chaiml-gy-exp78-sft-gy-_36416

developer_uid: rirv938

submission_id: chaiml-gy-exp78-sft-gy-_36416_v2

model_name: chaiml-gy-exp78-sft-gy-_36416_v2

model_group: ChaiML/gy-exp78-sft-gy-d

status: torndown

timestamp: 2025-07-08T15:10:04+00:00

num_battles: 11099

num_wins: 5463

celo_rating: 1292.21

family_friendly_score: 0.5262

family_friendly_standard_error: 0.007061353411351113

submission_type: basic

model_repo: ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep6

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': 0.5237815850481311, 'latency_mean': 1.9090925240516663, 'latency_p50': 1.8852227926254272, 'latency_p90': 2.14112765789032}, {'batch_size': 3, 'throughput': 1.0497932628453424, 'latency_mean': 2.850605503320694, 'latency_p50': 2.842584252357483, 'latency_p90': 3.151800751686096}, {'batch_size': 5, 'throughput': 1.3397013190454141, 'latency_mean': 3.7121181011199953, 'latency_p50': 3.719348192214966, 'latency_p90': 4.119830918312073}, {'batch_size': 6, 'throughput': 1.4422775916534547, 'latency_mean': 4.113365514278412, 'latency_p50': 4.150301814079285, 'latency_p90': 4.525870037078858}, {'batch_size': 8, 'throughput': 1.58378342351953, 'latency_mean': 5.011401782035827, 'latency_p50': 4.959126710891724, 'latency_p90': 5.7318106412887575}, {'batch_size': 10, 'throughput': 1.6728503501143859, 'latency_mean': 5.925467393398285, 'latency_p50': 5.938109517097473, 'latency_p90': 6.631269526481629}]

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

display_name: chaiml-gy-exp78-sft-gy-_36416_v2

is_internal_developer: True

language_model: ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep6

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-08

win_ratio: 0.4922065050905487

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['You:', '</s>', '###', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', '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-exp78-sft-gy-36416-v2-mkmlizer
Waiting for job on chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer to finish
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: Downloaded to shared memory in 214.310s
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: Checking if ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep6 already exists in ChaiML
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpotg_jins, device:0
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: quantized model in 50.655s
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: Processed model ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep6 in 264.966s
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia/config.json
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia/special_tokens_map.json
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia/tokenizer_config.json
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia/tokenizer.json
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-36416-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:12, 29.83it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:15, 22.83it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.89it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 22.95it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 26.72it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 25.91it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:13, 25.14it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 30.99it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 20.66it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:16, 19.31it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.52it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.78it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:14, 22.04it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 23.16it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 22.56it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 23.83it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 24.08it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:13, 23.16it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:12, 23.91it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:14, 19.78it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:17, 16.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:12, 22.26it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:13, 20.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.82it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 23.54it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.77it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.54it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 25.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.58it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:13, 19.14it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:11, 22.70it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 20.06it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 23.34it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:09, 24.49it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:09, 24.08it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.32it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:10, 23.09it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 25.96it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:08, 26.41it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 24.65it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 25.07it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 27.71it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:11, 18.37it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:10, 19.08it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:12, 16.21it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 22.00it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 23.02it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.67it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 25.42it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 22.78it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.12it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:07, 23.10it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 21.35it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 22.36it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.53it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 22.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:13,  1.19s/it]
Loading 0:  56%|█████▌    | 203/363 [00:24<02:39,  1.00it/s]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:35,  1.62it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:13,  2.07it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:54,  2.73it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.92it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  5.00it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:23,  5.96it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:16,  8.39it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13,  9.69it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:09, 12.96it/s]
Loading 0:  66%|██████▌   | 239/363 [00:25<00:08, 14.40it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 21.66it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 22.34it/s]
Loading 0:  70%|███████   | 255/363 [00:26<00:04, 25.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:04, 25.59it/s]
Loading 0:  73%|███████▎  | 266/363 [00:26<00:03, 31.29it/s]
Loading 0:  74%|███████▍  | 270/363 [00:26<00:04, 20.66it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:03, 23.09it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:03, 24.42it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 25.65it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 22.64it/s]
Loading 0:  80%|███████▉  | 289/363 [00:27<00:02, 25.86it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:02, 25.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 24.79it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 24.95it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 22.48it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 20.45it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 21.81it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 22.52it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 26.95it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 24.07it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 30.21it/s]
Loading 0:  91%|█████████ | 331/363 [00:29<00:01, 27.76it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:00, 28.97it/s]
Loading 0:  93%|█████████▎| 339/363 [00:29<00:00, 28.94it/s]
Loading 0:  94%|█████████▍| 342/363 [00:29<00:01, 16.69it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 20.38it/s]
Loading 0:  96%|█████████▌| 349/363 [00:30<00:00, 19.38it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 25.84it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 24.87it/s]
                                                            
Job chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer completed after 314.37s with status: succeeded
Stopping job with name chaiml-gy-exp78-sft-gy-36416-v2-mkmlizer
Pipeline stage MKMLizer completed in 315.30s
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-exp78-sft-gy-36416-v2
Waiting for inference service chaiml-gy-exp78-sft-gy-36416-v2 to be ready
Failed to get response for submission chaiml-adrian-your-toxi_89049_v2: HTTPConnectionPool(host='chaiml-adrian-your-toxi-89049-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-gy-exp78-sft-gy-36416-v2 ready after 372.4084312915802s
Pipeline stage MKMLDeployer completed in 372.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.708928346633911s
Received healthy response to inference request in 2.274959087371826s
Received healthy response to inference request in 1.8719327449798584s
Received healthy response to inference request in 2.209724187850952s
Received healthy response to inference request in 2.0524754524230957s
5 requests
0 failed requests
5th percentile: 1.908041286468506
10th percentile: 1.9441498279571534
20th percentile: 2.0163669109344484
30th percentile: 2.083925199508667
40th percentile: 2.1468246936798097
50th percentile: 2.209724187850952
60th percentile: 2.2358181476593018
70th percentile: 2.2619121074676514
80th percentile: 2.5617529392242435
90th percentile: 3.1353406429290773
95th percentile: 3.422134494781494
99th percentile: 3.6515695762634275
mean time: 2.423603963851929
Pipeline stage StressChecker completed in 13.41s
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 0.91s
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 1.09s
Shutdown handler de-registered
chaiml-gy-exp78-sft-gy-_36416_v2 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 6431.36s
Shutdown handler de-registered
chaiml-gy-exp78-sft-gy-_36416_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp78-sft-gy-_36416_v2 status is now torndown due to DeploymentManager action