chaiml-csfs-v3-2-dpo-lr2e7b04

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v3-2-dpo-lr2e7b04_v1

model_name: chaiml-csfs-v3-2-dpo-lr2e7b04_v1

model_group: ChaiML/csfs-v3-2-dpo-lr2

status: inactive

timestamp: 2025-10-16T00:02:43+00:00

num_battles: 6230

num_wins: 3317

celo_rating: 1290.03

family_friendly_score: 0.49639999999999995

family_friendly_standard_error: 0.0070708845274123945

submission_type: basic

model_repo: ChaiML/csfs-v3-2-dpo-lr2e7b04

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': 0.3781280697112397, 'latency_mean': 2.6444819462299347, 'latency_p50': 2.6372417211532593, 'latency_p90': 2.8947076320648195}, {'batch_size': 2, 'throughput': 0.5669654343525715, 'latency_mean': 3.5226382327079775, 'latency_p50': 3.5141106843948364, 'latency_p90': 3.8288876533508303}, {'batch_size': 3, 'throughput': 0.6905111742436709, 'latency_mean': 4.3322177147865295, 'latency_p50': 4.332762837409973, 'latency_p90': 4.845925807952881}, {'batch_size': 4, 'throughput': 0.7868008753626458, 'latency_mean': 5.056128497123718, 'latency_p50': 5.078939080238342, 'latency_p90': 5.776537489891052}, {'batch_size': 5, 'throughput': 0.8449011172180494, 'latency_mean': 5.892130678892135, 'latency_p50': 5.933694958686829, 'latency_p90': 6.768270587921142}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-csfs-v3-2-dpo-lr2e7b04_v1

is_internal_developer: True

language_model: ChaiML/csfs-v3-2-dpo-lr2e7b04

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-10-15

win_ratio: 0.5324237560192616

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', '####', '</s>', 'You:'], '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-lr2e7b04-v1-mkmlizer
Waiting for job on chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer to finish
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: Downloaded to shared memory in 51.826s
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: Checking if ChaiML/csfs-v3-2-dpo-lr2e7b04 already exists in ChaiML
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6shofp0c, device:0
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: quantized model in 41.759s
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: Processed model ChaiML/csfs-v3-2-dpo-lr2e7b04 in 93.586s
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia/config.json
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia/special_tokens_map.json
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia/tokenizer_config.json
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia/tokenizer.json
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr2e7b04-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.31it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.76it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 39.11it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 30.97it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.18it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.86it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.51it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.70it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.41it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.22it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 34.73it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.87it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.82it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.62it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.66it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.52it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.41it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.65it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.34it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 31.02it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.74it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.59it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.54it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.85it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.16it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.58it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.11it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.64it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.59it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.42it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.46it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.74it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.92it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.73it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 29.84it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.26it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.74it/s]
Loading 0:  60%|██████    | 219/363 [00:19<00:28,  4.97it/s]
Loading 0:  62%|██████▏   | 224/363 [00:19<00:20,  6.92it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.55it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:10, 11.92it/s]
Loading 0:  66%|██████▌   | 238/363 [00:20<00:08, 15.25it/s]
Loading 0:  67%|██████▋   | 242/363 [00:20<00:06, 18.06it/s]
Loading 0:  68%|██████▊   | 247/363 [00:20<00:05, 21.44it/s]
Loading 0:  69%|██████▉   | 251/363 [00:20<00:04, 23.86it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 26.79it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.15it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 23.71it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.48it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.54it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 30.31it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.72it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 28.92it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 27.58it/s]
Loading 0:  83%|████████▎ | 303/363 [00:22<00:02, 28.83it/s]
Loading 0:  85%|████████▍ | 307/363 [00:22<00:02, 18.99it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 19.15it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 26.71it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 26.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 30.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 29.74it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.13it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 32.16it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.14it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.86it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.30it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.74it/s]
                                                            
Job chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer completed after 164.37s with status: succeeded
Stopping job with name chaiml-csfs-v3-2-dpo-lr2e7b04-v1-mkmlizer
Pipeline stage MKMLizer completed in 164.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.35s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-csfs-v3-2-dpo-lr2e7b04-v1
Waiting for inference service chaiml-csfs-v3-2-dpo-lr2e7b04-v1 to be ready
Inference service chaiml-csfs-v3-2-dpo-lr2e7b04-v1 ready after 60.282652854919434s
Pipeline stage MKMLDeployer completed in 60.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4579453468322754s
Received healthy response to inference request in 2.3532752990722656s
Received healthy response to inference request in 2.273784637451172s
Received healthy response to inference request in 2.0862538814544678s
Received healthy response to inference request in 2.2475996017456055s
5 requests
0 failed requests
5th percentile: 2.1185230255126952
10th percentile: 2.1507921695709227
20th percentile: 2.215330457687378
30th percentile: 2.2528366088867187
40th percentile: 2.2633106231689455
50th percentile: 2.273784637451172
60th percentile: 2.305580902099609
70th percentile: 2.337377166748047
80th percentile: 2.3742093086242675
90th percentile: 2.4160773277282717
95th percentile: 2.4370113372802735
99th percentile: 2.453758544921875
mean time: 2.2837717533111572
Pipeline stage StressChecker completed in 12.66s
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 0.64s
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 0.62s
Shutdown handler de-registered
chaiml-csfs-v3-2-dpo-lr2e7b04_v1 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 2979.67s
Shutdown handler de-registered
chaiml-csfs-v3-2-dpo-lr2e7b04_v1 status is now inactive due to auto deactivation removed underperforming models