chaiml-gy-exp91-dpo-exp_59578

developer_uid: bogoconic1

submission_id: chaiml-gy-exp91-dpo-exp_59578_v1

model_name: chaiml-gy-exp91-dpo-exp_59578_v1

model_group: ChaiML/gy-exp91-dpo-exp8

status: torndown

timestamp: 2025-07-05T19:44:15+00:00

num_battles: 6816

num_wins: 3617

celo_rating: 1310.41

family_friendly_score: 0.48240000000000005

family_friendly_standard_error: 0.007066685786137657

submission_type: basic

model_repo: ChaiML/gy-exp91-dpo-exp86ep8s2-majib-0630-swag-augmentation-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5185706596251013, 'latency_mean': 1.9282508420944213, 'latency_p50': 1.896176815032959, 'latency_p90': 2.1552310228347777}, {'batch_size': 3, 'throughput': 1.0370362546322294, 'latency_mean': 2.8790453600883485, 'latency_p50': 2.853887915611267, 'latency_p90': 3.159816765785217}, {'batch_size': 5, 'throughput': 1.3240135072987291, 'latency_mean': 3.751230217218399, 'latency_p50': 3.7316391468048096, 'latency_p90': 4.2514955520629885}, {'batch_size': 6, 'throughput': 1.4255662547828802, 'latency_mean': 4.1775880050659175, 'latency_p50': 4.178308010101318, 'latency_p90': 4.684652638435364}, {'batch_size': 8, 'throughput': 1.564759510994074, 'latency_mean': 5.0646103310585024, 'latency_p50': 5.059748649597168, 'latency_p90': 5.707982301712036}, {'batch_size': 10, 'throughput': 1.636014256647521, 'latency_mean': 6.061945259571075, 'latency_p50': 6.093771934509277, 'latency_p90': 6.733756113052368}]

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

display_name: chaiml-gy-exp91-dpo-exp_59578_v1

is_internal_developer: True

language_model: ChaiML/gy-exp91-dpo-exp86ep8s2-majib-0630-swag-augmentation-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-05

