chaiml-mistral32-sft-hi_11245

developer_uid: NischayDnk

submission_id: chaiml-mistral32-sft-hi_11245_v1

model_name: chaiml-mistral32-sft-hi_11245_v1

model_group: ChaiML/mistral32-sft-hig

status: torndown

timestamp: 2025-06-24T06:29:01+00:00

num_battles: 7142

num_wins: 3835

celo_rating: 1302.15

family_friendly_score: 0.5156000000000001

family_friendly_standard_error: 0.007067625343777075

submission_type: basic

model_repo: ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1-1-1

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': 0.5199719504018987, 'latency_mean': 1.9230552852153777, 'latency_p50': 1.9054844379425049, 'latency_p90': 2.133906626701355}, {'batch_size': 3, 'throughput': 1.0598071512889893, 'latency_mean': 2.8230800247192382, 'latency_p50': 2.8292934894561768, 'latency_p90': 3.1618212461471558}, {'batch_size': 5, 'throughput': 1.347076690602598, 'latency_mean': 3.680689355134964, 'latency_p50': 3.6854718923568726, 'latency_p90': 4.068614912033081}, {'batch_size': 6, 'throughput': 1.439921355644205, 'latency_mean': 4.129153635501861, 'latency_p50': 4.132846236228943, 'latency_p90': 4.565538644790649}, {'batch_size': 8, 'throughput': 1.5863107057368686, 'latency_mean': 4.988382794857025, 'latency_p50': 4.9884644746780396, 'latency_p90': 5.562934255599975}, {'batch_size': 10, 'throughput': 1.6791274091242314, 'latency_mean': 5.893009105920791, 'latency_p50': 5.899548768997192, 'latency_p90': 6.782896065711975}]

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

display_name: chaiml-mistral32-sft-hi_11245_v1

is_internal_developer: False

language_model: ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1-1-1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-06-23

win_ratio: 0.5369644357322879

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_end|>', '<|im_start|>'], '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-11245-v1-mkmlizer
Waiting for job on chaiml-mistral32-sft-hi-11245-v1-mkmlizer to finish
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: Downloaded to shared memory in 74.493s
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: Checking if ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1-1-1 already exists in ChaiML
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv9c4gqq3, device:0
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: quantized model in 48.802s
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: Processed model ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1-1-1 in 123.336s
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1/config.json
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1/special_tokens_map.json
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1/tokenizer_config.json
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1/tokenizer.json
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1/flywheel_model.1.safetensors
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-11245-v1/flywheel_model.0.safetensors
chaiml-mistral32-sft-hi-11245-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.43it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.75it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.60it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.16it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.33it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.72it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:09, 35.15it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:15, 21.71it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:14, 22.38it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:17, 18.92it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 24.14it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.90it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.37it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.64it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.65it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.02it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.82it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.13it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.32it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.45it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.87it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 26.28it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:09, 26.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.90it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 19.91it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 23.56it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 23.63it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.12it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:10, 23.50it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.79it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.59it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.49it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.13it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.92it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 23.35it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:10, 20.16it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.32it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.45it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.80it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.83it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 27.33it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.03it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.22it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.65it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.38it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.62it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.89it/s]
Loading 0:  55%|█████▌    | 200/363 [00:08<00:06, 26.60it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 26.60it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<04:11,  1.55s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<03:14,  1.21s/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<00:55,  2.67it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:37,  3.89it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  5.05it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.05it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.06it/s]
Loading 0:  64%|██████▍   | 232/363 [00:24<00:12, 10.89it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.59it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.59it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.01it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.99it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.19it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 30.00it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 23.03it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 22.07it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 23.37it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.96it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.07it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.58it/s]
Loading 0:  80%|███████▉  | 289/363 [00:26<00:02, 27.97it/s]
Loading 0:  81%|████████  | 293/363 [00:26<00:02, 23.93it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 28.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.41it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.71it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.42it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 24.16it/s]
Loading 0:  87%|████████▋ | 316/363 [00:27<00:01, 25.14it/s]
Loading 0:  88%|████████▊ | 319/363 [00:27<00:01, 25.52it/s]
Loading 0:  89%|████████▊ | 322/363 [00:27<00:01, 24.85it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 27.52it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 24.39it/s]
Loading 0:  92%|█████████▏| 334/363 [00:27<00:01, 27.57it/s]
Loading 0:  93%|█████████▎| 337/363 [00:28<00:01, 23.59it/s]
Loading 0:  94%|█████████▎| 340/363 [00:28<00:00, 25.01it/s]
Loading 0:  94%|█████████▍| 343/363 [00:28<00:01, 15.15it/s]
Loading 0:  96%|█████████▌| 348/363 [00:28<00:00, 17.80it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 23.14it/s]
Loading 0:  98%|█████████▊| 357/363 [00:29<00:00, 22.10it/s]
                                                            
Job chaiml-mistral32-sft-hi-11245-v1-mkmlizer completed after 156.66s with status: succeeded
Stopping job with name chaiml-mistral32-sft-hi-11245-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-sft-hi-11245-v1
Waiting for inference service chaiml-mistral32-sft-hi-11245-v1 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', '')
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', '')
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-11245-v1 ready after 130.8753218650818s
Pipeline stage MKMLDeployer completed in 131.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5315394401550293s
Received healthy response to inference request in 1.993659257888794s
Received healthy response to inference request in 2.286402702331543s
Received healthy response to inference request in 1.9624133110046387s
Received healthy response to inference request in 2.0938735008239746s
5 requests
0 failed requests
5th percentile: 1.9686625003814697
10th percentile: 1.9749116897583008
20th percentile: 1.987410068511963
30th percentile: 2.0137021064758303
40th percentile: 2.0537878036499024
50th percentile: 2.0938735008239746
60th percentile: 2.170885181427002
70th percentile: 2.2478968620300295
80th percentile: 2.33543004989624
90th percentile: 2.433484745025635
95th percentile: 2.482512092590332
99th percentile: 2.52173397064209
mean time: 2.173577642440796
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 0.84s
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 0.73s
Shutdown handler de-registered
chaiml-mistral32-sft-hi_11245_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral32-sft-hi-11245-v1-profiler
Waiting for inference service chaiml-mistral32-sft-hi-11245-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 2995.16s
Shutdown handler de-registered
chaiml-mistral32-sft-hi_11245_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sft-hi_11245_v1 status is now torndown due to DeploymentManager action