chaiml-gy-exp124-dpo-ex_30605

developer_uid: bogoconic1

submission_id: chaiml-gy-exp124-dpo-ex_30605_v1

model_name: chaiml-gy-exp124-dpo-ex_30605_v1

model_group: ChaiML/gy-exp124-dpo-exp

status: torndown

timestamp: 2025-07-08T13:39:03+00:00

num_battles: 6920

num_wins: 3602

celo_rating: 1311.47

family_friendly_score: 0.5354

family_friendly_standard_error: 0.007053323188398501

submission_type: basic

model_repo: ChaiML/gy-exp124-dpo-exp77ep2s4-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5953378044229558, 'latency_mean': 1.6796010768413543, 'latency_p50': 1.6845299005508423, 'latency_p90': 1.857019853591919}, {'batch_size': 3, 'throughput': 1.063027692726977, 'latency_mean': 2.8166225039958954, 'latency_p50': 2.7929970026016235, 'latency_p90': 3.115813946723938}, {'batch_size': 5, 'throughput': 1.2842450888369639, 'latency_mean': 3.8788903939723967, 'latency_p50': 3.895826816558838, 'latency_p90': 4.385309386253357}, {'batch_size': 6, 'throughput': 1.3528038551457473, 'latency_mean': 4.421590158939361, 'latency_p50': 4.4074543714523315, 'latency_p90': 4.99722421169281}, {'batch_size': 8, 'throughput': 1.4051920071449606, 'latency_mean': 5.65379039645195, 'latency_p50': 5.663301587104797, 'latency_p90': 6.311466836929322}, {'batch_size': 10, 'throughput': 1.4415341444537122, 'latency_mean': 6.875017018318176, 'latency_p50': 6.897179365158081, 'latency_p90': 7.760126900672913}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp124-dpo-ex_30605_v1

is_internal_developer: False

language_model: ChaiML/gy-exp124-dpo-exp77ep2s4-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-08

win_ratio: 0.5205202312138728

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-exp124-dpo-ex-30605-v1-mkmlizer
Waiting for job on chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer to finish
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: Downloaded to shared memory in 58.511s
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: Checking if ChaiML/gy-exp124-dpo-exp77ep2s4-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp48usfheh, device:0
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: quantized model in 31.487s
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: Processed model ChaiML/gy-exp124-dpo-exp77ep2s4-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 89.999s
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp124-dpo-ex-30605-v1/nvidia
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp124-dpo-ex-30605-v1/nvidia/config.json
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp124-dpo-ex-30605-v1/nvidia/special_tokens_map.json
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp124-dpo-ex-30605-v1/nvidia/tokenizer_config.json
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp124-dpo-ex-30605-v1/nvidia/tokenizer.json
chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.55it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.42it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:06, 49.41it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.72it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 45.93it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 45.52it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 45.53it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 42.11it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 40.39it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.46it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.69it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.22it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 38.16it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.95it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:06, 40.62it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.31it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.39it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.86it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.25it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.42it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.30it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.32it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.49it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.24it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.68it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.90it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.63it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.22it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.64it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.18it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.53it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.02it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.79it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.34it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.05it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 40.85it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 42.99it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.75it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 41.75it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.01it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.30it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 27.21it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.27it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.96it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.06it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.12it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.19it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 32.20it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 35.44it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:03, 32.06it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.05it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 38.36it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:02, 38.58it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 38.09it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 37.55it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 35.46it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 35.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:03, 19.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.44it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 23.16it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 31.50it/s]
Loading 0:  89%|████████▉ | 323/363 [00:08<00:01, 31.38it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:00, 35.18it/s]
Loading 0:  92%|█████████▏| 333/363 [00:09<00:00, 36.31it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 37.48it/s]
Loading 0:  94%|█████████▍| 343/363 [00:09<00:00, 39.74it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 34.32it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 41.61it/s]
Loading 0:  99%|█████████▉| 360/363 [00:09<00:00, 41.56it/s]
                                                            
Job chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer completed after 116.36s with status: succeeded
Stopping job with name chaiml-gy-exp124-dpo-ex-30605-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.93s
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-exp124-dpo-ex-30605-v1
Waiting for inference service chaiml-gy-exp124-dpo-ex-30605-v1 to be ready
Inference service chaiml-gy-exp124-dpo-ex-30605-v1 ready after 191.1488687992096s
Pipeline stage MKMLDeployer completed in 191.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6178483963012695s
Received healthy response to inference request in 1.658294916152954s
Received healthy response to inference request in 1.8980774879455566s
Received healthy response to inference request in 1.5709023475646973s
Received healthy response to inference request in 1.5358939170837402s
5 requests
0 failed requests
5th percentile: 1.5428956031799317
10th percentile: 1.5498972892761231
20th percentile: 1.5639006614685058
30th percentile: 1.5883808612823487
40th percentile: 1.6233378887176513
50th percentile: 1.658294916152954
60th percentile: 1.7542079448699952
70th percentile: 1.850120973587036
80th percentile: 2.0420316696166996
90th percentile: 2.3299400329589846
95th percentile: 2.4738942146301266
99th percentile: 2.589057559967041
mean time: 1.8562034130096436
Pipeline stage StressChecker completed in 10.92s
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 0.62s
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 0.65s
Shutdown handler de-registered
chaiml-gy-exp124-dpo-ex_30605_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 0.10s
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-exp124-dpo-ex-30605-v1-profiler
Waiting for inference service chaiml-gy-exp124-dpo-ex-30605-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5267.27s
Shutdown handler de-registered
chaiml-gy-exp124-dpo-ex_30605_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp124-dpo-ex_30605_v1 status is now torndown due to DeploymentManager action