chaiml-gy-exp146-dpo-ex_52663

developer_uid: bogoconic1

submission_id: chaiml-gy-exp146-dpo-ex_52663_v3

model_name: chaiml-gy-exp146-dpo-ex_52663_v3

model_group: ChaiML/gy-exp146-dpo-exp

status: torndown

timestamp: 2025-07-12T19:03:36+00:00

num_battles: 6836

num_wins: 3819

celo_rating: 1316.05

family_friendly_score: 0.5322

family_friendly_standard_error: 0.007056389445034904

submission_type: basic

model_repo: ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2

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': 0.525682578054495, 'latency_mean': 1.9021834135055542, 'latency_p50': 1.8904415369033813, 'latency_p90': 2.1115811347961424}, {'batch_size': 3, 'throughput': 1.0602340379409607, 'latency_mean': 2.8206674790382387, 'latency_p50': 2.81148099899292, 'latency_p90': 3.1185803413391113}, {'batch_size': 5, 'throughput': 1.3390661023877355, 'latency_mean': 3.7166199398040773, 'latency_p50': 3.7062114477157593, 'latency_p90': 4.114153742790222}, {'batch_size': 6, 'throughput': 1.433930939428089, 'latency_mean': 4.1541836082935335, 'latency_p50': 4.154616713523865, 'latency_p90': 4.6714146614074705}, {'batch_size': 8, 'throughput': 1.5773046152577967, 'latency_mean': 5.037985243797302, 'latency_p50': 5.059248089790344, 'latency_p90': 5.69967041015625}, {'batch_size': 10, 'throughput': 1.6508310024940067, 'latency_mean': 5.9966978931427, 'latency_p50': 5.9880218505859375, 'latency_p90': 6.6782273054122925}]

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

display_name: chaiml-gy-exp146-dpo-ex_52663_v3

is_internal_developer: False

language_model: ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-12

win_ratio: 0.5586600351082505

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': ['<|im_end|>', '<|im_start|>', '\n'], '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-exp146-dpo-ex-52663-v3-mkmlizer
Waiting for job on chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer to finish
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: Downloaded to shared memory in 69.778s
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: Checking if ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgpidxx2d, device:0
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: quantized model in 60.986s
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: Processed model ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2 in 130.765s
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v3/nvidia
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v3/nvidia/config.json
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v3/nvidia/tokenizer.json
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v3/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v3/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 31.94it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:14, 24.90it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.23it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:16, 21.01it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:12, 28.17it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 21.76it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 25.00it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.24it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:18, 17.57it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.86it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:12, 24.24it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.92it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 25.50it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 25.17it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.90it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:12, 24.73it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:14, 20.80it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:16, 17.92it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 22.87it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 21.95it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.88it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 22.92it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.19it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.49it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.45it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.58it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 24.14it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:13, 18.22it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:12, 20.14it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:12, 20.29it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:10, 23.60it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:11, 21.25it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 24.96it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:09, 24.89it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 23.49it/s]
Loading 0:  38%|███▊      | 138/363 [00:06<00:08, 25.60it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:10, 22.12it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 25.75it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:10, 21.14it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 18.04it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:09, 20.99it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:09, 21.22it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:08, 22.79it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 23.35it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 23.41it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 25.85it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 22.25it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:06, 26.03it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 27.60it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.43it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.58it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 19.88it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 21.23it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:07, 21.23it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:57,  1.84s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:53,  1.46s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<02:07,  1.22it/s]
Loading 0:  58%|█████▊    | 211/363 [00:27<01:33,  1.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:07,  2.20it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:48,  2.99it/s]
Loading 0:  61%|██████    | 220/363 [00:27<00:36,  3.87it/s]
Loading 0:  61%|██████▏   | 223/363 [00:28<00:27,  5.15it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.05it/s]
Loading 0:  63%|██████▎   | 229/363 [00:28<00:17,  7.84it/s]
Loading 0:  64%|██████▍   | 232/363 [00:28<00:13,  9.54it/s]
Loading 0:  65%|██████▍   | 235/363 [00:28<00:10, 11.87it/s]
Loading 0:  66%|██████▌   | 238/363 [00:28<00:09, 13.88it/s]
Loading 0:  66%|██████▋   | 241/363 [00:28<00:07, 15.43it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:06, 17.04it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:06, 18.64it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:06, 18.81it/s]
Loading 0:  70%|██████▉   | 253/363 [00:29<00:05, 19.88it/s]
Loading 0:  71%|███████   | 256/363 [00:29<00:05, 20.72it/s]
Loading 0:  71%|███████▏  | 259/363 [00:29<00:05, 20.38it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:04, 21.71it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:03, 25.39it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:05, 16.04it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 17.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:30<00:06, 14.60it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:04, 20.02it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:03, 20.61it/s]
Loading 0:  79%|███████▉  | 286/363 [00:31<00:03, 20.72it/s]
Loading 0:  80%|███████▉  | 289/363 [00:31<00:03, 22.02it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:03, 22.72it/s]
Loading 0:  81%|████████▏ | 295/363 [00:31<00:03, 21.90it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:02, 23.36it/s]
Loading 0:  83%|████████▎ | 303/363 [00:31<00:02, 25.19it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 15.04it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:02, 18.36it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 18.62it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 20.48it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:02, 21.09it/s]
Loading 0:  89%|████████▊ | 322/363 [00:33<00:02, 20.21it/s]
Loading 0:  90%|████████▉ | 325/363 [00:33<00:01, 21.31it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 22.00it/s]
Loading 0:  91%|█████████ | 331/363 [00:33<00:01, 21.47it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 22.88it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 19.33it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 12.43it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 17.40it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 16.99it/s]
Loading 0:  97%|█████████▋| 353/363 [00:34<00:00, 20.34it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 21.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 21.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 22.10it/s]
                                                            
Job chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer completed after 167.03s with status: succeeded
Stopping job with name chaiml-gy-exp146-dpo-ex-52663-v3-mkmlizer
Pipeline stage MKMLizer completed in 167.55s
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-gy-exp146-dpo-ex-52663-v3
Waiting for inference service chaiml-gy-exp146-dpo-ex-52663-v3 to be ready
Inference service chaiml-gy-exp146-dpo-ex-52663-v3 ready after 210.75983929634094s
Pipeline stage MKMLDeployer completed in 211.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7052536010742188s
Received healthy response to inference request in 2.025434732437134s
Received healthy response to inference request in 2.0094447135925293s
Received healthy response to inference request in 1.8551719188690186s
Received healthy response to inference request in 2.440629482269287s
5 requests
0 failed requests
5th percentile: 1.8860264778137208
10th percentile: 1.9168810367584228
20th percentile: 1.978590154647827
30th percentile: 2.0126427173614503
40th percentile: 2.019038724899292
50th percentile: 2.025434732437134
60th percentile: 2.191512632369995
70th percentile: 2.3575905323028565
80th percentile: 2.4935543060302736
90th percentile: 2.599403953552246
95th percentile: 2.6523287773132322
99th percentile: 2.6946686363220214
mean time: 2.2071868896484377
Pipeline stage StressChecker completed in 12.86s
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 0.75s
Shutdown handler de-registered
chaiml-gy-exp146-dpo-ex_52663_v3 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp146-dpo-ex-52663-v3-profiler
Waiting for inference service chaiml-gy-exp146-dpo-ex-52663-v3-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 3327.26s
Shutdown handler de-registered
chaiml-gy-exp146-dpo-ex_52663_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp146-dpo-ex_52663_v3 status is now torndown due to DeploymentManager action