chaiml-csfs-v3-3-dpo-lr_86358

developer_uid: rirv938

submission_id: chaiml-csfs-v3-3-dpo-lr_86358_v9

model_name: chaiml-csfs-v3-3-dpo-lr_86358_v9

model_group: ChaiML/csfs-v3-3-dpo-lr5

status: torndown

timestamp: 2025-12-12T18:27:20+00:00

num_battles: 9091

num_wins: 4604

celo_rating: 1297.42

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/csfs-v3-3-dpo-lr5e6b01-lora

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': 0.4538246592836012, 'latency_mean': 2.203372929096222, 'latency_p50': 2.1900289058685303, 'latency_p90': 2.4174201488494873}, {'batch_size': 3, 'throughput': 0.827818920768945, 'latency_mean': 3.6103156983852385, 'latency_p50': 3.6085907220840454, 'latency_p90': 3.9416103124618527}, {'batch_size': 5, 'throughput': 0.9989115130525861, 'latency_mean': 4.991583820581436, 'latency_p50': 4.996541619300842, 'latency_p90': 5.652821826934814}, {'batch_size': 6, 'throughput': 1.0527541311172983, 'latency_mean': 5.672454793453216, 'latency_p50': 5.687901139259338, 'latency_p90': 6.434784770011902}, {'batch_size': 10, 'throughput': 1.1552819461275572, 'latency_mean': 8.59495549082756, 'latency_p50': 8.51842987537384, 'latency_p90': 9.711002564430236}]

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

display_name: chaiml-csfs-v3-3-dpo-lr_86358_v9

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/csfs-v3-3-dpo-lr5e6b01-lora

model_size: 24B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2025-11-27

win_ratio: 0.5064349356506435

generation_params: {'temperature': 0.8, '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-v3-3-dpo-lr-86358-v9-mkmlizer
Waiting for job on chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer to finish
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Stopping job with name chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer
Waiting for job on chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer to finish
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: Downloaded to shared memory in 54.169s
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: Checking if ChaiML/csfs-v3-3-dpo-lr5e6b01-lora already exists in ChaiML
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjqn6v1xs, device:0
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: quantized model in 48.608s
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: Processed model ChaiML/csfs-v3-3-dpo-lr5e6b01-lora in 102.778s
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia/config.json
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia/special_tokens_map.json
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia/tokenizer_config.json
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia/tokenizer.json
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-3-dpo-lr-86358-v9/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.42it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 34.18it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 31.02it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.50it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.06it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.01it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.52it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.31it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.20it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.93it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.50it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.36it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.39it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.94it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.94it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.67it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.67it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.65it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.15it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.04it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.37it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.04it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.17it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.93it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.38it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:19, 13.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:13, 18.05it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:21, 11.04it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:16, 14.33it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:15, 14.61it/s]
Loading 0:  38%|███▊      | 138/363 [00:06<00:11, 19.53it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:11, 19.32it/s]
Loading 0:  41%|████      | 148/363 [00:06<00:07, 27.41it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:09, 21.56it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:09, 22.34it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:10, 19.34it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:07, 26.27it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 25.70it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 27.57it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 26.11it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.89it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:07, 24.93it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 23.14it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 24.16it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:16, 10.22it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:16, 10.21it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:15, 10.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:04,  1.51s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:10,  1.19s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:44,  1.49it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:17,  1.97it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:57,  2.61it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.83it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.97it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:22,  6.07it/s]
Loading 0:  63%|██████▎   | 229/363 [00:24<00:14,  9.09it/s]
Loading 0:  64%|██████▍   | 232/363 [00:24<00:12, 10.81it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:08, 14.74it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:07, 15.70it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 21.36it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 22.16it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 25.65it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 25.38it/s]
Loading 0:  73%|███████▎  | 265/363 [00:25<00:03, 32.24it/s]
Loading 0:  74%|███████▍  | 269/363 [00:26<00:04, 22.98it/s]
Loading 0:  75%|███████▌  | 273/363 [00:26<00:03, 23.01it/s]
Loading 0:  76%|███████▌  | 276/363 [00:26<00:03, 21.80it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.61it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 24.24it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 28.95it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 27.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 26.43it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.89it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 23.18it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 24.21it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 24.79it/s]
Loading 0:  87%|████████▋ | 316/363 [00:28<00:02, 22.73it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 24.05it/s]
Loading 0:  89%|████████▊ | 322/363 [00:28<00:01, 24.55it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.53it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.41it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:00, 28.22it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.71it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 16.10it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 21.87it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 22.49it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 26.19it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 23.92it/s]
                                                            
Job chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer completed after 195.62s with status: succeeded
Stopping job with name chaiml-csfs-v3-3-dpo-lr-86358-v9-mkmlizer
Pipeline stage MKMLizer completed in 279.30s
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-v3-3-dpo-lr-86358-v9
Waiting for inference service chaiml-csfs-v3-3-dpo-lr-86358-v9 to be ready
Inference service chaiml-csfs-v3-3-dpo-lr-86358-v9 ready after 170.73250818252563s
Pipeline stage MKMLDeployer completed in 171.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0652506351470947s
Received healthy response to inference request in 2.127945899963379s
Received healthy response to inference request in 2.3617453575134277s
Received healthy response to inference request in 2.5893683433532715s
Received healthy response to inference request in 2.1671738624572754s
5 requests
0 failed requests
5th percentile: 2.1357914924621584
10th percentile: 2.1436370849609374
20th percentile: 2.159328269958496
30th percentile: 2.206088161468506
40th percentile: 2.2839167594909666
50th percentile: 2.3617453575134277
60th percentile: 2.4527945518493652
70th percentile: 2.5438437461853027
80th percentile: 2.684544801712036
90th percentile: 2.8748977184295654
95th percentile: 2.97007417678833
99th percentile: 3.0462153434753416
mean time: 2.4622968196868897
Pipeline stage StressChecker completed in 14.16s
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 0.88s
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 0.99s
Shutdown handler de-registered
chaiml-csfs-v3-3-dpo-lr_86358_v9 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4701.40s
Shutdown handler de-registered
chaiml-csfs-v3-3-dpo-lr_86358_v9 status is now torndown due to DeploymentManager action