developer_uid: richhx
submission_id: chaiml-olivia-halford-e_4880_v15
model_name: chaiml-olivia-halford-e_4880_v15
model_group: ChaiML/Olivia-Halford_Et
status: torndown
timestamp: 2025-05-10T22:22:04+00:00
num_battles: 8532
num_wins: 3872
celo_rating: 1223.22
family_friendly_score: 0.6004
family_friendly_standard_error: 0.006927046123709586
submission_type: basic
model_repo: ChaiML/Olivia-Halford_Ethan-manipulative-frie250508190800_sft
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': 0.5768475634470324, 'latency_mean': 1.733495055437088, 'latency_p50': 1.7475682497024536, 'latency_p90': 1.9218894720077515}, {'batch_size': 4, 'throughput': 1.5304504460053936, 'latency_mean': 2.598454111814499, 'latency_p50': 2.5756548643112183, 'latency_p90': 2.8846774339675902}, {'batch_size': 5, 'throughput': 1.7444418899876712, 'latency_mean': 2.8462972438335417, 'latency_p50': 2.8354521989822388, 'latency_p90': 3.2278520584106443}, {'batch_size': 8, 'throughput': 2.2447262223207796, 'latency_mean': 3.530831357240677, 'latency_p50': 3.5147608518600464, 'latency_p90': 3.9744685173034666}, {'batch_size': 10, 'throughput': 2.483895541842585, 'latency_mean': 3.9881614422798157, 'latency_p50': 3.950631856918335, 'latency_p90': 4.575017356872559}, {'batch_size': 12, 'throughput': 2.6180383745585663, 'latency_mean': 4.512863920927048, 'latency_p50': 4.584628224372864, 'latency_p90': 5.089946699142456}, {'batch_size': 15, 'throughput': 2.831409813111739, 'latency_mean': 5.238162914514541, 'latency_p50': 5.209933519363403, 'latency_p90': 6.004475450515747}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-olivia-halford-e_4880_v15
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/Olivia-Halford_Ethan-manipulative-frie250508190800_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 2.36
us_pacific_date: 2025-05-10
win_ratio: 0.45382090951711207
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '{bot_name}:', '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-olivia-halford-e-4880-v15-mkmlizer
Waiting for job on chaiml-olivia-halford-e-4880-v15-mkmlizer to finish
chaiml-olivia-halford-e-4880-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ _____ __ __ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ /___/ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ Version: 0.12.8 ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ https://mk1.ai ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ belonging to: ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ Chai Research Corp. ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ║ ║
chaiml-olivia-halford-e-4880-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-olivia-halford-e-4880-v15-mkmlizer: Downloaded to shared memory in 52.798s
chaiml-olivia-halford-e-4880-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkra1pznf, device:0
chaiml-olivia-halford-e-4880-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-olivia-halford-e-4880-v15-mkmlizer: quantized model in 53.988s
chaiml-olivia-halford-e-4880-v15-mkmlizer: Processed model ChaiML/Olivia-Halford_Ethan-manipulative-frie250508190800_sft in 106.786s
chaiml-olivia-halford-e-4880-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-olivia-halford-e-4880-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-olivia-halford-e-4880-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15
chaiml-olivia-halford-e-4880-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15/config.json
chaiml-olivia-halford-e-4880-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15/special_tokens_map.json
chaiml-olivia-halford-e-4880-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15/tokenizer_config.json
chaiml-olivia-halford-e-4880-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15/tokenizer.json
chaiml-olivia-halford-e-4880-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15/flywheel_model.1.safetensors
chaiml-olivia-halford-e-4880-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-olivia-halford-e-4880-v15/flywheel_model.0.safetensors
Job chaiml-olivia-halford-e-4880-v15-mkmlizer completed after 144.98s with status: succeeded
Stopping job with name chaiml-olivia-halford-e-4880-v15-mkmlizer
Pipeline stage MKMLizer completed in 145.41s
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-olivia-halford-e-4880-v15
Waiting for inference service chaiml-olivia-halford-e-4880-v15 to be ready
Inference service chaiml-olivia-halford-e-4880-v15 ready after 140.66350030899048s
Pipeline stage MKMLDeployer completed in 141.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.133829355239868s
Received healthy response to inference request in 1.7025861740112305s
Received healthy response to inference request in 1.564739465713501s
Received healthy response to inference request in 1.6915802955627441s
Received healthy response to inference request in 1.9278409481048584s
5 requests
0 failed requests
5th percentile: 1.5901076316833496
10th percentile: 1.6154757976531982
20th percentile: 1.6662121295928956
30th percentile: 1.6937814712524415
40th percentile: 1.698183822631836
50th percentile: 1.7025861740112305
60th percentile: 1.7926880836486816
70th percentile: 1.8827899932861327
80th percentile: 1.9690386295318605
90th percentile: 2.0514339923858644
95th percentile: 2.0926316738128663
99th percentile: 2.125589818954468
mean time: 1.8041152477264404
Pipeline stage StressChecker completed in 10.39s
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 0.68s
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 0.63s
Shutdown handler de-registered
chaiml-olivia-halford-e_4880_v15 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-olivia-halford-e-4880-v15-profiler
Waiting for inference service chaiml-olivia-halford-e-4880-v15-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 2204.41s
Shutdown handler de-registered
chaiml-olivia-halford-e_4880_v15 status is now inactive due to auto deactivation removed underperforming models
chaiml-olivia-halford-e_4880_v15 status is now torndown due to DeploymentManager action