developer_uid: bogoconic1
submission_id: chaiml-gy-exp48-sft-gy-_48800_v2
model_name: chaiml-gy-exp48-sft-gy-_48800_v2
model_group: ChaiML/gy-exp48-sft-gy-d
status: torndown
timestamp: 2025-07-01T12:44:08+00:00
num_battles: 10159
num_wins: 4042
celo_rating: 1215.52
family_friendly_score: 0.6788000000000001
family_friendly_standard_error: 0.006603492409324024
submission_type: basic
model_repo: ChaiML/gy-exp48-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen5x5-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': 0.5958491360153504, 'latency_mean': 1.6781615090370179, 'latency_p50': 1.6871867179870605, 'latency_p90': 1.847834587097168}, {'batch_size': 3, 'throughput': 1.0764133061552257, 'latency_mean': 2.7771406209468843, 'latency_p50': 2.7670321464538574, 'latency_p90': 3.066512608528137}, {'batch_size': 5, 'throughput': 1.2825777275977157, 'latency_mean': 3.8829556775093077, 'latency_p50': 3.8842382431030273, 'latency_p90': 4.390646171569824}, {'batch_size': 6, 'throughput': 1.3507275931363112, 'latency_mean': 4.413765568733215, 'latency_p50': 4.4333168268203735, 'latency_p90': 4.938148641586304}, {'batch_size': 8, 'throughput': 1.408818322320631, 'latency_mean': 5.642527829408646, 'latency_p50': 5.616487145423889, 'latency_p90': 6.331105852127075}, {'batch_size': 10, 'throughput': 1.4434104343239982, 'latency_mean': 6.877725278139114, 'latency_p50': 6.871322512626648, 'latency_p90': 7.7100026845932}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp48-sft-gy-_48800_v2
is_internal_developer: True
language_model: ChaiML/gy-exp48-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen5x5-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-07-01
win_ratio: 0.3978738064770155
generation_params: {'temperature': 0.001, '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-exp48-sft-gy-48800-v2-mkmlizer
Waiting for job on chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer to finish
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ Version: 0.29.3 ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ belonging to: ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ║ ║
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: Downloaded to shared memory in 28.850s
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: Checking if ChaiML/gy-exp48-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen5x5-ep2 already exists in ChaiML
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4n2wc27h, device:0
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: quantized model in 32.018s
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: Processed model ChaiML/gy-exp48-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen5x5-ep2 in 60.869s
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp48-sft-gy-48800-v2
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp48-sft-gy-48800-v2/config.json
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp48-sft-gy-48800-v2/special_tokens_map.json
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp48-sft-gy-48800-v2/tokenizer_config.json
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp48-sft-gy-48800-v2/tokenizer.json
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp48-sft-gy-48800-v2/flywheel_model.0.safetensors
chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.78it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:09, 37.37it/s] Loading 0: 4%|▍ | 15/363 [00:00<00:10, 34.76it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:08, 40.17it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:08, 38.43it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:08, 37.14it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 35.77it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 38.15it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:08, 36.02it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 38.25it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:08, 36.52it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:08, 35.32it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:08, 35.87it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 20.38it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:11, 25.49it/s] Loading 0: 20%|██ | 73/363 [00:02<00:11, 25.59it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:09, 30.30it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:09, 29.50it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:08, 34.03it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 31.84it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 39.40it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:06, 39.35it/s] Loading 0: 30%|██▉ | 108/363 [00:03<00:06, 41.65it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 34.88it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 35.89it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 