chaiml-csfs-v5-1-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-csfs-v5-1-dpo_v1

model_name: training123

model_group: ChaiML/csfs-v5-1-dpo

status: inactive

timestamp: 2025-11-22T12:32:38+00:00

num_battles: 6212

num_wins: 3144

celo_rating: 1296.57

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/csfs-v5-1-dpo

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': 0.3814709368051932, 'latency_mean': 2.6213302314281464, 'latency_p50': 2.6222294569015503, 'latency_p90': 2.8808406591415405}, {'batch_size': 2, 'throughput': 0.5731571382765421, 'latency_mean': 3.4855057287216185, 'latency_p50': 3.4735602140426636, 'latency_p90': 3.813160610198975}, {'batch_size': 3, 'throughput': 0.7036719796174055, 'latency_mean': 4.25682382106781, 'latency_p50': 4.272216320037842, 'latency_p90': 4.638314318656922}, {'batch_size': 4, 'throughput': 0.7979080458699763, 'latency_mean': 4.997476660013199, 'latency_p50': 5.033693909645081, 'latency_p90': 5.650380325317383}, {'batch_size': 5, 'throughput': 0.8622722149444011, 'latency_mean': 5.772910515069961, 'latency_p50': 5.782680034637451, 'latency_p90': 6.639611339569091}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/csfs-v5-1-dpo

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-22

win_ratio: 0.506117192530586

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': ['</s>', 'You:', 'User:', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-v5-1-dpo-v1-mkmlizer
Waiting for job on chaiml-csfs-v5-1-dpo-v1-mkmlizer to finish
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-csfs-v5-1-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-csfs-v5-1-dpo-v1-mkmlizer: Downloaded to shared memory in 90.137s
chaiml-csfs-v5-1-dpo-v1-mkmlizer: Checking if ChaiML/csfs-v5-1-dpo already exists in ChaiML
chaiml-csfs-v5-1-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpadwc2hd7, device:0
chaiml-csfs-v5-1-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-csfs-v5-1-dpo-v1-mkmlizer: quantized model in 50.275s
chaiml-csfs-v5-1-dpo-v1-mkmlizer: Processed model ChaiML/csfs-v5-1-dpo in 140.413s
chaiml-csfs-v5-1-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-csfs-v5-1-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-csfs-v5-1-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia
chaiml-csfs-v5-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia/config.json
chaiml-csfs-v5-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia/special_tokens_map.json
chaiml-csfs-v5-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia/tokenizer_config.json
chaiml-csfs-v5-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia/tokenizer.json
chaiml-csfs-v5-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-csfs-v5-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-csfs-v5-1-dpo-v1/nvidia/flywheel_model.1.safetensors
chaiml-csfs-v5-1-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.47it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.30it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.68it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.59it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.20it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.10it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.05it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.42it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.99it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.12it/s]
Loading 0:  13%|█▎        | 47/363 [00:01<00:14, 21.55it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:23, 13.55it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:35,  8.65it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:34,  8.93it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:33,  9.12it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:39,  7.54it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:27, 10.82it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:27, 10.49it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:27, 10.68it/s]
Loading 0:  22%|██▏       | 79/363 [00:05<00:17, 16.48it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.67it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.79it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:12, 21.24it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:14, 18.41it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:10, 25.77it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:11, 23.46it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:11, 22.06it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:09, 25.24it/s]
Loading 0:  31%|███▏      | 114/363 [00:06<00:11, 20.80it/s]
Loading 0:  33%|███▎      | 120/363 [00:06<00:09, 25.91it/s]
Loading 0:  34%|███▍      | 123/363 [00:06<00:10, 23.49it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:08, 28.19it/s]
Loading 0:  37%|███▋      | 133/363 [00:07<00:08, 26.11it/s]
Loading 0:  38%|███▊      | 138/363 [00:07<00:07, 28.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:08, 27.15it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:06, 33.72it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:09, 23.31it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:08, 23.56it/s]
Loading 0:  44%|████▎     | 158/363 [00:08<00:10, 19.83it/s]
Loading 0:  45%|████▌     | 165/363 [00:08<00:07, 26.67it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:07, 25.80it/s]
Loading 0:  48%|████▊     | 174/363 [00:08<00:06, 28.23it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:06, 26.80it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:06, 27.26it/s]
Loading 0:  52%|█████▏    | 187/363 [00:09<00:07, 24.80it/s]
Loading 0:  52%|█████▏    | 190/363 [00:09<00:07, 22.13it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:07, 23.08it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:07, 23.48it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:06, 23.48it/s]
Loading 0:  55%|█████▌    | 201/363 [00:24<03:03,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:24<02:32,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:31,  1.69it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:10,  2.16it/s]
Loading 0:  59%|█████▉    | 214/363 [00:25<00:52,  2.83it/s]
Loading 0:  60%|██████    | 218/363 [00:25<00:35,  4.06it/s]
Loading 0:  61%|██████    | 221/363 [00:25<00:27,  5.18it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:22,  6.24it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:15,  8.76it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13, 10.09it/s]
Loading 0:  65%|██████▌   | 237/363 [00:26<00:08, 14.76it/s]
Loading 0:  66%|██████▌   | 240/363 [00:26<00:08, 15.34it/s]
Loading 0:  68%|██████▊   | 246/363 [00:26<00:05, 20.59it/s]
Loading 0:  69%|██████▊   | 249/363 [00:26<00:05, 19.89it/s]
Loading 0:  70%|███████   | 255/363 [00:26<00:04, 22.22it/s]
Loading 0:  71%|███████   | 258/363 [00:26<00:04, 21.02it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:03, 27.72it/s]
Loading 0:  74%|███████▍  | 268/363 [00:27<00:04, 22.38it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:04, 21.08it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:04, 22.01it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:03, 22.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 25.74it/s]
Loading 0:  79%|███████▊  | 285/363 [00:28<00:03, 23.23it/s]
Loading 0:  80%|████████  | 291/363 [00:28<00:02, 28.26it/s]
Loading 0:  81%|████████  | 294/363 [00:28<00:02, 24.77it/s]
Loading 0:  82%|████████▏ | 299/363 [00:28<00:02, 27.56it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 24.58it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 22.55it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 22.82it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 23.42it/s]
Loading 0:  88%|████████▊ | 318/363 [00:29<00:01, 26.90it/s]
Loading 0:  88%|████████▊ | 321/363 [00:29<00:01, 24.36it/s]
Loading 0:  90%|█████████ | 327/363 [00:29<00:01, 29.36it/s]
Loading 0:  91%|█████████ | 330/363 [00:29<00:01, 25.77it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:00, 28.45it/s]
Loading 0:  93%|█████████▎| 338/363 [00:30<00:00, 27.13it/s]
Loading 0:  94%|█████████▍| 341/363 [00:30<00:01, 16.00it/s]
Loading 0:  96%|█████████▌| 347/363 [00:30<00:00, 21.32it/s]
Loading 0:  96%|█████████▋| 350/363 [00:30<00:00, 21.80it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 25.44it/s]
Loading 0:  99%|█████████▊| 358/363 [00:30<00:00, 23.55it/s]
                                                            
