developer_uid: chai_backend_admin
submission_id: chaiml-1107-quang-ir-mi_40948_v1
model_name: training123
model_group: ChaiML/1107-quang-ir-mix
status: torndown
timestamp: 2025-11-10T20:21:43+00:00
num_battles: 5849
num_wins: 2973
celo_rating: 1303.94
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_0164641ep_2e6ct
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': 0.38097748902419054, 'latency_mean': 2.6247088742256164, 'latency_p50': 2.610909104347229, 'latency_p90': 2.876410484313965}, {'batch_size': 2, 'throughput': 0.5659331737791811, 'latency_mean': 3.531087853908539, 'latency_p50': 3.547447681427002, 'latency_p90': 3.8238354206085203}, {'batch_size': 3, 'throughput': 0.7009941665676958, 'latency_mean': 4.263200376033783, 'latency_p50': 4.2599815130233765, 'latency_p90': 4.847342300415039}, {'batch_size': 4, 'throughput': 0.7916937346118251, 'latency_mean': 5.034392356872559, 'latency_p50': 5.031888842582703, 'latency_p90': 5.667606019973754}, {'batch_size': 5, 'throughput': 0.8535767326002762, 'latency_mean': 5.828558136224746, 'latency_p50': 5.853157997131348, 'latency_p90': 6.641556286811828}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_0164641ep_2e6ct
model_size: 24B
ranking_group: single
throughput_3p7s: 0.6
us_pacific_date: 2025-11-07
win_ratio: 0.5082920157291845
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', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
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
Running pipeline stage MKMLizer
Starting job with name chaiml-1107-quang-ir-mi-40948-v1-mkmlizer
Waiting for job on chaiml-1107-quang-ir-mi-40948-v1-mkmlizer to finish
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: Downloaded to shared memory in 60.713s
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: Checking if ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_0164641ep_2e6ct already exists in ChaiML
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph6txjv8z, device:0
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: quantized model in 42.624s
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: Processed model ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_0164641ep_2e6ct in 103.337s
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia/config.json
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia/tokenizer_config.json
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia/special_tokens_map.json
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia/tokenizer.json
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', '')
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia/flywheel_model.0.safetensors
chaiml-1107-quang-ir-mi-40948-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-40948-v1/nvidia/flywheel_model.1.safetensors
Job chaiml-1107-quang-ir-mi-40948-v1-mkmlizer completed after 154.65s with status: succeeded
Stopping job with name chaiml-1107-quang-ir-mi-40948-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1107-quang-ir-mi-40948-v1
Waiting for inference service chaiml-1107-quang-ir-mi-40948-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', '')
Inference service chaiml-1107-quang-ir-mi-40948-v1 ready after 170.8457419872284s
Pipeline stage MKMLDeployer completed in 171.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.493903875350952s
Received healthy response to inference request in 2.6294920444488525s
Received healthy response to inference request in 2.15277361869812s
Received healthy response to inference request in 2.429629325866699s
Received healthy response to inference request in 2.3802237510681152s
5 requests
0 failed requests
5th percentile: 2.198263645172119
10th percentile: 2.243753671646118
20th percentile: 2.334733724594116
30th percentile: 2.390104866027832
40th percentile: 2.4098670959472654
50th percentile: 2.429629325866699
60th percentile: 2.4553391456604006
70th percentile: 2.4810489654541015
80th percentile: 2.521021509170532
90th percentile: 2.5752567768096926
95th percentile: 2.6023744106292725
99th percentile: 2.6240685176849365
mean time: 2.4172045230865478
Pipeline stage StressChecker completed in 13.49s
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 0.70s
Shutdown handler de-registered
chaiml-1107-quang-ir-mi_40948_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 0.09s
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-1107-quang-ir-mi-40948-v1-profiler
Waiting for inference service chaiml-1107-quang-ir-mi-40948-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 4972.96s
Shutdown handler de-registered
chaiml-1107-quang-ir-mi_40948_v1 status is now torndown due to DeploymentManager action