developer_uid: bogoconic1
submission_id: chaiml-gy-exp47-sft-gy-_71449_v3
model_name: chaiml-gy-exp47-sft-gy-_71449_v3
model_group: ChaiML/gy-exp47-sft-gy-d
status: torndown
timestamp: 2025-07-03T06:23:25+00:00
num_battles: 7448
num_wins: 3683
celo_rating: 1283.61
family_friendly_score: 0.5388
family_friendly_standard_error: 0.0070497455273222445
submission_type: basic
model_repo: ChaiML/gy-exp47-sft-gy-datamix-v1-head1000-ep2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5955517533248829, 'latency_mean': 1.6789396345615386, 'latency_p50': 1.6701760292053223, 'latency_p90': 1.8351752996444701}, {'batch_size': 3, 'throughput': 1.0579463658504995, 'latency_mean': 2.819709643125534, 'latency_p50': 2.8239035606384277, 'latency_p90': 3.0904914855957033}, {'batch_size': 5, 'throughput': 1.2832884207036248, 'latency_mean': 3.878986037969589, 'latency_p50': 3.8886473178863525, 'latency_p90': 4.279728960990906}, {'batch_size': 6, 'throughput': 1.344437356636097, 'latency_mean': 4.434680120944977, 'latency_p50': 4.419573426246643, 'latency_p90': 4.984871101379394}, {'batch_size': 8, 'throughput': 1.4088611818756327, 'latency_mean': 5.6456054520607, 'latency_p50': 5.682207822799683, 'latency_p90': 6.313737893104554}, {'batch_size': 10, 'throughput': 1.4393789628086269, 'latency_mean': 6.887026233673096, 'latency_p50': 6.930597186088562, 'latency_p90': 7.73955180644989}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp47-sft-gy-_71449_v3
is_internal_developer: True
language_model: ChaiML/gy-exp47-sft-gy-datamix-v1-head1000-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-07-02
win_ratio: 0.4944951664876477
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp47-sft-gy-71449-v3-mkmlizer
Waiting for job on chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer to finish
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: Downloaded to shared memory in 31.566s
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: Checking if ChaiML/gy-exp47-sft-gy-datamix-v1-head1000-ep2 already exists in ChaiML
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpipy1nfy4, device:0
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: quantized model in 30.847s
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: Processed model ChaiML/gy-exp47-sft-gy-datamix-v1-head1000-ep2 in 62.413s
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp47-sft-gy-71449-v3/nvidia
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp47-sft-gy-71449-v3/nvidia/config.json
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp47-sft-gy-71449-v3/nvidia/special_tokens_map.json
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp47-sft-gy-71449-v3/nvidia/tokenizer_config.json
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp47-sft-gy-71449-v3/nvidia/tokenizer.json
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp47-sft-gy-71449-v3/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.11it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.07it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.41it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.90it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.01it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.01it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.91it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.64it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.83it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.79it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.30it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.90it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.52it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 42.62it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 40.68it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 40.61it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 46.99it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.08it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 41.07it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.83it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.21it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.89it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.45it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 26.87it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 34.65it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.54it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.55it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:05, 38.09it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 37.83it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.63it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.21it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.38it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 44.34it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.82it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.21it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.15it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 47.04it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 28.46it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.31it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.00it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.45it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.38it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.30it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 40.40it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 40.36it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.22it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 40.49it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 33.12it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 38.60it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 38.67it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 40.65it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 22.21it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 23.50it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 25.59it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 31.06it/s]
Loading 0:  89%|████████▉ | 324/363 [00:08<00:01, 32.49it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:01, 33.93it/s]
Loading 0:  91%|█████████▏| 332/363 [00:08<00:00, 34.25it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 39.74it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 39.63it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 40.00it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 45.80it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 43.91it/s]
                                                            

Job chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer completed after 84.9s with status: succeeded
Stopping job with name chaiml-gy-exp47-sft-gy-71449-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.45s
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-gy-exp47-sft-gy-71449-v3
Waiting for inference service chaiml-gy-exp47-sft-gy-71449-v3 to be ready
Inference service chaiml-gy-exp47-sft-gy-71449-v3 ready after 271.8730297088623s
Pipeline stage MKMLDeployer completed in 272.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3688058853149414s
Received healthy response to inference request in 1.895695686340332s
Received healthy response to inference request in 1.5648117065429688s
Received healthy response to inference request in 1.678626537322998s
Received healthy response to inference request in 1.8952233791351318s
5 requests
0 failed requests
5th percentile: 1.5875746726989746
10th percentile: 1.6103376388549804
20th percentile: 1.6558635711669922
30th percentile: 1.7219459056854247
40th percentile: 1.8085846424102783
50th percentile: 1.8952233791351318
60th percentile: 1.895412302017212
70th percentile: 1.895601224899292
80th percentile: 2.190317726135254
90th percentile: 2.779561805725098
95th percentile: 3.0741838455200194
99th percentile: 3.309881477355957
mean time: 2.0806326389312746
Pipeline stage StressChecker completed in 11.83s
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 0.64s
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 0.92s
Shutdown handler de-registered
chaiml-gy-exp47-sft-gy-_71449_v3 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
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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp47-sft-gy-71449-v3-profiler
Waiting for inference service chaiml-gy-exp47-sft-gy-71449-v3-profiler to be ready
Inference service chaiml-gy-exp47-sft-gy-71449-v3-profiler ready after 202.01502108573914s
Pipeline stage MKMLProfilerDeployer completed in 202.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-gy-exp47-sft-49cec18388723c38b953b8e1fc5d668b-deplomxjb8:/code/chaiverse_profiler_1751524479 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-gy-exp47-sft-49cec18388723c38b953b8e1fc5d668b-deplomxjb8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751524479 && 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_1751524479/summary.json'
kubectl exec -it chaiml-gy-exp47-sft-49cec18388723c38b953b8e1fc5d668b-deplomxjb8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1751524479/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1122.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-gy-exp47-sft-gy-71449-v3-profiler is running
Tearing down inference service chaiml-gy-exp47-sft-gy-71449-v3-profiler
Service chaiml-gy-exp47-sft-gy-71449-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.22s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4493.95s
Shutdown handler de-registered
chaiml-gy-exp47-sft-gy-_71449_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp47-sft-gy-_71449_v3 status is now torndown due to DeploymentManager action