chaiml-gy-exp168-sft-gy_63614

developer_uid: bogoconic1

submission_id: chaiml-gy-exp168-sft-gy_63614_v2

model_name: chaiml-gy-exp168-sft-gy_63614_v2

model_group: ChaiML/gy-exp168-sft-gy-

status: torndown

timestamp: 2025-07-15T17:27:36+00:00

num_battles: 7956

num_wins: 4232

celo_rating: 1311.71

family_friendly_score: 0.5246

family_friendly_standard_error: 0.007062504371680062

submission_type: basic

model_repo: ChaiML/gy-exp168-sft-gy-datamix-v1-MM3-lastmsg-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': 0.5213557220683103, 'latency_mean': 1.9179742181301116, 'latency_p50': 1.9091821908950806, 'latency_p90': 2.150477957725525}, {'batch_size': 3, 'throughput': 1.0532047135977198, 'latency_mean': 2.8433582067489622, 'latency_p50': 2.860347867012024, 'latency_p90': 3.1411787986755373}, {'batch_size': 5, 'throughput': 1.3392466932443592, 'latency_mean': 3.713337174654007, 'latency_p50': 3.7124669551849365, 'latency_p90': 4.122139954566955}, {'batch_size': 6, 'throughput': 1.4539530848753828, 'latency_mean': 4.104285637140274, 'latency_p50': 4.111665487289429, 'latency_p90': 4.535966420173645}, {'batch_size': 8, 'throughput': 1.5695937700190912, 'latency_mean': 5.060192466974258, 'latency_p50': 5.046872496604919, 'latency_p90': 5.670313096046447}, {'batch_size': 10, 'throughput': 1.6564154494187242, 'latency_mean': 5.975331554412842, 'latency_p50': 6.019891381263733, 'latency_p90': 6.680185222625732}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gy-exp168-sft-gy_63614_v2

is_internal_developer: False

language_model: ChaiML/gy-exp168-sft-gy-datamix-v1-MM3-lastmsg-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-15

win_ratio: 0.5319255907491202

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': ['<|im_end|>', '<|im_start|>', '\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': 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-exp168-sft-gy-63614-v2-mkmlizer
Waiting for job on chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer to finish
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: Downloaded to shared memory in 61.489s
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: Checking if ChaiML/gy-exp168-sft-gy-datamix-v1-MM3-lastmsg-ep2 already exists in ChaiML
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyq_nirj2, device:0
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: quantized model in 48.410s
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: Processed model ChaiML/gy-exp168-sft-gy-datamix-v1-MM3-lastmsg-ep2 in 109.899s
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia/config.json
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia/special_tokens_map.json
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia/tokenizer_config.json
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia/tokenizer.json
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp168-sft-gy-63614-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.22it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.82it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.55it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 28.92it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.82it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.47it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.80it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.31it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.09it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.39it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.58it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.24it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.04it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.58it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.68it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.20it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.65it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.87it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.32it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.82it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.86it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.49it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.13it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.61it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.03it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 24.97it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.52it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.29it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.26it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.22it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 25.42it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.48it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 26.12it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.61it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.50it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.10it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.12it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.25it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.32it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.89it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.35it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.34it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.54it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:05, 30.18it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 20.17it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 21.42it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.33it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.33it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.17it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.85it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.06it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.16it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.11it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.04it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.73it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.39it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.19it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.37it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.70it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.47it/s]
Loading 0:  71%|███████   | 258/363 [00:24<00:04, 22.59it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.10it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.43it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.40it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.57it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.17it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.35it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.88it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.61it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.58it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.83it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.43it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.68it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.60it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.65it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.69it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.22it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.84it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.64it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.04it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.40it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.89it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.34it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.24it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 24.58it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 22.81it/s]
Loading 0: 100%|█████████▉| 362/363 [00:29<00:00, 26.16it/s]
                                                            
Job chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer completed after 138.12s with status: succeeded
Stopping job with name chaiml-gy-exp168-sft-gy-63614-v2-mkmlizer
Pipeline stage MKMLizer completed in 138.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp168-sft-gy-63614-v2
Waiting for inference service chaiml-gy-exp168-sft-gy-63614-v2 to be ready
Inference service chaiml-gy-exp168-sft-gy-63614-v2 ready after 251.65933799743652s
Pipeline stage MKMLDeployer completed in 252.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6101505756378174s
Received healthy response to inference request in 2.4898524284362793s
Received healthy response to inference request in 2.097816228866577s
Received healthy response to inference request in 2.0666401386260986s
Received healthy response to inference request in 2.1424460411071777s
5 requests
0 failed requests
5th percentile: 2.0728753566741944
10th percentile: 2.07911057472229
20th percentile: 2.0915810108184814
30th percentile: 2.106742191314697
40th percentile: 2.1245941162109374
50th percentile: 2.1424460411071777
60th percentile: 2.281408596038818
70th percentile: 2.420371150970459
80th percentile: 2.513912057876587
90th percentile: 2.562031316757202
95th percentile: 2.5860909461975097
99th percentile: 2.605338649749756
mean time: 2.28138108253479
Pipeline stage StressChecker completed in 12.80s
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 0.72s
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-exp168-sft-gy_63614_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 0.13s
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-exp168-sft-gy-63614-v2-profiler
Waiting for inference service chaiml-gy-exp168-sft-gy-63614-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 3264.50s
Shutdown handler de-registered
chaiml-gy-exp168-sft-gy_63614_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp168-sft-gy_63614_v2 status is now torndown due to DeploymentManager action
chaiml-gy-exp168-sft-gy_63614_v2 status is now torndown due to DeploymentManager action