chaiml-gy-exp204-sft-gro_7278

developer_uid: bogoconic1

submission_id: chaiml-gy-exp204-sft-gro_7278_v1

model_name: chaiml-gy-exp204-sft-gro_7278_v1

model_group: ChaiML/gy-exp204-sft-gro

status: torndown

timestamp: 2025-07-20T21:12:02+00:00

num_battles: 8763

num_wins: 4256

celo_rating: 1278.2

family_friendly_score: 0.652

family_friendly_standard_error: 0.006736408538679939

submission_type: basic

model_repo: ChaiML/gy-exp204-sft-grok-payloads-0705-only-wins-lastmsgloss-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5217138245351357, 'latency_mean': 1.9166349291801452, 'latency_p50': 1.9263399839401245, 'latency_p90': 2.13007538318634}, {'batch_size': 3, 'throughput': 1.0579710193730483, 'latency_mean': 2.8249070274829866, 'latency_p50': 2.8237757682800293, 'latency_p90': 3.1327523708343508}, {'batch_size': 5, 'throughput': 1.3545244071393563, 'latency_mean': 3.6654875147342683, 'latency_p50': 3.6617084741592407, 'latency_p90': 4.0653023481369015}, {'batch_size': 6, 'throughput': 1.4466843426332097, 'latency_mean': 4.113947464227676, 'latency_p50': 4.122328758239746, 'latency_p90': 4.573077511787415}, {'batch_size': 8, 'throughput': 1.5805695204124304, 'latency_mean': 5.011002715826034, 'latency_p50': 5.029330730438232, 'latency_p90': 5.647140884399414}, {'batch_size': 10, 'throughput': 1.674620367192755, 'latency_mean': 5.908751494884491, 'latency_p50': 5.914527893066406, 'latency_p90': 6.629300880432129}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gy-exp204-sft-gro_7278_v1

is_internal_developer: False

language_model: ChaiML/gy-exp204-sft-grok-payloads-0705-only-wins-lastmsgloss-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-07-20

win_ratio: 0.48567842063220357

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_start|>', '</s>', '\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly\n{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{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-exp204-sft-gro-7278-v1-mkmlizer
Waiting for job on chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer to finish
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-gy-exp199-sft-ex_74653_v1: HTTPConnectionPool(host='chaiml-gy-exp199-sft-ex-74653-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: Downloaded to shared memory in 78.218s
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: Checking if ChaiML/gy-exp204-sft-grok-payloads-0705-only-wins-lastmsgloss-ep2 already exists in ChaiML
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7wf12_12, device:0
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: quantized model in 47.414s
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: Processed model ChaiML/gy-exp204-sft-grok-payloads-0705-only-wins-lastmsgloss-ep2 in 125.632s
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia/config.json
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia/special_tokens_map.json
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia/tokenizer_config.json
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia/tokenizer.json
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp204-sft-gro-7278-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.64it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.36it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.56it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.40it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.52it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.56it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.27it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 24.94it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.87it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.75it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.89it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.73it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.21it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.80it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.77it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.01it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.20it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.72it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.67it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.84it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.02it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.26it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.69it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.30it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.45it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.63it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.32it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.73it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.50it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.82it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.21it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.31it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.89it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 23.79it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 23.45it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:09, 22.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.57it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 24.39it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.17it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 26.99it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.26it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 25.13it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.72it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.75it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.20it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.20it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:00,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.88it/s]
Loading 0:  60%|█████▉    | 217/363 [00:22<00:38,  3.82it/s]
Loading 0:  61%|██████    | 220/363 [00:22<00:29,  4.85it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.38it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.85it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.14it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.76it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.04it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.70it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.92it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.16it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 30.82it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.74it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:03, 23.09it/s]
Loading 0:  76%|███████▌  | 275/363 [00:25<00:04, 19.21it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.62it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.59it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.19it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.29it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.88it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.85it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.78it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.95it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.31it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.09it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.22it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 27.06it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 26.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.51it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.40it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 20.88it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.58it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.14it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 22.86it/s]
                                                            
Job chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer completed after 158.41s with status: succeeded
Stopping job with name chaiml-gy-exp204-sft-gro-7278-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp204-sft-gro-7278-v1
Waiting for inference service chaiml-gy-exp204-sft-gro-7278-v1 to be ready
Failed to get response for submission chaiml-gy-exp169-sft-gy_40094_v2: HTTPConnectionPool(host='chaiml-gy-exp169-sft-gy-40094-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp199-sft-ex_74653_v1: HTTPConnectionPool(host='chaiml-gy-exp199-sft-ex-74653-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-gy-exp204-sft-gro-7278-v1 ready after 322.33149695396423s
Pipeline stage MKMLDeployer completed in 322.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5713188648223877s
Received healthy response to inference request in 1.897519588470459s
Received healthy response to inference request in 1.8192100524902344s
Received healthy response to inference request in 2.2787535190582275s
Received healthy response to inference request in 2.0973381996154785s
5 requests
0 failed requests
5th percentile: 1.8348719596862793
10th percentile: 1.8505338668823241
20th percentile: 1.881857681274414
30th percentile: 1.937483310699463
40th percentile: 2.0174107551574707
50th percentile: 2.0973381996154785
60th percentile: 2.169904327392578
70th percentile: 2.242470455169678
80th percentile: 2.3372665882110595
90th percentile: 2.454292726516724
95th percentile: 2.5128057956695558
99th percentile: 2.559616250991821
mean time: 2.1328280448913572
Pipeline stage StressChecker completed in 12.37s
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 0.71s
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 0.73s
Shutdown handler de-registered
chaiml-gy-exp204-sft-gro_7278_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 0.14s
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-exp204-sft-gro-7278-v1-profiler
Waiting for inference service chaiml-gy-exp204-sft-gro-7278-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 5492.36s
Shutdown handler de-registered
chaiml-gy-exp204-sft-gro_7278_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp204-sft-gro_7278_v1 status is now torndown due to DeploymentManager action