chaiml-gy-exp13-sft-gy-_81696

developer_uid: bogoconic1

submission_id: chaiml-gy-exp13-sft-gy-_81696_v1

model_name: chaiml-gy-exp13-sft-gy-_81696_v1

model_group: ChaiML/gy-exp13-sft-gy-1

status: torndown

timestamp: 2025-06-26T13:46:20+00:00

num_battles: 8896

num_wins: 4481

celo_rating: 1289.2

family_friendly_score: 0.5282

family_friendly_standard_error: 0.007059812462098409

submission_type: basic

model_repo: ChaiML/gy-exp13-sft-gy-1266-1301-7850x4-pref-grok-ctx2500-64tok-96tok-512tok-onlylast-original-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': 0.5948633778556064, 'latency_mean': 1.6809544265270233, 'latency_p50': 1.6843247413635254, 'latency_p90': 1.8569878578186034}, {'batch_size': 3, 'throughput': 1.0721221969580024, 'latency_mean': 2.7909300339221956, 'latency_p50': 2.8085676431655884, 'latency_p90': 3.091307258605957}, {'batch_size': 5, 'throughput': 1.291179391955535, 'latency_mean': 3.848816591501236, 'latency_p50': 3.857886791229248, 'latency_p90': 4.343747282028199}, {'batch_size': 6, 'throughput': 1.3587472439458357, 'latency_mean': 4.391394065618515, 'latency_p50': 4.400245428085327, 'latency_p90': 4.928626656532288}, {'batch_size': 8, 'throughput': 1.4117075233786383, 'latency_mean': 5.6333642518520355, 'latency_p50': 5.599959015846252, 'latency_p90': 6.336888360977173}, {'batch_size': 10, 'throughput': 1.4403755787673422, 'latency_mean': 6.893439894914627, 'latency_p50': 7.001739144325256, 'latency_p90': 7.690938591957092}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp13-sft-gy-_81696_v1

is_internal_developer: True

language_model: ChaiML/gy-exp13-sft-gy-1266-1301-7850x4-pref-grok-ctx2500-64tok-96tok-512tok-onlylast-original-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-06-26

win_ratio: 0.5037095323741008

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-exp13-sft-gy-81696-v1-mkmlizer
Waiting for job on chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer to finish
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: Downloaded to shared memory in 41.994s
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: Checking if ChaiML/gy-exp13-sft-gy-1266-1301-7850x4-pref-grok-ctx2500-64tok-96tok-512tok-onlylast-original-ep1 already exists in ChaiML
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp49dgpago, device:0
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: quantized model in 31.566s
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: Processed model ChaiML/gy-exp13-sft-gy-1266-1301-7850x4-pref-grok-ctx2500-64tok-96tok-512tok-onlylast-original-ep1 in 73.561s
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp13-sft-gy-81696-v1
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp13-sft-gy-81696-v1/special_tokens_map.json
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp13-sft-gy-81696-v1/config.json
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp13-sft-gy-81696-v1/tokenizer_config.json
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp13-sft-gy-81696-v1/tokenizer.json
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp13-sft-gy-81696-v1/flywheel_model.0.safetensors
chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.37it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.77it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 41.32it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.41it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.32it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.67it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.25it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 45.72it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.98it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 47.96it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:10, 27.45it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.60it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 35.07it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.05it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 39.48it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.90it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.57it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.89it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 42.81it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 36.43it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.18it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.25it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.45it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.43it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 41.87it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.98it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 29.69it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 28.04it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:06, 32.25it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:06, 30.21it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 36.90it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 37.61it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 37.80it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 35.95it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 37.92it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 36.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 37.61it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 35.82it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 37.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 36.31it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:04, 36.19it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 28.21it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.42it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 28.38it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.68it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.38it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.76it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.08it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 33.78it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 41.30it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 42.04it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.97it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.62it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.05it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 43.28it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.71it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 43.15it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 23.13it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.02it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 26.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 31.66it/s]
Loading 0:  89%|████████▉ | 324/363 [00:09<00:01, 32.97it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 35.41it/s]
Loading 0:  92%|█████████▏| 333/363 [00:09<00:00, 36.45it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 39.59it/s]
Loading 0:  94%|█████████▍| 343/363 [00:09<00:00, 41.67it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 34.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 42.48it/s]
Loading 0:  99%|█████████▉| 360/363 [00:09<00:00, 42.34it/s]
                                                            
Job chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer completed after 94.65s with status: succeeded
Stopping job with name chaiml-gy-exp13-sft-gy-81696-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp13-sft-gy-81696-v1
Waiting for inference service chaiml-gy-exp13-sft-gy-81696-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-gy-exp13-sft-gy-81696-v1 ready after 140.97038555145264s
Pipeline stage MKMLDeployer completed in 141.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5736515522003174s
Received healthy response to inference request in 1.742555856704712s
Received healthy response to inference request in 1.8957080841064453s
Received healthy response to inference request in 1.7146785259246826s
Received healthy response to inference request in 1.6998052597045898s
5 requests
0 failed requests
5th percentile: 1.7027799129486083
10th percentile: 1.705754566192627
20th percentile: 1.7117038726806642
30th percentile: 1.7202539920806885
40th percentile: 1.7314049243927
50th percentile: 1.742555856704712
60th percentile: 1.8038167476654052
70th percentile: 1.8650776386260985
80th percentile: 2.03129677772522
90th percentile: 2.3024741649627685
95th percentile: 2.4380628585815427
99th percentile: 2.5465338134765623
mean time: 1.9252798557281494
Pipeline stage StressChecker completed in 11.76s
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 0.98s
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 0.70s
Shutdown handler de-registered
chaiml-gy-exp13-sft-gy-_81696_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5202.54s
Shutdown handler de-registered
chaiml-gy-exp13-sft-gy-_81696_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp13-sft-gy-_81696_v1 status is now torndown due to DeploymentManager action