developer_uid: bogoconic1
submission_id: chaiml-gy-exp45-sft-gy-_91835_v2
model_name: chaiml-gy-exp45-sft-gy-_91835_v2
model_group: ChaiML/gy-exp45-sft-gy-d
status: torndown
timestamp: 2025-06-30T11:20:36+00:00
num_battles: 11010
num_wins: 5531
celo_rating: 1288.69
family_friendly_score: 0.534
family_friendly_standard_error: 0.00705470056061914
submission_type: basic
model_repo: ChaiML/gy-exp45-sft-gy-datamix-v1-exp24-rmchosen-ge0.6-v0-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': 0.5954608529405322, 'latency_mean': 1.679199105501175, 'latency_p50': 1.6785085201263428, 'latency_p90': 1.8507272958755494}, {'batch_size': 3, 'throughput': 1.0592462830063605, 'latency_mean': 2.8231262588500976, 'latency_p50': 2.805967688560486, 'latency_p90': 3.063989543914795}, {'batch_size': 5, 'throughput': 1.2680012173017745, 'latency_mean': 3.9167618417739867, 'latency_p50': 3.926243782043457, 'latency_p90': 4.387681531906128}, {'batch_size': 6, 'throughput': 1.345865327840575, 'latency_mean': 4.4312624728679655, 'latency_p50': 4.369803786277771, 'latency_p90': 5.035915637016297}, {'batch_size': 8, 'throughput': 1.4108394049340505, 'latency_mean': 5.623217883110047, 'latency_p50': 5.646784424781799, 'latency_p90': 6.204640412330627}, {'batch_size': 10, 'throughput': 1.4317372144581453, 'latency_mean': 6.929988660812378, 'latency_p50': 6.959407567977905, 'latency_p90': 7.766318535804748}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp45-sft-gy-_91835_v2
is_internal_developer: True
language_model: ChaiML/gy-exp45-sft-gy-datamix-v1-exp24-rmchosen-ge0.6-v0-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-06-30
win_ratio: 0.5023614895549501
generation_params: {'temperature': 0.3, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 20, 'presence_penalty': 0.7, 'frequency_penalty': 0.7, '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': 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 chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer
Waiting for job on chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer to finish
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: Downloaded to shared memory in 30.776s
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: Checking if ChaiML/gy-exp45-sft-gy-datamix-v1-exp24-rmchosen-ge0.6-v0-ep2 already exists in ChaiML
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpygdpyiu0, device:0
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: quantized model in 30.722s
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: Processed model ChaiML/gy-exp45-sft-gy-datamix-v1-exp24-rmchosen-ge0.6-v0-ep2 in 61.499s
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp45-sft-gy-91835-v2
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp45-sft-gy-91835-v2/config.json
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp45-sft-gy-91835-v2/special_tokens_map.json
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp45-sft-gy-91835-v2/tokenizer_config.json
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp45-sft-gy-91835-v2/tokenizer.json
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp45-sft-gy-91835-v2/flywheel_model.0.safetensors
chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 29.88it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.18it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.99it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.36it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.50it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.40it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.35it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 41.04it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 40.43it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:06, 45.08it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:09, 31.40it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:09, 31.91it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.54it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 36.32it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 37.16it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:07, 35.26it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 38.12it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 35.92it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 38.78it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:06, 37.37it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 37.49it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 42.22it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 39.86it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 41.33it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 33.99it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 40.72it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 40.34it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 25.54it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.96it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.97it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.09it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.64it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.89it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.48it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.32it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.54it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 41.15it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.89it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.64it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 41.91it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.30it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.49it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 26.81it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.11it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.22it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.74it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.63it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.96it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.21it/s]
Loading 0:  72%|███████▏  | 262/363 [00:07<00:02, 37.38it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 36.69it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 40.95it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 41.62it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 41.17it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 42.89it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 34.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 38.16it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 22.89it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 25.27it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 25.43it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.68it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 36.46it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 41.47it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 41.62it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 41.84it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 42.79it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 35.29it/s]
                                                            

Job chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer completed after 84.88s with status: succeeded
Stopping job with name chaiml-gy-exp45-sft-gy-91835-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.46s
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-gy-exp45-sft-gy-91835-v2
Waiting for inference service chaiml-gy-exp45-sft-gy-91835-v2 to be ready
Inference service chaiml-gy-exp45-sft-gy-91835-v2 ready after 212.17970895767212s
Pipeline stage MKMLDeployer completed in 213.16s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.5384840965270996s
Received healthy response to inference request in 2.047060012817383s
Received healthy response to inference request in 1.9655265808105469s
Received healthy response to inference request in 2.0340960025787354s
5 requests
1 failed requests
5th percentile: 1.9792404651641846
10th percentile: 1.9929543495178224
20th percentile: 2.020382118225098
30th percentile: 2.036688804626465
40th percentile: 2.041874408721924
50th percentile: 2.047060012817383
60th percentile: 2.2436296463012697
70th percentile: 2.440199279785156
80th percentile: 6.060337305068973
90th percentile: 13.104043722152712
95th percentile: 16.625896930694577
99th percentile: 19.443379497528074
mean time: 5.746583366394043
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7443466186523438s
Received healthy response to inference request in 1.7706592082977295s
Received healthy response to inference request in 2.058828115463257s
Received healthy response to inference request in 1.666409969329834s
Received healthy response to inference request in 1.925354242324829s
5 requests
0 failed requests
5th percentile: 1.681997299194336
10th percentile: 1.697584629058838
20th percentile: 1.7287592887878418
30th percentile: 1.7496091365814208
40th percentile: 1.7601341724395752
50th percentile: 1.7706592082977295
60th percentile: 1.8325372219085694
70th percentile: 1.894415235519409
80th percentile: 1.9520490169525146
90th percentile: 2.0054385662078857
95th percentile: 2.0321333408355713
99th percentile: 2.05348916053772
mean time: 1.8331196308135986
Pipeline stage StressChecker completed in 40.63s
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 0.71s
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 0.81s
Shutdown handler de-registered
chaiml-gy-exp45-sft-gy-_91835_v2 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp45-sft-gy-91835-v2-profiler
Waiting for inference service chaiml-gy-exp45-sft-gy-91835-v2-profiler to be ready
Inference service chaiml-gy-exp45-sft-gy-91835-v2-profiler ready after 212.76110076904297s
Pipeline stage MKMLProfilerDeployer completed in 213.57s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-gy-exp45-sft-f7b55ed22430fbf3a35fce6aed14780f-deplonx9r9:/code/chaiverse_profiler_1751283087 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-gy-exp45-sft-f7b55ed22430fbf3a35fce6aed14780f-deplonx9r9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751283087 && 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_1751283087/summary.json'
kubectl exec -it chaiml-gy-exp45-sft-f7b55ed22430fbf3a35fce6aed14780f-deplonx9r9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1751283087/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1124.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-gy-exp45-sft-gy-91835-v2-profiler is running
Tearing down inference service chaiml-gy-exp45-sft-gy-91835-v2-profiler
Service chaiml-gy-exp45-sft-gy-91835-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.13s
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2539.50s
Shutdown handler de-registered
chaiml-gy-exp45-sft-gy-_91835_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp45-sft-gy-_91835_v2 status is now torndown due to DeploymentManager action