developer_uid: bogoconic1
submission_id: chaiml-gy-exp35-sftlora-_2298_v7
model_name: chaiml-gy-exp35-sftlora-_2298_v7
model_group: ChaiML/gy-exp35-sftlora-
status: torndown
timestamp: 2025-07-01T20:24:18+00:00
num_battles: 8401
num_wins: 4302
celo_rating: 1299.41
family_friendly_score: 0.5178
family_friendly_standard_error: 0.007066585597019256
submission_type: basic
model_repo: ChaiML/gy-exp35-sftlora-exp32ep8stg2-gy-exp24payloads-grok-v2prompt-ep6
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5252522196157019, 'latency_mean': 1.9037206482887268, 'latency_p50': 1.8787286281585693, 'latency_p90': 2.1293691635131835}, {'batch_size': 3, 'throughput': 1.050582157544126, 'latency_mean': 2.8479900300502776, 'latency_p50': 2.857902765274048, 'latency_p90': 3.0996257066726685}, {'batch_size': 5, 'throughput': 1.3218815860058373, 'latency_mean': 3.7627965092658995, 'latency_p50': 3.7927606105804443, 'latency_p90': 4.194911551475525}, {'batch_size': 6, 'throughput': 1.4256651262515205, 'latency_mean': 4.162221287488937, 'latency_p50': 4.173010468482971, 'latency_p90': 4.61587290763855}, {'batch_size': 8, 'throughput': 1.5477209776832246, 'latency_mean': 5.129012678861618, 'latency_p50': 5.1430089473724365, 'latency_p90': 5.74445481300354}, {'batch_size': 10, 'throughput': 1.6436842490310661, 'latency_mean': 6.011959493160248, 'latency_p50': 5.9922791719436646, 'latency_p90': 6.7335162401199335}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp35-sftlora-_2298_v7
is_internal_developer: True
language_model: ChaiML/gy-exp35-sftlora-exp32ep8stg2-gy-exp24payloads-grok-v2prompt-ep6
model_size: 24B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-07-01
win_ratio: 0.5120818950124986
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|>', '\n', '<|im_end|>'], '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-exp35-sftlora-2298-v7-mkmlizer
Waiting for job on chaiml-gy-exp35-sftlora-2298-v7-mkmlizer to finish
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: Downloaded to shared memory in 53.363s
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: Checking if ChaiML/gy-exp35-sftlora-exp32ep8stg2-gy-exp24payloads-grok-v2prompt-ep6 already exists in ChaiML
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuhu6nwb3, device:0
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: quantized model in 49.703s
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: Processed model ChaiML/gy-exp35-sftlora-exp32ep8stg2-gy-exp24payloads-grok-v2prompt-ep6 in 103.067s
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7/config.json
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7/special_tokens_map.json
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7/tokenizer_config.json
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7/tokenizer.json
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7/flywheel_model.1.safetensors
chaiml-gy-exp35-sftlora-2298-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp35-sftlora-2298-v7/flywheel_model.0.safetensors
Job chaiml-gy-exp35-sftlora-2298-v7-mkmlizer completed after 136.11s with status: succeeded
Stopping job with name chaiml-gy-exp35-sftlora-2298-v7-mkmlizer
Pipeline stage MKMLizer completed in 136.68s
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-exp35-sftlora-2298-v7
Waiting for inference service chaiml-gy-exp35-sftlora-2298-v7 to be ready
Inference service chaiml-gy-exp35-sftlora-2298-v7 ready after 210.88870191574097s
Pipeline stage MKMLDeployer completed in 211.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.799539804458618s
Received healthy response to inference request in 2.2217042446136475s
Received healthy response to inference request in 1.9507639408111572s
Received healthy response to inference request in 1.8934414386749268s
Received healthy response to inference request in 2.063917398452759s
5 requests
0 failed requests
5th percentile: 1.9049059391021728
10th percentile: 1.916370439529419
20th percentile: 1.9392994403839112
30th percentile: 1.9733946323394775
40th percentile: 2.018656015396118
50th percentile: 2.063917398452759
60th percentile: 2.1270321369171143
70th percentile: 2.19014687538147
80th percentile: 2.3372713565826415
90th percentile: 2.56840558052063
95th percentile: 2.683972692489624
99th percentile: 2.776426382064819
mean time: 2.1858733654022218
Pipeline stage StressChecker completed in 12.46s
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 1.05s
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 0.72s
Shutdown handler de-registered
chaiml-gy-exp35-sftlora-_2298_v7 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp35-sftlora-2298-v7-profiler
Waiting for inference service chaiml-gy-exp35-sftlora-2298-v7-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 5268.69s
Shutdown handler de-registered
chaiml-gy-exp35-sftlora-_2298_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp35-sftlora-_2298_v7 status is now torndown due to DeploymentManager action