developer_uid: zonemercy
submission_id: chaiml-1105-quang-ir-mi_1988_v16
model_name: training123
model_group: ChaiML/1105-quang-ir-mix
status: torndown
timestamp: 2025-11-23T19:21:18+00:00
num_battles: 7506
num_wins: 3584
celo_rating: 1278.87
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250003
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 1
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4274759881991281, 'latency_mean': 2.3392014002799986, 'latency_p50': 2.3375091552734375, 'latency_p90': 2.5400712490081787}, {'batch_size': 3, 'throughput': 0.8519457634168757, 'latency_mean': 3.505010681152344, 'latency_p50': 3.4871513843536377, 'latency_p90': 3.789662504196167}, {'batch_size': 5, 'throughput': 1.1143806392135238, 'latency_mean': 4.455521070957184, 'latency_p50': 4.427542090415955, 'latency_p90': 4.972718358039856}, {'batch_size': 6, 'throughput': 1.2003076559898016, 'latency_mean': 4.962372570037842, 'latency_p50': 4.96200168132782, 'latency_p90': 5.5361443042755125}, {'batch_size': 8, 'throughput': 1.3360376142695027, 'latency_mean': 5.950975475311279, 'latency_p50': 5.9745107889175415, 'latency_p90': 6.564611935615539}, {'batch_size': 10, 'throughput': 1.4350421402735163, 'latency_mean': 6.909457942247391, 'latency_p50': 6.895927429199219, 'latency_p90': 7.81978964805603}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250003
model_size: 24B
ranking_group: single
throughput_3p7s: 0.92
us_pacific_date: 2025-11-20
win_ratio: 0.47748467892352786
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': ['####\n', '</s>', 'You:', '####', '\n'], 'max_input_tokens': 2048, 'best_of': 1, 'max_output_tokens': 80}
formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLizer
Starting job with name chaiml-1105-quang-ir-mi-1988-v16-mkmlizer
Waiting for job on chaiml-1105-quang-ir-mi-1988-v16-mkmlizer to finish
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  belonging to:                                                      ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: Downloaded to shared memory in 65.338s
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: Checking if ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250003 already exists in ChaiML
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmptne7__jr, device:0
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: quantized model in 312.903s
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: Processed model ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250003 in 378.242s
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia/config.json
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia/special_tokens_map.json
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia/tokenizer_config.json
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia/tokenizer.json
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia/flywheel_model.1.safetensors
chaiml-1105-quang-ir-mi-1988-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-1988-v16/nvidia/flywheel_model.0.safetensors
Job chaiml-1105-quang-ir-mi-1988-v16-mkmlizer completed after 420.35s with status: succeeded
Stopping job with name chaiml-1105-quang-ir-mi-1988-v16-mkmlizer
Pipeline stage MKMLizer completed in 421.10s
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-1105-quang-ir-mi-1988-v16
Waiting for inference service chaiml-1105-quang-ir-mi-1988-v16 to be ready
Inference service chaiml-1105-quang-ir-mi-1988-v16 ready after 151.15432858467102s
Pipeline stage MKMLDeployer completed in 151.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.304643154144287s
Received healthy response to inference request in 1.7858591079711914s
Received healthy response to inference request in 1.759333610534668s
Received healthy response to inference request in 1.808154582977295s
Received healthy response to inference request in 1.7851994037628174s
5 requests
0 failed requests
5th percentile: 1.7645067691802978
10th percentile: 1.7696799278259276
20th percentile: 1.7800262451171875
30th percentile: 1.7853313446044923
40th percentile: 1.7855952262878418
50th percentile: 1.7858591079711914
60th percentile: 1.7947772979736327
70th percentile: 1.8036954879760743
80th percentile: 1.9074522972106935
90th percentile: 2.1060477256774903
95th percentile: 2.2053454399108885
99th percentile: 2.284783611297607
mean time: 1.8886379718780517
Pipeline stage StressChecker completed in 10.95s
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 0.92s
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-1105-quang-ir-mi_1988_v16 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1105-quang-ir-mi-1988-v16-profiler
Waiting for inference service chaiml-1105-quang-ir-mi-1988-v16-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 2646.21s
Shutdown handler de-registered
chaiml-1105-quang-ir-mi_1988_v16 status is now torndown due to DeploymentManager action