chaiml-gy-exp90-sft-gy-_85111

developer_uid: bogoconic1

submission_id: chaiml-gy-exp90-sft-gy-_85111_v1

model_name: chaiml-gy-exp90-sft-gy-_85111_v1

model_group: ChaiML/gy-exp90-sft-gy-d

status: torndown

timestamp: 2025-07-05T13:22:20+00:00

num_battles: 8493

num_wins: 4365

celo_rating: 1294.68

family_friendly_score: 0.5236000000000001

family_friendly_standard_error: 0.007063186816161669

submission_type: basic

model_repo: ChaiML/gy-exp90-sft-gy-datamix-v1-bo8-ep4

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5801838614501014, 'latency_mean': 1.7234138071537017, 'latency_p50': 1.7370846271514893, 'latency_p90': 1.8927443981170655}, {'batch_size': 3, 'throughput': 1.0542449147473145, 'latency_mean': 2.826983551979065, 'latency_p50': 2.8298494815826416, 'latency_p90': 3.112563705444336}, {'batch_size': 5, 'throughput': 1.2590291780641785, 'latency_mean': 3.9498120558261873, 'latency_p50': 3.919255018234253, 'latency_p90': 4.482472825050354}, {'batch_size': 6, 'throughput': 1.3167284375995854, 'latency_mean': 4.531634178161621, 'latency_p50': 4.554393649101257, 'latency_p90': 5.136205935478211}, {'batch_size': 8, 'throughput': 1.3645943291010572, 'latency_mean': 5.82363363981247, 'latency_p50': 5.836406946182251, 'latency_p90': 6.567233252525329}, {'batch_size': 10, 'throughput': 1.4036047318049498, 'latency_mean': 7.062026282548905, 'latency_p50': 7.132049798965454, 'latency_p90': 8.04687008857727}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp90-sft-gy-_85111_v1

is_internal_developer: True

language_model: ChaiML/gy-exp90-sft-gy-datamix-v1-bo8-ep4

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-07-05

win_ratio: 0.5139526669021547

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-exp90-sft-gy-85111-v1-mkmlizer
Waiting for job on chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer to finish
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission albertwang8192-2025-07-05-1_v1: HTTPConnectionPool(host='albertwang8192-2025-07-05-1-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: Downloaded to shared memory in 45.618s
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: Checking if ChaiML/gy-exp90-sft-gy-datamix-v1-bo8-ep4 already exists in ChaiML
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppnk9ynrc, device:0
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: quantized model in 31.401s
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: Processed model ChaiML/gy-exp90-sft-gy-datamix-v1-bo8-ep4 in 77.020s
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp90-sft-gy-85111-v1/nvidia
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp90-sft-gy-85111-v1/nvidia/config.json
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp90-sft-gy-85111-v1/nvidia/special_tokens_map.json
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp90-sft-gy-85111-v1/nvidia/tokenizer_config.json
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp90-sft-gy-85111-v1/nvidia/tokenizer.json
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp90-sft-gy-85111-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.59it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.72it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.59it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.35it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 44.95it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.51it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.23it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 45.86it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 44.91it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 48.24it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 25.93it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.35it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 35.08it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.44it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.79it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 38.73it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 38.01it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 38.82it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 32.17it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 32.97it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.03it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.20it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 38.65it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 40.27it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 24.29it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.15it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 31.65it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.00it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.12it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 33.68it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 35.62it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 35.25it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 38.25it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 37.23it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 39.24it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 40.05it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 40.83it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 42.87it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 35.09it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 39.62it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 28.67it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.36it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 28.72it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.61it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.52it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.01it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 34.76it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 37.40it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 36.45it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.15it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 37.02it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.78it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 37.26it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.91it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 40.91it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 41.17it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 43.04it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 44.03it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.28it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 22.98it/s]
Loading 0:  88%|████████▊ | 319/363 [00:09<00:01, 30.71it/s]
Loading 0:  89%|████████▉ | 324/363 [00:09<00:01, 33.57it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 36.42it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 39.25it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 33.99it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 41.73it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 42.47it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 43.78it/s]
Loading 0: 100%|█████████▉| 362/363 [00:10<00:00, 41.23it/s]
                                                            
Job chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer completed after 104.65s with status: succeeded
Stopping job with name chaiml-gy-exp90-sft-gy-85111-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.17s
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-exp90-sft-gy-85111-v1
Waiting for inference service chaiml-gy-exp90-sft-gy-85111-v1 to be ready
Inference service chaiml-gy-exp90-sft-gy-85111-v1 ready after 221.2595670223236s
Pipeline stage MKMLDeployer completed in 221.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3731589317321777s
Received healthy response to inference request in 1.6809582710266113s
Received healthy response to inference request in 1.561720371246338s
Received healthy response to inference request in 2.566864252090454s
Received healthy response to inference request in 1.9912996292114258s
5 requests
0 failed requests
5th percentile: 1.5855679512023926
10th percentile: 1.6094155311584473
20th percentile: 1.6571106910705566
30th percentile: 1.7430265426635743
40th percentile: 1.8671630859375
50th percentile: 1.9912996292114258
60th percentile: 2.1440433502197265
70th percentile: 2.296787071228027
80th percentile: 2.411899995803833
90th percentile: 2.4893821239471436
95th percentile: 2.5281231880187987
99th percentile: 2.559116039276123
mean time: 2.0348002910614014
Pipeline stage StressChecker completed in 11.66s
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 0.63s
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-gy-exp90-sft-gy-_85111_v1 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 3110.63s
Shutdown handler de-registered
chaiml-gy-exp90-sft-gy-_85111_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp90-sft-gy-_85111_v1 status is now torndown due to DeploymentManager action