developer_uid: bogoconic1
submission_id: chaiml-gy-exp126-dpo-e_77990_v13
model_name: chaiml-gy-exp126-dpo-e_77990_v13
model_group: ChaiML/gy-exp126-dpo-exp
status: torndown
timestamp: 2025-07-11T13:54:56+00:00
num_battles: 7380
num_wins: 3535
celo_rating: 1276.57
family_friendly_score: 0.5302
family_friendly_standard_error: 0.007058157833315999
submission_type: basic
model_repo: ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5641018005653549, 'latency_mean': 1.7726346611976624, 'latency_p50': 1.7693572044372559, 'latency_p90': 1.9673017978668212}, {'batch_size': 4, 'throughput': 1.4700203749543395, 'latency_mean': 2.7075632286071776, 'latency_p50': 2.6822378635406494, 'latency_p90': 3.06830780506134}, {'batch_size': 5, 'throughput': 1.6766613196213431, 'latency_mean': 2.964667890071869, 'latency_p50': 2.953316807746887, 'latency_p90': 3.2711735725402833}, {'batch_size': 8, 'throughput': 2.139043263923036, 'latency_mean': 3.7170294713974, 'latency_p50': 3.716976284980774, 'latency_p90': 4.146100473403931}, {'batch_size': 10, 'throughput': 2.3599764534858187, 'latency_mean': 4.200344529151916, 'latency_p50': 4.164614796638489, 'latency_p90': 4.72825288772583}, {'batch_size': 12, 'throughput': 2.5093762142879243, 'latency_mean': 4.740378011465072, 'latency_p50': 4.727176666259766, 'latency_p90': 5.3837052345275875}, {'batch_size': 15, 'throughput': 2.680669141751355, 'latency_mean': 5.519042203426361, 'latency_p50': 5.5239337682724, 'latency_p90': 6.22941517829895}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp126-dpo-e_77990_v13
is_internal_developer: False
language_model: ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2
model_size: 24B
ranking_group: single
throughput_3p7s: 2.14
us_pacific_date: 2025-07-11
win_ratio: 0.47899728997289975
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_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 1024, 'best_of': 1, '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-exp126-dpo-e-77990-v13-mkmlizer
Waiting for job on chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer to finish
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: Downloaded to shared memory in 54.467s
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: Checking if ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2 already exists in ChaiML
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy7_rs6l4, device:0
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: quantized model in 48.474s
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: Processed model ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2 in 102.942s
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia/config.json
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia/special_tokens_map.json
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia/tokenizer_config.json
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia/tokenizer.json
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v13/nvidia/flywheel_model.0.safetensors
Job chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer completed after 136.5s with status: succeeded
Stopping job with name chaiml-gy-exp126-dpo-e-77990-v13-mkmlizer
Pipeline stage MKMLizer completed in 137.00s
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-exp126-dpo-e-77990-v13
Waiting for inference service chaiml-gy-exp126-dpo-e-77990-v13 to be ready
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7c61bc695410>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-gy-exp126-dpo-e-77990-v13 ready after 210.92397952079773s
Pipeline stage MKMLDeployer completed in 211.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4508705139160156s
Received healthy response to inference request in 1.815887451171875s
Received healthy response to inference request in 1.7622790336608887s
Received healthy response to inference request in 1.6390142440795898s
Received healthy response to inference request in 1.577446699142456s
5 requests
0 failed requests
5th percentile: 1.5897602081298827
10th percentile: 1.6020737171173096
20th percentile: 1.6267007350921632
30th percentile: 1.6636672019958496
40th percentile: 1.7129731178283691
50th percentile: 1.7622790336608887
60th percentile: 1.7837224006652832
70th percentile: 1.8051657676696777
80th percentile: 1.9428840637207032
90th percentile: 2.196877288818359
95th percentile: 2.3238739013671874
99th percentile: 2.42547119140625
mean time: 1.849099588394165
Pipeline stage StressChecker completed in 11.06s
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 1.04s
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 0.79s
Shutdown handler de-registered
chaiml-gy-exp126-dpo-e_77990_v13 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 0.13s
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-exp126-dpo-e-77990-v13-profiler
Waiting for inference service chaiml-gy-exp126-dpo-e-77990-v13-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 2599.14s
Shutdown handler de-registered
chaiml-gy-exp126-dpo-e_77990_v13 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp126-dpo-e_77990_v13 status is now torndown due to DeploymentManager action