chaiml-1113-quang-ir-mi_16731

developer_uid: chai_backend_admin

submission_id: chaiml-1113-quang-ir-mi_16731_v1

model_name: training123

model_group: ChaiML/1113-quang-ir-mix

status: torndown

timestamp: 2025-11-17T06:51:27+00:00

num_battles: 5604

num_wins: 2975

celo_rating: 1306.92

family_friendly_score: 0.4538

family_friendly_standard_error: 0.007040817566163747

submission_type: basic

model_repo: ChaiML/1113-quang-ir-mixall-cld-i0a8-freev2-rm-cldimprv-dpo_freev22_0164642ep_2e5cs

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': 0.3802715981154614, 'latency_mean': 2.629579292535782, 'latency_p50': 2.6527743339538574, 'latency_p90': 2.875872325897217}, {'batch_size': 2, 'throughput': 0.5716212419920411, 'latency_mean': 3.495619169473648, 'latency_p50': 3.487367272377014, 'latency_p90': 3.801254081726074}, {'batch_size': 3, 'throughput': 0.6993738677293488, 'latency_mean': 4.281232438087463, 'latency_p50': 4.286790609359741, 'latency_p90': 4.594099760055542}, {'batch_size': 4, 'throughput': 0.7959608616228733, 'latency_mean': 5.003991740942001, 'latency_p50': 5.011991739273071, 'latency_p90': 5.646884846687317}, {'batch_size': 5, 'throughput': 0.8615861956615952, 'latency_mean': 5.774066045284271, 'latency_p50': 5.786803245544434, 'latency_p90': 6.530798816680908}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/1113-quang-ir-mixall-cld-i0a8-freev2-rm-cldimprv-dpo_freev22_0164642ep_2e5cs

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-13

win_ratio: 0.530870806566738

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:', '####'], '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name chaiml-1113-quang-ir-mi-16731-v1-mkmlizer
Waiting for job on chaiml-1113-quang-ir-mi-16731-v1-mkmlizer to finish
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Stopping job with name chaiml-1113-quang-ir-mi-16731-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-1113-quang-ir-mi-16731-v1-mkmlizer
Waiting for job on chaiml-1113-quang-ir-mi-16731-v1-mkmlizer to finish
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Downloaded to shared memory in 52.920s
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Checking if ChaiML/1113-quang-ir-mixall-cld-i0a8-freev2-rm-cldimprv-dpo_freev22_0164642ep_2e5cs already exists in ChaiML
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcdxxyyqx, device:0
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Downloaded to shared memory in 53.937s
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Checking if ChaiML/1113-quang-ir-mixall-cld-i0a8-freev2-rm-cldimprv-dpo_freev22_0164642ep_2e5cs already exists in ChaiML
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyyndcgvm, device:0
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: quantized model in 42.623s
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Processed model ChaiML/1113-quang-ir-mixall-cld-i0a8-freev2-rm-cldimprv-dpo_freev22_0164642ep_2e5cs in 96.560s
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia/config.json
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia/special_tokens_map.json
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia/tokenizer_config.json
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia/tokenizer.json
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia/flywheel_model.1.safetensors
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1113-quang-ir-mi-16731-v1/nvidia/flywheel_model.0.safetensors
chaiml-1113-quang-ir-mi-16731-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.28it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.03it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.30it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.84it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.00it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.73it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.52it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.98it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.62it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.42it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.21it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 28.10it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.07it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.32it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 29.13it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 26.28it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.65it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.26it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.66it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 31.22it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.77it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.99it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.66it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.16it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.37it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.30it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.26it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.35it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 25.60it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.79it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.63it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.19it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.30it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.70it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.25it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.50it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.63it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.64it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.41it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.79it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.18it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.45it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.51it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.86it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.52it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.78it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.00it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 26.38it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.68it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.88it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 31.01it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.08it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.53it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.61it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.50it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.85it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.54it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.29it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.47it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.73it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.62it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.39it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 15.40it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 17.78it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 24.76it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 25.15it/s]
                                                            
Job chaiml-1113-quang-ir-mi-16731-v1-mkmlizer completed after 154.19s with status: succeeded
Stopping job with name chaiml-1113-quang-ir-mi-16731-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.54s
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-1113-quang-ir-mi-16731-v1
Waiting for inference service chaiml-1113-quang-ir-mi-16731-v1 to be ready
Inference service chaiml-1113-quang-ir-mi-16731-v1 ready after 151.24829840660095s
Pipeline stage MKMLDeployer completed in 151.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.783895969390869s
Received healthy response to inference request in 2.2462306022644043s
Received healthy response to inference request in 2.125051498413086s
Received healthy response to inference request in 2.2548987865448s
Received healthy response to inference request in 2.0859646797180176s
5 requests
0 failed requests
5th percentile: 2.0937820434570313
10th percentile: 2.101599407196045
20th percentile: 2.117234134674072
30th percentile: 2.1492873191833497
40th percentile: 2.1977589607238768
50th percentile: 2.2462306022644043
60th percentile: 2.2496978759765627
70th percentile: 2.2531651496887206
80th percentile: 2.3606982231140137
90th percentile: 2.5722970962524414
95th percentile: 2.6780965328216553
99th percentile: 2.7627360820770264
mean time: 2.2992083072662353
Pipeline stage StressChecker completed in 12.87s
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-1113-quang-ir-mi_16731_v1 status is now deployed due to DeploymentManager action
Shutdown handler 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 2973.51s
Shutdown handler de-registered
chaiml-1113-quang-ir-mi_16731_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1113-quang-ir-mi_16731_v1 status is now torndown due to DeploymentManager action