developer_uid: NischayDnk
submission_id: chaiml-mistral31-ff4kex_97458_v1
model_name: chaiml-mistral31-ff4kex_97458_v1
model_group: ChaiML/mistral31-ff4kexp
status: torndown
timestamp: 2025-04-11T16:29:30+00:00
num_battles: 7530
num_wins: 3984
celo_rating: 1304.84
family_friendly_score: 0.5322
family_friendly_standard_error: 0.007056389445034904
submission_type: basic
model_repo: ChaiML/mistral31-ff4kexp1-dpo-v1-beta05-data31prefpubv1
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': 0.36791011286377323, 'latency_mean': 2.7179617965221405, 'latency_p50': 2.725490689277649, 'latency_p90': 3.02220561504364}, {'batch_size': 2, 'throughput': 0.5763838054238526, 'latency_mean': 3.4630993640422822, 'latency_p50': 3.4361164569854736, 'latency_p90': 3.8168325662612914}, {'batch_size': 3, 'throughput': 0.7227787485184153, 'latency_mean': 4.148099530935287, 'latency_p50': 4.166109204292297, 'latency_p90': 4.57049720287323}, {'batch_size': 4, 'throughput': 0.8344202366220601, 'latency_mean': 4.770587310791016, 'latency_p50': 4.770927429199219, 'latency_p90': 5.2978291511535645}, {'batch_size': 5, 'throughput': 0.9185867469539145, 'latency_mean': 5.408405299186707, 'latency_p50': 5.42803418636322, 'latency_p90': 6.0889003515243525}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mistral31-ff4kex_97458_v1
is_internal_developer: False
language_model: ChaiML/mistral31-ff4kexp1-dpo-v1-beta05-data31prefpubv1
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-04-11
win_ratio: 0.5290836653386454
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 70, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\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': 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-ff4kex-97458-v1-mkmlizer
Waiting for job on chaiml-mistral31-ff4kex-97458-v1-mkmlizer to finish
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: Downloaded to shared memory in 75.331s
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8wa6tsji, device:0
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: quantized model in 53.118s
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: Processed model ChaiML/mistral31-ff4kexp1-dpo-v1-beta05-data31prefpubv1 in 128.449s
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1/config.json
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1/special_tokens_map.json
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1/tokenizer_config.json
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1/tokenizer.json
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1/flywheel_model.1.safetensors
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-97458-v1/flywheel_model.0.safetensors
chaiml-mistral31-ff4kex-97458-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.08it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.92it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 34.29it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.64it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.80it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.29it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.07it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.78it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.12it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.02it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.60it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 31.05it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.03it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 29.86it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.12it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.04it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.00it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:11, 25.46it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.18it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.49it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.95it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.26it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.41it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 23.34it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.04it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.75it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.16it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.54it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.06it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.63it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.92it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 33.19it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 24.35it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.51it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.64it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.73it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 28.49it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 27.93it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.01it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.55it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.67it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 27.47it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 24.73it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.33it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.40it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.40it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.92it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.19it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.38it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.47it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:14,  9.04it/s]
Loading 0:  64%|██████▎   | 231/363 [00:22<00:12, 10.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.41it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.91it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.06it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.54it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 24.43it/s]
Loading 0:  71%|███████   | 258/363 [00:23<00:04, 22.42it/s]
Loading 0:  73%|███████▎  | 264/363 [00:23<00:03, 29.35it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 23.20it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.84it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.02it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.35it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.28it/s]
Loading 0:  79%|███████▊  | 285/363 [00:24<00:03, 24.20it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.50it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 29.19it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.23it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.97it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.78it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:01, 25.51it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.59it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.20it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.74it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.48it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.18it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 28.26it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.80it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.50it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.17it/s]
Loading 0:  99%|█████████▊| 358/363 [00:34<00:00,  6.19it/s]
                                                            

Job chaiml-mistral31-ff4kex-97458-v1-mkmlizer completed after 156.41s with status: succeeded
Stopping job with name chaiml-mistral31-ff4kex-97458-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral31-ff4kex-97458-v1
Waiting for inference service chaiml-mistral31-ff4kex-97458-v1 to be ready
Inference service chaiml-mistral31-ff4kex-97458-v1 ready after 110.41997599601746s
Pipeline stage MKMLDeployer completed in 110.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.75097393989563s
Received healthy response to inference request in 2.5096049308776855s
Received healthy response to inference request in 2.7324044704437256s
Received healthy response to inference request in 2.621673107147217s
Received healthy response to inference request in 2.6589481830596924s
5 requests
0 failed requests
5th percentile: 2.5320185661315917
10th percentile: 2.554432201385498
20th percentile: 2.5992594718933106
30th percentile: 2.629128122329712
40th percentile: 2.6440381526947023
50th percentile: 2.6589481830596924
60th percentile: 2.6883306980133055
70th percentile: 2.717713212966919
80th percentile: 2.9361183643341064
90th percentile: 3.343546152114868
95th percentile: 3.547260046005249
99th percentile: 3.710231161117554
mean time: 2.85472092628479
Pipeline stage StressChecker completed in 15.81s
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 0.69s
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 0.71s
Shutdown handler de-registered
chaiml-mistral31-ff4kex_97458_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral31-ff4kex-97458-v1-profiler
Waiting for inference service chaiml-mistral31-ff4kex-97458-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5529.78s
Shutdown handler de-registered
chaiml-mistral31-ff4kex_97458_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-ff4kex_97458_v1 status is now torndown due to DeploymentManager action