chaiml-1107-quang-ir-mi_46703

developer_uid: chai_backend_admin

submission_id: chaiml-1107-quang-ir-mi_46703_v1

model_name: training123

model_group: ChaiML/1107-quang-ir-mix

status: torndown

timestamp: 2025-11-10T21:51:47+00:00

num_battles: 5482

num_wins: 2778

celo_rating: 1293.16

family_friendly_score: 0.5472

family_friendly_standard_error: 0.0070394908906823645

submission_type: basic

model_repo: ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_0164641ep_5e6cs

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': 0.37726557298291186, 'latency_mean': 2.6505534064769747, 'latency_p50': 2.667584776878357, 'latency_p90': 2.8975983381271364}, {'batch_size': 2, 'throughput': 0.5599717081783688, 'latency_mean': 3.56216210603714, 'latency_p50': 3.5754815340042114, 'latency_p90': 3.8444562673568723}, {'batch_size': 3, 'throughput': 0.6967658414097271, 'latency_mean': 4.295566884279251, 'latency_p50': 4.320453763008118, 'latency_p90': 4.721163821220398}, {'batch_size': 4, 'throughput': 0.7815891769820055, 'latency_mean': 5.09867299079895, 'latency_p50': 5.108375549316406, 'latency_p90': 5.837245321273803}, {'batch_size': 5, 'throughput': 0.8415137891908409, 'latency_mean': 5.921494108438492, 'latency_p50': 5.891167044639587, 'latency_p90': 6.579526376724243}]

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_5e6cs

model_size: 24B

ranking_group: single

throughput_3p7s: 0.59

us_pacific_date: 2025-11-07

win_ratio: 0.5067493615468807

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:', '</s>', '\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-1107-quang-ir-mi-46703-v1-mkmlizer
Waiting for job on chaiml-1107-quang-ir-mi-46703-v1-mkmlizer to finish
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: Downloaded to shared memory in 85.770s
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: Checking if ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_0164641ep_5e6cs already exists in ChaiML
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8xuvdzyf, device:0
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia/special_tokens_map.json
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia/config.json
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia/tokenizer_config.json
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia/tokenizer.json
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia/flywheel_model.1.safetensors
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-46703-v1/nvidia/flywheel_model.0.safetensors
chaiml-1107-quang-ir-mi-46703-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.46it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:10, 32.39it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:10, 33.58it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 38.35it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 34.86it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.05it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.63it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.86it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.45it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.07it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.93it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.61it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.64it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.95it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.85it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.84it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.84it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.91it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.47it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.64it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.04it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.24it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.15it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.58it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.44it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.22it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.45it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 33.23it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.20it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.60it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.43it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.83it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.59it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.85it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.84it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.81it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.92it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.00it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.87it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.46it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.74it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.14it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.67it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.45it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.85it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.65it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.20it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.47it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:12, 10.84it/s]
Loading 0:  65%|██████▌   | 236/363 [00:20<00:08, 14.32it/s]
Loading 0:  66%|██████▌   | 239/363 [00:20<00:08, 13.87it/s]
Loading 0:  67%|██████▋   | 244/363 [00:21<00:06, 18.86it/s]
Loading 0:  68%|██████▊   | 248/363 [00:21<00:06, 18.66it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.46it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.90it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 32.82it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 23.17it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.04it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.77it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.27it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.57it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.04it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.93it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.86it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.09it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.32it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.07it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.84it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.26it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.33it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.09it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.72it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.09it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.70it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.14it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.64it/s]
                                                            
Job chaiml-1107-quang-ir-mi-46703-v1-mkmlizer completed after 185.47s with status: succeeded
Stopping job with name chaiml-1107-quang-ir-mi-46703-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1107-quang-ir-mi-46703-v1
Waiting for inference service chaiml-1107-quang-ir-mi-46703-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-1107-quang-ir-mi-46703-v1 ready after 171.1430914402008s
Pipeline stage MKMLDeployer completed in 172.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.311873197555542s
Received healthy response to inference request in 2.49609637260437s
Received healthy response to inference request in 2.1213698387145996s
Received healthy response to inference request in 2.0782899856567383s
Received healthy response to inference request in 2.3077564239501953s
5 requests
0 failed requests
5th percentile: 2.0869059562683105
10th percentile: 2.095521926879883
20th percentile: 2.1127538681030273
30th percentile: 2.158647155761719
40th percentile: 2.233201789855957
50th percentile: 2.3077564239501953
60th percentile: 2.309403133392334
70th percentile: 2.3110498428344726
80th percentile: 2.3487178325653075
90th percentile: 2.422407102584839
95th percentile: 2.4592517375946046
99th percentile: 2.488727445602417
mean time: 2.263077163696289
Pipeline stage StressChecker completed in 12.88s
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 0.62s
Shutdown handler de-registered
chaiml-1107-quang-ir-mi_46703_v1 status is now deployed due to DeploymentManager action
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 3103.89s
Shutdown handler de-registered
chaiml-1107-quang-ir-mi_46703_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1107-quang-ir-mi_46703_v1 status is now torndown due to DeploymentManager action