chaiml-1024-quang-instr_71270

developer_uid: chai_backend_admin

submission_id: chaiml-1024-quang-instr_71270_v1

model_name: chaiml-1024-quang-instr_71270_v1

model_group: ChaiML/1024-quang-instru

status: inactive

timestamp: 2025-10-24T22:30:34+00:00

num_battles: 6736

num_wins: 3776

celo_rating: 1293.68

family_friendly_score: 0.45899999999999996

family_friendly_standard_error: 0.007047254784666153

submission_type: basic

model_repo: ChaiML/1024-quang-instructed-retry-lastconv-adjustment

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': 0.38265637939539804, 'latency_mean': 2.6132150077819825, 'latency_p50': 2.619640588760376, 'latency_p90': 2.859722447395325}, {'batch_size': 2, 'throughput': 0.5749817074925395, 'latency_mean': 3.4742538285255433, 'latency_p50': 3.463595390319824, 'latency_p90': 3.7826048135757446}, {'batch_size': 3, 'throughput': 0.7119818247439864, 'latency_mean': 4.202956813573837, 'latency_p50': 4.1899330615997314, 'latency_p90': 4.768846249580383}, {'batch_size': 4, 'throughput': 0.8126358852280964, 'latency_mean': 4.898649295568466, 'latency_p50': 4.873667478561401, 'latency_p90': 5.549360275268555}, {'batch_size': 5, 'throughput': 0.8772898190468225, 'latency_mean': 5.676819057464599, 'latency_p50': 5.6788822412490845, 'latency_p90': 6.446439814567566}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-1024-quang-instr_71270_v1

is_internal_developer: True

language_model: ChaiML/1024-quang-instructed-retry-lastconv-adjustment

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-10-24

win_ratio: 0.5605700712589073

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', '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-1024-quang-instr-71270-v1-mkmlizer
Waiting for job on chaiml-1024-quang-instr-71270-v1-mkmlizer to finish
chaiml-1024-quang-instr-71270-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║                                                                     ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║                                                                     ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║                                                                     ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║                                                                     ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ║                                                                     ║
chaiml-1024-quang-instr-71270-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1024-quang-instr-71270-v1-mkmlizer: Downloaded to shared memory in 64.380s
chaiml-1024-quang-instr-71270-v1-mkmlizer: Checking if ChaiML/1024-quang-instructed-retry-lastconv-adjustment already exists in ChaiML
chaiml-1024-quang-instr-71270-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxr2m447m, device:0
chaiml-1024-quang-instr-71270-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1024-quang-instr-71270-v1-mkmlizer: quantized model in 41.945s
chaiml-1024-quang-instr-71270-v1-mkmlizer: Processed model ChaiML/1024-quang-instructed-retry-lastconv-adjustment in 106.325s
chaiml-1024-quang-instr-71270-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1024-quang-instr-71270-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1024-quang-instr-71270-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia
chaiml-1024-quang-instr-71270-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia/config.json
chaiml-1024-quang-instr-71270-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia/special_tokens_map.json
chaiml-1024-quang-instr-71270-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia/tokenizer_config.json
chaiml-1024-quang-instr-71270-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia/tokenizer.json
chaiml-1024-quang-instr-71270-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia/flywheel_model.0.safetensors
chaiml-1024-quang-instr-71270-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1024-quang-instr-71270-v1/nvidia/flywheel_model.1.safetensors
chaiml-1024-quang-instr-71270-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.47it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.31it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.76it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.29it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.22it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.05it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.76it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.49it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.92it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.46it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.82it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.62it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.24it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.63it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.32it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.29it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.62it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.10it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.03it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.17it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.67it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.22it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.08it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.06it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.65it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.07it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.87it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.55it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.98it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.81it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.65it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.35it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.36it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.35it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.45it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.91it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.43it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.84it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:21,  6.64it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.24it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:13, 10.15it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 15.87it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.77it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.02it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.21it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.52it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.31it/s]
Loading 0:  72%|███████▏  | 263/363 [00:21<00:03, 25.97it/s]
Loading 0:  74%|███████▎  | 267/363 [00:21<00:04, 20.96it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:04, 19.42it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:04, 21.48it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 29.23it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.15it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.92it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.48it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.23it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.58it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.59it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.48it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.03it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.57it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.95it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.05it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.54it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.71it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.26it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.52it/s]
                                                            
Job chaiml-1024-quang-instr-71270-v1-mkmlizer completed after 184.26s with status: succeeded
Stopping job with name chaiml-1024-quang-instr-71270-v1-mkmlizer
Pipeline stage MKMLizer completed in 184.78s
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-1024-quang-instr-71270-v1
Waiting for inference service chaiml-1024-quang-instr-71270-v1 to be ready
Inference service chaiml-1024-quang-instr-71270-v1 ready after 90.3786678314209s
Pipeline stage MKMLDeployer completed in 91.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.435697317123413s
Received healthy response to inference request in 3.1936635971069336s
Received healthy response to inference request in 3.102694034576416s
Received healthy response to inference request in 2.1131627559661865s
Received healthy response to inference request in 2.1808407306671143s
5 requests
0 failed requests
5th percentile: 2.126698350906372
10th percentile: 2.140233945846558
20th percentile: 2.1673051357269286
30th percentile: 2.231812047958374
40th percentile: 2.3337546825408935
50th percentile: 2.435697317123413
60th percentile: 2.7024960041046144
70th percentile: 2.9692946910858153
80th percentile: 3.1208879470825197
90th percentile: 3.1572757720947267
95th percentile: 3.17546968460083
99th percentile: 3.190024814605713
mean time: 2.605211687088013
Pipeline stage StressChecker completed in 14.55s
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 0.64s
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 0.71s
Shutdown handler de-registered
chaiml-1024-quang-instr_71270_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 3045.14s
Shutdown handler de-registered
chaiml-1024-quang-instr_71270_v1 status is now inactive due to auto deactivation removed underperforming models