chaiml-slerpv5-mistral_24540

developer_uid: richhx

submission_id: chaiml-slerpv5-mistral_24540_v20

model_name: chaiml-slerpv5-mistral_24540_v20

model_group: ChaiML/slerpv5_mistral31

status: torndown

timestamp: 2025-06-20T23:04:54+00:00

num_battles: 6949

num_wins: 3277

celo_rating: 1270.17

family_friendly_score: 0.5822

family_friendly_standard_error: 0.006974857131153297

submission_type: basic

model_repo: ChaiML/slerpv5_mistral31_simpo_dpo_dpoold_s2

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': 0.5254768407751078, 'latency_mean': 1.9029349505901336, 'latency_p50': 1.9038993120193481, 'latency_p90': 2.1248730421066284}, {'batch_size': 3, 'throughput': 1.0560596013556944, 'latency_mean': 2.8331117153167726, 'latency_p50': 2.8147934675216675, 'latency_p90': 3.154438591003418}, {'batch_size': 5, 'throughput': 1.333956025774297, 'latency_mean': 3.714743257761002, 'latency_p50': 3.7119123935699463, 'latency_p90': 4.101731777191162}, {'batch_size': 6, 'throughput': 1.4530995907615998, 'latency_mean': 4.112733929157257, 'latency_p50': 4.0691492557525635, 'latency_p90': 4.634633183479309}, {'batch_size': 8, 'throughput': 1.5670768742309622, 'latency_mean': 5.0719671320915225, 'latency_p50': 5.062021613121033, 'latency_p90': 5.697531580924988}, {'batch_size': 10, 'throughput': 1.659984933226009, 'latency_mean': 5.958725508451462, 'latency_p50': 5.970112681388855, 'latency_p90': 6.735493946075439}]

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

display_name: chaiml-slerpv5-mistral_24540_v20

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/slerpv5_mistral31_simpo_dpo_dpoold_s2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-06-20

