chaiml-csfs-v5-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v5-dpo_v1

model_name: training123

model_group: ChaiML/csfs-v5-dpo

status: torndown

timestamp: 2025-11-25T00:41:11+00:00

num_battles: 6070

num_wins: 3312

celo_rating: 1309.16

family_friendly_score: 0.5626

family_friendly_standard_error: 0.0070154292812343285

submission_type: basic

model_repo: ChaiML/csfs-v5-dpo

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': 0.3847866005483377, 'latency_mean': 2.59874746799469, 'latency_p50': 2.5981165170669556, 'latency_p90': 2.8582964897155763}, {'batch_size': 2, 'throughput': 0.5685714981630372, 'latency_mean': 3.5151783454418184, 'latency_p50': 3.540757417678833, 'latency_p90': 3.8226351499557496}, {'batch_size': 3, 'throughput': 0.711112958748049, 'latency_mean': 4.209137223958969, 'latency_p50': 4.180044054985046, 'latency_p90': 4.686407828330993}, {'batch_size': 4, 'throughput': 0.8026028371984194, 'latency_mean': 4.967251923084259, 'latency_p50': 4.9616700410842896, 'latency_p90': 5.635791230201721}, {'batch_size': 5, 'throughput': 0.8654251567304655, 'latency_mean': 5.740309458971024, 'latency_p50': 5.749960541725159, 'latency_p90': 6.49298415184021}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/csfs-v5-dpo

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-21

win_ratio: 0.5456342668863262

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': ['</s>', 'You:', '\n', 'User:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-v5-dpo-v1-mkmlizer
Waiting for job on chaiml-csfs-v5-dpo-v1-mkmlizer to finish
chaiml-csfs-v5-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v5-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v5-dpo-v1-mkmlizer: Downloaded to shared memory in 96.120s
chaiml-csfs-v5-dpo-v1-mkmlizer: Checking if ChaiML/csfs-v5-dpo already exists in ChaiML
chaiml-csfs-v5-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvj57w0l3, device:0
chaiml-csfs-v5-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v5-dpo-v1-mkmlizer: quantized model in 41.639s
chaiml-csfs-v5-dpo-v1-mkmlizer: Processed model ChaiML/csfs-v5-dpo in 137.760s
chaiml-csfs-v5-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v5-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v5-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia
chaiml-csfs-v5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia/config.json
chaiml-csfs-v5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia/special_tokens_map.json
chaiml-csfs-v5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia/tokenizer_config.json
chaiml-csfs-v5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia/tokenizer.json
chaiml-csfs-v5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v5-dpo-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v5-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.00it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.29it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.69it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.52it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.50it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 32.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.98it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.49it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.50it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.50it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 35.21it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 38.68it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:09, 29.49it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:09, 30.61it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:10, 27.99it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.87it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:08, 32.61it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:08, 31.18it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:07, 34.67it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.64it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.88it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.44it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.22it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 33.44it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 33.84it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 34.47it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 35.26it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:06, 35.19it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.05it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.95it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.44it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 25.87it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 33.53it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 32.69it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.87it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.23it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.94it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.21it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 30.35it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:06, 27.19it/s]
Loading 0:  55%|█████▌    | 201/363 [00:18<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.82it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:32,  4.40it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:24,  5.74it/s]
Loading 0:  62%|██████▏   | 226/363 [00:19<00:19,  7.10it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.76it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.58it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.68it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 19.74it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.65it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 26.03it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:03, 27.01it/s]
Loading 0:  73%|███████▎  | 266/363 [00:20<00:02, 34.09it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.97it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.91it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 32.14it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 31.16it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 34.59it/s]
Loading 0:  81%|████████▏ | 295/363 [00:21<00:02, 32.52it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.77it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 31.94it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 30.93it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 27.28it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 32.91it/s]
Loading 0:  89%|████████▊ | 322/363 [00:22<00:01, 31.69it/s]
Loading 0:  90%|█████████ | 327/363 [00:22<00:01, 35.33it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 33.56it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.39it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 35.06it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 21.26it/s]
Loading 0:  96%|█████████▌| 348/363 [00:23<00:00, 23.04it/s]
Loading 0:  98%|█████████▊| 355/363 [00:23<00:00, 30.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 30.29it/s]
                                                            
Job chaiml-csfs-v5-dpo-v1-mkmlizer completed after 206.93s with status: succeeded
Stopping job with name chaiml-csfs-v5-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-csfs-v5-dpo-v1
Waiting for inference service chaiml-csfs-v5-dpo-v1 to be ready
Inference service chaiml-csfs-v5-dpo-v1 ready after 150.95837783813477s
Pipeline stage MKMLDeployer completed in 151.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4477293491363525s
Received healthy response to inference request in 2.219738006591797s
Received healthy response to inference request in 2.492992401123047s
Received healthy response to inference request in 2.3149335384368896s
Received healthy response to inference request in 2.3404743671417236s
5 requests
0 failed requests
5th percentile: 2.2387771129608156
10th percentile: 2.257816219329834
20th percentile: 2.295894432067871
30th percentile: 2.3200417041778563
40th percentile: 2.33025803565979
50th percentile: 2.3404743671417236
60th percentile: 2.383376359939575
70th percentile: 2.4262783527374268
80th percentile: 2.4567819595336915
90th percentile: 2.474887180328369
95th percentile: 2.483939790725708
99th percentile: 2.491181879043579
mean time: 2.3631735324859617
Pipeline stage StressChecker completed in 13.21s
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 0.65s
Shutdown handler de-registered
chaiml-csfs-v5-dpo_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-csfs-v5-dpo-v1-profiler
Waiting for inference service chaiml-csfs-v5-dpo-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 5064.10s
Shutdown handler de-registered
chaiml-csfs-v5-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-csfs-v5-dpo_v1 status is now torndown due to DeploymentManager action