developer_uid: chai_backend_admin
submission_id: chaiml-1105-quang-ir-mix_1988_v1
model_name: training123
model_group: ChaiML/1105-quang-ir-mix
status: protected
timestamp: 2025-11-25T00:24:40+00:00
num_battles: 5574
num_wins: 2828
celo_rating: 1310.89
family_friendly_score: 0.5358
family_friendly_standard_error: 0.007052919395541112
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: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3662487370131561, 'latency_mean': 2.730258150100708, 'latency_p50': 2.6721818447113037, 'latency_p90': 2.9217090368270875}, {'batch_size': 2, 'throughput': 0.5670230904423821, 'latency_mean': 3.5221442019939424, 'latency_p50': 3.525468945503235, 'latency_p90': 3.8415793657302855}, {'batch_size': 3, 'throughput': 0.7002999983622449, 'latency_mean': 4.270635173320771, 'latency_p50': 4.265557527542114, 'latency_p90': 4.711088013648987}, {'batch_size': 4, 'throughput': 0.7921795784758934, 'latency_mean': 5.034492301940918, 'latency_p50': 5.042749285697937, 'latency_p90': 5.736247134208679}, {'batch_size': 5, 'throughput': 0.8556818214842372, 'latency_mean': 5.828683902025222, 'latency_p50': 5.817187428474426, 'latency_p90': 6.642532753944397}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
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: 0.6
us_pacific_date: 2025-11-06
win_ratio: 0.5073555794761392
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': ['</s>', '####', '\n', 'You:', '####\n'], '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-1105-quang-ir-mix-1988-v1-mkmlizer
Waiting for job on chaiml-1105-quang-ir-mix-1988-v1-mkmlizer to finish
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ belonging to: ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ║ ║
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: Downloaded to shared memory in 57.641s
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: Checking if ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250003 already exists in ChaiML
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpekjr6va2, device:0
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: quantized model in 42.762s
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: Processed model ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250003 in 100.403s
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia/config.json
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia/special_tokens_map.json
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia/tokenizer_config.json
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia/tokenizer.json
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia/flywheel_model.0.safetensors
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mix-1988-v1/nvidia/flywheel_model.1.safetensors
chaiml-1105-quang-ir-mix-1988-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.70it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 39.67it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 37.24it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:09, 36.55it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 39.68it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:07, 42.34it/s] Loading 0: 10%|█ | 37/363 [00:01<00:12, 26.04it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:13, 24.48it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 32.40it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:09, 32.67it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:09, 33.57it/s] Loading 0: 17%|█▋ | 62/363 [00:01<00:08, 34.49it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.19it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 24.38it/s] Loading 0: 20%|██ | 74/363 [00:02<00:13, 21.99it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:12, 22.91it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:14, 18.88it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:15, 18.45it/s] Loading 0: 24%|██▍ | 87/363 [00:03<00:18, 14.68it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:16, 16.74it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:15, 16.92it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:10, 24.11it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:11, 23.17it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:11, 23.25it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.56it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 25.81it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.64it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:09, 26.30it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:08, 28.41it/s] Loading 0: 36%|███▋ | 132/363 [00:05<00:08, 26.71it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:06, 32.54it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 30.89it/s] Loading 0: 41%|████ | 149/363 [00:05<00:05, 37.50it/s] Loading 0: 42%|████▏ | 153/363 [00:05<00:09, 22.78it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:08, 23.73it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 30.57it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 29.88it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 33.20it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:05, 31.41it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:05, 32.33it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:05, 29.45it/s] Loading 0: 53%|█████▎ | 191/363 [00:06<00:05, 28.85it/s] Loading 0: 54%|█████▎ | 195/363 [00:07<00:06, 26.26it/s] Loading 0: 55%|█████▌ | 201/363 [00:20<02:13, 1.22it/s] Loading 0: 56%|█████▌ | 203/363 [00:20<01:54, 1.40it/s] Loading 0: 57%|█████▋ | 208/363 [00:20<01:13, 2.12it/s] Loading 0: 58%|█████▊ | 211/363 [00:20<00:56, 2.67it/s] Loading 0: 59%|█████▉ | 214/363 [00:20<00:43, 3.41it/s] Loading 0: 60%|██████ | 218/363 [00:20<00:30, 4.76it/s] Loading 0: 61%|██████ | 221/363 [00:20<00:23, 6.06it/s] Loading 0: 62%|██████▏ | 224/363 [00:21<00:19, 7.22it/s] Loading 0: 63%|██████▎ | 229/363 [00:21<00:12, 10.55it/s] Loading 0: 64%|██████▍ | 232/363 [00:21<00:10, 12.45it/s] Loading 0: 65%|██████▌ | 237/363 [00:21<00:07, 17.04it/s] Loading 0: 66%|██████▋ | 241/363 [00:21<00:06, 19.18it/s] Loading 0: 68%|██████▊ | 246/363 [00:21<00:04, 23.99it/s] Loading 0: 69%|██████▉ | 250/363 [00:21<00:04, 24.44it/s] Loading 0: 70%|███████ | 255/363 [00:21<00:03, 28.94it/s] Loading 0: 71%|███████▏ | 259/363 [00:22<00:03, 28.83it/s] Loading 0: 73%|███████▎ | 266/363 [00:22<00:02, 35.85it/s] Loading 0: 75%|███████▍ | 271/363 [00:22<00:03, 25.68it/s] Loading 0: 76%|███████▌ | 275/363 [00:22<00:03, 24.39it/s] Loading 0: 78%|███████▊ | 282/363 [00:22<00:02, 31.64it/s] Loading 0: 79%|███████▉ | 286/363 [00:22<00:02, 30.95it/s] Loading 0: 80%|████████ | 291/363 [00:23<00:02, 34.27it/s] Loading 0: 81%|████████▏ | 295/363 [00:23<00:02, 32.47it/s] Loading 0: 82%|████████▏ | 299/363 [00:23<00:01, 33.43it/s] Loading 0: 84%|████████▎ | 304/363 [00:23<00:01, 30.31it/s] Loading 0: 85%|████████▍ | 308/363 [00:23<00:01, 29.52it/s] Loading 0: 86%|████████▌ | 312/363 [00:23<00:01, 26.68it/s] Loading 0: 88%|████████▊ | 318/363 [00:24<00:01, 32.47it/s] Loading 0: 89%|████████▊ | 322/363 [00:24<00:01, 30.91it/s] Loading 0: 90%|█████████ | 327/363 [00:24<00:01, 34.52it/s] Loading 0: 91%|█████████ | 331/363 [00:24<00:00, 33.04it/s] Loading 0: 92%|█████████▏| 335/363 [00:24<00:00, 33.86it/s] Loading 0: 93%|█████████▎| 339/363 [00:24<00:00, 34.20it/s] Loading 0: 94%|█████████▍| 343/363 [00:25<00:00, 20.29it/s] Loading 0: 96%|█████████▌| 348/363 [00:25<00:00, 21.90it/s] Loading 0: 98%|█████████▊| 355/363 [00:25<00:00, 28.62it/s] Loading 0: 99%|█████████▉| 359/363 [00:25<00:00, 28.70it/s]
Job chaiml-1105-quang-ir-mix-1988-v1-mkmlizer completed after 154.78s with status: succeeded
Stopping job with name chaiml-1105-quang-ir-mix-1988-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.30s
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-1105-quang-ir-mix-1988-v1
Waiting for inference service chaiml-1105-quang-ir-mix-1988-v1 to be ready
Inference service chaiml-1105-quang-ir-mix-1988-v1 ready after 160.5764012336731s
Pipeline stage MKMLDeployer completed in 161.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.394049644470215s
Received healthy response to inference request in 2.261204481124878s
Received healthy response to inference request in 2.8566503524780273s
Received healthy response to inference request in 2.4436018466949463s
Received healthy response to inference request in 2.3345212936401367s
5 requests
0 failed requests
5th percentile: 2.2758678436279296
10th percentile: 2.2905312061309813
20th percentile: 2.319857931137085
30th percentile: 2.3464269638061523
40th percentile: 2.3702383041381836
50th percentile: 2.394049644470215
60th percentile: 2.4138705253601076
70th percentile: 2.43369140625
80th percentile: 2.5262115478515628
90th percentile: 2.691430950164795
95th percentile: 2.774040651321411
99th percentile: 2.840128412246704
mean time: 2.4580055236816407
Pipeline stage StressChecker completed in 13.78s
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 0.67s
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-1105-quang-ir-mix_1988_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1105-quang-ir-mix-1988-v1-profiler
Waiting for inference service chaiml-1105-quang-ir-mix-1988-v1-profiler to be ready
Inference service chaiml-1105-quang-ir-mix-1988-v1-profiler ready after 161.11066913604736s
Pipeline stage MKMLProfilerDeployer completed in 161.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-1105-quang-ira8f04de8269c82741636d37952b77ee8-deplodf758:/code/chaiverse_profiler_1762409830 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1105-quang-ira8f04de8269c82741636d37952b77ee8-deplodf758 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762409830 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762409830/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-1105-quang-ira8f04de8269c82741636d37952b77ee8-deplodf758:/code/chaiverse_profiler_1762411200 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1105-quang-ira8f04de8269c82741636d37952b77ee8-deplodf758 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762411200 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762411200/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1105-quang-ira8f04de8269c82741636d37952b77ee8-deplodf758 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1762411200/summary.json'
Pipeline stage MKMLProfilerRunner completed in 3046.00s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-1105-quang-ir-mix-1988-v1-profiler is running
Tearing down inference service chaiml-1105-quang-ir-mix-1988-v1-profiler
Service chaiml-1105-quang-ir-mix-1988-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.87s
Shutdown handler de-registered
chaiml-1105-quang-ir-mix_1988_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1105-quang-ir-mix_1988_v1 status is now torndown due to DeploymentManager action
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem
chaiml-1105-quang-ir-mix_1988_v1 status is now protected due to ABTestQueueItem