chaiml-gy-exp63-dpo-exp_33175

developer_uid: bogoconic1

submission_id: chaiml-gy-exp63-dpo-exp_33175_v1

model_name: chaiml-gy-exp63-dpo-exp_33175_v1

model_group: ChaiML/gy-exp63-dpo-exp3

status: torndown

timestamp: 2025-07-02T19:01:44+00:00

num_battles: 7087

num_wins: 3842

celo_rating: 1304.73

family_friendly_score: 0.5005999999999999

family_friendly_standard_error: 0.0070710627206948175

submission_type: basic

model_repo: ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5204159049815539, 'latency_mean': 1.9214187204837798, 'latency_p50': 1.9055631160736084, 'latency_p90': 2.135615611076355}, {'batch_size': 3, 'throughput': 1.0444339576997055, 'latency_mean': 2.8573657965660093, 'latency_p50': 2.8509877920150757, 'latency_p90': 3.161419177055359}, {'batch_size': 5, 'throughput': 1.3184869117979825, 'latency_mean': 3.7589186573028566, 'latency_p50': 3.756402373313904, 'latency_p90': 4.210280036926269}, {'batch_size': 6, 'throughput': 1.4162669802564591, 'latency_mean': 4.194732620716095, 'latency_p50': 4.237480640411377, 'latency_p90': 4.667934560775757}, {'batch_size': 8, 'throughput': 1.5673982725839808, 'latency_mean': 5.053192216157913, 'latency_p50': 5.081799149513245, 'latency_p90': 5.7402191162109375}, {'batch_size': 10, 'throughput': 1.6492278540820122, 'latency_mean': 5.999783382415772, 'latency_p50': 5.990449547767639, 'latency_p90': 6.750259780883789}]

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

display_name: chaiml-gy-exp63-dpo-exp_33175_v1

is_internal_developer: True

language_model: ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-02

win_ratio: 0.5421193735007761

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': ['<|im_start|>', '\n', '<|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-exp63-dpo-exp-33175-v1-mkmlizer
Waiting for job on chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer to finish
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  Version: 0.29.8                                                    ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: Downloaded to shared memory in 220.324s
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: Checking if ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2 already exists in ChaiML
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4bne0ofm, device:0
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: quantized model in 56.111s
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: Processed model ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2 in 276.436s
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia/special_tokens_map.json
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia/config.json
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia/tokenizer_config.json
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia/tokenizer.json
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33175-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:13, 26.07it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:16, 21.05it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.57it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 22.13it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:11, 29.16it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 22.33it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:11, 27.91it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.58it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:18, 17.84it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.54it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 21.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:12, 24.48it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.87it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 25.02it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 25.08it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.62it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:12, 24.41it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:13, 21.37it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:15, 18.20it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 23.30it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 22.32it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.40it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.39it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 19.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:04<00:09, 26.45it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 22.97it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 20.33it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 23.06it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 20.65it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 24.23it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:09, 24.99it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:09, 24.99it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.33it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.18it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.84it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:09, 24.59it/s]
Loading 0:  40%|████      | 146/363 [00:06<00:07, 29.87it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 22.36it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 17.74it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 20.64it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:09, 20.66it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:08, 23.95it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:08, 21.75it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 25.99it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 23.00it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.35it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 28.47it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:09, 18.65it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.67it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 20.28it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:08, 20.28it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<03:29,  1.29s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<02:53,  1.08s/it]
Loading 0:  57%|█████▋    | 208/363 [00:25<01:44,  1.48it/s]
Loading 0:  58%|█████▊    | 211/363 [00:26<01:20,  1.89it/s]
Loading 0:  59%|█████▉    | 214/363 [00:26<00:59,  2.49it/s]
Loading 0:  60%|██████    | 218/363 [00:26<00:40,  3.57it/s]
Loading 0:  61%|██████    | 221/363 [00:26<00:31,  4.55it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:26,  5.30it/s]
Loading 0:  63%|██████▎   | 228/363 [00:26<00:18,  7.45it/s]
Loading 0:  64%|██████▎   | 231/363 [00:27<00:15,  8.65it/s]
Loading 0:  65%|██████▌   | 237/363 [00:27<00:09, 13.01it/s]
Loading 0:  66%|██████▌   | 240/363 [00:27<00:08, 13.88it/s]
Loading 0:  68%|██████▊   | 246/363 [00:27<00:06, 19.06it/s]
Loading 0:  69%|██████▊   | 249/363 [00:27<00:06, 18.28it/s]
Loading 0:  70%|██████▉   | 253/363 [00:27<00:05, 21.70it/s]
Loading 0:  71%|███████   | 256/363 [00:28<00:04, 22.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:28<00:04, 22.44it/s]
Loading 0:  72%|███████▏  | 263/363 [00:28<00:03, 26.19it/s]
Loading 0:  74%|███████▎  | 267/363 [00:28<00:04, 20.06it/s]
Loading 0:  74%|███████▍  | 270/363 [00:28<00:05, 17.38it/s]
Loading 0:  75%|███████▌  | 274/363 [00:28<00:04, 20.47it/s]
Loading 0:  76%|███████▋  | 277/363 [00:29<00:04, 20.75it/s]
Loading 0:  78%|███████▊  | 282/363 [00:29<00:03, 24.10it/s]
Loading 0:  79%|███████▊  | 285/363 [00:29<00:03, 21.74it/s]
Loading 0:  80%|████████  | 291/363 [00:29<00:02, 25.85it/s]
Loading 0:  81%|████████  | 294/363 [00:29<00:03, 22.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:29<00:02, 25.35it/s]
Loading 0:  84%|████████▎ | 304/363 [00:30<00:02, 22.15it/s]
Loading 0:  85%|████████▍ | 307/363 [00:30<00:02, 20.49it/s]
Loading 0:  85%|████████▌ | 310/363 [00:30<00:02, 21.26it/s]
Loading 0:  86%|████████▌ | 313/363 [00:30<00:02, 21.61it/s]
Loading 0:  88%|████████▊ | 318/363 [00:30<00:01, 25.37it/s]
Loading 0:  88%|████████▊ | 321/363 [00:30<00:01, 22.82it/s]
Loading 0:  90%|█████████ | 327/363 [00:31<00:01, 27.99it/s]
Loading 0:  91%|█████████ | 330/363 [00:31<00:01, 24.60it/s]
Loading 0:  92%|█████████▏| 335/363 [00:31<00:01, 27.19it/s]
Loading 0:  93%|█████████▎| 338/363 [00:31<00:00, 25.48it/s]
Loading 0:  94%|█████████▍| 341/363 [00:32<00:01, 14.11it/s]
Loading 0:  95%|█████████▌| 346/363 [00:32<00:00, 18.97it/s]
Loading 0:  96%|█████████▌| 349/363 [00:32<00:00, 18.37it/s]
Loading 0:  98%|█████████▊| 355/363 [00:32<00:00, 24.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:32<00:00, 23.30it/s]
                                                            
