chaiml-devstral-24b-dpo_14531

developer_uid: rirv938

submission_id: chaiml-devstral-24b-dpo_14531_v3

model_name: chaiml-devstral-24b-dpo_14531_v3

model_group: ChaiML/devstral-24b-dpos

status: torndown

timestamp: 2025-07-08T15:10:50+00:00

num_battles: 11302

num_wins: 5808

celo_rating: 1306.22

family_friendly_score: 0.5287999999999999

family_friendly_standard_error: 0.007059328013345179

submission_type: basic

model_repo: ChaiML/devstral-24b-dpos1-prefsftgrok-v1-2e-11k-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': 0.5212174691238421, 'latency_mean': 1.918373178243637, 'latency_p50': 1.9114760160446167, 'latency_p90': 2.1300495624542237}, {'batch_size': 3, 'throughput': 1.0536040064053576, 'latency_mean': 2.8411153662204742, 'latency_p50': 2.838402271270752, 'latency_p90': 3.1057861566543576}, {'batch_size': 5, 'throughput': 1.3412810638917536, 'latency_mean': 3.7025032687187194, 'latency_p50': 3.7268409729003906, 'latency_p90': 4.11693959236145}, {'batch_size': 6, 'throughput': 1.4440799210281188, 'latency_mean': 4.121423021554947, 'latency_p50': 4.1568214893341064, 'latency_p90': 4.554549837112427}, {'batch_size': 8, 'throughput': 1.597620943833391, 'latency_mean': 4.975575693845749, 'latency_p50': 4.972834944725037, 'latency_p90': 5.5498268604278564}, {'batch_size': 10, 'throughput': 1.6725625140229956, 'latency_mean': 5.922332562208176, 'latency_p50': 5.902511358261108, 'latency_p90': 6.706295108795166}]

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

display_name: chaiml-devstral-24b-dpo_14531_v3

is_internal_developer: True

language_model: ChaiML/devstral-24b-dpos1-prefsftgrok-v1-2e-11k-1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-08

win_ratio: 0.5138913466643072

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['</s>', '\n', 'You:', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', '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-devstral-24b-dpo-14531-v3-mkmlizer
Waiting for job on chaiml-devstral-24b-dpo-14531-v3-mkmlizer to finish
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║                                                                     ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║                                                                     ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║                                                                     ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║                                                                     ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ║                                                                     ║
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: Downloaded to shared memory in 161.591s
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: Checking if ChaiML/devstral-24b-dpos1-prefsftgrok-v1-2e-11k-1 already exists in ChaiML
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq0f1ao72, device:0
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: quantized model in 50.789s
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: Processed model ChaiML/devstral-24b-dpos1-prefsftgrok-v1-2e-11k-1 in 212.381s
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia/config.json
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia/special_tokens_map.json
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia/tokenizer_config.json
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia/tokenizer.json
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia/flywheel_model.1.safetensors
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-devstral-24b-dpo-14531-v3/nvidia/flywheel_model.0.safetensors
chaiml-devstral-24b-dpo-14531-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 19.95it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.50it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.48it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.78it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.97it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 32.45it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.44it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 20.81it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.12it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.07it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 23.45it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:12, 24.78it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 23.80it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 24.75it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:11, 25.42it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.45it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 24.37it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.04it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 18.97it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 19.79it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:13, 21.83it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:14, 19.80it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:12, 21.84it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:14, 19.63it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:11, 23.58it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:11, 23.17it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.81it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 24.61it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 23.85it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 25.13it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:13, 18.89it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:13, 18.36it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 24.15it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:09, 24.86it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:09, 25.04it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.24it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 25.08it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.67it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.93it/s]
Loading 0:  40%|████      | 147/363 [00:06<00:06, 32.46it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 23.20it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.53it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.71it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.08it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 24.42it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:07, 24.96it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 23.83it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 25.32it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 25.93it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 24.99it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.99it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 28.13it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 17.01it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.64it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 20.90it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 22.21it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 22.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:11,  1.56s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:15,  1.22s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:46,  1.46it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:18,  1.93it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:56,  2.62it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:37,  3.83it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.95it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.95it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.45it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.80it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.38it/s]
Loading 0:  67%|██████▋   | 244/363 [00:25<00:06, 19.02it/s]
Loading 0:  68%|██████▊   | 247/363 [00:25<00:05, 20.67it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 21.66it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 24.85it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.69it/s]
Loading 0:  72%|███████▏  | 263/363 [00:25<00:03, 28.41it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:04, 22.56it/s]
Loading 0:  74%|███████▍  | 270/363 [00:26<00:04, 19.63it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:03, 22.76it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 23.16it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.06it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.55it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.12it/s]
Loading 0:  81%|████████  | 294/363 [00:27<00:02, 25.09it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 27.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 23.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.82it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.00it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.60it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.69it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 23.98it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.75it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.49it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.42it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 25.98it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.48it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 20.98it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.72it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 24.95it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 23.24it/s]
                                                            
Job chaiml-devstral-24b-dpo-14531-v3-mkmlizer completed after 240.71s with status: succeeded
Stopping job with name chaiml-devstral-24b-dpo-14531-v3-mkmlizer
Pipeline stage MKMLizer completed in 241.50s
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-devstral-24b-dpo-14531-v3
Waiting for inference service chaiml-devstral-24b-dpo-14531-v3 to be ready
Failed to get response for submission chaiml-adrian-your-toxi_89049_v2: HTTPConnectionPool(host='chaiml-adrian-your-toxi-89049-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-devstral-24b-dpo-14531-v3 ready after 403.8257489204407s
Pipeline stage MKMLDeployer completed in 404.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.702291488647461s
Received healthy response to inference request in 3.640378475189209s
Received healthy response to inference request in 2.0676395893096924s
Received healthy response to inference request in 1.8584768772125244s
Received healthy response to inference request in 1.9204556941986084s
5 requests
0 failed requests
5th percentile: 1.8708726406097411
10th percentile: 1.883268404006958
20th percentile: 1.9080599308013917
30th percentile: 1.9498924732208252
40th percentile: 2.008766031265259
50th percentile: 2.0676395893096924
60th percentile: 2.3215003490447996
70th percentile: 2.5753611087799073
80th percentile: 2.8899088859558106
90th percentile: 3.26514368057251
95th percentile: 3.4527610778808593
99th percentile: 3.602854995727539
mean time: 2.437848424911499
Pipeline stage StressChecker completed in 13.84s
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 0.80s
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 0.67s
Shutdown handler de-registered
chaiml-devstral-24b-dpo_14531_v3 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 3380.97s
Shutdown handler de-registered
chaiml-devstral-24b-dpo_14531_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-devstral-24b-dpo_14531_v3 status is now torndown due to DeploymentManager action