chaiml-csfs-v3-dpo-lr1e6b04

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v3-dpo-lr1e6b04_v1

model_name: chaiml-csfs-v3-dpo-lr1e6b04_v1

model_group: ChaiML/csfs-v3-dpo-lr1e6

status: inactive

timestamp: 2025-10-14T18:33:42+00:00

num_battles: 5663

num_wins: 2989

celo_rating: 1290.21

family_friendly_score: 0.5234

family_friendly_standard_error: 0.007063319899310805

submission_type: basic

model_repo: ChaiML/csfs-v3-dpo-lr1e6b04

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': 0.38170735719743865, 'latency_mean': 2.619709221124649, 'latency_p50': 2.6235893964767456, 'latency_p90': 2.865356969833374}, {'batch_size': 2, 'throughput': 0.5725186777283773, 'latency_mean': 3.484010932445526, 'latency_p50': 3.4722503423690796, 'latency_p90': 3.791201138496399}, {'batch_size': 3, 'throughput': 0.7045430742851095, 'latency_mean': 4.2443408155441285, 'latency_p50': 4.230427503585815, 'latency_p90': 4.894007539749145}, {'batch_size': 4, 'throughput': 0.808947782113657, 'latency_mean': 4.933397960662842, 'latency_p50': 4.889929413795471, 'latency_p90': 5.598020362854004}, {'batch_size': 5, 'throughput': 0.8705259534800365, 'latency_mean': 5.710753948688507, 'latency_p50': 5.754553198814392, 'latency_p90': 6.385578751564026}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-csfs-v3-dpo-lr1e6b04_v1

is_internal_developer: True

language_model: ChaiML/csfs-v3-dpo-lr1e6b04

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-10-14

win_ratio: 0.5278121137206427

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-dpo-lr1e6b04-v1-mkmlizer
Waiting for job on chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer to finish
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: Downloaded to shared memory in 91.837s
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: Checking if ChaiML/csfs-v3-dpo-lr1e6b04 already exists in ChaiML
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz3v5oyey, device:0
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: quantized model in 42.619s
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: Processed model ChaiML/csfs-v3-dpo-lr1e6b04 in 134.456s
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia/config.json
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia/special_tokens_map.json
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia/tokenizer_config.json
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia/tokenizer.json
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-dpo-lr1e6b04-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.58it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 37.43it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 39.47it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.22it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.17it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 29.16it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.50it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.21it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.75it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.45it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.84it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.93it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.53it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.60it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.84it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.50it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 27.08it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.55it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.40it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.76it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 31.03it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.78it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.72it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.94it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.42it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.20it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.51it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.74it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.66it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 24.20it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:07, 26.49it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 27.88it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 29.86it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 27.90it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 31.56it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:06, 29.76it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 30.59it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 24.29it/s]
Loading 0:  53%|█████▎    | 193/363 [00:06<00:06, 25.33it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:06, 26.23it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:46,  1.03s/it]
Loading 0:  56%|█████▌    | 203/363 [00:19<02:17,  1.16it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:22,  1.87it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<01:02,  2.42it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:46,  3.20it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.58it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.86it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  6.99it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13, 10.26it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.12it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.63it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.79it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 23.38it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.13it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.39it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.12it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.99it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 22.84it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.50it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.54it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.81it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.17it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.15it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.09it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 28.96it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.37it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:02, 25.43it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.06it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.22it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.51it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.61it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.52it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.05it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.45it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 20.86it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 26.94it/s]
                                                            
Job chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer completed after 176.03s with status: succeeded
Stopping job with name chaiml-csfs-v3-dpo-lr1e6b04-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-csfs-v3-dpo-lr1e6b04-v1
Waiting for inference service chaiml-csfs-v3-dpo-lr1e6b04-v1 to be ready
Inference service chaiml-csfs-v3-dpo-lr1e6b04-v1 ready after 50.294716358184814s
Pipeline stage MKMLDeployer completed in 50.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3256847858428955s
Received healthy response to inference request in 2.303447961807251s
Received healthy response to inference request in 2.3484859466552734s
Received healthy response to inference request in 2.33429217338562s
Received healthy response to inference request in 2.40798020362854s
5 requests
0 failed requests
5th percentile: 2.30789532661438
10th percentile: 2.3123426914215086
20th percentile: 2.3212374210357667
30th percentile: 2.3274062633514405
40th percentile: 2.33084921836853
50th percentile: 2.33429217338562
60th percentile: 2.3399696826934813
70th percentile: 2.345647192001343
80th percentile: 2.360384798049927
90th percentile: 2.384182500839233
95th percentile: 2.3960813522338866
99th percentile: 2.4056004333496093
mean time: 2.343978214263916
Pipeline stage StressChecker completed in 12.88s
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 0.60s
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 0.61s
Shutdown handler de-registered
chaiml-csfs-v3-dpo-lr1e6b04_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-v3-dpo-lr1e6b04-v1-profiler
Waiting for inference service chaiml-csfs-v3-dpo-lr1e6b04-v1-profiler to be ready
Inference service chaiml-csfs-v3-dpo-lr1e6b04-v1-profiler ready after 60.79822540283203s
Pipeline stage MKMLProfilerDeployer completed in 61.44s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts creator-studio/chaiml-csfs-v3-dpo-l52834e7b89a2a821739d829621d1d26b-deploc6rzq:/code/chaiverse_profiler_1760467209 --namespace creator-studio
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-csfs-v3-dpo-l52834e7b89a2a821739d829621d1d26b-deploc6rzq --namespace creator-studio -- sh -c 'cd /code/chaiverse_profiler_1760467209 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1760467209/summary.json'
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 3000.93s
Shutdown handler de-registered
chaiml-csfs-v3-dpo-lr1e6b04_v1 status is now inactive due to auto deactivation removed underperforming models