chaiml-gy-exp21-gy-1266_10196

developer_uid: bogoconic1

submission_id: chaiml-gy-exp21-gy-1266_10196_v2

model_name: chaiml-gy-exp21-gy-1266_10196_v2

model_group: ChaiML/gy-exp21-gy-1266-

status: torndown

timestamp: 2025-06-27T08:06:16+00:00

num_battles: 8880

num_wins: 4284

celo_rating: 1277.67

family_friendly_score: 0.5318

family_friendly_standard_error: 0.0070567522274768875

submission_type: basic

model_repo: ChaiML/gy-exp21-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8192964777609159, 'latency_mean': 1.2203889751434327, 'latency_p50': 1.2278677225112915, 'latency_p90': 1.3445306777954102}, {'batch_size': 4, 'throughput': 1.6916522479965073, 'latency_mean': 2.35286435008049, 'latency_p50': 2.3806811571121216, 'latency_p90': 2.5714028120040893}, {'batch_size': 5, 'throughput': 1.828140093001172, 'latency_mean': 2.724416587352753, 'latency_p50': 2.701474189758301, 'latency_p90': 3.0137709856033323}, {'batch_size': 8, 'throughput': 2.0042288122012084, 'latency_mean': 3.966891430616379, 'latency_p50': 3.9826273918151855, 'latency_p90': 4.445837473869323}, {'batch_size': 10, 'throughput': 2.04633244389131, 'latency_mean': 4.840156294107437, 'latency_p50': 4.891038656234741, 'latency_p90': 5.403561902046204}, {'batch_size': 12, 'throughput': 2.0826749411889316, 'latency_mean': 5.71052165389061, 'latency_p50': 5.763755917549133, 'latency_p90': 6.4919513940811155}, {'batch_size': 15, 'throughput': 2.1019494210452376, 'latency_mean': 7.029802421331405, 'latency_p50': 7.061792969703674, 'latency_p90': 7.792507123947144}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp21-gy-1266_10196_v2

is_internal_developer: True

language_model: ChaiML/gy-exp21-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2

model_size: 8B

ranking_group: single

throughput_3p7s: 1.99

us_pacific_date: 2025-06-27

win_ratio: 0.48243243243243245

generation_params: {'temperature': 0.8, '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': 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-exp21-gy-1266-10196-v2-mkmlizer
Waiting for job on chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer to finish
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: Downloaded to shared memory in 19.928s
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: Checking if ChaiML/gy-exp21-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0gjzsn87, device:0
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: quantized model in 21.730s
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: Processed model ChaiML/gy-exp21-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 in 41.659s
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp21-gy-1266-10196-v2
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp21-gy-1266-10196-v2/config.json
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp21-gy-1266-10196-v2/special_tokens_map.json
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp21-gy-1266-10196-v2/tokenizer_config.json
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp21-gy-1266-10196-v2/tokenizer.json
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp21-gy-1266-10196-v2/flywheel_model.0.safetensors
chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.04it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.26it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 48.29it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 49.75it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 51.62it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 47.80it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 46.69it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 52.47it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 47.51it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 45.63it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.71it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 46.31it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 45.21it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.85it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 33.01it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 38.68it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:04, 39.84it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 41.28it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 42.61it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:04, 35.86it/s]
Loading 0:  41%|████      | 120/291 [00:02<00:03, 43.25it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 43.77it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 43.98it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 41.48it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 40.71it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 44.88it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:03, 45.15it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 46.17it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 42.90it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 42.03it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 41.72it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 45.85it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 45.27it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 27.64it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 30.96it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.13it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 40.09it/s]
Loading 0:  73%|███████▎  | 213/291 [00:05<00:01, 41.27it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 46.43it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 43.22it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 43.41it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 48.46it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 44.68it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 44.58it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 49.19it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 45.76it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 44.70it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 49.25it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 45.73it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 44.50it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 26.40it/s]
                                                            
Job chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer completed after 63.43s with status: succeeded
Stopping job with name chaiml-gy-exp21-gy-1266-10196-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp21-gy-1266-10196-v2
Waiting for inference service chaiml-gy-exp21-gy-1266-10196-v2 to be ready
Inference service chaiml-gy-exp21-gy-1266-10196-v2 ready after 150.51106023788452s
Pipeline stage MKMLDeployer completed in 151.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8915467262268066s
Received healthy response to inference request in 1.3843653202056885s
Received healthy response to inference request in 1.3127472400665283s
Received healthy response to inference request in 1.5801115036010742s
Received healthy response to inference request in 1.3020904064178467s
5 requests
0 failed requests
5th percentile: 1.304221773147583
10th percentile: 1.3063531398773194
20th percentile: 1.310615873336792
30th percentile: 1.3270708560943603
40th percentile: 1.3557180881500244
50th percentile: 1.3843653202056885
60th percentile: 1.4626637935638427
70th percentile: 1.5409622669219971
80th percentile: 1.6423985481262207
90th percentile: 1.7669726371765138
95th percentile: 1.8292596817016602
99th percentile: 1.8790893173217773
mean time: 1.4941722393035888
Pipeline stage StressChecker completed in 8.86s
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 0.83s
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 0.91s
Shutdown handler de-registered
chaiml-gy-exp21-gy-1266_10196_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 0.12s
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-exp21-gy-1266-10196-v2-profiler
Waiting for inference service chaiml-gy-exp21-gy-1266-10196-v2-profiler to be ready
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 2665.92s
Shutdown handler de-registered
chaiml-gy-exp21-gy-1266_10196_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp21-gy-1266_10196_v2 status is now torndown due to DeploymentManager action