chaiml-mistral32-sft-hi_84864

developer_uid: NischayDnk

submission_id: chaiml-mistral32-sft-hi_84864_v2

model_name: chaiml-mistral32-sft-hi_84864_v2

model_group: ChaiML/mistral32-sft-hig

status: torndown

timestamp: 2025-06-24T01:26:31+00:00

num_battles: 6187

num_wins: 3249

celo_rating: 1302.37

family_friendly_score: 0.51

family_friendly_standard_error: 0.007069653456853455

submission_type: basic

model_repo: ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1

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': 0.5182949224465153, 'latency_mean': 1.929303411245346, 'latency_p50': 1.9340357780456543, 'latency_p90': 2.129766082763672}, {'batch_size': 3, 'throughput': 1.0593004758648334, 'latency_mean': 2.822384703159332, 'latency_p50': 2.823474884033203, 'latency_p90': 3.181491255760193}, {'batch_size': 5, 'throughput': 1.3419433824890963, 'latency_mean': 3.714599225521088, 'latency_p50': 3.672097086906433, 'latency_p90': 4.131584525108337}, {'batch_size': 6, 'throughput': 1.4339471170769935, 'latency_mean': 4.150134644508362, 'latency_p50': 4.117204904556274, 'latency_p90': 4.6863703489303585}, {'batch_size': 8, 'throughput': 1.5542794312973212, 'latency_mean': 5.100369390249252, 'latency_p50': 5.07566773891449, 'latency_p90': 5.685245561599731}, {'batch_size': 10, 'throughput': 1.6522268410314827, 'latency_mean': 6.001339931488037, 'latency_p50': 5.979943752288818, 'latency_p90': 6.709035420417785}]

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

display_name: chaiml-mistral32-sft-hi_84864_v2

is_internal_developer: False

language_model: ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-06-23

win_ratio: 0.5251333441086148

generation_params: {'temperature': 0.6, 'top_p': 0.9, 'min_p': 0.05, '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|>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': 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-sft-hi-84864-v2-mkmlizer
Waiting for job on chaiml-mistral32-sft-hi-84864-v2-mkmlizer to finish
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: Downloaded to shared memory in 122.256s
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: Checking if ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1 already exists in ChaiML
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprod1xzkd, device:0
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: quantized model in 49.299s
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: Processed model ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1 in 171.556s
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2/config.json
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2/special_tokens_map.json
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2/tokenizer_config.json
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2/tokenizer.json
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2/flywheel_model.1.safetensors
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v2/flywheel_model.0.safetensors
chaiml-mistral32-sft-hi-84864-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.66it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.29it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 31.92it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.42it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.02it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.50it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.87it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 20.71it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.29it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:13, 24.49it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 26.19it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.04it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.20it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.60it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.42it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.99it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.08it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.31it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 23.32it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.35it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.75it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.73it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 26.39it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 22.88it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.71it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 25.07it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.77it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.59it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.64it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 27.74it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 23.30it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.87it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.27it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 33.57it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:09, 22.74it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:09, 22.39it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:09, 21.12it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.75it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.44it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.04it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 26.59it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.62it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.13it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.22it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.04it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.18it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:07, 23.13it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.13it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<04:11,  1.55s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:16,  1.23s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:47,  1.44it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:19,  1.92it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:57,  2.59it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:38,  3.77it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:29,  4.87it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.90it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.36it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.70it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.31it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.56it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 20.94it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 23.77it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.12it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 29.16it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.38it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.04it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 22.10it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 22.85it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.37it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.81it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.73it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 26.96it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.56it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.64it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.63it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.43it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.73it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.39it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.06it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.05it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 26.47it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:01, 24.78it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.66it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 19.87it/s]
Loading 0:  96%|█████████▌| 349/363 [00:29<00:00, 19.01it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 24.20it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 22.17it/s]
                                                            
Job chaiml-mistral32-sft-hi-84864-v2-mkmlizer completed after 196.99s with status: succeeded
Stopping job with name chaiml-mistral32-sft-hi-84864-v2-mkmlizer
Pipeline stage MKMLizer completed in 197.47s
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-hi-84864-v2
Waiting for inference service chaiml-mistral32-sft-hi-84864-v2 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-mistral32-sft-hi-84864-v2 ready after 130.44661617279053s
Pipeline stage MKMLDeployer completed in 130.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6554653644561768s
Received healthy response to inference request in 1.971818208694458s
Received healthy response to inference request in 2.621849536895752s
Received healthy response to inference request in 1.9130408763885498s
Received healthy response to inference request in 1.9564898014068604s
5 requests
0 failed requests
5th percentile: 1.9217306613922118
10th percentile: 1.930420446395874
20th percentile: 1.9478000164031983
30th percentile: 1.95955548286438
40th percentile: 1.965686845779419
50th percentile: 1.971818208694458
60th percentile: 2.2318307399749755
70th percentile: 2.491843271255493
80th percentile: 2.628572702407837
90th percentile: 2.642019033432007
95th percentile: 2.648742198944092
99th percentile: 2.6541207313537596
mean time: 2.223732757568359
Pipeline stage StressChecker completed in 12.44s
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 0.68s
Shutdown handler de-registered
chaiml-mistral32-sft-hi_84864_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-sft-hi-84864-v2-profiler
Waiting for inference service chaiml-mistral32-sft-hi-84864-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 2968.80s
Shutdown handler de-registered
chaiml-mistral32-sft-hi_84864_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sft-hi_84864_v2 status is now torndown due to DeploymentManager action