developer_uid: NischayDnk
submission_id: chaiml-qwen32b-sft-exp1_16150_v3
model_name: chaiml-qwen32b-sft-exp1_16150_v3
model_group: ChaiML/qwen32b-sft-exp1-
status: torndown
timestamp: 2025-04-14T03:18:55+00:00
num_battles: 8147
num_wins: 3193
celo_rating: 1206.24
family_friendly_score: 0.5811999999999999
family_friendly_standard_error: 0.006977199438170017
submission_type: basic
model_repo: ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.30141961720345906, 'latency_mean': 3.317527838945389, 'latency_p50': 3.304973006248474, 'latency_p90': 3.7205163717269896}, {'batch_size': 3, 'throughput': 0.7123726296726918, 'latency_mean': 4.196916482448578, 'latency_p50': 4.216786742210388, 'latency_p90': 4.685329699516297}, {'batch_size': 5, 'throughput': 1.0368043707119796, 'latency_mean': 4.797156586647033, 'latency_p50': 4.7782286405563354, 'latency_p90': 5.286436533927917}, {'batch_size': 6, 'throughput': 1.173934968436621, 'latency_mean': 5.06404153585434, 'latency_p50': 5.072638034820557, 'latency_p90': 5.682856488227844}, {'batch_size': 10, 'throughput': 1.5711559757173754, 'latency_mean': 6.293552052974701, 'latency_p50': 6.260523557662964, 'latency_p90': 7.088327693939209}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen32b-sft-exp1_16150_v3
is_internal_developer: False
language_model: ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k
model_size: 33B
ranking_group: single
throughput_3p7s: 0.51
us_pacific_date: 2025-04-13
win_ratio: 0.39192340738922304
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '', '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-qwen32b-sft-exp1-16150-v3-mkmlizer
Waiting for job on chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer to finish
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ /___/ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: Downloaded to shared memory in 92.239s
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6ghbujih, device:0
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: quantized model in 63.668s
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: Processed model ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k in 155.908s
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/config.json
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/added_tokens.json
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/special_tokens_map.json
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/tokenizer_config.json
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/merges.txt
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/vocab.json
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/tokenizer.json
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/flywheel_model.2.safetensors
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/flywheel_model.1.safetensors
chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v3/flywheel_model.0.safetensors
Job chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer completed after 198.37s with status: succeeded
Stopping job with name chaiml-qwen32b-sft-exp1-16150-v3-mkmlizer
Pipeline stage MKMLizer completed in 198.88s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.43s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32b-sft-exp1-16150-v3
Waiting for inference service chaiml-qwen32b-sft-exp1-16150-v3 to be ready
Inference service chaiml-qwen32b-sft-exp1-16150-v3 ready after 120.75542426109314s
Pipeline stage MKMLDeployer completed in 121.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.554729700088501s
Received healthy response to inference request in 3.2291197776794434s
Received healthy response to inference request in 3.049870729446411s
Received healthy response to inference request in 3.0623888969421387s
Received healthy response to inference request in 3.0450899600982666s
5 requests
0 failed requests
5th percentile: 3.0460461139678956
10th percentile: 3.0470022678375246
20th percentile: 3.048914575576782
30th percentile: 3.0523743629455566
40th percentile: 3.0573816299438477
50th percentile: 3.0623888969421387
60th percentile: 3.1290812492370605
70th percentile: 3.1957736015319824
80th percentile: 3.294241762161255
90th percentile: 3.4244857311248778
95th percentile: 3.4896077156066894
99th percentile: 3.541705303192139
mean time: 3.188239812850952
Pipeline stage StressChecker completed in 17.45s
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 0.65s
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 0.64s
Shutdown handler de-registered
chaiml-qwen32b-sft-exp1_16150_v3 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen32b-sft-exp1-16150-v3-profiler
Waiting for inference service chaiml-qwen32b-sft-exp1-16150-v3-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 3142.47s
Shutdown handler de-registered
chaiml-qwen32b-sft-exp1_16150_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-sft-exp1_16150_v3 status is now torndown due to DeploymentManager action