chaiml-gy-exp26-sft-gy-_56631

developer_uid: bogoconic1

submission_id: chaiml-gy-exp26-sft-gy-_56631_v1

model_name: chaiml-gy-exp26-sft-gy-_56631_v1

model_group: ChaiML/gy-exp26-sft-gy-e

status: torndown

timestamp: 2025-06-27T12:35:45+00:00

num_battles: 6733

num_wins: 3372

celo_rating: 1288.89

family_friendly_score: 0.5114000000000001

family_friendly_standard_error: 0.007069229661002675

submission_type: basic

model_repo: ChaiML/gy-exp26-sft-gy-exp24sftdata-rm512-win-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': 0.5884142573551869, 'latency_mean': 1.6993148136138916, 'latency_p50': 1.691564917564392, 'latency_p90': 1.8887661218643188}, {'batch_size': 3, 'throughput': 1.0518013053159474, 'latency_mean': 2.84082359790802, 'latency_p50': 2.8356244564056396, 'latency_p90': 3.164860391616821}, {'batch_size': 5, 'throughput': 1.2575067565964277, 'latency_mean': 3.9564021933078766, 'latency_p50': 4.003868341445923, 'latency_p90': 4.431351637840271}, {'batch_size': 6, 'throughput': 1.3068309344387337, 'latency_mean': 4.55789510846138, 'latency_p50': 4.594316244125366, 'latency_p90': 5.147731781005859}, {'batch_size': 8, 'throughput': 1.3732019301399907, 'latency_mean': 5.771605855226516, 'latency_p50': 5.746135115623474, 'latency_p90': 6.514767694473266}, {'batch_size': 10, 'throughput': 1.4087481281007983, 'latency_mean': 7.055462311506272, 'latency_p50': 7.0655437707901, 'latency_p90': 7.95185956954956}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp26-sft-gy-_56631_v1

is_internal_developer: True

language_model: ChaiML/gy-exp26-sft-gy-exp24sftdata-rm512-win-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-06-27

win_ratio: 0.5008168721223824

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': ['<|im_end|>', '\n', '<|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-exp26-sft-gy-56631-v1-mkmlizer
Waiting for job on chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer to finish
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: Downloaded to shared memory in 42.123s
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: Checking if ChaiML/gy-exp26-sft-gy-exp24sftdata-rm512-win-ep2 already exists in ChaiML
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqk45woy_, device:0
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: quantized model in 29.606s
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: Processed model ChaiML/gy-exp26-sft-gy-exp24sftdata-rm512-win-ep2 in 71.729s
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp26-sft-gy-56631-v1
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp26-sft-gy-56631-v1/config.json
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp26-sft-gy-56631-v1/special_tokens_map.json
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp26-sft-gy-56631-v1/tokenizer_config.json
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp26-sft-gy-56631-v1/tokenizer.json
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp26-sft-gy-56631-v1/flywheel_model.0.safetensors
chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 32.80it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.64it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.18it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.66it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.48it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.87it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.86it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.31it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.04it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.83it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.08it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.32it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.59it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 43.36it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 43.42it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 44.26it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 42.15it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 43.20it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 43.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 41.98it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 44.53it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 45.80it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 38.13it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.01it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.84it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.81it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.25it/s]
Loading 0:  44%|████▍     | 160/363 [00:03<00:05, 37.21it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:04, 39.73it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 41.24it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 42.27it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 40.22it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 39.82it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 44.46it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 44.63it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 43.71it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 45.14it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:03, 38.11it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 43.13it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 32.70it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.02it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.55it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.61it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.99it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.49it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.66it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.88it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 43.51it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.18it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 44.72it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 41.50it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 40.50it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.03it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 45.25it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 46.02it/s]
Loading 0:  84%|████████▍ | 306/363 [00:07<00:02, 25.63it/s]
Loading 0:  85%|████████▌ | 310/363 [00:07<00:01, 26.62it/s]
Loading 0:  87%|████████▋ | 314/363 [00:07<00:01, 28.77it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.22it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.56it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 34.42it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 42.36it/s]
Loading 0:  94%|█████████▍| 342/363 [00:08<00:00, 42.97it/s]
Loading 0:  96%|█████████▌| 347/363 [00:08<00:00, 44.28it/s]
Loading 0:  97%|█████████▋| 353/363 [00:08<00:00, 41.91it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 41.86it/s]
                                                            
Job chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer completed after 94.79s with status: succeeded
Stopping job with name chaiml-gy-exp26-sft-gy-56631-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.32s
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-exp26-sft-gy-56631-v1
Waiting for inference service chaiml-gy-exp26-sft-gy-56631-v1 to be ready
Inference service chaiml-gy-exp26-sft-gy-56631-v1 ready after 150.52286195755005s
Pipeline stage MKMLDeployer completed in 151.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.221733808517456s
Received healthy response to inference request in 1.7158174514770508s
Received healthy response to inference request in 1.709834337234497s
Received healthy response to inference request in 1.5037014484405518s
Received healthy response to inference request in 1.8635690212249756s
5 requests
0 failed requests
5th percentile: 1.5449280261993408
10th percentile: 1.5861546039581298
20th percentile: 1.668607759475708
30th percentile: 1.7110309600830078
40th percentile: 1.7134242057800293
50th percentile: 1.7158174514770508
60th percentile: 1.7749180793762207
70th percentile: 1.8340187072753906
80th percentile: 1.9352019786834718
90th percentile: 2.0784678936004637
95th percentile: 2.15010085105896
99th percentile: 2.207407217025757
mean time: 1.8029312133789062
Pipeline stage StressChecker completed in 10.35s
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 0.80s
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-exp26-sft-gy-_56631_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp26-sft-gy-56631-v1-profiler
Waiting for inference service chaiml-gy-exp26-sft-gy-56631-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 5317.69s
Shutdown handler de-registered
chaiml-gy-exp26-sft-gy-_56631_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp26-sft-gy-_56631_v1 status is now torndown due to DeploymentManager action