chaiml-gy-exp25-sft-gy-_81473

developer_uid: bogoconic1

submission_id: chaiml-gy-exp25-sft-gy-_81473_v1

model_name: chaiml-gy-exp25-sft-gy-_81473_v1

model_group: ChaiML/gy-exp25-sft-gy-e

status: torndown

timestamp: 2025-06-27T11:30:50+00:00

num_battles: 9429

num_wins: 4682

celo_rating: 1285.94

family_friendly_score: 0.5358

family_friendly_standard_error: 0.007052919395541112

submission_type: basic

model_repo: ChaiML/gy-exp25-sft-gy-exp12sftdata-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': 0.5926744642706021, 'latency_mean': 1.6871502327919006, 'latency_p50': 1.6954233646392822, 'latency_p90': 1.8802769422531127}, {'batch_size': 3, 'throughput': 1.0605135769584528, 'latency_mean': 2.8229122877120973, 'latency_p50': 2.827783942222595, 'latency_p90': 3.1255309104919435}, {'batch_size': 5, 'throughput': 1.267094933147831, 'latency_mean': 3.9225428605079653, 'latency_p50': 3.9342795610427856, 'latency_p90': 4.420305442810059}, {'batch_size': 6, 'throughput': 1.3314859928540448, 'latency_mean': 4.481833769083023, 'latency_p50': 4.483619570732117, 'latency_p90': 5.065898036956787}, {'batch_size': 8, 'throughput': 1.3864019310855207, 'latency_mean': 5.7346365821361545, 'latency_p50': 5.703414678573608, 'latency_p90': 6.3854995489120485}, {'batch_size': 10, 'throughput': 1.4211560419612363, 'latency_mean': 6.976745746135712, 'latency_p50': 6.97973906993866, 'latency_p90': 7.833727407455444}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp25-sft-gy-_81473_v1

is_internal_developer: True

language_model: ChaiML/gy-exp25-sft-gy-exp12sftdata-rm512-win-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-06-27

win_ratio: 0.49655318697634954

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_start|>', '<|im_end|>', '\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': 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-exp25-sft-gy-81473-v1-mkmlizer
Waiting for job on chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer to finish
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: Downloaded to shared memory in 39.481s
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: Checking if ChaiML/gy-exp25-sft-gy-exp12sftdata-rm512-win-ep2 already exists in ChaiML
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjviwuwcz, device:0
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: quantized model in 30.024s
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: Processed model ChaiML/gy-exp25-sft-gy-exp12sftdata-rm512-win-ep2 in 69.506s
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp25-sft-gy-81473-v1
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp25-sft-gy-81473-v1/config.json
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp25-sft-gy-81473-v1/special_tokens_map.json
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp25-sft-gy-81473-v1/tokenizer_config.json
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp25-sft-gy-81473-v1/tokenizer.json
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp25-sft-gy-81473-v1/flywheel_model.0.safetensors
chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.51it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.94it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.79it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.91it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.66it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.84it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.60it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.25it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.69it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.78it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 38.87it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.52it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 39.32it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.91it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.83it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 41.57it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 45.50it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.47it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.05it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.67it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.79it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.43it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.13it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.60it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.90it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.75it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.84it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.72it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.66it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.64it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.14it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.43it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 41.62it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.53it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.99it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.94it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.66it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 47.30it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.27it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.03it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.08it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.57it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.90it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.50it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.38it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.82it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 42.36it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.07it/s]
Loading 0:  77%|███████▋  | 280/363 [00:07<00:02, 41.05it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 40.34it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 44.54it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 44.67it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 48.23it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 23.24it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:01, 25.52it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.91it/s]
Loading 0:  90%|████████▉ | 325/363 [00:08<00:01, 36.83it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 33.35it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 41.61it/s]
Loading 0:  95%|█████████▍| 344/363 [00:08<00:00, 40.71it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 40.84it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 44.80it/s]
Loading 0:  99%|█████████▉| 360/363 [00:09<00:00, 43.85it/s]
                                                            
Job chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer completed after 94.8s with status: succeeded
Stopping job with name chaiml-gy-exp25-sft-gy-81473-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp25-sft-gy-81473-v1
Waiting for inference service chaiml-gy-exp25-sft-gy-81473-v1 to be ready
Inference service chaiml-gy-exp25-sft-gy-81473-v1 ready after 150.79911184310913s
Pipeline stage MKMLDeployer completed in 151.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.036602020263672s
Received healthy response to inference request in 1.5726232528686523s
Received healthy response to inference request in 1.7002506256103516s
Received healthy response to inference request in 1.5040199756622314s
Received healthy response to inference request in 1.7808823585510254s
5 requests
0 failed requests
5th percentile: 1.5177406311035155
10th percentile: 1.5314612865447998
20th percentile: 1.5589025974273683
30th percentile: 1.598148727416992
40th percentile: 1.6491996765136718
50th percentile: 1.7002506256103516
60th percentile: 1.732503318786621
70th percentile: 1.7647560119628907
80th percentile: 1.8320262908935547
90th percentile: 1.9343141555786132
95th percentile: 1.9854580879211425
99th percentile: 2.026373233795166
mean time: 1.7188756465911865
Pipeline stage StressChecker completed in 9.79s
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 0.82s
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 0.68s
Shutdown handler de-registered
chaiml-gy-exp25-sft-gy-_81473_v1 status is now deployed due to DeploymentManager action
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
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 4688.40s
Shutdown handler de-registered
chaiml-gy-exp25-sft-gy-_81473_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp25-sft-gy-_81473_v1 status is now torndown due to DeploymentManager action