developer_uid: chai_backend_admin
submission_id: chaiml-collin-servant-p_49347_v1
model_name: chaiml-collin-servant-p_49347_v1
model_group: ChaiML/Collin-Servant-Pr
status: torndown
timestamp: 2025-05-12T18:31:21+00:00
num_battles: 12042
num_wins: 6250
celo_rating: 1289.75
family_friendly_score: 0.5192
family_friendly_standard_error: 0.007065852531719014
submission_type: basic
model_repo: ChaiML/Collin-Servant-Prince-forbidden-love_S250512101740_sft
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': 0.5346394283083343, 'latency_mean': 1.8703642833232879, 'latency_p50': 1.8677211999893188, 'latency_p90': 2.061390733718872}, {'batch_size': 3, 'throughput': 1.1068495770243676, 'latency_mean': 2.709575433731079, 'latency_p50': 2.711043357849121, 'latency_p90': 2.978205418586731}, {'batch_size': 5, 'throughput': 1.4112673641082563, 'latency_mean': 3.525604168176651, 'latency_p50': 3.508816719055176, 'latency_p90': 3.9180956840515138}, {'batch_size': 6, 'throughput': 1.5265934163005594, 'latency_mean': 3.9071104025840757, 'latency_p50': 3.9004851579666138, 'latency_p90': 4.358362865447998}, {'batch_size': 8, 'throughput': 1.7002624278756282, 'latency_mean': 4.676880623102188, 'latency_p50': 4.652961730957031, 'latency_p90': 5.297870326042175}, {'batch_size': 10, 'throughput': 1.7760300153909963, 'latency_mean': 5.577869954109192, 'latency_p50': 5.602577090263367, 'latency_p90': 6.2611863851547245}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-collin-servant-p_49347_v1
is_internal_developer: True
language_model: ChaiML/Collin-Servant-Prince-forbidden-love_S250512101740_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.47
us_pacific_date: 2025-05-12
win_ratio: 0.5190167746221558
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####\n', '####', '\n', '</s>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {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-collin-servant-p-49347-v1-mkmlizer
Waiting for job on chaiml-collin-servant-p-49347-v1-mkmlizer to finish
chaiml-collin-servant-p-49347-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ _____ __ __ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ /___/ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ belonging to: ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ║ ║
chaiml-collin-servant-p-49347-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-collin-servant-p-49347-v1-mkmlizer: Downloaded to shared memory in 83.174s
chaiml-collin-servant-p-49347-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyu49lmzu, device:0
chaiml-collin-servant-p-49347-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-collin-servant-p-49347-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-collin-servant-p-49347-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-collin-servant-p-49347-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1
chaiml-collin-servant-p-49347-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1/config.json
chaiml-collin-servant-p-49347-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1/special_tokens_map.json
chaiml-collin-servant-p-49347-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1/tokenizer_config.json
chaiml-collin-servant-p-49347-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1/tokenizer.json
chaiml-collin-servant-p-49347-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1/flywheel_model.1.safetensors
chaiml-collin-servant-p-49347-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-p-49347-v1/flywheel_model.0.safetensors
chaiml-collin-servant-p-49347-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.44it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:09, 36.72it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 34.77it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 35.61it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:10, 31.95it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:08, 36.99it/s] Loading 0: 10%|▉ | 36/363 [00:01<00:14, 23.28it/s] Loading 0: 11%|█ | 40/363 [00:01<00:12, 26.08it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:11, 26.99it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:11, 28.63it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 27.52it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:10, 30.33it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:10, 28.37it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 29.05it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 25.96it/s] Loading 0: 20%|██ | 73/363 [00:02<00:13, 22.06it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 26.86it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:10, 25.90it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 26.92it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:10, 26.56it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:12, 21.38it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:09, 28.52it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:09, 27.55it/s] Loading 0: 29%|██▉ | 107/363 [00:03<00:10, 23.41it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.42it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 25.76it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 28.62it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:09, 25.52it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 29.71it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:08, 28.05it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:07, 29.99it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 28.20it/s] Loading 0: 40%|████ | 146/363 [00:05<00:07, 30.60it/s] Loading 0: 41%|████▏ | 150/363 [00:05<00:08, 23.75it/s] Loading 0: 42%|████▏ | 153/363 [00:05<00:10, 20.25it/s] Loading 0: 43%|████▎ | 157/363 [00:05<00:08, 23.73it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:08, 24.04it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 