chaiml-gy-exp105-dpo-ex_69790

developer_uid: bogoconic1

submission_id: chaiml-gy-exp105-dpo-ex_69790_v1

model_name: chaiml-gy-exp105-dpo-ex_69790_v1

model_group: ChaiML/gy-exp105-dpo-exp

status: torndown

timestamp: 2025-07-07T09:25:42+00:00

num_battles: 9708

num_wins: 5079

celo_rating: 1305.6

family_friendly_score: 0.5192

family_friendly_standard_error: 0.007065852531719014

submission_type: basic

model_repo: ChaiML/gy-exp105-dpo-exp95ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5164500111909093, 'latency_mean': 1.9361960315704345, 'latency_p50': 1.9349480867385864, 'latency_p90': 2.1459977626800537}, {'batch_size': 3, 'throughput': 1.0454616664009955, 'latency_mean': 2.866595063209534, 'latency_p50': 2.838255524635315, 'latency_p90': 3.165714430809021}, {'batch_size': 5, 'throughput': 1.3209878590566604, 'latency_mean': 3.768152498006821, 'latency_p50': 3.7734503746032715, 'latency_p90': 4.165731263160706}, {'batch_size': 6, 'throughput': 1.413302820829682, 'latency_mean': 4.216263166666031, 'latency_p50': 4.2224719524383545, 'latency_p90': 4.672048354148865}, {'batch_size': 8, 'throughput': 1.5600352403304376, 'latency_mean': 5.10335340499878, 'latency_p50': 5.079975605010986, 'latency_p90': 5.722929048538208}, {'batch_size': 10, 'throughput': 1.6314050069083867, 'latency_mean': 6.067575210332871, 'latency_p50': 6.025606751441956, 'latency_p90': 6.863083720207214}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gy-exp105-dpo-ex_69790_v1

is_internal_developer: False

language_model: ChaiML/gy-exp105-dpo-exp95ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-07-07

win_ratio: 0.5231767614338689

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp105-dpo-ex-69790-v1-mkmlizer
Waiting for job on chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer to finish
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: Downloaded to shared memory in 80.562s
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: Checking if ChaiML/gy-exp105-dpo-exp95ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep1 already exists in ChaiML
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzcpw_sj7, device:0
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: quantized model in 48.736s
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: Processed model ChaiML/gy-exp105-dpo-exp95ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep1 in 129.299s
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia/config.json
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia/special_tokens_map.json
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia/tokenizer_config.json
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia/tokenizer.json
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp105-dpo-ex-69790-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.32it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.73it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.88it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 34.06it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.49it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.80it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.64it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.26it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.00it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 26.06it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:13, 22.95it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.07it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.52it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.39it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.77it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.27it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.17it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.35it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.75it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.66it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.48it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 25.76it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:10, 26.01it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:10, 25.50it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.43it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 25.02it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 22.42it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.87it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 26.46it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.88it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 26.93it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.48it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.49it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.13it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:09, 23.12it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:08, 23.12it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:10, 19.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.16it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.94it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.26it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 26.73it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.31it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.14it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.22it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.06it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.24it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.24it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:33,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.13it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.79it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.96it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  5.03it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:23,  5.91it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:16,  8.28it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.51it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.16it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 14.68it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 19.71it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.28it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 23.96it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 21.69it/s]
Loading 0:  72%|███████▏  | 262/363 [00:25<00:04, 24.92it/s]
Loading 0:  73%|███████▎  | 266/363 [00:25<00:03, 27.75it/s]
Loading 0:  74%|███████▍  | 270/363 [00:25<00:05, 17.88it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.05it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 21.92it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.45it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.23it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.99it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 26.76it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.38it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.32it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.36it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.13it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.23it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.30it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.68it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.94it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.81it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:00, 28.37it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.89it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 16.20it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.56it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.10it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 25.01it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 22.89it/s]
                                                            
Job chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer completed after 156.96s with status: succeeded
Stopping job with name chaiml-gy-exp105-dpo-ex-69790-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp105-dpo-ex-69790-v1
Waiting for inference service chaiml-gy-exp105-dpo-ex-69790-v1 to be ready
Inference service chaiml-gy-exp105-dpo-ex-69790-v1 ready after 201.08140659332275s
Pipeline stage MKMLDeployer completed in 201.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4183642864227295s
Received healthy response to inference request in 2.06772780418396s
Received healthy response to inference request in 2.4554998874664307s
Received healthy response to inference request in 2.1472158432006836s
Received healthy response to inference request in 2.533188819885254s
5 requests
0 failed requests
5th percentile: 2.0836254119873048
10th percentile: 2.0995230197906496
20th percentile: 2.131318235397339
30th percentile: 2.201445531845093
40th percentile: 2.309904909133911
50th percentile: 2.4183642864227295
60th percentile: 2.43321852684021
70th percentile: 2.4480727672576905
80th percentile: 2.471037673950195
90th percentile: 2.5021132469177245
95th percentile: 2.5176510334014894
99th percentile: 2.530081262588501
mean time: 2.3243993282318116
Pipeline stage StressChecker completed in 13.27s
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 0.67s
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-gy-exp105-dpo-ex_69790_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5198.68s
Shutdown handler de-registered
chaiml-gy-exp105-dpo-ex_69790_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp105-dpo-ex_69790_v1 status is now torndown due to DeploymentManager action