chaiml-mistral31-24b-dpo_1260

developer_uid: NischayDnk

submission_id: chaiml-mistral31-24b-dpo_1260_v1

model_name: chaiml-mistral31-24b-dpo_1260_v1

model_group: ChaiML/mistral31-24b-dpo

status: torndown

timestamp: 2025-05-12T12:16:43+00:00

num_battles: 12413

num_wins: 6689

celo_rating: 1312.68

family_friendly_score: 0.5334

family_friendly_standard_error: 0.007055273772150873

submission_type: basic

model_repo: ChaiML/mistral31-24b-dpoexp1-s1-new-sft-retryv2top20lex-2e-b02

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.558806955761434, 'latency_mean': 1.7894602012634278, 'latency_p50': 1.7594678401947021, 'latency_p90': 2.0073797702789307}, {'batch_size': 4, 'throughput': 1.3817638890878559, 'latency_mean': 2.8842546558380127, 'latency_p50': 2.873005747795105, 'latency_p90': 3.192771482467651}, {'batch_size': 5, 'throughput': 1.5411412996751892, 'latency_mean': 3.2241232907772064, 'latency_p50': 3.1954901218414307, 'latency_p90': 3.550752568244934}, {'batch_size': 8, 'throughput': 1.863478880811637, 'latency_mean': 4.263292555809021, 'latency_p50': 4.281317591667175, 'latency_p90': 4.769217181205749}, {'batch_size': 10, 'throughput': 1.9806049224811224, 'latency_mean': 5.00100772857666, 'latency_p50': 4.981201529502869, 'latency_p90': 5.661907148361206}, {'batch_size': 12, 'throughput': 2.047046653990181, 'latency_mean': 5.7914521551132205, 'latency_p50': 5.7379831075668335, 'latency_p90': 6.5057152032852175}, {'batch_size': 15, 'throughput': 2.1089483127571036, 'latency_mean': 7.005198537111283, 'latency_p50': 7.021147131919861, 'latency_p90': 7.99813859462738}]

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

display_name: chaiml-mistral31-24b-dpo_1260_v1

is_internal_developer: False

language_model: ChaiML/mistral31-24b-dpoexp1-s1-new-sft-retryv2top20lex-2e-b02

model_size: 24B

ranking_group: single

throughput_3p7s: 1.72

us_pacific_date: 2025-05-12

win_ratio: 0.5388705389510997

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': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 768, '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-mistral31-24b-dpo-1260-v1-mkmlizer
Waiting for job on chaiml-mistral31-24b-dpo-1260-v1-mkmlizer to finish
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: Downloaded to shared memory in 76.140s
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyvmhay7a, device:0
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: quantized model in 53.086s
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: Processed model ChaiML/mistral31-24b-dpoexp1-s1-new-sft-retryv2top20lex-2e-b02 in 129.227s
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1/config.json
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1/special_tokens_map.json
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1/tokenizer_config.json
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1/tokenizer.json
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1/flywheel_model.1.safetensors
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-dpo-1260-v1/flywheel_model.0.safetensors
chaiml-mistral31-24b-dpo-1260-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.17it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.00it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 34.19it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.87it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.00it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.51it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 21.91it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.71it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.97it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.04it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.97it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.09it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.37it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.43it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.07it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.27it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.64it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.03it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.45it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.52it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.96it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.77it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.82it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.78it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.28it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.79it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.26it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.75it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.01it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.18it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.76it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.74it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.20it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.16it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 23.61it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.63it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.05it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.82it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.83it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.20it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.84it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.23it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.24it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.16it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.16it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:57,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.23it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.94it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.19it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.35it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.37it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.42it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.04it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.94it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.27it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.27it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.55it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.34it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 32.00it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.90it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 22.88it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 21.98it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.68it/s]
Loading 0:  79%|███████▊  | 285/363 [00:24<00:03, 24.41it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.58it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.89it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 24.86it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.28it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.31it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.47it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.58it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.04it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.01it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 26.07it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.41it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 26.53it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:12,  1.71it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.84it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.55it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.25it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.82it/s]
                                                            
Job chaiml-mistral31-24b-dpo-1260-v1-mkmlizer completed after 155.5s with status: succeeded
Stopping job with name chaiml-mistral31-24b-dpo-1260-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral31-24b-dpo-1260-v1
Waiting for inference service chaiml-mistral31-24b-dpo-1260-v1 to be ready
Inference service chaiml-mistral31-24b-dpo-1260-v1 ready after 110.43482708930969s
Pipeline stage MKMLDeployer completed in 110.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.722618341445923s
Received healthy response to inference request in 2.09592866897583s
Received healthy response to inference request in 1.9260952472686768s
Received healthy response to inference request in 2.16363525390625s
Received healthy response to inference request in 1.9608917236328125s
5 requests
0 failed requests
5th percentile: 1.933054542541504
10th percentile: 1.940013837814331
20th percentile: 1.9539324283599853
30th percentile: 1.987899112701416
40th percentile: 2.041913890838623
50th percentile: 2.09592866897583
60th percentile: 2.1230113029479982
70th percentile: 2.150093936920166
80th percentile: 2.2754318714141846
90th percentile: 2.4990251064300537
95th percentile: 2.6108217239379883
99th percentile: 2.7002590179443358
mean time: 2.1738338470458984
Pipeline stage StressChecker completed in 12.26s
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 0.72s
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-mistral31-24b-dpo_1260_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral31-24b-dpo-1260-v1-profiler
Waiting for inference service chaiml-mistral31-24b-dpo-1260-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 2626.55s
Shutdown handler de-registered
chaiml-mistral31-24b-dpo_1260_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-24b-dpo_1260_v1 status is now torndown due to DeploymentManager action