chaiml-mistral32-sft-hi_84864

developer_uid: NischayDnk

submission_id: chaiml-mistral32-sft-hi_84864_v4

model_name: chaiml-mistral32-sft-hi_84864_v4

model_group: ChaiML/mistral32-sft-hig

status: torndown

timestamp: 2025-06-28T18:51:12+00:00

num_battles: 7293

num_wins: 3696

celo_rating: 1285.83

family_friendly_score: 0.5198

family_friendly_standard_error: 0.007065521353728966

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': 0.523432160610069, 'latency_mean': 1.9103700065612792, 'latency_p50': 1.894804835319519, 'latency_p90': 2.12973313331604}, {'batch_size': 3, 'throughput': 1.0466276385449058, 'latency_mean': 2.8533130788803103, 'latency_p50': 2.8547332286834717, 'latency_p90': 3.1366498470306396}, {'batch_size': 5, 'throughput': 1.3401696565362653, 'latency_mean': 3.7145598900318144, 'latency_p50': 3.723103404045105, 'latency_p90': 4.087080430984497}, {'batch_size': 6, 'throughput': 1.4464830650448581, 'latency_mean': 4.123789000511169, 'latency_p50': 4.100855827331543, 'latency_p90': 4.634017300605774}, {'batch_size': 8, 'throughput': 1.5868764012857117, 'latency_mean': 5.008935070037841, 'latency_p50': 5.023701429367065, 'latency_p90': 5.587312054634094}, {'batch_size': 10, 'throughput': 1.6542542891016496, 'latency_mean': 5.989421797990799, 'latency_p50': 5.982316851615906, 'latency_p90': 6.702532267570495}]

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

display_name: chaiml-mistral32-sft-hi_84864_v4

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: 2025-06-28

win_ratio: 0.5067873303167421

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-84864-v4-mkmlizer
Waiting for job on chaiml-mistral32-sft-hi-84864-v4-mkmlizer to finish
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: Downloaded to shared memory in 58.145s
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: Checking if ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1 already exists in ChaiML
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz2fxz774, device:0
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: quantized model in 47.877s
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: Processed model ChaiML/mistral32-sft-highlex20june-top5kconvos-nomask-exp1 in 106.022s
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4/config.json
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4/special_tokens_map.json
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4/tokenizer_config.json
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4/tokenizer.json
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4/flywheel_model.1.safetensors
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-hi-84864-v4/flywheel_model.0.safetensors
chaiml-mistral32-sft-hi-84864-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.70it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.88it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.48it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.30it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.55it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.52it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 34.05it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 19.65it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.33it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.62it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.79it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.99it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 27.94it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.72it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.46it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.47it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:15, 18.97it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 23.68it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.60it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.53it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.93it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.56it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.38it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 24.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.93it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 25.07it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.84it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.00it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.84it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:08, 25.84it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.75it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.91it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.33it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.14it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.60it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.74it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.34it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.36it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.00it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.87it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.66it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 28.18it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.59it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.24it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.31it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.61it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.61it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.91it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.14it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.25it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.23it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 10.99it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.81it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.42it/s]
Loading 0:  67%|██████▋   | 244/363 [00:23<00:06, 19.14it/s]
Loading 0:  68%|██████▊   | 247/363 [00:24<00:05, 20.69it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.34it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.40it/s]
Loading 0:  71%|███████   | 258/363 [00:24<00:04, 22.07it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.33it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 22.16it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.09it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.43it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.05it/s]
Loading 0:  77%|███████▋  | 280/363 [00:25<00:03, 24.25it/s]
Loading 0:  78%|███████▊  | 283/363 [00:25<00:03, 25.13it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:03, 24.90it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.33it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 24.82it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.60it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.35it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.74it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.90it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.21it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 26.93it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.19it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.27it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 26.07it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.50it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 27.16it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.71it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.26it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.13it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.37it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.27it/s]
                                                            
Job chaiml-mistral32-sft-hi-84864-v4-mkmlizer completed after 135.46s with status: succeeded
Stopping job with name chaiml-mistral32-sft-hi-84864-v4-mkmlizer
Pipeline stage MKMLizer completed in 136.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-sft-hi-84864-v4
Waiting for inference service chaiml-mistral32-sft-hi-84864-v4 to be ready
Inference service chaiml-mistral32-sft-hi-84864-v4 ready after 170.59130024909973s
Pipeline stage MKMLDeployer completed in 171.29s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.674630880355835s
Received healthy response to inference request in 2.0656301975250244s
Received healthy response to inference request in 1.9362964630126953s
Received healthy response to inference request in 1.953927755355835s
5 requests
1 failed requests
5th percentile: 1.9398227214813233
10th percentile: 1.9433489799499513
20th percentile: 1.950401496887207
30th percentile: 1.9762682437896728
40th percentile: 2.0209492206573487
50th percentile: 2.0656301975250244
60th percentile: 2.3092304706573485
70th percentile: 2.5528307437896727
80th percentile: 6.173658800125125
90th percentile: 13.171714639663698
95th percentile: 16.67074255943298
99th percentile: 19.469964895248413
mean time: 5.760051155090332
%s, retrying in %s seconds...
Received healthy response to inference request in 2.08015513420105s
Received healthy response to inference request in 1.930119514465332s
Received healthy response to inference request in 2.130958080291748s
Received healthy response to inference request in 2.0213358402252197s
Received healthy response to inference request in 2.225778341293335s
5 requests
0 failed requests
5th percentile: 1.9483627796173095
10th percentile: 1.966606044769287
20th percentile: 2.003092575073242
30th percentile: 2.0330996990203856
40th percentile: 2.0566274166107177
50th percentile: 2.08015513420105
60th percentile: 2.100476312637329
70th percentile: 2.1207974910736085
80th percentile: 2.1499221324920654
90th percentile: 2.1878502368927
95th percentile: 2.2068142890930176
99th percentile: 2.2219855308532717
mean time: 2.077669382095337
Pipeline stage StressChecker completed in 42.01s
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 0.73s
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 0.74s
Shutdown handler de-registered
chaiml-mistral32-sft-hi_84864_v4 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 3311.41s
Shutdown handler de-registered
chaiml-mistral32-sft-hi_84864_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sft-hi_84864_v4 status is now torndown due to DeploymentManager action