chaiml-gy-exp97-dpo-exp_26589

developer_uid: bogoconic1

submission_id: chaiml-gy-exp97-dpo-exp_26589_v1

model_name: chaiml-gy-exp97-dpo-exp_26589_v1

model_group: ChaiML/gy-exp97-dpo-exp9

status: torndown

timestamp: 2025-07-06T13:16:52+00:00

num_battles: 10110

num_wins: 5351

celo_rating: 1309.93

family_friendly_score: 0.527

family_friendly_standard_error: 0.00706075066830716

submission_type: basic

model_repo: ChaiML/gy-exp97-dpo-exp95ep2s2-grok-payloads-0705-dpo-diff-gt0.05-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': 0.5289464722438113, 'latency_mean': 1.89042586684227, 'latency_p50': 1.868226408958435, 'latency_p90': 2.131025195121765}, {'batch_size': 3, 'throughput': 1.0549545957085107, 'latency_mean': 2.83195548415184, 'latency_p50': 2.813399910926819, 'latency_p90': 3.118044447898865}, {'batch_size': 5, 'throughput': 1.3391007955513201, 'latency_mean': 3.715017716884613, 'latency_p50': 3.70374596118927, 'latency_p90': 4.1156052350997925}, {'batch_size': 6, 'throughput': 1.4334104860560013, 'latency_mean': 4.169388464689255, 'latency_p50': 4.153258800506592, 'latency_p90': 4.64359941482544}, {'batch_size': 8, 'throughput': 1.5813477349059883, 'latency_mean': 5.021116361618042, 'latency_p50': 4.955566167831421, 'latency_p90': 5.673804235458373}, {'batch_size': 10, 'throughput': 1.6536010506268424, 'latency_mean': 5.987651174068451, 'latency_p50': 5.952291369438171, 'latency_p90': 6.769331526756287}]

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

display_name: chaiml-gy-exp97-dpo-exp_26589_v1

is_internal_developer: False

language_model: ChaiML/gy-exp97-dpo-exp95ep2s2-grok-payloads-0705-dpo-diff-gt0.05-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-06