Job chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer completed after 321.19s with status: succeeded
Stopping job with name chaiml-gy-exp63-dpo-exp-33175-v1-mkmlizer
Pipeline stage MKMLizer completed in 321.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp63-dpo-exp-33175-v1
Waiting for inference service chaiml-gy-exp63-dpo-exp-33175-v1 to be ready
Inference service chaiml-gy-exp63-dpo-exp-33175-v1 ready after 220.77180004119873s
Pipeline stage MKMLDeployer completed in 221.55s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.812068462371826s
Received healthy response to inference request in 2.1607279777526855s
Received healthy response to inference request in 2.120380401611328s
Received healthy response to inference request in 2.21462082862854s
5 requests
1 failed requests
5th percentile: 2.1284499168395996
10th percentile: 2.136519432067871
20th percentile: 2.152658462524414
30th percentile: 2.1715065479278564
40th percentile: 2.1930636882781984
50th percentile: 2.21462082862854
60th percentile: 2.4535998821258547
70th percentile: 2.692578935623169
80th percentile: 6.2866634368896515
90th percentile: 13.235853385925296
95th percentile: 16.710448360443113
99th percentile: 19.490124340057374
mean time: 5.898568201065063
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9760057926177979s
Received healthy response to inference request in 1.9499521255493164s
Received healthy response to inference request in 1.9504568576812744s
Received healthy response to inference request in 1.8955204486846924s
Received healthy response to inference request in 2.0591530799865723s
5 requests
0 failed requests
5th percentile: 1.906406784057617
10th percentile: 1.917293119430542
20th percentile: 1.9390657901763917
30th percentile: 1.950053071975708
40th percentile: 1.9502549648284913
50th percentile: 1.9504568576812744
60th percentile: 1.9606764316558838
70th percentile: 1.9708960056304932
80th percentile: 1.9926352500915527
90th percentile: 2.0258941650390625
95th percentile: 2.0425236225128174
99th percentile: 2.055827188491821
mean time: 1.9662176609039306
Pipeline stage StressChecker completed in 42.57s
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 0.79s
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 0.79s
Shutdown handler de-registered
chaiml-gy-exp63-dpo-exp_33175_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 3416.39s
Shutdown handler de-registered
chaiml-gy-exp63-dpo-exp_33175_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp63-dpo-exp_33175_v1 status is now torndown due to DeploymentManager action