developer_uid: bogoconic1
submission_id: chaiml-gy-exp178-nemo12_98026_v2
model_name: chaiml-gy-exp178-nemo12_98026_v2
model_group: ChaiML/gy-exp178-Nemo12B
status: torndown
timestamp: 2025-07-17T10:31:26+00:00
num_battles: 5733
num_wins: 2958
celo_rating: 1280.54
family_friendly_score: 0.5342
family_friendly_standard_error: 0.007054507211705152
submission_type: basic
model_repo: ChaiML/gy-exp178-Nemo12B-sft-gy-datamix-v1-Grok-AR-cosine-ep3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5884541018374109, 'latency_mean': 1.6992544686794282, 'latency_p50': 1.7017415761947632, 'latency_p90': 1.8833457469940185}, {'batch_size': 3, 'throughput': 1.0429591564996605, 'latency_mean': 2.864882526397705, 'latency_p50': 2.8629738092422485, 'latency_p90': 3.178068923950195}, {'batch_size': 5, 'throughput': 1.2369297680098748, 'latency_mean': 4.027974919080735, 'latency_p50': 4.060402154922485, 'latency_p90': 4.521650695800782}, {'batch_size': 6, 'throughput': 1.3176643940074597, 'latency_mean': 4.534686255455017, 'latency_p50': 4.545255661010742, 'latency_p90': 5.055083632469177}, {'batch_size': 8, 'throughput': 1.3592866515308397, 'latency_mean': 5.851465032100678, 'latency_p50': 5.834164619445801, 'latency_p90': 6.570833992958069}, {'batch_size': 10, 'throughput': 1.3926167744433473, 'latency_mean': 7.117750508785248, 'latency_p50': 7.133987903594971, 'latency_p90': 8.047200393676757}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp178-nemo12_98026_v2
is_internal_developer: False
language_model: ChaiML/gy-exp178-Nemo12B-sft-gy-datamix-v1-Grok-AR-cosine-ep3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.2
us_pacific_date: 2025-07-17
win_ratio: 0.5159602302459445
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': 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-exp178-nemo12-98026-v2-mkmlizer
Waiting for job on chaiml-gy-exp178-nemo12-98026-v2-mkmlizer to finish
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ belonging to: ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ║ ║
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: Downloaded to shared memory in 31.903s
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: Checking if ChaiML/gy-exp178-Nemo12B-sft-gy-datamix-v1-Grok-AR-cosine-ep3 already exists in ChaiML
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9dhl7tkk, device:0
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission junhua024-chai-06-full-_16215_v4: HTTPConnectionPool(host='junhua024-chai-06-full-16215-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp178-nemo12-98026-v2/nvidia
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp178-nemo12-98026-v2/nvidia/config.json
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp178-nemo12-98026-v2/nvidia/special_tokens_map.json
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp178-nemo12-98026-v2/nvidia/tokenizer_config.json
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp178-nemo12-98026-v2/nvidia/tokenizer.json
chaiml-gy-exp178-nemo12-98026-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp178-nemo12-98026-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-gy-exp178-nemo12-98026-v2-mkmlizer completed after 96.11s with status: succeeded
Stopping job with name chaiml-gy-exp178-nemo12-98026-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp178-nemo12-98026-v2
Waiting for inference service chaiml-gy-exp178-nemo12-98026-v2 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service chaiml-gy-exp178-nemo12-98026-v2 ready after 302.23692083358765s
Pipeline stage MKMLDeployer completed in 303.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.465115785598755s
Received healthy response to inference request in 1.6704809665679932s
Received healthy response to inference request in 1.8739354610443115s
Received healthy response to inference request in 1.8517374992370605s
Received healthy response to inference request in 1.7730746269226074s
5 requests
0 failed requests
5th percentile: 1.690999698638916
10th percentile: 1.7115184307098388
20th percentile: 1.7525558948516846
30th percentile: 1.788807201385498
40th percentile: 1.8202723503112792
50th percentile: 1.8517374992370605
60th percentile: 1.860616683959961
70th percentile: 1.8694958686828613
80th percentile: 1.9921715259552002
90th percentile: 2.2286436557769775
95th percentile: 2.346879720687866
99th percentile: 2.4414685726165772
mean time: 1.9268688678741455
Pipeline stage StressChecker completed in 12.68s
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 1.63s
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 1.30s
Shutdown handler de-registered
chaiml-gy-exp178-nemo12_98026_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp178-nemo12-98026-v2-profiler
Waiting for inference service chaiml-gy-exp178-nemo12-98026-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3153.96s
Shutdown handler de-registered
chaiml-gy-exp178-nemo12_98026_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp178-nemo12_98026_v2 status is now torndown due to DeploymentManager action
chaiml-gy-exp178-nemo12_98026_v2 status is now torndown due to DeploymentManager action