chaiml-gy-exp5-sft-grok_42253

developer_uid: bogoconic1

submission_id: chaiml-gy-exp5-sft-grok_42253_v6

model_name: chaiml-gy-exp5-sft-grok_42253_v6

model_group: ChaiML/gy-exp5-sft-grok-

status: torndown

timestamp: 2025-07-03T17:14:53+00:00

num_battles: 10912

num_wins: 5508

celo_rating: 1288.99

family_friendly_score: 0.6042000000000001

family_friendly_standard_error: 0.006915813184290045

submission_type: basic

model_repo: ChaiML/gy-exp5-sft-grok-dpo-orig-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': 0.5895293005663956, 'latency_mean': 1.6960929095745088, 'latency_p50': 1.688057541847229, 'latency_p90': 1.8769218921661377}, {'batch_size': 3, 'throughput': 1.0509168621372755, 'latency_mean': 2.842794259786606, 'latency_p50': 2.847419023513794, 'latency_p90': 3.1620345592498778}, {'batch_size': 5, 'throughput': 1.2658884956327416, 'latency_mean': 3.937200746536255, 'latency_p50': 3.9191256761550903, 'latency_p90': 4.379598474502563}, {'batch_size': 6, 'throughput': 1.3216283778332754, 'latency_mean': 4.507713671922684, 'latency_p50': 4.457326173782349, 'latency_p90': 5.127923512458801}, {'batch_size': 8, 'throughput': 1.3877489068952527, 'latency_mean': 5.719794598817825, 'latency_p50': 5.678795218467712, 'latency_p90': 6.401196718215942}, {'batch_size': 10, 'throughput': 1.4177389961762743, 'latency_mean': 7.004788272380829, 'latency_p50': 6.993075728416443, 'latency_p90': 7.944325685501099}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp5-sft-grok_42253_v6

is_internal_developer: True

language_model: ChaiML/gy-exp5-sft-grok-dpo-orig-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-07-03

win_ratio: 0.5047653958944281

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], '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-exp5-sft-grok-42253-v6-mkmlizer
Waiting for job on chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer to finish
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║                                                                     ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║                                                                     ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║                                                                     ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║                                                                     ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ║                                                                     ║
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: Downloaded to shared memory in 42.678s
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: Checking if ChaiML/gy-exp5-sft-grok-dpo-orig-ep2 already exists in ChaiML
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpilm029hx, device:0
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: quantized model in 31.181s
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: Processed model ChaiML/gy-exp5-sft-grok-dpo-orig-ep2 in 73.859s
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp5-sft-grok-42253-v6/nvidia
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp5-sft-grok-42253-v6/nvidia/config.json
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp5-sft-grok-42253-v6/nvidia/special_tokens_map.json
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp5-sft-grok-42253-v6/nvidia/tokenizer_config.json
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp5-sft-grok-42253-v6/nvidia/tokenizer.json
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp5-sft-grok-42253-v6/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 29.92it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.84it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.74it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 42.24it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 44.14it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.49it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 43.27it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 42.80it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 42.73it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 44.25it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 45.28it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 25.20it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 32.09it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.75it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 35.64it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.63it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.20it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.49it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.42it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.43it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 34.83it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.48it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.49it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.31it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.65it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.47it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.46it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.14it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:06, 31.42it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:06, 30.50it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 38.43it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 38.94it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 39.40it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 41.06it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.75it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 41.75it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:03, 41.78it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 41.73it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 43.52it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 35.14it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 39.73it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 31.18it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 31.73it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 30.58it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.73it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 35.28it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.01it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 36.59it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 38.52it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 37.32it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.38it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 36.84it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.98it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 36.63it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 38.65it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 37.91it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 39.80it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 39.42it/s]
Loading 0:  83%|████████▎ | 300/363 [00:08<00:01, 39.09it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:03, 19.64it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.98it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 23.79it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 32.21it/s]
Loading 0:  89%|████████▉ | 324/363 [00:09<00:01, 34.95it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 37.14it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 39.73it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 33.78it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 41.22it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 40.84it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 41.15it/s]
Loading 0:  99%|█████████▉| 361/363 [00:09<00:00, 42.59it/s]
                                                            
Job chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer completed after 94.92s with status: succeeded
Stopping job with name chaiml-gy-exp5-sft-grok-42253-v6-mkmlizer
Pipeline stage MKMLizer completed in 95.45s
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-exp5-sft-grok-42253-v6
Waiting for inference service chaiml-gy-exp5-sft-grok-42253-v6 to be ready
Inference service chaiml-gy-exp5-sft-grok-42253-v6 ready after 211.88086080551147s
Pipeline stage MKMLDeployer completed in 212.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.548762798309326s
Received healthy response to inference request in 1.8223876953125s
Received healthy response to inference request in 1.9825153350830078s
Received healthy response to inference request in 2.004603385925293s
Received healthy response to inference request in 1.6147356033325195s
5 requests
0 failed requests
5th percentile: 1.6562660217285157
10th percentile: 1.6977964401245118
20th percentile: 1.7808572769165039
30th percentile: 1.8544132232666015
40th percentile: 1.9184642791748048
50th percentile: 1.9825153350830078
60th percentile: 1.9913505554199218
70th percentile: 2.0001857757568358
80th percentile: 2.1134352684020996
90th percentile: 2.331099033355713
95th percentile: 2.4399309158325195
99th percentile: 2.5269964218139647
mean time: 1.9946009635925293
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 0.90s
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 1.13s
Shutdown handler de-registered
chaiml-gy-exp5-sft-grok_42253_v6 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5910.36s
Shutdown handler de-registered
chaiml-gy-exp5-sft-grok_42253_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp5-sft-grok_42253_v6 status is now torndown due to DeploymentManager action