chaiml-csfs-v3-2-dpo-lr5e7b04

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v3-2-dpo-lr5e7b04_v1

model_name: chaiml-csfs-v3-2-dpo-lr5e7b04_v1

model_group: ChaiML/csfs-v3-2-dpo-lr5

status: inactive

timestamp: 2025-10-16T00:07:56+00:00

num_battles: 5907

num_wins: 3180

celo_rating: 1297.46

family_friendly_score: 0.479

family_friendly_standard_error: 0.007064828377250222

submission_type: basic

model_repo: ChaiML/csfs-v3-2-dpo-lr5e7b04

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3823462343948961, 'latency_mean': 2.615304833650589, 'latency_p50': 2.61767315864563, 'latency_p90': 2.8729317426681518}, {'batch_size': 2, 'throughput': 0.5719901873644785, 'latency_mean': 3.486452714204788, 'latency_p50': 3.4763907194137573, 'latency_p90': 3.797815203666687}, {'batch_size': 3, 'throughput': 0.7011008678906044, 'latency_mean': 4.262413531541824, 'latency_p50': 4.26202917098999, 'latency_p90': 4.627409791946411}, {'batch_size': 4, 'throughput': 0.7984431677069328, 'latency_mean': 4.99479625582695, 'latency_p50': 4.978226065635681, 'latency_p90': 5.700182366371155}, {'batch_size': 5, 'throughput': 0.8571841667581651, 'latency_mean': 5.8096447801589965, 'latency_p50': 5.8315218687057495, 'latency_p90': 6.537830758094787}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-csfs-v3-2-dpo-lr5e7b04_v1

is_internal_developer: True

language_model: ChaiML/csfs-v3-2-dpo-lr5e7b04

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-15

win_ratio: 0.5383443372270188

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '####', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}

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-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer
Waiting for job on chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer to finish
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: Downloaded to shared memory in 54.880s
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: Checking if ChaiML/csfs-v3-2-dpo-lr5e7b04 already exists in ChaiML
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxcivyb8l, device:0
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: quantized model in 41.608s
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: Processed model ChaiML/csfs-v3-2-dpo-lr5e7b04 in 96.488s
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia/config.json
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia/special_tokens_map.json
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia/tokenizer_config.json
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia/tokenizer.json
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr5e7b04-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:13, 26.47it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:22, 15.54it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:21, 16.65it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:18, 19.32it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:18, 19.22it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:17, 20.23it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.84it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 35.40it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.98it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.46it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.29it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:09, 31.40it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:08, 34.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:09, 32.99it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 34.31it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 31.20it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 28.00it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 32.00it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 33.11it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:09, 29.13it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 28.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.73it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.88it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.62it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 31.08it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:07, 32.36it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:07, 33.27it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:06, 34.37it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 33.11it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.40it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.61it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.25it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.63it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.19it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 32.06it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.13it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.84it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.75it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 31.06it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.86it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.94it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.84it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:32,  4.43it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.79it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.80it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.61it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.67it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 19.68it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 21.26it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.56it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.21it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.47it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.34it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.25it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.35it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.65it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.82it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.36it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.69it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 30.36it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.83it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.67it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.39it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.78it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.41it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.21it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.70it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.30it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.96it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.53it/s]
                                                            
Job chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer completed after 166.01s with status: succeeded
Stopping job with name chaiml-csfs-v3-2-dpo-lr5e7b04-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-csfs-v3-2-dpo-lr5e7b04-v1
Waiting for inference service chaiml-csfs-v3-2-dpo-lr5e7b04-v1 to be ready
Inference service chaiml-csfs-v3-2-dpo-lr5e7b04-v1 ready after 60.34899544715881s
Pipeline stage MKMLDeployer completed in 60.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3463070392608643s
Received healthy response to inference request in 2.2417526245117188s
Received healthy response to inference request in 2.1457557678222656s
Received healthy response to inference request in 2.083799362182617s
Received healthy response to inference request in 2.1152148246765137s
5 requests
0 failed requests
5th percentile: 2.0900824546813963
10th percentile: 2.096365547180176
20th percentile: 2.1089317321777346
30th percentile: 2.121323013305664
40th percentile: 2.133539390563965
50th percentile: 2.1457557678222656
60th percentile: 2.184154510498047
70th percentile: 2.222553253173828
80th percentile: 2.2626635074615478
90th percentile: 2.3044852733612062
95th percentile: 2.3253961563110352
99th percentile: 2.3421248626708984
mean time: 2.1865659236907957
Pipeline stage StressChecker completed in 12.17s
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 0.63s
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 0.64s
Shutdown handler de-registered
chaiml-csfs-v3-2-dpo-lr5e7b04_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-csfs-v3-2-dpo-lr5e7b04-v1-profiler
Waiting for inference service chaiml-csfs-v3-2-dpo-lr5e7b04-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 2970.81s
Shutdown handler de-registered
chaiml-csfs-v3-2-dpo-lr5e7b04_v1 status is now inactive due to auto deactivation removed underperforming models