chaiml-gy-exp13-sftdpo-g_1305

developer_uid: bogoconic1

submission_id: chaiml-gy-exp13-sftdpo-g_1305_v1

model_name: chaiml-gy-exp13-sftdpo-g_1305_v1

model_group: ChaiML/gy-exp13-sftdpo-g

status: torndown

timestamp: 2025-06-26T17:33:36+00:00

num_battles: 8579

num_wins: 4351

celo_rating: 1290.54

family_friendly_score: 0.5464

family_friendly_standard_error: 0.007040554523615309

submission_type: basic

model_repo: ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.587228781350605, 'latency_mean': 1.702729550600052, 'latency_p50': 1.6980739831924438, 'latency_p90': 1.861304759979248}, {'batch_size': 3, 'throughput': 1.0422757389040658, 'latency_mean': 2.8715085101127626, 'latency_p50': 2.861099123954773, 'latency_p90': 3.231173825263977}, {'batch_size': 5, 'throughput': 1.2438227650302862, 'latency_mean': 3.9921267509460447, 'latency_p50': 4.013576149940491, 'latency_p90': 4.461684250831604}, {'batch_size': 6, 'throughput': 1.309247906202664, 'latency_mean': 4.568439806699753, 'latency_p50': 4.601666808128357, 'latency_p90': 5.098836040496826}, {'batch_size': 8, 'throughput': 1.3561274857105958, 'latency_mean': 5.855605789422989, 'latency_p50': 5.921689748764038, 'latency_p90': 6.557872152328491}, {'batch_size': 10, 'throughput': 1.4045647470209948, 'latency_mean': 7.071401079893112, 'latency_p50': 7.001480579376221, 'latency_p90': 8.021755743026734}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp13-sftdpo-g_1305_v1

is_internal_developer: True

language_model: ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.21

us_pacific_date: 2025-06-26

win_ratio: 0.5071686676768854

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], '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': False}

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-exp13-sftdpo-g-1305-v1-mkmlizer
Waiting for job on chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer to finish
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: Downloaded to shared memory in 42.768s
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: Checking if ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep2 already exists in ChaiML
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4wbwj50i, device:0
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: quantized model in 30.132s
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: Processed model ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep2 in 72.900s
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-g-1305-v1
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-g-1305-v1/config.json
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-g-1305-v1/special_tokens_map.json
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-g-1305-v1/tokenizer_config.json
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-g-1305-v1/tokenizer.json
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-g-1305-v1/flywheel_model.0.safetensors
chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.05it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.74it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.32it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.04it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.66it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.40it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.27it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.54it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.55it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.85it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.16it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.39it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 35.07it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.99it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.34it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.85it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 43.99it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 41.95it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.71it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 40.58it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.33it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.77it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.19it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 41.07it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.07it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:06, 34.47it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.59it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.95it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.01it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 39.58it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 41.71it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:05, 34.66it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 41.39it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 41.88it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 42.20it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 39.75it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 33.79it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 38.70it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 30.07it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.51it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.36it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.27it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 36.06it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:02, 39.26it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 40.31it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 40.30it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 42.14it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 35.58it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 42.59it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:01, 42.72it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 42.53it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 44.09it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 36.36it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 40.68it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 23.40it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 25.31it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 25.40it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 33.81it/s]
Loading 0:  89%|████████▉ | 324/363 [00:08<00:01, 36.11it/s]
Loading 0:  91%|█████████ | 329/363 [00:08<00:00, 38.58it/s]
Loading 0:  92%|█████████▏| 334/363 [00:08<00:00, 41.02it/s]
Loading 0:  93%|█████████▎| 339/363 [00:08<00:00, 35.30it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 42.35it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 41.85it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 42.03it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 40.38it/s]
                                                            
Job chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer completed after 104.95s with status: succeeded
Stopping job with name chaiml-gy-exp13-sftdpo-g-1305-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp13-sftdpo-g-1305-v1
Waiting for inference service chaiml-gy-exp13-sftdpo-g-1305-v1 to be ready
Inference service chaiml-gy-exp13-sftdpo-g-1305-v1 ready after 150.5680751800537s
Pipeline stage MKMLDeployer completed in 151.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.382680654525757s
Received healthy response to inference request in 1.6685948371887207s
Received healthy response to inference request in 1.834549903869629s
Received healthy response to inference request in 1.5711698532104492s
Received healthy response to inference request in 1.5954627990722656s
5 requests
0 failed requests
5th percentile: 1.5760284423828126
10th percentile: 1.5808870315551757
20th percentile: 1.5906042098999023
30th percentile: 1.6100892066955566
40th percentile: 1.6393420219421386
50th percentile: 1.6685948371887207
60th percentile: 1.734976863861084
70th percentile: 1.8013588905334472
80th percentile: 1.9441760540008546
90th percentile: 2.1634283542633055
95th percentile: 2.273054504394531
99th percentile: 2.3607554244995117
mean time: 1.8104916095733643
Pipeline stage StressChecker completed in 10.29s
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 0.67s
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 0.67s
Shutdown handler de-registered
chaiml-gy-exp13-sftdpo-g_1305_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 0.11s
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-exp13-sftdpo-g-1305-v1-profiler
Waiting for inference service chaiml-gy-exp13-sftdpo-g-1305-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 4868.28s
Shutdown handler de-registered
chaiml-gy-exp13-sftdpo-g_1305_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp13-sftdpo-g_1305_v1 status is now torndown due to DeploymentManager action