developer_uid: bogoconic1
submission_id: chaiml-gy-exp24-sft-gy-_36625_v5
model_name: chaiml-gy-exp24-sft-gy-_36625_v5
model_group: ChaiML/gy-exp24-sft-gy-d
status: torndown
timestamp: 2025-06-29T19:29:55+00:00
num_battles: 6437
num_wins: 3462
celo_rating: 1304.06
family_friendly_score: 0.5358
family_friendly_standard_error: 0.007052919395541112
submission_type: basic
model_repo: ChaiML/gy-exp24-sft-gy-datamix-v1-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': 0.6006151706558177, 'latency_mean': 1.6648337972164153, 'latency_p50': 1.6573309898376465, 'latency_p90': 1.8340673208236693}, {'batch_size': 3, 'throughput': 1.0731436794685125, 'latency_mean': 2.7896881890296936, 'latency_p50': 2.7987618446350098, 'latency_p90': 3.084209752082825}, {'batch_size': 5, 'throughput': 1.2902179826632219, 'latency_mean': 3.8545497918128966, 'latency_p50': 3.8435606956481934, 'latency_p90': 4.274110555648804}, {'batch_size': 6, 'throughput': 1.3490965826756447, 'latency_mean': 4.422566217184067, 'latency_p50': 4.399531006813049, 'latency_p90': 4.916351342201233}, {'batch_size': 8, 'throughput': 1.3992454940417354, 'latency_mean': 5.6819374001026155, 'latency_p50': 5.707382082939148, 'latency_p90': 6.384980654716491}, {'batch_size': 10, 'throughput': 1.4277378103328633, 'latency_mean': 6.954672058820725, 'latency_p50': 6.992345690727234, 'latency_p90': 7.812296581268311}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp24-sft-gy-_36625_v5
is_internal_developer: True
language_model: ChaiML/gy-exp24-sft-gy-datamix-v1-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-06-29
win_ratio: 0.537828180829579
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|>', '<|im_start|>', '\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-exp24-sft-gy-36625-v5-mkmlizer
Waiting for job on chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer to finish
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║                                                                     ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║                                                                     ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║                                                                     ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║                                                                     ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ║                                                                     ║
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: Downloaded to shared memory in 32.008s
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: Checking if ChaiML/gy-exp24-sft-gy-datamix-v1-ep2 already exists in ChaiML
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsxp0_33f, device:0
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: quantized model in 30.960s
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: Processed model ChaiML/gy-exp24-sft-gy-datamix-v1-ep2 in 62.969s
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp24-sft-gy-36625-v5
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp24-sft-gy-36625-v5/config.json
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp24-sft-gy-36625-v5/special_tokens_map.json
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp24-sft-gy-36625-v5/tokenizer_config.json
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp24-sft-gy-36625-v5/tokenizer.json
chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp24-sft-gy-36625-v5/flywheel_model.0.safetensors
Job chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer completed after 94.28s with status: succeeded
Stopping job with name chaiml-gy-exp24-sft-gy-36625-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp24-sft-gy-36625-v5
Waiting for inference service chaiml-gy-exp24-sft-gy-36625-v5 to be ready
Inference service chaiml-gy-exp24-sft-gy-36625-v5 ready after 191.0403492450714s
Pipeline stage MKMLDeployer completed in 191.65s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission nitral-ai-captain-bmo-12b_v75: HTTPConnectionPool(host='nitral-ai-captain-bmo-12b-v75-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.2139930725097656s
Received healthy response to inference request in 1.5472750663757324s
Received healthy response to inference request in 1.8113577365875244s
Received healthy response to inference request in 1.9198927879333496s
5 requests
1 failed requests
5th percentile: 1.6000916004180907
10th percentile: 1.6529081344604493
20th percentile: 1.758541202545166
30th percentile: 1.8330647468566894
40th percentile: 1.8764787673950196
50th percentile: 1.9198927879333496
60th percentile: 2.037532901763916
70th percentile: 2.155173015594482
80th percentile: 5.804020738601688
90th percentile: 12.984076070785523
95th percentile: 16.57410373687744
99th percentile: 19.446125869750976
mean time: 5.531330013275147
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6780152320861816s
Received healthy response to inference request in 1.8246486186981201s
Received healthy response to inference request in 1.891132116317749s
Received healthy response to inference request in 1.6569607257843018s
Received healthy response to inference request in 2.0410656929016113s
5 requests
0 failed requests
5th percentile: 1.6611716270446777
10th percentile: 1.6653825283050536
20th percentile: 1.6738043308258057
30th percentile: 1.7073419094085693
40th percentile: 1.7659952640533447
50th percentile: 1.8246486186981201
60th percentile: 1.8512420177459716
70th percentile: 1.8778354167938232
80th percentile: 1.9211188316345216
90th percentile: 1.9810922622680665
95th percentile: 2.011078977584839
99th percentile: 2.035068349838257
mean time: 1.8183644771575929
Pipeline stage StressChecker completed in 39.91s
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 0.69s
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-exp24-sft-gy-_36625_v5 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 0.10s
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-exp24-sft-gy-36625-v5-profiler
Waiting for inference service chaiml-gy-exp24-sft-gy-36625-v5-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3621.34s
Shutdown handler de-registered
chaiml-gy-exp24-sft-gy-_36625_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp24-sft-gy-_36625_v5 status is now torndown due to DeploymentManager action