:13<00:01, 52.74it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:01, 53.08it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:01, 54.76it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 52.12it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:01, 52.59it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:01, 54.42it/s]
Loading 0:  82%|████████▏ | 299/363 [00:14<00:01, 51.20it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 48.97it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 30.38it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 31.77it/s]
Loading 0:  88%|████████▊ | 321/363 [00:15<00:01, 35.20it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:00, 44.32it/s]
Loading 0:  92%|█████████▏| 335/363 [00:15<00:00, 45.13it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 47.09it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 45.30it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 52.43it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 50.53it/s]
                                                            
Job chaiml-rirv938-0sw-96p-18713-v14-mkmlizer completed after 113.3s with status: succeeded
Stopping job with name chaiml-rirv938-0sw-96p-18713-v14-mkmlizer
Pipeline stage MKMLizer completed in 114.07s
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-18713-v14
Waiting for inference service chaiml-rirv938-0sw-96p-18713-v14 to be ready
Inference service chaiml-rirv938-0sw-96p-18713-v14 ready after 60.67935657501221s
Pipeline stage MKMLDeployer completed in 61.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1134095191955566s
Received healthy response to inference request in 1.4290642738342285s
Received healthy response to inference request in 1.5770363807678223s
Received healthy response to inference request in 1.3230195045471191s
Received healthy response to inference request in 1.5564310550689697s
5 requests
0 failed requests
5th percentile: 1.344228458404541
10th percentile: 1.3654374122619628
20th percentile: 1.4078553199768067
30th percentile: 1.4545376300811768
40th percentile: 1.5054843425750732
50th percentile: 1.5564310550689697
60th percentile: 1.5646731853485107
70th percentile: 1.5729153156280518
80th percentile: 1.6843110084533692
90th percentile: 1.898860263824463
95th percentile: 2.0061348915100097
99th percentile: 2.091954593658447
mean time: 1.5997921466827392
Pipeline stage StressChecker completed in 9.32s
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 1.53s
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 0.63s
Shutdown handler de-registered
chaiml-rirv938-0sw-96p_18713_v14 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 0.09s
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-18713-v14-profiler
Waiting for inference service chaiml-rirv938-0sw-96p-18713-v14-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 2221.98s
Shutdown handler de-registered
chaiml-rirv938-0sw-96p_18713_v14 status is now inactive due to auto deactivation removed underperforming models
chaiml-rirv938-0sw-96p_18713_v14 status is now torndown due to DeploymentManager action