chaiml-mistral32-sft-to_87676

developer_uid: NischayDnk

submission_id: chaiml-mistral32-sft-to_87676_v1

model_name: chaiml-mistral32-sft-to_87676_v1

model_group: ChaiML/mistral32-sft-top

status: torndown

timestamp: 2025-07-06T16:20:13+00:00

num_battles: 7557

num_wins: 3689

celo_rating: 1283.46

family_friendly_score: 0.48740000000000006

family_friendly_standard_error: 0.007068822249851809

submission_type: basic

model_repo: ChaiML/mistral32-sft-top10klex-dpos1-try1-lorav2-deepseeksft

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': 0.4786513133218113, 'latency_mean': 2.0889842438697817, 'latency_p50': 2.0919554233551025, 'latency_p90': 2.326383423805237}, {'batch_size': 3, 'throughput': 0.9214017285649535, 'latency_mean': 3.246285467147827, 'latency_p50': 3.246598482131958, 'latency_p90': 3.610687494277954}, {'batch_size': 5, 'throughput': 1.1525344757285856, 'latency_mean': 4.31727751493454, 'latency_p50': 4.353474140167236, 'latency_p90': 4.7981650829315186}, {'batch_size': 6, 'throughput': 1.225273704158903, 'latency_mean': 4.868083364963532, 'latency_p50': 4.870244860649109, 'latency_p90': 5.439644122123719}, {'batch_size': 8, 'throughput': 1.33078257239734, 'latency_mean': 5.956059020757675, 'latency_p50': 5.964038610458374, 'latency_p90': 6.797773623466491}, {'batch_size': 10, 'throughput': 1.4008583018533511, 'latency_mean': 7.0435788834095, 'latency_p50': 7.05419659614563, 'latency_p90': 7.888223791122437}]

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

display_name: chaiml-mistral32-sft-to_87676_v1

is_internal_developer: False

language_model: ChaiML/mistral32-sft-top10klex-dpos1-try1-lorav2-deepseeksft

model_size: 24B

ranking_group: single

throughput_3p7s: 1.04

us_pacific_date: 2025-07-06

win_ratio: 0.4881566759296017

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{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': 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-mistral32-sft-to-87676-v1-mkmlizer
Waiting for job on chaiml-mistral32-sft-to-87676-v1-mkmlizer to finish
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-87676-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-20250611-retune-u_1558_v3: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral32-sft-to-87676-v1-mkmlizer: Downloaded to shared memory in 353.768s
chaiml-mistral32-sft-to-87676-v1-mkmlizer: Checking if ChaiML/mistral32-sft-top10klex-dpos1-try1-lorav2-deepseeksft already exists in ChaiML
chaiml-mistral32-sft-to-87676-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppgqq4p3z, device:0
chaiml-mistral32-sft-to-87676-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
chaiml-mistral32-sft-to-87676-v1-mkmlizer: quantized model in 48.729s
chaiml-mistral32-sft-to-87676-v1-mkmlizer: Processed model ChaiML/mistral32-sft-top10klex-dpos1-try1-lorav2-deepseeksft in 402.498s
chaiml-mistral32-sft-to-87676-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sft-to-87676-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sft-to-87676-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sft-to-87676-v1/nvidia
chaiml-mistral32-sft-to-87676-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-to-87676-v1/nvidia/config.json
chaiml-mistral32-sft-to-87676-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sft-to-87676-v1/nvidia/tokenizer.json
chaiml-mistral32-sft-to-87676-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-to-87676-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-sft-to-87676-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-to-87676-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-sft-to-87676-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.63it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.75it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 31.58it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.52it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.03it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.23it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.09it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.47it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.70it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.88it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.65it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.58it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.58it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.72it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.42it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.85it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.52it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.68it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.62it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.00it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 19.75it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 25.29it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:10, 25.40it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 25.08it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 20.41it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.09it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 22.04it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.93it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.04it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.60it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.99it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.97it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.25it/s]
Loading 0:  40%|████      | 146/363 [00:05<00:07, 30.16it/s]
Loading 0:  41%|████▏     | 150/363 [00:05<00:08, 24.09it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:10, 20.00it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.08it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.51it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.51it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.63it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.34it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.63it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.98it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.25it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.21it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.02it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.54it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 24.93it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.93it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<04:05,  1.52s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<03:11,  1.20s/it]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:44,  1.48it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:17,  1.96it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:56,  2.65it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:37,  3.89it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  5.04it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.16it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.73it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.18it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 15.06it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.39it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.73it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.56it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.76it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.76it/s]
Loading 0:  73%|███████▎  | 265/363 [00:25<00:03, 31.31it/s]
Loading 0:  74%|███████▍  | 269/363 [00:25<00:04, 22.29it/s]
Loading 0:  75%|███████▍  | 272/363 [00:25<00:03, 22.78it/s]
Loading 0:  76%|███████▌  | 275/363 [00:25<00:04, 19.53it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.20it/s]
Loading 0:  79%|███████▉  | 286/363 [00:26<00:02, 25.70it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.21it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 26.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.64it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.73it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.14it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.28it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.53it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.34it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.16it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 23.79it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 26.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:01, 24.28it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.07it/s]
Loading 0:  95%|█████████▌| 346/363 [00:28<00:00, 18.96it/s]
Loading 0:  96%|█████████▌| 349/363 [00:28<00:00, 18.54it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 22.15it/s]
Loading 0:  98%|█████████▊| 356/363 [00:29<00:00, 23.63it/s]
Loading 0:  99%|█████████▉| 359/363 [00:29<00:00, 23.69it/s]
                                                            
Job chaiml-mistral32-sft-to-87676-v1-mkmlizer completed after 443.67s with status: succeeded
Stopping job with name chaiml-mistral32-sft-to-87676-v1-mkmlizer
Pipeline stage MKMLizer completed in 444.49s
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-mistral32-sft-to-87676-v1
Waiting for inference service chaiml-mistral32-sft-to-87676-v1 to be ready
Inference service chaiml-mistral32-sft-to-87676-v1 ready after 211.12789058685303s
Pipeline stage MKMLDeployer completed in 211.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.15037202835083s
Received healthy response to inference request in 2.484987735748291s
Received healthy response to inference request in 2.3130271434783936s
Received healthy response to inference request in 2.1896939277648926s
Received healthy response to inference request in 2.611881971359253s
5 requests
0 failed requests
5th percentile: 2.214360570907593
10th percentile: 2.239027214050293
20th percentile: 2.2883605003356933
30th percentile: 2.347419261932373
40th percentile: 2.416203498840332
50th percentile: 2.484987735748291
60th percentile: 2.5357454299926756
70th percentile: 2.5865031242370606
80th percentile: 2.919579982757569
90th percentile: 3.534976005554199
95th percentile: 3.842674016952514
99th percentile: 4.088832426071167
mean time: 2.749992561340332
Pipeline stage StressChecker completed in 15.41s
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 0.75s
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 0.78s
Shutdown handler de-registered
chaiml-mistral32-sft-to_87676_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-sft-to-87676-v1-profiler
Waiting for inference service chaiml-mistral32-sft-to-87676-v1-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 3347.82s
Shutdown handler de-registered
chaiml-mistral32-sft-to_87676_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sft-to_87676_v1 status is now torndown due to DeploymentManager action