chaiml-gy-exp60-dpo-gy-_15080

developer_uid: bogoconic1

submission_id: chaiml-gy-exp60-dpo-gy-_15080_v1

model_name: chaiml-gy-exp60-dpo-gy-_15080_v1

model_group: ChaiML/gy-exp60-dpo-gy-d

status: torndown

timestamp: 2025-07-02T11:18:05+00:00

num_battles: 8990

num_wins: 3835

celo_rating: 1235.06

family_friendly_score: 0.72

family_friendly_standard_error: 0.0063498031465550175

submission_type: basic

model_repo: ChaiML/gy-exp60-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-agreement-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5975857308739787, 'latency_mean': 1.6732670843601227, 'latency_p50': 1.6641238927841187, 'latency_p90': 1.8474514961242676}, {'batch_size': 3, 'throughput': 1.0669241968187781, 'latency_mean': 2.804168554544449, 'latency_p50': 2.832046389579773, 'latency_p90': 3.0572484493255616}, {'batch_size': 5, 'throughput': 1.276523337967811, 'latency_mean': 3.9054759347438814, 'latency_p50': 3.9004772901535034, 'latency_p90': 4.3847280740737915}, {'batch_size': 6, 'throughput': 1.33898706939508, 'latency_mean': 4.466001703739166, 'latency_p50': 4.497212767601013, 'latency_p90': 4.9492377758026125}, {'batch_size': 8, 'throughput': 1.40169224927753, 'latency_mean': 5.668397936820984, 'latency_p50': 5.6458717584609985, 'latency_p90': 6.3904752969741825}, {'batch_size': 10, 'throughput': 1.4235660399489591, 'latency_mean': 6.9594278657436375, 'latency_p50': 6.978929162025452, 'latency_p90': 7.915910530090332}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp60-dpo-gy-_15080_v1

is_internal_developer: True

language_model: ChaiML/gy-exp60-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-agreement-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-07-02

win_ratio: 0.42658509454949944

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_end|>', '<|im_start|>', '\n'], '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-exp60-dpo-gy-15080-v1-mkmlizer
Waiting for job on chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer to finish
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  Version: 0.29.8                                                    ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: Downloaded to shared memory in 38.192s
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: Checking if ChaiML/gy-exp60-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-agreement-ep1 already exists in ChaiML
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptechw6j0, device:0
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: quantized model in 31.421s
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: Processed model ChaiML/gy-exp60-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-agreement-ep1 in 69.614s
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp60-dpo-gy-15080-v1/nvidia
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp60-dpo-gy-15080-v1/nvidia/config.json
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp60-dpo-gy-15080-v1/nvidia/special_tokens_map.json
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp60-dpo-gy-15080-v1/nvidia/tokenizer_config.json
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp60-dpo-gy-15080-v1/nvidia/tokenizer.json
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp60-dpo-gy-15080-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.81it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.71it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 39.43it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:09, 37.52it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 42.13it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:08, 40.38it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:08, 39.40it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 40.21it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 33.27it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:07, 41.32it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:10, 29.01it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:10, 29.53it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.55it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 33.37it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 36.93it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 37.89it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 39.16it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 40.78it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 33.83it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:06, 41.94it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 43.59it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:05, 42.21it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 44.17it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 37.44it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.89it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 43.53it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 27.45it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 29.72it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:06, 33.41it/s]
Loading 0:  44%|████▍     | 159/363 [00:04<00:06, 33.44it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 38.53it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.20it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 39.80it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 41.31it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.83it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 40.74it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 40.74it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 42.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 40.77it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:04, 37.37it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 39.86it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 31.08it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 31.62it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.24it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 37.06it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 36.54it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.76it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 39.59it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 40.89it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 43.16it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 35.46it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 42.99it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 42.27it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 41.38it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 42.89it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 36.19it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 40.77it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 22.76it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 24.75it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 24.61it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.12it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 36.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 37.40it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 42.85it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 41.75it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 41.65it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 46.14it/s]
Loading 0:  99%|█████████▉| 361/363 [00:09<00:00, 46.01it/s]
                                                            
Job chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer completed after 94.08s with status: succeeded
Stopping job with name chaiml-gy-exp60-dpo-gy-15080-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.56s
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-exp60-dpo-gy-15080-v1
Waiting for inference service chaiml-gy-exp60-dpo-gy-15080-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-gy-exp60-dpo-gy-15080-v1 ready after 211.51609706878662s
Pipeline stage MKMLDeployer completed in 212.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.105398416519165s
Received healthy response to inference request in 1.4900469779968262s
Received healthy response to inference request in 1.474726915359497s
Received healthy response to inference request in 1.5452523231506348s
Received healthy response to inference request in 1.6272170543670654s
5 requests
0 failed requests
5th percentile: 1.477790927886963
10th percentile: 1.4808549404144287
20th percentile: 1.4869829654693603
30th percentile: 1.5010880470275878
40th percentile: 1.5231701850891113
50th percentile: 1.5452523231506348
60th percentile: 1.578038215637207
70th percentile: 1.6108241081237793
80th percentile: 1.7228533267974855
90th percentile: 1.9141258716583252
95th percentile: 2.009762144088745
99th percentile: 2.086271162033081
mean time: 1.6485283374786377
Pipeline stage StressChecker completed in 9.61s
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 0.95s
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 0.76s
Shutdown handler de-registered
chaiml-gy-exp60-dpo-gy-_15080_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp60-dpo-gy-15080-v1-profiler
Waiting for inference service chaiml-gy-exp60-dpo-gy-15080-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5413.37s
Shutdown handler de-registered
chaiml-gy-exp60-dpo-gy-_15080_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp60-dpo-gy-_15080_v1 status is now torndown due to DeploymentManager action