chaiml-gy-exp10-sft-gy-_39508

developer_uid: bogoconic1

submission_id: chaiml-gy-exp10-sft-gy-_39508_v2

model_name: chaiml-gy-exp10-sft-gy-_39508_v2

model_group: ChaiML/gy-exp10-sft-gy-1

status: torndown

timestamp: 2025-06-26T08:24:38+00:00

num_battles: 9019

num_wins: 4644

celo_rating: 1299.17

family_friendly_score: 0.5186

family_friendly_standard_error: 0.007066173504804421

submission_type: basic

model_repo: ChaiML/gy-exp10-sft-gy-1266-1301-7850-pref-grok-ctx2500-onlylast-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': 0.5899590165456291, 'latency_mean': 1.6949344348907471, 'latency_p50': 1.7064833641052246, 'latency_p90': 1.848877239227295}, {'batch_size': 3, 'throughput': 1.0582607806833275, 'latency_mean': 2.8290013706684114, 'latency_p50': 2.837358593940735, 'latency_p90': 3.11046359539032}, {'batch_size': 5, 'throughput': 1.2654419015195, 'latency_mean': 3.937456420660019, 'latency_p50': 3.9695593118667603, 'latency_p90': 4.376537799835205}, {'batch_size': 6, 'throughput': 1.333857411621425, 'latency_mean': 4.476865108013153, 'latency_p50': 4.458290696144104, 'latency_p90': 5.077848100662232}, {'batch_size': 8, 'throughput': 1.3905959094315756, 'latency_mean': 5.725553741455078, 'latency_p50': 5.690250277519226, 'latency_p90': 6.46875946521759}, {'batch_size': 10, 'throughput': 1.424738527415026, 'latency_mean': 6.9811166429519655, 'latency_p50': 7.016334295272827, 'latency_p90': 7.755371451377869}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp10-sft-gy-_39508_v2

is_internal_developer: True

language_model: ChaiML/gy-exp10-sft-gy-1266-1301-7850-pref-grok-ctx2500-onlylast-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-06-26

win_ratio: 0.514912961525668

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': ['<|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-exp10-sft-gy-39508-v2-mkmlizer
Waiting for job on chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer to finish
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: Downloaded to shared memory in 32.249s
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: Checking if ChaiML/gy-exp10-sft-gy-1266-1301-7850-pref-grok-ctx2500-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8_3zq25x, device:0
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: quantized model in 31.410s
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: Processed model ChaiML/gy-exp10-sft-gy-1266-1301-7850-pref-grok-ctx2500-onlylast-ep2 in 63.660s
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp10-sft-gy-39508-v2
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp10-sft-gy-39508-v2/config.json
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp10-sft-gy-39508-v2/special_tokens_map.json
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp10-sft-gy-39508-v2/tokenizer_config.json
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp10-sft-gy-39508-v2/tokenizer.json
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp10-sft-gy-39508-v2/flywheel_model.0.safetensors
chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 29.86it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.73it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 40.68it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.78it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.10it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 47.11it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 35.73it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 43.86it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 44.22it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:07, 41.79it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.20it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.58it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 36.20it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 32.10it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 39.51it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 40.79it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 42.29it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 40.69it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:06, 40.40it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:06, 39.19it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 42.25it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 43.17it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 34.37it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 29.72it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.20it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 28.93it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:06, 31.08it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:06, 29.53it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 33.60it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:06, 30.93it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 38.45it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 38.59it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 38.53it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 37.78it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 37.83it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 35.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.51it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 36.27it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 37.93it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 36.35it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:04, 36.22it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 26.61it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 28.22it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 27.84it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 32.90it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.30it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 34.57it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 33.55it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 36.69it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.04it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.87it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 36.28it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 37.84it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 35.88it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 38.06it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 36.30it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 37.89it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 36.17it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 36.27it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 19.94it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.93it/s]
Loading 0:  86%|████████▌ | 312/363 [00:09<00:02, 23.21it/s]
Loading 0:  88%|████████▊ | 319/363 [00:09<00:01, 31.94it/s]
Loading 0:  89%|████████▉ | 324/363 [00:09<00:01, 34.23it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 36.79it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 39.10it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 32.23it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 39.29it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 39.59it/s]
Loading 0:  98%|█████████▊| 356/363 [00:10<00:00, 41.15it/s]
Loading 0:  99%|█████████▉| 361/363 [00:10<00:00, 41.97it/s]
                                                            
Job chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer completed after 84.36s with status: succeeded
Stopping job with name chaiml-gy-exp10-sft-gy-39508-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp10-sft-gy-39508-v2
Waiting for inference service chaiml-gy-exp10-sft-gy-39508-v2 to be ready
Inference service chaiml-gy-exp10-sft-gy-39508-v2 ready after 150.56076908111572s
Pipeline stage MKMLDeployer completed in 151.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4393999576568604s
Received healthy response to inference request in 1.7008109092712402s
Received healthy response to inference request in 1.9540190696716309s
Received healthy response to inference request in 1.8365962505340576s
Received healthy response to inference request in 1.5610158443450928s
5 requests
0 failed requests
5th percentile: 1.5889748573303222
10th percentile: 1.6169338703155518
20th percentile: 1.6728518962860108
30th percentile: 1.7279679775238037
40th percentile: 1.7822821140289307
50th percentile: 1.8365962505340576
60th percentile: 1.8835653781890869
70th percentile: 1.9305345058441161
80th percentile: 2.0510952472686768
90th percentile: 2.2452476024627686
95th percentile: 2.3423237800598145
99th percentile: 2.419984722137451
mean time: 1.8983684062957764
Pipeline stage StressChecker completed in 10.99s
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 0.68s
Shutdown handler de-registered
chaiml-gy-exp10-sft-gy-_39508_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 0.11s
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-exp10-sft-gy-39508-v2-profiler
Waiting for inference service chaiml-gy-exp10-sft-gy-39508-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4775.51s
Shutdown handler de-registered
chaiml-gy-exp10-sft-gy-_39508_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp10-sft-gy-_39508_v2 status is now torndown due to DeploymentManager action