chaiml-gy-exp23-sftqwen_72714

developer_uid: bogoconic1

submission_id: chaiml-gy-exp23-sftqwen_72714_v1

model_name: chaiml-gy-exp23-sftqwen_72714_v1

model_group: ChaiML/gy-exp23-sftqwen2

status: torndown

timestamp: 2025-06-27T07:28:26+00:00

num_battles: 8194

num_wins: 4074

celo_rating: 1284.22

family_friendly_score: 0.5254

family_friendly_standard_error: 0.007061937977637583

submission_type: basic

model_repo: ChaiML/gy-exp23-sftqwen25-14b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14769689600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.488828930478482, 'latency_mean': 2.045581556558609, 'latency_p50': 2.04543936252594, 'latency_p90': 2.2642022609710692}, {'batch_size': 3, 'throughput': 0.8836766727748233, 'latency_mean': 3.384830539226532, 'latency_p50': 3.374792218208313, 'latency_p90': 3.7036225318908693}, {'batch_size': 5, 'throughput': 1.0592676732409818, 'latency_mean': 4.70910530090332, 'latency_p50': 4.718247652053833, 'latency_p90': 5.219513559341431}, {'batch_size': 6, 'throughput': 1.1094213719863486, 'latency_mean': 5.38828542470932, 'latency_p50': 5.402612566947937, 'latency_p90': 6.046227264404297}, {'batch_size': 10, 'throughput': 1.1881769287441502, 'latency_mean': 8.335403878688812, 'latency_p50': 8.318193078041077, 'latency_p90': 9.409736108779907}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp23-sftqwen_72714_v1

is_internal_developer: True

language_model: ChaiML/gy-exp23-sftqwen25-14b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2

