chaiml-cogito32b-sfts1-d_4119

developer_uid: NischayDnk

submission_id: chaiml-cogito32b-sfts1-d_4119_v1

model_name: chaiml-cogito32b-sfts1-d_4119_v1

model_group: ChaiML/cogito32b-sfts1-d

status: torndown

timestamp: 2025-05-16T19:26:58+00:00

num_battles: 12037

num_wins: 5867

celo_rating: 1274.16

family_friendly_score: 0.5744

family_friendly_standard_error: 0.006992347817435857

submission_type: basic

model_repo: ChaiML/cogito32b-sfts1-datapret-top2kfflex-onlysel

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32759331840.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.35910685546619453, 'latency_mean': 2.7846200942993162, 'latency_p50': 2.775402784347534, 'latency_p90': 3.0956012487411497}, {'batch_size': 2, 'throughput': 0.5809890802525686, 'latency_mean': 3.434873243570328, 'latency_p50': 3.4231395721435547, 'latency_p90': 3.776334810256958}, {'batch_size': 3, 'throughput': 0.7438817583878078, 'latency_mean': 4.019876160621643, 'latency_p50': 4.053561449050903, 'latency_p90': 4.43562262058258}, {'batch_size': 4, 'throughput': 0.865569552440946, 'latency_mean': 4.600969272851944, 'latency_p50': 4.583234071731567, 'latency_p90': 5.162028503417968}, {'batch_size': 5, 'throughput': 0.9628338742874579, 'latency_mean': 5.160905545949936, 'latency_p50': 5.1601715087890625, 'latency_p90': 5.7810487985610965}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-cogito32b-sfts1-d_4119_v1

is_internal_developer: False

language_model: ChaiML/cogito32b-sfts1-datapret-top2kfflex-onlysel

model_size: 33B

ranking_group: single

throughput_3p7s: 0.66

us_pacific_date: 2025-05-16

win_ratio: 0.4874138074270998

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, '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-cogito32b-sfts1-d-4119-v1-mkmlizer
Waiting for job on chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer to finish
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║       /___/                                                         ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: Downloaded to shared memory in 106.184s
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplys1juks, device:0
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: quantized model in 64.651s
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: Processed model ChaiML/cogito32b-sfts1-datapret-top2kfflex-onlysel in 170.836s
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/config.json
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/added_tokens.json
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/special_tokens_map.json
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/tokenizer_config.json
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/merges.txt
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/vocab.json
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/tokenizer.json
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/flywheel_model.2.safetensors
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/flywheel_model.0.safetensors
chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sfts1-d-4119-v1/flywheel_model.1.safetensors
Job chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer completed after 207.75s with status: succeeded
Stopping job with name chaiml-cogito32b-sfts1-d-4119-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito32b-sfts1-d-4119-v1
Waiting for inference service chaiml-cogito32b-sfts1-d-4119-v1 to be ready
Inference service chaiml-cogito32b-sfts1-d-4119-v1 ready after 140.7741198539734s
Pipeline stage MKMLDeployer completed in 141.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4766530990600586s
Received healthy response to inference request in 2.9009146690368652s
Received healthy response to inference request in 2.7195358276367188s
Received healthy response to inference request in 2.6547532081604004s
Received healthy response to inference request in 2.5925233364105225s
5 requests
0 failed requests
5th percentile: 2.604969310760498
10th percentile: 2.6174152851104737
20th percentile: 2.642307233810425
30th percentile: 2.667709732055664
40th percentile: 2.6936227798461916
50th percentile: 2.7195358276367188
60th percentile: 2.792087364196777
70th percentile: 2.864638900756836
80th percentile: 3.016062355041504
90th percentile: 3.246357727050781
95th percentile: 3.36150541305542
99th percentile: 3.4536235618591307
mean time: 2.868876028060913
Pipeline stage StressChecker completed in 15.86s
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 0.78s
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 0.77s
Shutdown handler de-registered
chaiml-cogito32b-sfts1-d_4119_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 0.12s
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-cogito32b-sfts1-d-4119-v1-profiler
Waiting for inference service chaiml-cogito32b-sfts1-d-4119-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 3395.60s
Shutdown handler de-registered
chaiml-cogito32b-sfts1-d_4119_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-sfts1-d_4119_v1 status is now torndown due to DeploymentManager action