chaiml-1027-quang-ir-lt_98232

developer_uid: qdv206

submission_id: chaiml-1027-quang-ir-lt_98232_v1

model_name: adjkjdnkjd

model_group: ChaiML/1027-quang-ir-ltr

status: torndown

timestamp: 2025-10-31T17:06:40+00:00

num_battles: 6145

num_wins: 3155

celo_rating: 1279.14

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1027-quang-ir-ltry-mixall-dvbot5-dvtri500

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4713677220222483, 'latency_mean': 2.1213921213150027, 'latency_p50': 2.1175084114074707, 'latency_p90': 2.3316882610321046}, {'batch_size': 2, 'throughput': 0.6861326460734654, 'latency_mean': 2.9127329540252687, 'latency_p50': 2.9191190004348755, 'latency_p90': 3.1468837022781373}, {'batch_size': 3, 'throughput': 0.8347602340147767, 'latency_mean': 3.587606530189514, 'latency_p50': 3.6122201681137085, 'latency_p90': 4.01435124874115}, {'batch_size': 4, 'throughput': 0.9324468365947568, 'latency_mean': 4.2773103070259095, 'latency_p50': 4.265443325042725, 'latency_p90': 4.970611929893494}, {'batch_size': 5, 'throughput': 0.9946501577047114, 'latency_mean': 5.010802832841873, 'latency_p50': 5.037174582481384, 'latency_p90': 5.685665917396546}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: adjkjdnkjd

is_internal_developer: False

language_model: ChaiML/1027-quang-ir-ltry-mixall-dvbot5-dvtri500

model_size: 24B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2025-10-28

win_ratio: 0.5134255492270138

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '\n', '####\n', '</s>', '####'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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-1027-quang-ir-lt-98232-v1-mkmlizer
Waiting for job on chaiml-1027-quang-ir-lt-98232-v1-mkmlizer to finish
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║                                                                     ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║                                                                     ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║                                                                     ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║                                                                     ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ║                                                                     ║
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: Downloaded to shared memory in 56.735s
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: Checking if ChaiML/1027-quang-ir-ltry-mixall-dvbot5-dvtri500 already exists in ChaiML
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp32aru9rx, device:0
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: quantized model in 284.870s
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: Processed model ChaiML/1027-quang-ir-ltry-mixall-dvbot5-dvtri500 in 341.605s
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia/config.json
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia/special_tokens_map.json
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia/tokenizer_config.json
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia/tokenizer.json
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia/flywheel_model.1.safetensors
chaiml-1027-quang-ir-lt-98232-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1027-quang-ir-lt-98232-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-1027-quang-ir-lt-98232-v1-mkmlizer completed after 415.53s with status: succeeded
Stopping job with name chaiml-1027-quang-ir-lt-98232-v1-mkmlizer
Pipeline stage MKMLizer completed in 416.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1027-quang-ir-lt-98232-v1
Waiting for inference service chaiml-1027-quang-ir-lt-98232-v1 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-pointwise-end-to_85479_v9: HTTPConnectionPool(host='chaiml-pointwise-end-to-85479-v9-predictor.creator-studio.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-1027-quang-ir-lt-98232-v1 ready after 100.32132506370544s
Pipeline stage MKMLDeployer completed in 101.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5242576599121094s
Received healthy response to inference request in 1.7533900737762451s
Received healthy response to inference request in 2.1051385402679443s
Received healthy response to inference request in 1.796518325805664s
Received healthy response to inference request in 1.7227911949157715s
5 requests
0 failed requests
5th percentile: 1.7289109706878663
10th percentile: 1.735030746459961
20th percentile: 1.7472702980041503
30th percentile: 1.7620157241821288
40th percentile: 1.7792670249938964
50th percentile: 1.796518325805664
60th percentile: 1.9199664115905761
70th percentile: 2.043414497375488
80th percentile: 2.1889623641967773
90th percentile: 2.3566100120544435
95th percentile: 2.4404338359832765
99th percentile: 2.507492895126343
mean time: 1.9804191589355469
Pipeline stage StressChecker completed in 11.48s
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 0.67s
Shutdown handler de-registered
chaiml-1027-quang-ir-lt_98232_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1027-quang-ir-lt-98232-v1-profiler
Waiting for inference service chaiml-1027-quang-ir-lt-98232-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 4860.08s
Shutdown handler de-registered
chaiml-1027-quang-ir-lt_98232_v1 status is now torndown due to DeploymentManager action