developer_uid: bogoconic1
submission_id: chaiml-gy-exp192-sft-gy_72888_v2
model_name: chaiml-gy-exp192-sft-gy_72888_v2
model_group: ChaiML/gy-exp192-sft-gy-
status: torndown
timestamp: 2025-07-20T12:04:50+00:00
num_battles: 8919
num_wins: 4652
celo_rating: 1289.71
family_friendly_score: 0.5462
family_friendly_standard_error: 0.007040817566163747
submission_type: basic
model_repo: ChaiML/gy-exp192-sft-gy-datamix-v1-AR-6kchars-alltokenloss-ep2
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': 0.5240191827444199, 'latency_mean': 1.9082058048248292, 'latency_p50': 1.911982774734497, 'latency_p90': 2.1143393516540527}, {'batch_size': 3, 'throughput': 1.0493333642256302, 'latency_mean': 2.8479436242580416, 'latency_p50': 2.8387794494628906, 'latency_p90': 3.16045823097229}, {'batch_size': 5, 'throughput': 1.3356841389974905, 'latency_mean': 3.712003878355026, 'latency_p50': 3.7214620113372803, 'latency_p90': 4.120449185371399}, {'batch_size': 6, 'throughput': 1.450511984194978, 'latency_mean': 4.1168311560153965, 'latency_p50': 4.113274812698364, 'latency_p90': 4.588383197784424}, {'batch_size': 8, 'throughput': 1.565954366315803, 'latency_mean': 5.064516203403473, 'latency_p50': 5.095110297203064, 'latency_p90': 5.771884274482726}, {'batch_size': 10, 'throughput': 1.656560487604716, 'latency_mean': 5.981826630830764, 'latency_p50': 6.023790955543518, 'latency_p90': 6.688494610786438}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp192-sft-gy_72888_v2
is_internal_developer: False
language_model: ChaiML/gy-exp192-sft-gy-datamix-v1-AR-6kchars-alltokenloss-ep2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-07-20
win_ratio: 0.5215831371229959
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', '</s>', '<|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-exp192-sft-gy-72888-v2-mkmlizer
Waiting for job on chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer to finish
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission junhua024-chai-11-full-_99974_v2: HTTPConnectionPool(host='junhua024-chai-11-full-99974-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: Downloaded to shared memory in 69.387s
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: Checking if ChaiML/gy-exp192-sft-gy-datamix-v1-AR-6kchars-alltokenloss-ep2 already exists in ChaiML
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk0y0tdm9, device:0
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: quantized model in 47.999s
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: Processed model ChaiML/gy-exp192-sft-gy-datamix-v1-AR-6kchars-alltokenloss-ep2 in 117.387s
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia/config.json
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia/special_tokens_map.json
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia/tokenizer_config.json
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia/tokenizer.json
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp192-sft-gy-72888-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.75it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.89it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.92it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.51it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.84it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.09it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.53it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.33it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.93it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.77it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.48it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.17it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.06it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.91it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.81it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.25it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.74it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.56it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:10, 26.92it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 24.24it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.99it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.95it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 24.10it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.60it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.18it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.14it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 26.19it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.72it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.31it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.38it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.99it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.53it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:07, 30.29it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:11, 18.42it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:09, 21.56it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 22.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.23it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.22it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 25.67it/s]
Loading 0:  48%|████▊     | 175/363 [00:06<00:07, 25.82it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:07, 25.15it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.77it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.21it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.36it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.05it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.05it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:08,  1.16s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:34,  1.03it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.15it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.84it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.09it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.25it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.38it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.94it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.34it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.43it/s]
Loading 0:  66%|██████▋   | 241/363 [00:23<00:07, 17.38it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.38it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.27it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.73it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.48it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 32.06it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.10it/s]
Loading 0:  75%|███████▌  | 273/363 [00:25<00:04, 21.75it/s]
Loading 0:  76%|███████▌  | 276/363 [00:25<00:04, 20.81it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.65it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.71it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.63it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 26.73it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 26.96it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.04it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 21.59it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 22.44it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 22.26it/s]
Loading 0:  87%|████████▋ | 316/363 [00:26<00:02, 23.36it/s]
Loading 0:  88%|████████▊ | 319/363 [00:26<00:01, 24.37it/s]
Loading 0:  89%|████████▊ | 322/363 [00:27<00:01, 24.12it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 26.80it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 23.24it/s]
Loading 0:  92%|█████████▏| 334/363 [00:27<00:01, 26.79it/s]
Loading 0:  93%|█████████▎| 337/363 [00:27<00:01, 22.76it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.92it/s]
Loading 0:  95%|█████████▌| 346/363 [00:28<00:00, 20.11it/s]
Loading 0:  96%|█████████▌| 349/363 [00:28<00:00, 19.30it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 24.73it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 24.81it/s]
                                                            

Job chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer completed after 149.48s with status: succeeded
Stopping job with name chaiml-gy-exp192-sft-gy-72888-v2-mkmlizer
Pipeline stage MKMLizer completed in 149.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp192-sft-gy-72888-v2
Waiting for inference service chaiml-gy-exp192-sft-gy-72888-v2 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-gy-exp192-sft-gy-72888-v2 ready after 331.7467074394226s
Pipeline stage MKMLDeployer completed in 332.20s
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 2.813692569732666s
Received healthy response to inference request in 1.9599981307983398s
Received healthy response to inference request in 2.544877529144287s
Received healthy response to inference request in 1.9140448570251465s
5 requests
1 failed requests
5th percentile: 1.9232355117797852
10th percentile: 1.9324261665344238
20th percentile: 1.950807476043701
30th percentile: 2.0769740104675294
40th percentile: 2.310925769805908
50th percentile: 2.544877529144287
60th percentile: 2.652403545379639
70th percentile: 2.75992956161499
80th percentile: 6.2764955520629915
90th percentile: 13.202101516723634
95th percentile: 16.664904499053954
99th percentile: 19.43514688491821
mean time: 5.872064113616943
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9569942951202393s
Received healthy response to inference request in 1.9459428787231445s
Received healthy response to inference request in 2.073451280593872s
Received healthy response to inference request in 1.8875226974487305s
Received healthy response to inference request in 1.9960980415344238s
5 requests
0 failed requests
5th percentile: 1.8992067337036134
10th percentile: 1.910890769958496
20th percentile: 1.9342588424682616
30th percentile: 1.9481531620025634
40th percentile: 1.9525737285614013
50th percentile: 1.9569942951202393
60th percentile: 1.9726357936859131
70th percentile: 1.988277292251587
80th percentile: 2.0115686893463134
90th percentile: 2.042509984970093
95th percentile: 2.0579806327819825
99th percentile: 2.070357151031494
mean time: 1.972001838684082
Pipeline stage StressChecker completed in 41.88s
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 0.78s
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 0.70s
Shutdown handler de-registered
chaiml-gy-exp192-sft-gy_72888_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3212.37s
Shutdown handler de-registered
chaiml-gy-exp192-sft-gy_72888_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp192-sft-gy_72888_v2 status is now torndown due to DeploymentManager action