win_ratio: 0.5306631455399061

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_start|>', '\n', '<|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-exp91-dpo-exp-59578-v1-mkmlizer
Waiting for job on chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer to finish
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: Downloaded to shared memory in 86.755s
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: Checking if ChaiML/gy-exp91-dpo-exp86ep8s2-majib-0630-swag-augmentation-ep2 already exists in ChaiML
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf3tv8ddg, device:0
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: quantized model in 58.189s
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: Processed model ChaiML/gy-exp91-dpo-exp86ep8s2-majib-0630-swag-augmentation-ep2 in 144.945s
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia/config.json
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia/special_tokens_map.json
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia/tokenizer_config.json
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia/tokenizer.json
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp91-dpo-exp-59578-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 34.82it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 27.56it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 29.08it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.39it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.01it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.85it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 32.18it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 20.75it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:16, 19.42it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.50it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 21.13it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 24.86it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 22.18it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.05it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 22.97it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.57it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.63it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 19.23it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 19.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:13, 21.67it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 21.45it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 23.01it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 23.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.71it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.21it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 24.60it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.10it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:13, 19.47it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 22.99it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.00it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 25.62it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.86it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 26.16it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:08, 26.06it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 25.15it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.51it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:09, 23.78it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 27.21it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 22.68it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 18.72it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.66it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.89it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:08, 24.40it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:08, 21.96it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 26.13it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 23.13it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.36it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 28.42it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:09, 17.86it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.81it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 21.20it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:07, 21.20it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<03:25,  1.27s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<02:51,  1.07s/it]
Loading 0:  57%|█████▋    | 208/363 [00:25<01:43,  1.49it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<01:19,  1.91it/s]
Loading 0:  59%|█████▉    | 214/363 [00:25<00:59,  2.51it/s]
Loading 0:  60%|██████    | 218/363 [00:26<00:40,  3.58it/s]
Loading 0:  61%|██████    | 221/363 [00:26<00:31,  4.56it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:25,  5.45it/s]
Loading 0:  63%|██████▎   | 228/363 [00:26<00:17,  7.68it/s]
Loading 0:  64%|██████▎   | 231/363 [00:26<00:14,  8.87it/s]
Loading 0:  65%|██████▌   | 237/363 [00:27<00:09, 13.22it/s]
Loading 0:  66%|██████▌   | 240/363 [00:27<00:08, 13.92it/s]
Loading 0:  67%|██████▋   | 244/363 [00:27<00:06, 17.38it/s]
Loading 0:  68%|██████▊   | 247/363 [00:27<00:06, 18.85it/s]
Loading 0:  69%|██████▉   | 250/363 [00:27<00:05, 19.90it/s]
Loading 0:  70%|███████   | 255/363 [00:27<00:04, 23.28it/s]
Loading 0:  71%|███████   | 258/363 [00:27<00:04, 21.31it/s]
Loading 0:  72%|███████▏  | 263/363 [00:27<00:03, 26.99it/s]
Loading 0:  74%|███████▎  | 267/363 [00:28<00:04, 21.32it/s]
Loading 0:  74%|███████▍  | 270/363 [00:28<00:05, 18.01it/s]
Loading 0:  75%|███████▌  | 274/363 [00:28<00:04, 21.06it/s]
Loading 0:  76%|███████▋  | 277/363 [00:28<00:04, 21.37it/s]
Loading 0:  77%|███████▋  | 280/363 [00:28<00:03, 23.13it/s]
Loading 0:  78%|███████▊  | 283/363 [00:28<00:03, 23.68it/s]
Loading 0:  79%|███████▉  | 286/363 [00:29<00:03, 23.28it/s]
Loading 0:  80%|████████  | 291/363 [00:29<00:02, 25.60it/s]
Loading 0:  81%|████████  | 294/363 [00:29<00:03, 22.64it/s]
Loading 0:  82%|████████▏ | 299/363 [00:29<00:02, 25.18it/s]
Loading 0:  84%|████████▎ | 304/363 [00:29<00:02, 22.02it/s]
Loading 0:  85%|████████▍ | 307/363 [00:30<00:02, 20.24it/s]
Loading 0:  85%|████████▌ | 310/363 [00:30<00:02, 21.03it/s]
Loading 0:  86%|████████▌ | 313/363 [00:30<00:02, 21.06it/s]
Loading 0:  88%|████████▊ | 318/363 [00:30<00:01, 23.97it/s]
Loading 0:  88%|████████▊ | 321/363 [00:30<00:01, 21.63it/s]
Loading 0:  90%|████████▉ | 325/363 [00:30<00:01, 25.06it/s]
Loading 0:  90%|█████████ | 328/363 [00:30<00:01, 25.05it/s]
Loading 0:  91%|█████████ | 331/363 [00:31<00:01, 23.92it/s]
Loading 0:  92%|█████████▏| 334/363 [00:31<00:01, 24.80it/s]
Loading 0:  93%|█████████▎| 337/363 [00:31<00:01, 20.53it/s]
Loading 0:  94%|█████████▍| 341/363 [00:31<00:01, 13.16it/s]
Loading 0:  95%|█████████▌| 346/363 [00:31<00:00, 18.23it/s]
Loading 0:  96%|█████████▌| 349/363 [00:32<00:00, 17.53it/s]
Loading 0:  97%|█████████▋| 353/363 [00:32<00:00, 21.03it/s]
Loading 0:  98%|█████████▊| 356/363 [00:32<00:00, 22.10it/s]
Loading 0:  99%|█████████▉| 359/363 [00:32<00:00, 22.19it/s]
                                                            
Job chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer completed after 188.06s with status: succeeded
Stopping job with name chaiml-gy-exp91-dpo-exp-59578-v1-mkmlizer
Pipeline stage MKMLizer completed in 188.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp91-dpo-exp-59578-v1
Waiting for inference service chaiml-gy-exp91-dpo-exp-59578-v1 to be ready
Inference service chaiml-gy-exp91-dpo-exp-59578-v1 ready after 220.85990810394287s
Pipeline stage MKMLDeployer completed in 221.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7019362449645996s
Received healthy response to inference request in 2.2083771228790283s
Received healthy response to inference request in 1.8994696140289307s
Received healthy response to inference request in 1.9713468551635742s
Received healthy response to inference request in 2.227412223815918s
5 requests
0 failed requests
5th percentile: 1.9138450622558594
10th percentile: 1.928220510482788
20th percentile: 1.9569714069366455
30th percentile: 2.018752908706665
40th percentile: 2.1135650157928465
50th percentile: 2.2083771228790283
60th percentile: 2.215991163253784
70th percentile: 2.22360520362854
80th percentile: 2.322317028045654
90th percentile: 2.512126636505127
95th percentile: 2.6070314407348634
99th percentile: 2.6829552841186524
mean time: 2.2017084121704102
Pipeline stage StressChecker completed in 12.55s
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 0.72s
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 0.93s
Shutdown handler de-registered
chaiml-gy-exp91-dpo-exp_59578_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5420.85s
Shutdown handler de-registered
chaiml-gy-exp91-dpo-exp_59578_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp91-dpo-exp_59578_v1 status is now torndown due to DeploymentManager action