chaiml-gy-exp96-dpo-exp8_5290

developer_uid: bogoconic1

submission_id: chaiml-gy-exp96-dpo-exp8_5290_v1

model_name: chaiml-gy-exp96-dpo-exp8_5290_v1

model_group: ChaiML/gy-exp96-dpo-exp8

status: torndown

timestamp: 2025-07-06T13:47:28+00:00

num_battles: 7980

num_wins: 4198

celo_rating: 1309.2

family_friendly_score: 0.5336000000000001

family_friendly_standard_error: 0.007055083840749166

submission_type: basic

model_repo: ChaiML/gy-exp96-dpo-exp86ep8s2-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': 0.5156272355558185, 'latency_mean': 1.939261019229889, 'latency_p50': 1.9481109380722046, 'latency_p90': 2.1350802421569823}, {'batch_size': 3, 'throughput': 1.049626861485081, 'latency_mean': 2.8527057814598082, 'latency_p50': 2.8438724279403687, 'latency_p90': 3.1410554885864257}, {'batch_size': 5, 'throughput': 1.3378670661808296, 'latency_mean': 3.70889265537262, 'latency_p50': 3.6986167430877686, 'latency_p90': 4.186102557182312}, {'batch_size': 6, 'throughput': 1.433055351849407, 'latency_mean': 4.156261962652207, 'latency_p50': 4.184583425521851, 'latency_p90': 4.606463241577148}, {'batch_size': 8, 'throughput': 1.579429593065454, 'latency_mean': 5.013183181285858, 'latency_p50': 5.047587275505066, 'latency_p90': 5.657579231262207}, {'batch_size': 10, 'throughput': 1.66394398737381, 'latency_mean': 5.95879245877266, 'latency_p50': 5.987937808036804, 'latency_p90': 6.642063069343567}]

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

display_name: chaiml-gy-exp96-dpo-exp8_5290_v1

is_internal_developer: False

language_model: ChaiML/gy-exp96-dpo-exp86ep8s2-grok-payloads-0705-dpo-diff-gt0.05-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-06

win_ratio: 0.5260651629072681

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-exp96-dpo-exp8-5290-v1-mkmlizer
Waiting for job on chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer to finish
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: Downloaded to shared memory in 77.095s
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: Checking if ChaiML/gy-exp96-dpo-exp86ep8s2-grok-payloads-0705-dpo-diff-gt0.05-ep2 already exists in ChaiML
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3wi7uxyt, device:0
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia/config.json
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia/special_tokens_map.json
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia/tokenizer_config.json
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia/tokenizer.json
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-5290-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.16it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 27.27it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.78it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 26.93it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.78it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 28.08it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:09, 35.37it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:14, 22.93it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:13, 23.42it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:16, 19.57it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.41it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.43it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 27.90it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.50it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.97it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.23it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.69it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.50it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.91it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 25.10it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.20it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.17it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.00it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 24.31it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.58it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.66it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 22.61it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.08it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:09, 25.85it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 25.37it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.43it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.84it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.87it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:09, 24.15it/s]
Loading 0:  40%|████      | 146/363 [00:05<00:07, 29.46it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 21.67it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 18.89it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.76it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 22.19it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.04it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.87it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 27.61it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.53it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.63it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.45it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.02it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.19it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.74it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.74it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:08,  1.16s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:35,  1.03it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:33,  1.66it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.11it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.78it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.97it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.96it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.41it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.85it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.57it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.28it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.38it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 19.88it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 24.78it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.57it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 29.05it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.32it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.20it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 22.15it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 22.76it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.82it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.46it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.12it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.20it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 27.41it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.00it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.58it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.91it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.68it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.12it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.86it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 26.89it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 25.48it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.24it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 20.76it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.02it/s]
Loading 0:  97%|█████████▋| 353/363 [00:29<00:00, 22.38it/s]
Loading 0:  98%|█████████▊| 357/363 [00:29<00:00, 20.86it/s]
                                                            
Job chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer completed after 156.06s with status: succeeded
Stopping job with name chaiml-gy-exp96-dpo-exp8-5290-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.57s
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-exp96-dpo-exp8-5290-v1
Waiting for inference service chaiml-gy-exp96-dpo-exp8-5290-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission function_patif_2025-06-06: ('http://chaiml-20250611-retune-u-1558-v3-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:47764->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-gy-exp96-dpo-exp8-5290-v1 ready after 210.95658421516418s
Pipeline stage MKMLDeployer completed in 211.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0834598541259766s
Received healthy response to inference request in 1.9664804935455322s
Received healthy response to inference request in 1.942760705947876s
Received healthy response to inference request in 2.221004009246826s
Received healthy response to inference request in 2.447213649749756s
5 requests
0 failed requests
5th percentile: 1.9475046634674071
10th percentile: 1.9522486209869385
20th percentile: 1.961736536026001
30th percentile: 2.017385196685791
40th percentile: 2.1191946029663087
50th percentile: 2.221004009246826
60th percentile: 2.3114878654479982
70th percentile: 2.40197172164917
80th percentile: 2.574462890625
90th percentile: 2.8289613723754883
95th percentile: 2.9562106132507324
99th percentile: 3.0580100059509276
mean time: 2.3321837425231933
Pipeline stage StressChecker completed in 13.10s
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 0.73s
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 0.66s
Shutdown handler de-registered
chaiml-gy-exp96-dpo-exp8_5290_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 0.14s
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-exp96-dpo-exp8-5290-v1-profiler
Waiting for inference service chaiml-gy-exp96-dpo-exp8-5290-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 3349.59s
Shutdown handler de-registered
chaiml-gy-exp96-dpo-exp8_5290_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp96-dpo-exp8_5290_v1 status is now torndown due to DeploymentManager action