26.53it/s] Loading 0: 46%|████▋ | 168/363 [00:06<00:08, 24.13it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 28.58it/s] Loading 0: 49%|████▉ | 177/363 [00:06<00:07, 25.30it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 27.46it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:07, 24.22it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 22.15it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 21.51it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:07, 21.04it/s] Loading 0: 55%|█████▍ | 199/363 [00:07<00:07, 22.76it/s] Loading 0: 55%|█████▌ | 200/363 [00:21<00:07, 22.76it/s] Loading 0: 55%|█████▌ | 201/363 [00:21<04:02, 1.50s/it] Loading 0: 56%|█████▌ | 203/363 [00:22<03:10, 1.19s/it] Loading 0: 57%|█████▋ | 208/363 [00:22<01:43, 1.49it/s] Loading 0: 58%|█████▊ | 211/363 [00:22<01:16, 1.99it/s] Loading 0: 59%|█████▉ | 214/363 [00:22<00:55, 2.68it/s] Loading 0: 60%|██████ | 218/363 [00:22<00:37, 3.91it/s] Loading 0: 61%|██████ | 221/363 [00:22<00:28, 5.04it/s] Loading 0: 62%|██████▏ | 224/363 [00:23<00:23, 6.01it/s] Loading 0: 63%|██████▎ | 229/363 [00:23<00:14, 8.98it/s] Loading 0: 64%|██████▍ | 232/363 [00:23<00:12, 10.57it/s] Loading 0: 65%|██████▍ | 235/363 [00:23<00:10, 12.78it/s] Loading 0: 66%|██████▌ | 238/363 [00:23<00:08, 15.03it/s] Loading 0: 66%|██████▋ | 241/363 [00:23<00:07, 16.63it/s] Loading 0: 67%|██████▋ | 245/363 [00:23<00:05, 20.91it/s] Loading 0: 68%|██████▊ | 248/363 [00:24<00:06, 17.78it/s] Loading 0: 70%|██████▉ | 253/363 [00:24<00:04, 23.81it/s] Loading 0: 71%|███████ | 257/363 [00:24<00:04, 21.47it/s] Loading 0: 72%|███████▏ | 262/363 [00:24<00:03, 26.01it/s] Loading 0: 73%|███████▎ | 266/363 [00:24<00:03, 28.72it/s] Loading 0: 74%|███████▍ | 270/363 [00:25<00:05, 18.04it/s] Loading 0: 75%|███████▌ | 274/363 [00:25<00:04, 21.02it/s] Loading 0: 76%|███████▋ | 277/363 [00:25<00:04, 21.42it/s] Loading 0: 77%|███████▋ | 280/363 [00:25<00:03, 22.79it/s] Loading 0: 78%|███████▊ | 283/363 [00:25<00:03, 23.87it/s] Loading 0: 79%|███████▉ | 286/363 [00:25<00:03, 23.16it/s] Loading 0: 80%|███████▉ | 289/363 [00:25<00:03, 24.45it/s] Loading 0: 80%|████████ | 292/363 [00:25<00:02, 25.41it/s] Loading 0: 81%|████████▏ | 295/363 [00:26<00:02, 24.07it/s] Loading 0: 82%|████████▏ | 299/363 [00:26<00:02, 23.41it/s] Loading 0: 84%|████████▎ | 304/363 [00:26<00:02, 20.72it/s] Loading 0: 85%|████████▍ | 307/363 [00:26<00:02, 19.30it/s] Loading 0: 85%|████████▌ | 310/363 [00:26<00:02, 20.92it/s] Loading 0: 86%|████████▌ | 313/363 [00:26<00:02, 21.58it/s] Loading 0: 87%|████████▋ | 316/363 [00:27<00:02, 23.15it/s] Loading 0: 88%|████████▊ | 319/363 [00:27<00:01, 24.47it/s] Loading 0: 89%|████████▊ | 322/363 [00:27<00:01, 23.67it/s] Loading 0: 90%|████████▉ | 325/363 [00:27<00:01, 25.05it/s] Loading 0: 90%|█████████ | 328/363 [00:27<00:01, 25.41it/s] Loading 0: 91%|█████████ | 331/363 [00:27<00:01, 24.39it/s] Loading 0: 92%|█████████▏| 334/363 [00:27<00:01, 25.57it/s] Loading 0: 93%|█████████▎| 337/363 [00:27<00:01, 21.61it/s] Loading 0: 94%|█████████▎| 340/363 [00:28<00:00, 23.49it/s] Loading 0: 94%|█████████▍| 343/363 [00:34<00:14, 1.41it/s] Loading 0: 96%|█████████▌| 347/363 [00:35<00:07, 2.16it/s] Loading 0: 96%|█████████▋| 350/363 [00:35<00:04, 2.88it/s] Loading 0: 98%|█████████▊| 355/363 [00:35<00:01, 4.55it/s] Loading 0: 99%|█████████▊| 358/363 [00:35<00:00, 5.59it/s]
Job chaiml-collin-servant-p-49347-v1-mkmlizer completed after 175.92s with status: succeeded
Stopping job with name chaiml-collin-servant-p-49347-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.41s
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 chaiml-collin-servant-p-49347-v1
Waiting for inference service chaiml-collin-servant-p-49347-v1 to be ready
Inference service chaiml-collin-servant-p-49347-v1 ready after 110.43427968025208s
Pipeline stage MKMLDeployer completed in 110.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5495963096618652s
Received healthy response to inference request in 2.16282057762146s
Received healthy response to inference request in 2.1030070781707764s
Received healthy response to inference request in 2.0818188190460205s
Received healthy response to inference request in 2.38455867767334s
5 requests
0 failed requests
5th percentile: 2.0860564708709717
10th percentile: 2.090294122695923
20th percentile: 2.098769426345825
30th percentile: 2.114969778060913
40th percentile: 2.1388951778411864
50th percentile: 2.16282057762146
60th percentile: 2.251515817642212
70th percentile: 2.340211057662964
80th percentile: 2.417566204071045
90th percentile: 2.4835812568664553
95th percentile: 2.5165887832641602
99th percentile: 2.542994804382324
mean time: 2.2563602924346924
Pipeline stage StressChecker completed in 12.85s
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 0.77s
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 0.76s
Shutdown handler de-registered
chaiml-collin-servant-p_49347_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-collin-servant-p-49347-v1-profiler
Waiting for inference service chaiml-collin-servant-p-49347-v1-profiler to be ready
Inference service chaiml-collin-servant-p-49347-v1-profiler ready after 120.6587827205658s
Pipeline stage MKMLProfilerDeployer completed in 121.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-collin-servanc7fa798e16ad1bf2687ce81769b143f5-deplor4jx5:/code/chaiverse_profiler_1747075285 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-collin-servanc7fa798e16ad1bf2687ce81769b143f5-deplor4jx5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1747075285 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1747075285/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 2707.72s
Shutdown handler de-registered
chaiml-collin-servant-p_49347_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-collin-servant-p_49347_v1 status is now torndown due to DeploymentManager action