chaiml-csfs-v4-dpo-lr5e_32913

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v4-dpo-lr5e_32913_v1

model_name: chaiml-csfs-v4-dpo-lr5e_32913_v1

model_group: ChaiML/csfs-v4-dpo-lr5e6

status: inactive

timestamp: 2025-10-17T07:05:56+00:00

num_battles: 5226

num_wins: 2900

celo_rating: 1302.03

family_friendly_score: 0.505

family_friendly_standard_error: 0.007070714249635605

submission_type: basic

model_repo: ChaiML/csfs-v4-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': 0.38907829519528464, 'latency_mean': 2.5700800049304964, 'latency_p50': 2.560930609703064, 'latency_p90': 2.8524047136306763}, {'batch_size': 2, 'throughput': 0.5794541625051034, 'latency_mean': 3.4463350486755373, 'latency_p50': 3.4572231769561768, 'latency_p90': 3.767139935493469}, {'batch_size': 3, 'throughput': 0.7165456028693039, 'latency_mean': 4.170606573820114, 'latency_p50': 4.139784812927246, 'latency_p90': 4.8618262767791744}, {'batch_size': 4, 'throughput': 0.8093604461871002, 'latency_mean': 4.916525840759277, 'latency_p50': 4.93338680267334, 'latency_p90': 5.5281377792358395}, {'batch_size': 5, 'throughput': 0.8771913992392859, 'latency_mean': 5.666532492637634, 'latency_p50': 5.675731062889099, 'latency_p90': 6.433430743217468}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-csfs-v4-dpo-lr5e_32913_v1

is_internal_developer: True

language_model: ChaiML/csfs-v4-dpo-lr5e6b01-lora

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-10-17

win_ratio: 0.5549177190968235

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': ['You:', '\n', '####', '</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-v4-dpo-lr5e-32913-v1-mkmlizer
Waiting for job on chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer to finish
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: Downloaded to shared memory in 53.831s
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: Checking if ChaiML/csfs-v4-dpo-lr5e6b01-lora already exists in ChaiML
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj69tm3fz, device:0
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: quantized model in 44.313s
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: Processed model ChaiML/csfs-v4-dpo-lr5e6b01-lora in 98.144s
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v4-dpo-lr5e-32913-v1/nvidia/special_tokens_map.json
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v4-dpo-lr5e-32913-v1/nvidia/tokenizer_config.json
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v4-dpo-lr5e-32913-v1/nvidia/tokenizer.json
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v4-dpo-lr5e-32913-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.80it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.52it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 34.00it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.24it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.49it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.22it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.98it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.18it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.60it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 24.99it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.37it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 24.92it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.90it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.30it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.21it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.63it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.56it/s]
Loading 0:  23%|██▎       | 83/363 [00:03<00:10, 27.48it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 23.97it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.47it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:10, 25.75it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.33it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.05it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.89it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.06it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.42it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.83it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.27it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.75it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.53it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.13it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.80it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.94it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.89it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.66it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 25.99it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 28.20it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.74it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.05it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.18it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.37it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 23.83it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.73it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.10it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.63it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 23.63it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<02:46,  1.03s/it]
Loading 0:  56%|█████▌    | 203/363 [00:20<02:18,  1.16it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:23,  1.86it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:02,  2.42it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:46,  3.17it/s]
Loading 0:  60%|██████    | 218/363 [00:21<00:31,  4.55it/s]
Loading 0:  61%|██████    | 221/363 [00:21<00:24,  5.77it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:20,  6.86it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:13, 10.08it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.91it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.29it/s]
Loading 0:  66%|██████▋   | 241/363 [00:22<00:06, 18.32it/s]
Loading 0:  68%|██████▊   | 246/363 [00:22<00:05, 22.96it/s]
Loading 0:  69%|██████▉   | 250/363 [00:22<00:04, 23.45it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:03, 27.62it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 26.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 32.43it/s]
Loading 0:  74%|███████▍  | 270/363 [00:23<00:05, 17.64it/s]
Loading 0:  75%|███████▌  | 274/363 [00:23<00:04, 19.07it/s]
Loading 0:  76%|███████▋  | 277/363 [00:23<00:04, 17.75it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:03, 21.89it/s]
Loading 0:  79%|███████▊  | 285/363 [00:24<00:03, 21.16it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 27.35it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 26.55it/s]
Loading 0:  82%|████████▏ | 299/363 [00:24<00:02, 28.29it/s]
Loading 0:  84%|████████▎ | 304/363 [00:24<00:02, 26.03it/s]
Loading 0:  85%|████████▍ | 307/363 [00:24<00:02, 24.01it/s]
Loading 0:  86%|████████▌ | 311/363 [00:25<00:02, 22.40it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 30.22it/s]
Loading 0:  89%|████████▊ | 322/363 [00:25<00:01, 29.28it/s]
Loading 0:  90%|█████████ | 327/363 [00:25<00:01, 32.69it/s]
Loading 0:  91%|█████████ | 331/363 [00:25<00:01, 30.48it/s]
Loading 0:  92%|█████████▏| 335/363 [00:25<00:00, 31.52it/s]
Loading 0:  93%|█████████▎| 339/363 [00:25<00:00, 31.45it/s]
Loading 0:  94%|█████████▍| 343/363 [00:26<00:01, 19.62it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 21.14it/s]
Loading 0:  98%|█████████▊| 355/363 [00:26<00:00, 27.68it/s]
Loading 0:  99%|█████████▉| 359/363 [00:26<00:00, 27.43it/s]
                                                            
Job chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer completed after 174.24s with status: succeeded
Stopping job with name chaiml-csfs-v4-dpo-lr5e-32913-v1-mkmlizer
Pipeline stage MKMLizer completed in 174.78s
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-csfs-v4-dpo-lr5e-32913-v1
Waiting for inference service chaiml-csfs-v4-dpo-lr5e-32913-v1 to be ready
Inference service chaiml-csfs-v4-dpo-lr5e-32913-v1 ready after 70.29340529441833s
Pipeline stage MKMLDeployer completed in 70.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4351019859313965s
Received healthy response to inference request in 2.186943531036377s
Received healthy response to inference request in 2.1453857421875s
Received healthy response to inference request in 2.082172155380249s
Received healthy response to inference request in 2.282182216644287s
5 requests
0 failed requests
5th percentile: 2.0948148727416993
10th percentile: 2.1074575901031496
20th percentile: 2.1327430248260497
30th percentile: 2.153697299957275
40th percentile: 2.170320415496826
50th percentile: 2.186943531036377
60th percentile: 2.225039005279541
70th percentile: 2.263134479522705
80th percentile: 2.312766170501709
90th percentile: 2.3739340782165526
95th percentile: 2.4045180320739745
99th percentile: 2.428985195159912
mean time: 2.226357126235962
Pipeline stage StressChecker completed in 25.31s
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 0.66s
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 0.66s
Shutdown handler de-registered
chaiml-csfs-v4-dpo-lr5e_32913_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 3038.49s
Shutdown handler de-registered
chaiml-csfs-v4-dpo-lr5e_32913_v1 status is now inactive due to auto deactivation removed underperforming models