chaiml-gy-exp39-sft-gy-_78578

developer_uid: bogoconic1

submission_id: chaiml-gy-exp39-sft-gy-_78578_v1

model_name: chaiml-gy-exp39-sft-gy-_78578_v1

model_group: ChaiML/gy-exp39-sft-gy-7

status: torndown

timestamp: 2025-06-29T10:09:59+00:00

num_battles: 9278

num_wins: 4909

celo_rating: 1291.75

family_friendly_score: 0.5326

family_friendly_standard_error: 0.0070560221088089

submission_type: basic

model_repo: ChaiML/gy-exp39-sft-gy-7850-end-question-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': 0.5964955221084893, 'latency_mean': 1.6763567399978638, 'latency_p50': 1.6581957340240479, 'latency_p90': 1.8632135152816773}, {'batch_size': 3, 'throughput': 1.0660879524950055, 'latency_mean': 2.8015221989154817, 'latency_p50': 2.825658917427063, 'latency_p90': 3.093038821220398}, {'batch_size': 5, 'throughput': 1.265356363440779, 'latency_mean': 3.9326544761657716, 'latency_p50': 3.93840754032135, 'latency_p90': 4.306158781051636}, {'batch_size': 6, 'throughput': 1.3358238389319084, 'latency_mean': 4.4776079308986665, 'latency_p50': 4.466028213500977, 'latency_p90': 5.1197001218795775}, {'batch_size': 8, 'throughput': 1.394762564653691, 'latency_mean': 5.700421342849731, 'latency_p50': 5.6363208293914795, 'latency_p90': 6.439549660682678}, {'batch_size': 10, 'throughput': 1.4086758000490807, 'latency_mean': 7.050909330844879, 'latency_p50': 7.022040247917175, 'latency_p90': 7.944454860687256}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp39-sft-gy-_78578_v1

is_internal_developer: True

language_model: ChaiML/gy-exp39-sft-gy-7850-end-question-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-06-29

win_ratio: 0.5291010993748653

generation_params: {'temperature': 0.45, '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': 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-exp39-sft-gy-78578-v1-mkmlizer
Waiting for job on chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer to finish
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: Downloaded to shared memory in 39.952s
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: Checking if ChaiML/gy-exp39-sft-gy-7850-end-question-ep2 already exists in ChaiML
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk7tk_mtj, device:0
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: quantized model in 30.263s
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: Processed model ChaiML/gy-exp39-sft-gy-7850-end-question-ep2 in 70.216s
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp39-sft-gy-78578-v1
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp39-sft-gy-78578-v1/tokenizer.json
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp39-sft-gy-78578-v1/flywheel_model.0.safetensors
chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.07it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.84it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.65it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.12it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.76it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.01it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.63it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 47.78it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 47.27it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 50.63it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.93it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.96it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 35.77it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.78it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.29it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.28it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.84it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.73it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 44.24it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 38.21it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 37.02it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.12it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.93it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.95it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 44.31it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.58it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 26.79it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.61it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.03it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.96it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.88it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.43it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 39.39it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 39.96it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 39.93it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.95it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.77it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.81it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.90it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 41.58it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.46it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.94it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.69it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.75it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.95it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 35.25it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.32it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.42it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.35it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.47it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.86it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 43.41it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.22it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 44.91it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 23.82it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 25.23it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 27.87it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.83it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.68it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 37.46it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 43.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 41.51it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 40.92it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 45.69it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 43.09it/s]
                                                            
Job chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer completed after 94.22s with status: succeeded
Stopping job with name chaiml-gy-exp39-sft-gy-78578-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp39-sft-gy-78578-v1
Waiting for inference service chaiml-gy-exp39-sft-gy-78578-v1 to be ready
Inference service chaiml-gy-exp39-sft-gy-78578-v1 ready after 170.6231369972229s
Pipeline stage MKMLDeployer completed in 171.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.690207004547119s
Received healthy response to inference request in 1.5252156257629395s
Received healthy response to inference request in 1.881904125213623s
Received healthy response to inference request in 1.7474234104156494s
Received healthy response to inference request in 1.5663273334503174s
5 requests
0 failed requests
5th percentile: 1.533437967300415
10th percentile: 1.5416603088378906
20th percentile: 1.5581049919128418
30th percentile: 1.6025465488433839
40th percentile: 1.6749849796295166
50th percentile: 1.7474234104156494
60th percentile: 1.801215696334839
70th percentile: 1.8550079822540284
80th percentile: 2.0435647010803226
90th percentile: 2.366885852813721
95th percentile: 2.5285464286804196
99th percentile: 2.657874889373779
mean time: 1.8822154998779297
Pipeline stage StressChecker completed in 11.63s
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 0.75s
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-exp39-sft-gy-_78578_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5228.08s
Shutdown handler de-registered
chaiml-gy-exp39-sft-gy-_78578_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp39-sft-gy-_78578_v1 status is now torndown due to DeploymentManager action