chaiml-mistral32-24b-sf_16627

developer_uid: NischayDnk

submission_id: chaiml-mistral32-24b-sf_16627_v2

model_name: chaiml-mistral32-24b-sf_16627_v2

model_group: ChaiML/mistral32-24b-sft

status: torndown

timestamp: 2025-06-27T21:15:26+00:00

num_battles: 7891

num_wins: 3919

celo_rating: 1283.07

family_friendly_score: 0.5542

family_friendly_standard_error: 0.007029400543431851

submission_type: basic

model_repo: ChaiML/mistral32-24b-sfts1-exp1-highqualityjun27-s400-lora-4e

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5277909810685496, 'latency_mean': 1.8945914816856384, 'latency_p50': 1.8815263509750366, 'latency_p90': 2.112738752365112}, {'batch_size': 3, 'throughput': 1.0562356466304825, 'latency_mean': 2.83496622800827, 'latency_p50': 2.8214221000671387, 'latency_p90': 3.1299014329910277}, {'batch_size': 5, 'throughput': 1.3249379589223693, 'latency_mean': 3.73671049952507, 'latency_p50': 3.740010619163513, 'latency_p90': 4.162140846252441}, {'batch_size': 6, 'throughput': 1.4543558869089115, 'latency_mean': 4.106425030231476, 'latency_p50': 4.071225881576538, 'latency_p90': 4.689615988731385}, {'batch_size': 8, 'throughput': 1.576155809288478, 'latency_mean': 5.03874612569809, 'latency_p50': 5.01887845993042, 'latency_p90': 5.608173990249634}, {'batch_size': 10, 'throughput': 1.6559170473325215, 'latency_mean': 5.965067920684814, 'latency_p50': 5.9382712841033936, 'latency_p90': 6.78719687461853}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-mistral32-24b-sf_16627_v2

is_internal_developer: False

language_model: ChaiML/mistral32-24b-sfts1-exp1-highqualityjun27-s400-lora-4e

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-06-27

win_ratio: 0.49664174375871245

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>{bot_name}{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}

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-mistral32-24b-sf-16627-v2-mkmlizer
Waiting for job on chaiml-mistral32-24b-sf-16627-v2-mkmlizer to finish
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: Downloaded to shared memory in 55.710s
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: Checking if ChaiML/mistral32-24b-sfts1-exp1-highqualityjun27-s400-lora-4e already exists in ChaiML
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpldyr_1h4, device:0
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: quantized model in 48.371s
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: Processed model ChaiML/mistral32-24b-sfts1-exp1-highqualityjun27-s400-lora-4e in 104.082s
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2/config.json
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2/special_tokens_map.json
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2/tokenizer_config.json
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2/tokenizer.json
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2/flywheel_model.1.safetensors
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-24b-sf-16627-v2/flywheel_model.0.safetensors
chaiml-mistral32-24b-sf-16627-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.01it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.31it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.72it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.16it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.17it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.67it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:11, 30.31it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:14, 22.27it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:17, 19.09it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.35it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.56it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 24.07it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:12, 25.35it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:12, 25.04it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.31it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.73it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.78it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 22.99it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.87it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.93it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.39it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.16it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.40it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.91it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.99it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 26.97it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.21it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 25.06it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 24.93it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.07it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 29.09it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 25.28it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.43it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.83it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.28it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.33it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.85it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.00it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.90it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.95it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.54it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.38it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 25.28it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.38it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.28it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.78it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.86it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.15it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.15it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.86it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.08it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.19it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.12it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.03it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.65it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.37it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.20it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.48it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.84it/s]
Loading 0:  70%|██████▉   | 253/363 [00:24<00:04, 23.07it/s]
Loading 0:  71%|███████   | 256/363 [00:24<00:04, 23.90it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 23.86it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.55it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 21.82it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 20.84it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.28it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.08it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.95it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.75it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.60it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.73it/s]
Loading 0:  82%|████████▏ | 298/363 [00:26<00:02, 27.47it/s]
Loading 0:  83%|████████▎ | 303/363 [00:26<00:02, 29.41it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 20.13it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 21.55it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 22.30it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 25.64it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 22.78it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 27.67it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.10it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.24it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.97it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.50it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.02it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.86it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.06it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.06it/s]
                                                            
Job chaiml-mistral32-24b-sf-16627-v2-mkmlizer completed after 135.6s with status: succeeded
Stopping job with name chaiml-mistral32-24b-sf-16627-v2-mkmlizer
Pipeline stage MKMLizer completed in 136.26s
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-mistral32-24b-sf-16627-v2
Waiting for inference service chaiml-mistral32-24b-sf-16627-v2 to be ready
Inference service chaiml-mistral32-24b-sf-16627-v2 ready after 150.56751251220703s
Pipeline stage MKMLDeployer completed in 151.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4237539768218994s
Received healthy response to inference request in 1.9039888381958008s
Received healthy response to inference request in 1.9391834735870361s
Received healthy response to inference request in 2.0615193843841553s
Received healthy response to inference request in 1.9134669303894043s
5 requests
0 failed requests
5th percentile: 1.9058844566345214
10th percentile: 1.907780075073242
20th percentile: 1.9115713119506836
30th percentile: 1.9186102390289306
40th percentile: 1.9288968563079834
50th percentile: 1.9391834735870361
60th percentile: 1.9881178379058837
70th percentile: 2.0370522022247313
80th percentile: 2.133966302871704
90th percentile: 2.2788601398468016
95th percentile: 2.3513070583343505
99th percentile: 2.4092645931243895
mean time: 2.048382520675659
Pipeline stage StressChecker completed in 12.59s
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 0.78s
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 0.94s
Shutdown handler de-registered
chaiml-mistral32-24b-sf_16627_v2 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-24b-sf-16627-v2-profiler
Waiting for inference service chaiml-mistral32-24b-sf-16627-v2-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3226.63s
Shutdown handler de-registered
chaiml-mistral32-24b-sf_16627_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-24b-sf_16627_v2 status is now torndown due to DeploymentManager action