model_size: 15B

ranking_group: single

throughput_3p7s: 0.94

us_pacific_date: 2025-06-27

win_ratio: 0.49719306809860875

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_start|>', '<|im_end|>'], '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-exp23-sftqwen-72714-v1-mkmlizer
Waiting for job on chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer to finish
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: Downloaded to shared memory in 48.800s
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: Checking if ChaiML/gy-exp23-sftqwen25-14b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsy108hs2, device:0
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: quantized model in 38.496s
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: Processed model ChaiML/gy-exp23-sftqwen25-14b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 in 87.297s
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/config.json
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/added_tokens.json
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/special_tokens_map.json
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/tokenizer_config.json
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/merges.txt
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/vocab.json
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/tokenizer.json
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/flywheel_model.1.safetensors
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp23-sftqwen-72714-v1/flywheel_model.0.safetensors
chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/579 [00:00<00:17, 31.93it/s]
Loading 0:   2%|▏         | 13/579 [00:00<00:13, 43.11it/s]
Loading 0:   3%|▎         | 18/579 [00:00<00:13, 40.37it/s]
Loading 0:   4%|▍         | 25/579 [00:00<00:13, 42.20it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:13, 41.27it/s]
Loading 0:   6%|▌         | 36/579 [00:00<00:11, 46.03it/s]
Loading 0:   7%|▋         | 41/579 [00:01<00:14, 37.59it/s]
Loading 0:   8%|▊         | 49/579 [00:01<00:12, 43.44it/s]
Loading 0:   9%|▉         | 54/579 [00:01<00:12, 42.53it/s]
Loading 0:  11%|█         | 61/579 [00:01<00:11, 44.53it/s]
Loading 0:  11%|█▏        | 66/579 [00:01<00:11, 43.77it/s]
Loading 0:  13%|█▎        | 73/579 [00:01<00:11, 45.99it/s]
Loading 0:  14%|█▍        | 80/579 [00:01<00:10, 47.31it/s]
Loading 0:  15%|█▍        | 85/579 [00:02<00:15, 31.16it/s]
Loading 0:  16%|█▌        | 92/579 [00:02<00:13, 35.28it/s]
Loading 0:  17%|█▋        | 97/579 [00:02<00:13, 36.64it/s]
Loading 0:  18%|█▊        | 104/579 [00:02<00:11, 40.37it/s]
Loading 0:  19%|█▉        | 109/579 [00:02<00:11, 39.61it/s]
Loading 0:  20%|██        | 116/579 [00:02<00:11, 42.07it/s]
Loading 0:  21%|██        | 121/579 [00:02<00:11, 41.60it/s]
Loading 0:  22%|██▏       | 128/579 [00:03<00:10, 43.95it/s]
Loading 0:  23%|██▎       | 133/579 [00:03<00:10, 42.70it/s]
Loading 0:  24%|██▍       | 140/579 [00:03<00:09, 44.52it/s]
Loading 0:  25%|██▌       | 147/579 [00:03<00:09, 46.30it/s]
Loading 0:  26%|██▋       | 152/579 [00:03<00:09, 43.71it/s]
Loading 0:  27%|██▋       | 157/579 [00:03<00:10, 41.35it/s]
Loading 0:  28%|██▊       | 164/579 [00:03<00:09, 43.46it/s]
Loading 0:  29%|██▉       | 169/579 [00:04<00:09, 42.26it/s]
Loading 0:  30%|███       | 176/579 [00:04<00:09, 44.32it/s]
Loading 0:  31%|███▏      | 181/579 [00:04<00:09, 43.55it/s]
Loading 0:  32%|███▏      | 188/579 [00:04<00:08, 44.66it/s]
Loading 0:  33%|███▎      | 193/579 [00:04<00:12, 31.26it/s]
Loading 0:  34%|███▍      | 197/579 [00:04<00:12, 30.53it/s]
Loading 0:  35%|███▌      | 205/579 [00:05<00:10, 36.56it/s]
Loading 0:  36%|███▌      | 209/579 [00:05<00:10, 35.60it/s]
Loading 0:  37%|███▋      | 217/579 [00:05<00:08, 41.74it/s]
Loading 0:  38%|███▊      | 222/579 [00:05<00:08, 41.07it/s]
Loading 0:  40%|███▉      | 229/579 [00:05<00:08, 43.64it/s]
Loading 0:  40%|████      | 234/579 [00:05<00:08, 42.35it/s]
Loading 0:  42%|████▏     | 241/579 [00:05<00:07, 43.55it/s]
Loading 0:  42%|████▏     | 246/579 [00:06<00:07, 42.47it/s]
Loading 0:  44%|████▎     | 253/579 [00:06<00:07, 44.52it/s]
Loading 0:  45%|████▍     | 258/579 [00:06<00:07, 43.83it/s]
Loading 0:  46%|████▌     | 265/579 [00:06<00:06, 45.87it/s]
Loading 0:  47%|████▋     | 270/579 [00:06<00:06, 44.61it/s]
Loading 0:  48%|████▊     | 277/579 [00:06<00:06, 46.27it/s]
Loading 0:  49%|████▊     | 282/579 [00:06<00:06, 44.44it/s]
Loading 0:  50%|████▉     | 289/579 [00:06<00:06, 46.08it/s]
Loading 0:  51%|█████     | 296/579 [00:07<00:05, 47.97it/s]
Loading 0:  52%|█████▏    | 301/579 [00:07<00:08, 33.71it/s]
Loading 0:  53%|█████▎    | 305/579 [00:07<00:08, 33.18it/s]
Loading 0:  54%|█████▍    | 313/579 [00:07<00:06, 39.46it/s]
Loading 0:  55%|█████▍    | 318/579 [00:07<00:06, 39.54it/s]
Loading 0:  56%|█████▌    | 325/579 [00:07<00:06, 42.25it/s]
Loading 0:  57%|█████▋    | 330/579 [00:08<00:06, 41.14it/s]
Loading 0:  58%|█████▊    | 337/579 [00:08<00:05, 43.84it/s]
Loading 0:  59%|█████▉    | 342/579 [00:08<00:05, 43.32it/s]
Loading 0:  60%|██████    | 349/579 [00:08<00:05, 45.08it/s]
Loading 0:  61%|██████    | 354/579 [00:08<00:05, 43.30it/s]
Loading 0:  62%|██████▏   | 361/579 [00:08<00:04, 45.51it/s]
Loading 0:  63%|██████▎   | 366/579 [00:08<00:04, 44.35it/s]
Loading 0:  64%|██████▍   | 373/579 [00:08<00:04, 46.07it/s]
Loading 0:  65%|██████▌   | 378/579 [00:09<00:04, 44.14it/s]
Loading 0:  66%|██████▋   | 385/579 [00:09<00:04, 42.21it/s]
Loading 0:  67%|██████▋   | 390/579 [00:09<00:04, 40.32it/s]
Loading 0:  69%|██████▊   | 397/579 [00:09<00:04, 41.94it/s]
Loading 0:  70%|██████▉   | 404/579 [00:09<00:03, 44.19it/s]
Loading 0:  71%|███████   | 409/579 [00:09<00:05, 31.40it/s]
Loading 0:  71%|███████▏  | 413/579 [00:10<00:05, 31.13it/s]
Loading 0:  73%|███████▎  | 421/579 [00:10<00:04, 37.35it/s]
Loading 0:  74%|███████▎  | 426/579 [00:10<00:04, 38.07it/s]
Loading 0:  75%|███████▍  | 433/579 [00:10<00:03, 40.89it/s]
Loading 0:  76%|███████▌  | 438/579 [00:10<00:03, 39.59it/s]
Loading 0:  77%|███████▋  | 445/579 [00:10<00:03, 41.98it/s]
Loading 0:  78%|███████▊  | 450/579 [00:10<00:03, 41.50it/s]
Loading 0:  79%|███████▉  | 457/579 [00:11<00:02, 43.60it/s]
Loading 0:  80%|███████▉  | 462/579 [00:11<00:02, 42.84it/s]
Loading 0:  81%|████████  | 469/579 [00:11<00:02, 44.57it/s]
Loading 0:  82%|████████▏ | 474/579 [00:11<00:02, 43.51it/s]
Loading 0:  83%|████████▎ | 481/579 [00:11<00:02, 45.08it/s]
Loading 0:  84%|████████▍ | 486/579 [00:11<00:02, 43.66it/s]
Loading 0:  85%|████████▌ | 493/579 [00:11<00:01, 44.67it/s]
Loading 0:  86%|████████▌ | 498/579 [00:12<00:01, 43.70it/s]
Loading 0:  87%|████████▋ | 505/579 [00:12<00:01, 45.66it/s]
Loading 0:  88%|████████▊ | 512/579 [00:12<00:01, 45.46it/s]
Loading 0:  89%|████████▉ | 517/579 [00:26<00:43,  1.41it/s]
Loading 0:  90%|████████▉ | 521/579 [00:26<00:32,  1.79it/s]
Loading 0:  91%|█████████ | 525/579 [00:26<00:23,  2.30it/s]
Loading 0:  91%|█████████▏| 529/579 [00:26<00:16,  3.03it/s]
Loading 0:  92%|█████████▏| 534/579 [00:26<00:10,  4.21it/s]
Loading 0:  94%|█████████▎| 542/579 [00:26<00:05,  6.85it/s]
Loading 0:  94%|█████████▍| 546/579 [00:27<00:03,  8.38it/s]
Loading 0:  96%|█████████▌| 554/579 [00:27<00:01, 12.63it/s]
Loading 0:  97%|█████████▋| 559/579 [00:27<00:01, 15.42it/s]
Loading 0:  98%|█████████▊| 566/579 [00:27<00:00, 20.18it/s]
Loading 0:  99%|█████████▊| 571/579 [00:27<00:00, 23.34it/s]
Loading 0: 100%|█████████▉| 578/579 [00:27<00:00, 28.36it/s]
                                                            