win_ratio: 0.4715786444092675

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_start|>', '\n', '<|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-slerpv5-mistral-24540-v20-mkmlizer
Waiting for job on chaiml-slerpv5-mistral-24540-v20-mkmlizer to finish
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║                                                                     ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║                                                                     ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║                                                                     ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  belonging to:                                                      ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║                                                                     ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ║                                                                     ║
chaiml-slerpv5-mistral-24540-v20-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-slerpv5-mistral-24540-v20-mkmlizer: Downloaded to shared memory in 61.389s
chaiml-slerpv5-mistral-24540-v20-mkmlizer: Checking if ChaiML/slerpv5_mistral31_simpo_dpo_dpoold_s2 already exists in ChaiML
chaiml-slerpv5-mistral-24540-v20-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp53cpharv, device:0
chaiml-slerpv5-mistral-24540-v20-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv5-mistral-24540-v20-mkmlizer: quantized model in 48.189s
chaiml-slerpv5-mistral-24540-v20-mkmlizer: Processed model ChaiML/slerpv5_mistral31_simpo_dpo_dpoold_s2 in 109.579s
chaiml-slerpv5-mistral-24540-v20-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv5-mistral-24540-v20-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20
chaiml-slerpv5-mistral-24540-v20-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20/config.json
chaiml-slerpv5-mistral-24540-v20-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20/special_tokens_map.json
chaiml-slerpv5-mistral-24540-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20/tokenizer_config.json
chaiml-slerpv5-mistral-24540-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20/tokenizer.json
chaiml-slerpv5-mistral-24540-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20/flywheel_model.1.safetensors
chaiml-slerpv5-mistral-24540-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv5-mistral-24540-v20/flywheel_model.0.safetensors
chaiml-slerpv5-mistral-24540-v20-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:44,  3.12s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:04,  1.17it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:48,  3.22it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:15,  4.60it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:53,  6.35it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:44,  7.59it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:28, 11.54it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:26, 12.61it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.52it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.84it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 22.41it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 22.77it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 25.78it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 19.30it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:13, 22.63it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:13, 21.75it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.93it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 26.29it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 28.87it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:09, 27.48it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 29.87it/s]
Loading 0:  27%|██▋       | 99/363 [00:10<00:12, 21.87it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:11, 23.54it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 22.19it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 27.24it/s]
Loading 0:  32%|███▏      | 115/363 [00:10<00:09, 24.85it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 29.07it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 27.56it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 30.06it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 28.35it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 23.17it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 21.71it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:08, 26.48it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:08, 24.46it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 29.26it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 27.78it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 30.21it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 28.29it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 30.76it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 21.20it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 24.67it/s]
Loading 0:  52%|█████▏    | 187/363 [00:28<03:15,  1.11s/it]
Loading 0:  53%|█████▎    | 191/363 [00:28<02:16,  1.26it/s]
Loading 0:  53%|█████▎    | 194/363 [00:28<01:44,  1.62it/s]
Loading 0:  54%|█████▍    | 197/363 [00:28<01:17,  2.13it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:48,  3.30it/s]
Loading 0:  56%|█████▋    | 205/363 [00:28<00:38,  4.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:23,  6.54it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<00:18,  7.91it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:14,  9.93it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:12, 11.11it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:08, 15.69it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:07, 17.39it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:05, 20.86it/s]
Loading 0:  67%|██████▋   | 242/363 [00:30<00:05, 21.25it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:04, 24.77it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 24.68it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 21.29it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.62it/s]
Loading 0:  73%|███████▎  | 265/363 [00:31<00:03, 25.49it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:03, 23.91it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 28.82it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:03, 27.53it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 29.96it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 28.12it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 30.38it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 21.10it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 24.18it/s]
Loading 0:  84%|████████▎ | 304/363 [00:32<00:02, 22.88it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 27.97it/s]
Loading 0:  87%|████████▋ | 314/363 [00:32<00:01, 26.90it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:01, 29.03it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:01, 27.70it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 29.45it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 20.92it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 24.36it/s]
Loading 0:  94%|█████████▎| 340/363 [00:34<00:01, 22.81it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 27.73it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 26.83it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 29.48it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 27.77it/s]
                                                            
Job chaiml-slerpv5-mistral-24540-v20-mkmlizer completed after 196.7s with status: succeeded
Stopping job with name chaiml-slerpv5-mistral-24540-v20-mkmlizer
Pipeline stage MKMLizer completed in 197.20s
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-slerpv5-mistral-24540-v20
Waiting for inference service chaiml-slerpv5-mistral-24540-v20 to be ready
Inference service chaiml-slerpv5-mistral-24540-v20 ready after 120.45123147964478s
Pipeline stage MKMLDeployer completed in 121.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.554687023162842s
Received healthy response to inference request in 1.8570477962493896s
Received healthy response to inference request in 1.9312899112701416s
Received healthy response to inference request in 1.9063637256622314s
Received healthy response to inference request in 1.927962303161621s
5 requests
0 failed requests
5th percentile: 1.866910982131958
10th percentile: 1.8767741680145265
20th percentile: 1.896500539779663
30th percentile: 1.9106834411621094
40th percentile: 1.9193228721618651
50th percentile: 1.927962303161621
60th percentile: 1.9292933464050293
70th percentile: 1.9306243896484374
80th percentile: 2.0559693336486817
90th percentile: 2.3053281784057615
95th percentile: 2.4300076007843017
99th percentile: 2.529751138687134
mean time: 2.035470151901245
Pipeline stage StressChecker completed in 11.58s
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 0.77s
Shutdown handler de-registered
chaiml-slerpv5-mistral_24540_v20 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 0.35s
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-slerpv5-mistral-24540-v20-profiler
Waiting for inference service chaiml-slerpv5-mistral-24540-v20-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 3416.23s
Shutdown handler de-registered
chaiml-slerpv5-mistral_24540_v20 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv5-mistral_24540_v20 status is now torndown due to DeploymentManager action