Job chaiml-csfs-v5-1-dpo-v1-mkmlizer completed after 188.97s with status: succeeded
Stopping job with name chaiml-csfs-v5-1-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 189.42s
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-v5-1-dpo-v1
Waiting for inference service chaiml-csfs-v5-1-dpo-v1 to be ready
Inference service chaiml-csfs-v5-1-dpo-v1 ready after 151.27195477485657s
Pipeline stage MKMLDeployer completed in 151.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5342886447906494s
Received healthy response to inference request in 1.7363901138305664s
Received healthy response to inference request in 1.9280025959014893s
Received healthy response to inference request in 1.916304111480713s
Received healthy response to inference request in 1.9781651496887207s
5 requests
0 failed requests
5th percentile: 1.7723729133605957
10th percentile: 1.808355712890625
20th percentile: 1.8803213119506836
30th percentile: 1.9186438083648683
40th percentile: 1.9233232021331788
50th percentile: 1.9280025959014893
60th percentile: 1.9480676174163818
70th percentile: 1.9681326389312743
80th percentile: 2.0893898487091067
90th percentile: 2.311839246749878
95th percentile: 2.4230639457702634
99th percentile: 2.512043704986572
mean time: 2.018630123138428
Pipeline stage StressChecker completed in 11.29s
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 0.89s
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 0.70s
Shutdown handler de-registered
chaiml-csfs-v5-1-dpo_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 0.10s
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-v5-1-dpo-v1-profiler
Waiting for inference service chaiml-csfs-v5-1-dpo-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5059.84s
Shutdown handler de-registered