chaiml-csfs-v3-2-dpo-lr_22227

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v3-2-dpo-lr_22227_v1

model_name: chaiml-csfs-v3-2-dpo-lr_22227_v1

model_group: ChaiML/csfs-v3-2-dpo-lr1

status: inactive

timestamp: 2025-10-15T09:35:59+00:00

num_battles: 5904

num_wins: 3189

celo_rating: 1293.94

family_friendly_score: 0.49960000000000004

family_friendly_standard_error: 0.007071065549123414

submission_type: basic

model_repo: ChaiML/csfs-v3-2-dpo-lr1e5b01-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': 0.3828143052964885, 'latency_mean': 2.6121354150772094, 'latency_p50': 2.6184853315353394, 'latency_p90': 2.8716901779174804}, {'batch_size': 2, 'throughput': 0.579813691867653, 'latency_mean': 3.4432599902153016, 'latency_p50': 3.449610114097595, 'latency_p90': 3.745865535736084}, {'batch_size': 3, 'throughput': 0.72262092448704, 'latency_mean': 4.146684757471085, 'latency_p50': 4.162272334098816, 'latency_p90': 4.480929970741272}, {'batch_size': 4, 'throughput': 0.8258084693727762, 'latency_mean': 4.830049332380295, 'latency_p50': 4.821275949478149, 'latency_p90': 5.572505760192871}, {'batch_size': 5, 'throughput': 0.8804867395245325, 'latency_mean': 5.656879818439483, 'latency_p50': 5.673870801925659, 'latency_p90': 6.399605250358581}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-csfs-v3-2-dpo-lr_22227_v1

is_internal_developer: True

language_model: ChaiML/csfs-v3-2-dpo-lr1e5b01-lora

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-10-15

win_ratio: 0.5401422764227642

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', '####', '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-v3-2-dpo-lr-22227-v1-mkmlizer
Waiting for job on chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer to finish
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: Downloaded to shared memory in 54.249s
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: Checking if ChaiML/csfs-v3-2-dpo-lr1e5b01-lora already exists in ChaiML
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqv7dmcc8, device:0
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: quantized model in 42.316s
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: Processed model ChaiML/csfs-v3-2-dpo-lr1e5b01-lora in 96.565s
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia/config.json
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia/special_tokens_map.json
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia/tokenizer_config.json
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia/tokenizer.json
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v3-2-dpo-lr-22227-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.21it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 40.44it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.00it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.71it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.78it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.03it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.18it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.30it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.94it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.76it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.32it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.63it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.65it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.62it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.48it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.79it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.44it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.93it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.09it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.51it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.44it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.67it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.47it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 32.39it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 33.40it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.96it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.91it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.31it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.58it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.70it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 25.05it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.07it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.95it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.71it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.82it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.96it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.68it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 29.53it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.21it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.79it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.64it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.41it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.79it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.08it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.28it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.62it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.52it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.09it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.66it/s]
Loading 0:  67%|██████▋   | 244/363 [00:21<00:06, 19.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:21<00:06, 18.77it/s]
Loading 0:  70%|██████▉   | 253/363 [00:21<00:04, 23.71it/s]
Loading 0:  71%|███████   | 257/363 [00:21<00:04, 22.94it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.80it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 25.50it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.23it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.05it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.92it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.12it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.71it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.73it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.85it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.11it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.66it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.33it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.82it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.27it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.33it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.15it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.36it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.87it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.58it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.10it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 29.04it/s]
                                                            
Job chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer completed after 194.5s with status: succeeded
Stopping job with name chaiml-csfs-v3-2-dpo-lr-22227-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.02s
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-v3-2-dpo-lr-22227-v1
Waiting for inference service chaiml-csfs-v3-2-dpo-lr-22227-v1 to be ready
Inference service chaiml-csfs-v3-2-dpo-lr-22227-v1 ready after 70.28970670700073s
Pipeline stage MKMLDeployer completed in 71.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.584216356277466s
Received healthy response to inference request in 2.275442123413086s
Received healthy response to inference request in 2.109463930130005s
Received healthy response to inference request in 2.093414545059204s
Received healthy response to inference request in 2.1046082973480225s
5 requests
0 failed requests
5th percentile: 2.0956532955169678
10th percentile: 2.0978920459747314
20th percentile: 2.102369546890259
30th percentile: 2.1055794239044188
40th percentile: 2.107521677017212
50th percentile: 2.109463930130005
60th percentile: 2.175855207443237
70th percentile: 2.24224648475647
80th percentile: 2.337196969985962
90th percentile: 2.460706663131714
95th percentile: 2.52246150970459
99th percentile: 2.5718653869628905
mean time: 2.2334290504455567
Pipeline stage StressChecker completed in 12.48s
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 0.65s
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 0.63s
Shutdown handler de-registered
chaiml-csfs-v3-2-dpo-lr_22227_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-v3-2-dpo-lr-22227-v1-profiler
Waiting for inference service chaiml-csfs-v3-2-dpo-lr-22227-v1-profiler to be ready
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 3011.10s
Shutdown handler de-registered
chaiml-csfs-v3-2-dpo-lr_22227_v1 status is now inactive due to auto deactivation removed underperforming models