chaiml-csfs-v3-dpo-lr1e_73647

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v3-dpo-lr1e_73647_v1

model_name: chaiml-csfs-v3-dpo-lr1e_73647_v1

model_group: ChaiML/csfs-v3-dpo-lr1e6

status: inactive

timestamp: 2025-10-15T02:10:30+00:00

num_battles: 5836

num_wins: 3108

celo_rating: 1294.38

family_friendly_score: 0.518

family_friendly_standard_error: 0.0070664842743757665

submission_type: basic

model_repo: ChaiML/csfs-v3-dpo-lr1e6b01-cosine

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': 0.37950843572284587, 'latency_mean': 2.634861373901367, 'latency_p50': 2.6295297145843506, 'latency_p90': 2.909644031524658}, {'batch_size': 2, 'throughput': 0.5679058847654065, 'latency_mean': 3.5211149621009827, 'latency_p50': 3.517024517059326, 'latency_p90': 3.8348687171936033}, {'batch_size': 3, 'throughput': 0.6940991599212174, 'latency_mean': 4.310906106233597, 'latency_p50': 4.309793949127197, 'latency_p90': 4.939016938209534}, {'batch_size': 4, 'throughput': 0.7889705279600153, 'latency_mean': 5.057037887573242, 'latency_p50': 5.0347102880477905, 'latency_p90': 5.777322077751159}, {'batch_size': 5, 'throughput': 0.846996947651519, 'latency_mean': 5.869867825508118, 'latency_p50': 5.888831734657288, 'latency_p90': 6.689900875091553}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-csfs-v3-dpo-lr1e_73647_v1

is_internal_developer: True

language_model: ChaiML/csfs-v3-dpo-lr1e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-10-14

win_ratio: 0.5325565455791638

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-v3-dpo-lr1e-73647-v1-mkmlizer
Waiting for job on chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer to finish
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: Downloaded to shared memory in 60.435s
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: Checking if ChaiML/csfs-v3-dpo-lr1e6b01-cosine already exists in ChaiML
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdyj__5_a, device:0
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: quantized model in 42.355s
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: Processed model ChaiML/csfs-v3-dpo-lr1e6b01-cosine in 102.791s
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia/special_tokens_map.json
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia/config.json
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia/tokenizer_config.json
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia/tokenizer.json
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e-73647-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.16it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.83it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:10, 33.39it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 38.54it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.39it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 39.07it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.95it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.66it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.19it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.18it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.90it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.56it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.36it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 33.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.42it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.88it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.60it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 29.98it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.47it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.87it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.99it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.74it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.28it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 30.98it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.91it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 29.89it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 33.12it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.36it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.67it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 31.77it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.19it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 25.07it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.92it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.82it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.17it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.42it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.40it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.32it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 29.25it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.56it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.75it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.42it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.82it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.60it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:13,  9.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 15.57it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.52it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.68it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 22.86it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.12it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.02it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.64it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 23.54it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.96it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.57it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 30.75it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 31.32it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 28.65it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 27.79it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 23.54it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.39it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.98it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.46it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.43it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.01it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.25it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.86it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.31it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.57it/s]
                                                            
Job chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer completed after 195.0s with status: succeeded
Stopping job with name chaiml-csfs-v3-dpo-lr1e-73647-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.52s
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-dpo-lr1e-73647-v1
Waiting for inference service chaiml-csfs-v3-dpo-lr1e-73647-v1 to be ready
Inference service chaiml-csfs-v3-dpo-lr1e-73647-v1 ready after 50.26263666152954s
Pipeline stage MKMLDeployer completed in 50.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.343162775039673s
Received healthy response to inference request in 2.1554601192474365s
Received healthy response to inference request in 2.1286473274230957s
Received healthy response to inference request in 2.4597904682159424s
Received healthy response to inference request in 2.186689615249634s
5 requests
0 failed requests
5th percentile: 2.1340098857879637
10th percentile: 2.139372444152832
20th percentile: 2.1500975608825685
30th percentile: 2.161706018447876
40th percentile: 2.174197816848755
50th percentile: 2.186689615249634
60th percentile: 2.2492788791656495
70th percentile: 2.311868143081665
80th percentile: 2.366488313674927
90th percentile: 2.4131393909454344
95th percentile: 2.4364649295806884
99th percentile: 2.4551253604888914
mean time: 2.254750061035156
Pipeline stage StressChecker completed in 12.44s
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 0.93s
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 0.68s
Shutdown handler de-registered
chaiml-csfs-v3-dpo-lr1e_73647_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
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 2996.66s
Shutdown handler de-registered
chaiml-csfs-v3-dpo-lr1e_73647_v1 status is now inactive due to auto deactivation removed underperforming models