developer_uid: NischayDnk
submission_id: chaiml-nis-qwen32b-simp_98336_v1
model_name: chaiml-nis-qwen32b-simp_98336_v1
model_group: ChaiML/nis-qwen32b-simpo
status: torndown
timestamp: 2025-04-20T14:11:34+00:00
num_battles: 8822
num_wins: 5064
celo_rating: 1342.55
family_friendly_score: 0.4788
family_friendly_standard_error: 0.007064708911200801
submission_type: basic
model_repo: ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32759331840.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.27401419634035346, 'latency_mean': 3.649381353855133, 'latency_p50': 3.6504961252212524, 'latency_p90': 4.069753503799438}, {'batch_size': 2, 'throughput': 0.44377473761025, 'latency_mean': 4.497517385482788, 'latency_p50': 4.531090974807739, 'latency_p90': 4.910297083854675}, {'batch_size': 3, 'throughput': 0.5971914283202553, 'latency_mean': 4.995678346157074, 'latency_p50': 4.970466375350952, 'latency_p90': 5.578794169425964}, {'batch_size': 4, 'throughput': 0.7101056295718969, 'latency_mean': 5.6199660646915435, 'latency_p50': 5.561436891555786, 'latency_p90': 6.3777398586273195}, {'batch_size': 5, 'throughput': 0.7911492561187687, 'latency_mean': 6.280938729047775, 'latency_p50': 6.316884875297546, 'latency_p90': 6.892314147949219}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-nis-qwen32b-simp_98336_v1
is_internal_developer: False
language_model: ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2
model_size: 33B
ranking_group: single
throughput_3p7s: 0.29
us_pacific_date: 2025-04-20
win_ratio: 0.5740194967127635
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], 'max_input_tokens': 768, 'best_of': 5, '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-nis-qwen32b-simp-98336-v1-mkmlizer
Waiting for job on chaiml-nis-qwen32b-simp-98336-v1-mkmlizer to finish
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ _____ __ __ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ /___/ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ belonging to: ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: Downloaded to shared memory in 104.896s
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptynf7qn0, device:0
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: quantized model in 63.351s
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: Processed model ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2 in 168.248s
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/config.json
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/tokenizer_config.json
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/added_tokens.json
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/special_tokens_map.json
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/merges.txt
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/tokenizer.json
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/vocab.json
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/flywheel_model.2.safetensors
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/flywheel_model.1.safetensors
chaiml-nis-qwen32b-simp-98336-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v1/flywheel_model.0.safetensors
Job chaiml-nis-qwen32b-simp-98336-v1-mkmlizer completed after 207.18s with status: succeeded
Stopping job with name chaiml-nis-qwen32b-simp-98336-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-qwen32b-simp-98336-v1
Waiting for inference service chaiml-nis-qwen32b-simp-98336-v1 to be ready
Inference service chaiml-nis-qwen32b-simp-98336-v1 ready after 130.48295211791992s
Pipeline stage MKMLDeployer completed in 130.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.877685070037842s
Received healthy response to inference request in 3.295630693435669s
Received healthy response to inference request in 3.2368407249450684s
Received healthy response to inference request in 3.606196641921997s
Received healthy response to inference request in 3.5653042793273926s
5 requests
0 failed requests
5th percentile: 3.2485987186431884
10th percentile: 3.2603567123413084
20th percentile: 3.283872699737549
30th percentile: 3.3495654106140136
40th percentile: 3.4574348449707033
50th percentile: 3.5653042793273926
60th percentile: 3.5816612243652344
70th percentile: 3.598018169403076
80th percentile: 3.660494327545166
90th percentile: 3.769089698791504
95th percentile: 3.823387384414673
99th percentile: 3.866825532913208
mean time: 3.5163314819335936
Pipeline stage StressChecker completed in 18.89s
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 0.66s
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 0.70s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_98336_v1 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-nis-qwen32b-simp-98336-v1-profiler
Waiting for inference service chaiml-nis-qwen32b-simp-98336-v1-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 6773.28s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_98336_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-qwen32b-simp_98336_v1 status is now torndown due to DeploymentManager action