win_ratio: 0.5292779426310583

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': ['\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-exp97-dpo-exp-26589-v1-mkmlizer
Waiting for job on chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer to finish
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: Downloaded to shared memory in 103.080s
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: Checking if ChaiML/gy-exp97-dpo-exp95ep2s2-grok-payloads-0705-dpo-diff-gt0.05-ep2 already exists in ChaiML
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjr39uu9z, device:0
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission function_fijeb_2025-05-14: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: quantized model in 61.142s
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: Processed model ChaiML/gy-exp97-dpo-exp95ep2s2-grok-payloads-0705-dpo-diff-gt0.05-ep2 in 164.223s
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia/config.json
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia/special_tokens_map.json
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia/tokenizer_config.json
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia/tokenizer.json
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp97-dpo-exp-26589-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 32.84it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:14, 24.56it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 25.27it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:16, 20.99it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:12, 26.79it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 22.45it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:11, 30.19it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:16, 20.48it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.35it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:16, 19.19it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:16, 19.74it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:14, 21.76it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 22.60it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 22.21it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 26.34it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:15, 19.19it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.23it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.03it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:17, 16.64it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:13, 21.45it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 20.68it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 21.82it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:12, 21.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:15, 17.63it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 22.91it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.01it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.62it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:14, 18.19it/s]
Loading 0:  31%|███       | 111/363 [00:05<00:11, 21.37it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 19.61it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 23.27it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 23.02it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.59it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:09, 25.03it/s]
Loading 0:  36%|███▋      | 132/363 [00:06<00:10, 21.72it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:08, 25.49it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 24.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 23.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 25.06it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:10, 20.32it/s]
Loading 0:  42%|████▏     | 153/363 [00:07<00:12, 16.69it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:10, 19.64it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:09, 20.36it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 22.22it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 22.59it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.16it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:08, 23.87it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:08, 22.66it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 21.51it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:08, 22.44it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 19.85it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:09, 18.38it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.35it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 19.48it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:07, 21.40it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 21.40it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<05:00,  1.86s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:51,  1.45s/it]
Loading 0:  57%|█████▋    | 208/363 [00:26<02:04,  1.24it/s]
Loading 0:  58%|█████▊    | 211/363 [00:26<01:31,  1.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:06,  2.25it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:47,  3.07it/s]
Loading 0:  61%|██████    | 220/363 [00:27<00:35,  3.99it/s]
Loading 0:  62%|██████▏   | 224/363 [00:27<00:26,  5.30it/s]
Loading 0:  63%|██████▎   | 228/363 [00:27<00:18,  7.38it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:15,  8.51it/s]
Loading 0:  65%|██████▍   | 235/363 [00:28<00:11, 11.51it/s]
Loading 0:  66%|██████▌   | 238/363 [00:28<00:09, 13.18it/s]
Loading 0:  66%|██████▋   | 241/363 [00:28<00:08, 14.84it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:06, 17.28it/s]
Loading 0:  68%|██████▊   | 247/363 [00:28<00:06, 18.55it/s]
Loading 0:  69%|██████▉   | 250/363 [00:28<00:05, 19.03it/s]
Loading 0:  70%|███████   | 255/363 [00:28<00:04, 22.64it/s]
Loading 0:  71%|███████   | 258/363 [00:29<00:05, 19.71it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:04, 23.03it/s]
Loading 0:  74%|███████▎  | 267/363 [00:29<00:04, 19.60it/s]
Loading 0:  74%|███████▍  | 270/363 [00:29<00:05, 16.65it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:04, 19.53it/s]
Loading 0:  76%|███████▋  | 277/363 [00:30<00:04, 19.82it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:03, 21.13it/s]
Loading 0:  78%|███████▊  | 283/363 [00:30<00:03, 21.29it/s]
Loading 0:  79%|███████▉  | 286/363 [00:30<00:03, 20.96it/s]
Loading 0:  80%|███████▉  | 289/363 [00:30<00:03, 22.53it/s]
Loading 0:  80%|████████  | 292/363 [00:30<00:03, 22.96it/s]
Loading 0:  81%|████████▏ | 295/363 [00:30<00:03, 22.25it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:02, 23.61it/s]
Loading 0:  83%|████████▎ | 303/363 [00:31<00:02, 25.78it/s]
Loading 0:  84%|████████▍ | 306/363 [00:31<00:03, 15.44it/s]
Loading 0:  85%|████████▌ | 310/363 [00:31<00:02, 18.51it/s]
Loading 0:  86%|████████▌ | 313/363 [00:31<00:02, 19.19it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 20.76it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:02, 21.20it/s]
Loading 0:  89%|████████▊ | 322/363 [00:32<00:01, 21.65it/s]
Loading 0:  90%|█████████ | 327/363 [00:32<00:01, 24.46it/s]
Loading 0:  91%|█████████ | 330/363 [00:32<00:01, 20.54it/s]
Loading 0:  92%|█████████▏| 334/363 [00:32<00:01, 24.23it/s]
Loading 0:  93%|█████████▎| 337/363 [00:32<00:01, 20.64it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:01, 22.35it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:01, 12.56it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:01, 15.82it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:00, 16.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:33<00:00, 18.73it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 19.98it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 19.99it/s]
Loading 0: 100%|█████████▉| 362/363 [00:34<00:00, 22.15it/s]
                                                            
Job chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer completed after 208.3s with status: succeeded
Stopping job with name chaiml-gy-exp97-dpo-exp-26589-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.82s
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-exp97-dpo-exp-26589-v1
Waiting for inference service chaiml-gy-exp97-dpo-exp-26589-v1 to be ready
Inference service chaiml-gy-exp97-dpo-exp-26589-v1 ready after 210.78731608390808s
Pipeline stage MKMLDeployer completed in 211.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4982640743255615s
Received healthy response to inference request in 2.134279251098633s
Received healthy response to inference request in 1.8622565269470215s
Received healthy response to inference request in 2.227991819381714s
Received healthy response to inference request in 2.156719207763672s
5 requests
0 failed requests
5th percentile: 1.9166610717773438
10th percentile: 1.971065616607666
20th percentile: 2.0798747062683107
30th percentile: 2.1387672424316406
40th percentile: 2.1477432250976562
50th percentile: 2.156719207763672
60th percentile: 2.1852282524108886
70th percentile: 2.2137372970581053
80th percentile: 2.2820462703704836
90th percentile: 2.3901551723480225
95th percentile: 2.444209623336792
99th percentile: 2.4874531841278076
mean time: 2.17590217590332
Pipeline stage StressChecker completed in 12.27s
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 0.70s
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 0.75s
Shutdown handler de-registered
chaiml-gy-exp97-dpo-exp_26589_v1 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp97-dpo-exp-26589-v1-profiler
Waiting for inference service chaiml-gy-exp97-dpo-exp-26589-v1-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 3215.88s
Shutdown handler de-registered
chaiml-gy-exp97-dpo-exp_26589_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp97-dpo-exp_26589_v1 status is now torndown due to DeploymentManager action