developer_uid: NischayDnk
submission_id: chaiml-qwen-32b-sft-exp_26164_v1
model_name: chaiml-qwen-32b-sft-exp_26164_v1
model_group: ChaiML/qwen-32b-sft-exp2
status: torndown
timestamp: 2025-04-25T19:33:55+00:00
num_battles: 9355
num_wins: 4340
celo_rating: 1263.16
family_friendly_score: 0.5813999999999999
family_friendly_standard_error: 0.006976733333014814
submission_type: basic
model_repo: ChaiML/qwen-32b-sft-exp2-retrysftdata-top3klexical
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3884201811217052, 'latency_mean': 2.5744660222530364, 'latency_p50': 2.577761173248291, 'latency_p90': 2.8915477752685548}, {'batch_size': 3, 'throughput': 0.8645360661504696, 'latency_mean': 3.4485162234306337, 'latency_p50': 3.4776015281677246, 'latency_p90': 3.799280786514282}, {'batch_size': 5, 'throughput': 1.193114004969648, 'latency_mean': 4.163745577335358, 'latency_p50': 4.178347706794739, 'latency_p90': 4.621453142166137}, {'batch_size': 6, 'throughput': 1.2938281915390029, 'latency_mean': 4.606281076669693, 'latency_p50': 4.5719895362854, 'latency_p90': 5.162402582168579}, {'batch_size': 8, 'throughput': 1.4863659472174602, 'latency_mean': 5.324163924455643, 'latency_p50': 5.280231952667236, 'latency_p90': 6.147394967079163}, {'batch_size': 10, 'throughput': 1.603102430421248, 'latency_mean': 6.174277037382126, 'latency_p50': 6.15401029586792, 'latency_p90': 6.962905859947204}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen-32b-sft-exp_26164_v1
is_internal_developer: False
language_model: ChaiML/qwen-32b-sft-exp2-retrysftdata-top3klexical
model_size: 33B
ranking_group: single
throughput_3p7s: 1.0
us_pacific_date: 2025-04-25
win_ratio: 0.46392303580972744
generation_params: {'temperature': 0.45, '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': 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-qwen-32b-sft-exp-26164-v1-mkmlizer
Waiting for job on chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer to finish
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ /___/ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: Downloaded to shared memory in 116.577s
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9y68_nfe, device:0
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: quantized model in 63.209s
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: Processed model ChaiML/qwen-32b-sft-exp2-retrysftdata-top3klexical in 179.787s
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/config.json
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/added_tokens.json
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/special_tokens_map.json
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/tokenizer_config.json
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/merges.txt
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/vocab.json
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/tokenizer.json
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/flywheel_model.2.safetensors
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/flywheel_model.1.safetensors
chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-26164-v1/flywheel_model.0.safetensors
Job chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer completed after 217.85s with status: succeeded
Stopping job with name chaiml-qwen-32b-sft-exp-26164-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen-32b-sft-exp-26164-v1
Waiting for inference service chaiml-qwen-32b-sft-exp-26164-v1 to be ready
Inference service chaiml-qwen-32b-sft-exp-26164-v1 ready after 251.0779573917389s
Pipeline stage MKMLDeployer completed in 251.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0862436294555664s
Received healthy response to inference request in 2.8354063034057617s
Received healthy response to inference request in 2.6706533432006836s
Received healthy response to inference request in 3.035629987716675s
Received healthy response to inference request in 2.5710062980651855s
5 requests
0 failed requests
5th percentile: 2.590935707092285
10th percentile: 2.6108651161193848
20th percentile: 2.650723934173584
30th percentile: 2.7036039352416994
40th percentile: 2.7695051193237306
50th percentile: 2.8354063034057617
60th percentile: 2.915495777130127
70th percentile: 2.995585250854492
80th percentile: 3.0457527160644533
90th percentile: 3.06599817276001
95th percentile: 3.076120901107788
99th percentile: 3.0842190837860106
mean time: 2.8397879123687746
Pipeline stage StressChecker completed in 15.51s
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 0.70s
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 0.74s
Shutdown handler de-registered
chaiml-qwen-32b-sft-exp_26164_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 0.11s
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-qwen-32b-sft-exp-26164-v1-profiler
Waiting for inference service chaiml-qwen-32b-sft-exp-26164-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 5236.08s
Shutdown handler de-registered
chaiml-qwen-32b-sft-exp_26164_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen-32b-sft-exp_26164_v1 status is now torndown due to DeploymentManager action