Job chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer completed after 115.82s with status: succeeded
Stopping job with name chaiml-gy-exp23-sftqwen-72714-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.38s
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-exp23-sftqwen-72714-v1
Waiting for inference service chaiml-gy-exp23-sftqwen-72714-v1 to be ready
Inference service chaiml-gy-exp23-sftqwen-72714-v1 ready after 151.30529165267944s
Pipeline stage MKMLDeployer completed in 152.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.48237943649292s
Received healthy response to inference request in 2.240666389465332s
Received healthy response to inference request in 1.8699090480804443s
Received healthy response to inference request in 2.100374698638916s
Received healthy response to inference request in 2.071465015411377s
5 requests
0 failed requests
5th percentile: 1.910220241546631
10th percentile: 1.9505314350128173
20th percentile: 2.0311538219451903
30th percentile: 2.0772469520568846
40th percentile: 2.0888108253479003
50th percentile: 2.100374698638916
60th percentile: 2.1564913749694825
70th percentile: 2.212608051300049
80th percentile: 2.2890089988708495
90th percentile: 2.385694217681885
95th percentile: 2.4340368270874024
99th percentile: 2.4727109146118162
mean time: 2.1529589176177977
Pipeline stage StressChecker completed in 12.16s
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 0.67s
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 0.92s
Shutdown handler de-registered
chaiml-gy-exp23-sftqwen_72714_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3109.80s
Shutdown handler de-registered
chaiml-gy-exp23-sftqwen_72714_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp23-sftqwen_72714_v1 status is now torndown due to DeploymentManager action