43.17it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 42.90it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 42.21it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 43.98it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 26.79it/s] Loading 0: 41%|████ | 149/363 [00:04<00:07, 27.43it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 34.24it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 33.83it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 33.68it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 33.01it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 35.10it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 33.55it/s] Loading 0: 50%|█████ | 182/363 [00:05<00:05, 34.96it/s] Loading 0: 51%|█████ | 186/363 [00:05<00:05, 31.81it/s] Loading 0: 52%|█████▏ | 190/363 [00:05<00:05, 33.23it/s] Loading 0: 53%|█████▎ | 194/363 [00:05<00:05, 29.61it/s] Loading 0: 55%|█████▍ | 199/363 [00:05<00:04, 33.74it/s] Loading 0: 56%|█████▌ | 203/363 [00:06<00:05, 31.34it/s] Loading 0: 57%|█████▋ | 208/363 [00:06<00:04, 34.91it/s] Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 31.74it/s] Loading 0: 60%|█████▉ | 217/363 [00:06<00:04, 35.95it/s] Loading 0: 61%|██████ | 222/363 [00:06<00:04, 35.13it/s] Loading 0: 62%|██████▏ | 226/363 [00:06<00:06, 21.69it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:05, 22.27it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 26.66it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 25.76it/s] Loading 0: 67%|██████▋ | 244/363 [00:07<00:04, 29.58it/s] Loading 0: 68%|██████▊ | 248/363 [00:07<00:04, 27.00it/s] Loading 0: 70%|██████▉ | 253/363 [00:07<00:03, 31.60it/s] Loading 0: 71%|███████ | 257/363 [00:07<00:03, 30.23it/s] Loading 0: 72%|███████▏ | 262/363 [00:08<00:02, 33.96it/s] Loading 0: 73%|███████▎ | 266/363 [00:08<00:03, 31.26it/s] Loading 0: 75%|███████▍ | 271/363 [00:08<00:02, 35.01it/s] Loading 0: 76%|███████▌ | 275/363 [00:08<00:02, 30.42it/s] Loading 0: 77%|███████▋ | 280/363 [00:08<00:02, 34.11it/s] Loading 0: 78%|███████▊ | 284/363 [00:08<00:02, 31.38it/s] Loading 0: 80%|███████▉ | 289/363 [00:08<00:02, 35.29it/s] Loading 0: 81%|████████ | 293/363 [00:08<00:02, 32.65it/s] Loading 0: 82%|████████▏ | 299/363 [00:09<00:01, 37.40it/s] Loading 0: 84%|████████▎ | 304/363 [00:09<00:02, 21.70it/s] Loading 0: 85%|████████▍ | 308/363 [00:09<00:02, 24.40it/s] Loading 0: 86%|████████▌ | 312/363 [00:09<00:02, 24.95it/s] Loading 0: 88%|████████▊ | 320/363 [00:09<00:01, 34.49it/s] Loading 0: 90%|████████▉ | 326/363 [00:10<00:01, 35.80it/s] Loading 0: 91%|█████████ | 331/363 [00:10<00:00, 36.96it/s] Loading 0: 93%|█████████▎| 337/363 [00:10<00:00, 42.12it/s] Loading 0: 94%|█████████▍| 342/363 [00:10<00:00, 41.73it/s] Loading 0: 96%|█████████▌| 347/363 [00:10<00:00, 42.75it/s] Loading 0: 97%|█████████▋| 352/363 [00:10<00:00, 44.53it/s] Loading 0: 98%|█████████▊| 357/363 [00:10<00:00, 37.48it/s]
Job chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer completed after 96.45s with status: succeeded
Stopping job with name chaiml-gy-exp48-sft-gy-48800-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.07s
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-exp48-sft-gy-48800-v2
Waiting for inference service chaiml-gy-exp48-sft-gy-48800-v2 to be ready
Inference service chaiml-gy-exp48-sft-gy-48800-v2 ready after 211.63302779197693s
Pipeline stage MKMLDeployer completed in 212.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8677213191986084s
Received healthy response to inference request in 1.5932540893554688s
Received healthy response to inference request in 1.3537850379943848s
Received healthy response to inference request in 1.4285333156585693s
Received healthy response to inference request in 1.2511577606201172s
5 requests
0 failed requests
5th percentile: 1.2716832160949707
10th percentile: 1.2922086715698242
20th percentile: 1.3332595825195312
30th percentile: 1.3687346935272218
40th percentile: 1.3986340045928956
50th percentile: 1.4285333156585693
60th percentile: 1.494421625137329
70th percentile: 1.560309934616089
80th percentile: 1.6481475353240966
90th percentile: 1.7579344272613526
95th percentile: 1.8128278732299805
99th percentile: 1.8567426300048828
mean time: 1.4988903045654296
Pipeline stage StressChecker completed in 9.13s
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 0.73s
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 1.11s
Shutdown handler de-registered
chaiml-gy-exp48-sft-gy-_48800_v2 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp48-sft-gy-48800-v2-profiler
Waiting for inference service chaiml-gy-exp48-sft-gy-48800-v2-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 4285.07s
Shutdown handler de-registered
chaiml-gy-exp48-sft-gy-_48800_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp48-sft-gy-_48800_v2 status is now torndown due to DeploymentManager action