chaiml-gy-exp103-dpo-ex_40450

developer_uid: bogoconic1

submission_id: chaiml-gy-exp103-dpo-ex_40450_v1

model_name: chaiml-gy-exp103-dpo-ex_40450_v1

model_group: ChaiML/gy-exp103-dpo-exp

status: torndown

timestamp: 2025-07-07T06:21:46+00:00

num_battles: 7678

num_wins: 3991

celo_rating: 1304.18

family_friendly_score: 0.5349999999999999

family_friendly_standard_error: 0.007053722421530351

submission_type: basic

model_repo: ChaiML/gy-exp103-dpo-exp95ep2s2-grok-payloads-bo8-0705-dpo-diff-gt0.05-ep3

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': 0.5162010183699925, 'latency_mean': 1.9371073377132415, 'latency_p50': 1.9415439367294312, 'latency_p90': 2.164840912818909}, {'batch_size': 3, 'throughput': 1.0462781821661948, 'latency_mean': 2.8569453203678132, 'latency_p50': 2.832772374153137, 'latency_p90': 3.165311002731323}, {'batch_size': 5, 'throughput': 1.3313853599814447, 'latency_mean': 3.7300641524791716, 'latency_p50': 3.75469434261322, 'latency_p90': 4.154654121398925}, {'batch_size': 6, 'throughput': 1.447642919159861, 'latency_mean': 4.108632324934006, 'latency_p50': 4.1111578941345215, 'latency_p90': 4.5905373096466064}, {'batch_size': 8, 'throughput': 1.5689710895254152, 'latency_mean': 5.05397103190422, 'latency_p50': 5.022302031517029, 'latency_p90': 5.67225215435028}, {'batch_size': 10, 'throughput': 1.6695725001056094, 'latency_mean': 5.946379550695419, 'latency_p50': 5.951897859573364, 'latency_p90': 6.617629361152649}]

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

display_name: chaiml-gy-exp103-dpo-ex_40450_v1

is_internal_developer: False

language_model: ChaiML/gy-exp103-dpo-exp95ep2s2-grok-payloads-bo8-0705-dpo-diff-gt0.05-ep3

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-06

win_ratio: 0.5197968220890857

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_end|>', '<|im_start|>'], '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-exp103-dpo-ex-40450-v1-mkmlizer
Waiting for job on chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer to finish
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: Downloaded to shared memory in 77.069s
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: Checking if ChaiML/gy-exp103-dpo-exp95ep2s2-grok-payloads-bo8-0705-dpo-diff-gt0.05-ep3 already exists in ChaiML
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2kbdm2bk, device:0
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: quantized model in 47.121s
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: Processed model ChaiML/gy-exp103-dpo-exp95ep2s2-grok-payloads-bo8-0705-dpo-diff-gt0.05-ep3 in 124.190s
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia/config.json
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia/special_tokens_map.json
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia/tokenizer_config.json
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia/tokenizer.json
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp103-dpo-ex-40450-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.72it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.80it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.20it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.18it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.41it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.86it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:10, 32.36it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.48it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.54it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.79it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.72it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.72it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:12, 25.15it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.92it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.22it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.40it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.38it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.74it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.35it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.22it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.78it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.69it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.32it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.25it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.72it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.56it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.51it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.09it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.68it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.26it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.00it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:06, 32.68it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 30.04it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 34.27it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.90it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.15it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.36it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 23.92it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.39it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 24.42it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.32it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.72it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.88it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 24.92it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.76it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.50it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 23.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:00,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.16it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.29it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.37it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.41it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.07it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.18it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.05it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.11it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 23.10it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:03, 27.03it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.49it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 31.03it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:03, 24.23it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 22.79it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.94it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 24.23it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 28.19it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.98it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.54it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.24it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.65it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.87it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.80it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.31it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 29.22it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.75it/s]
Loading 0:  90%|████████▉ | 325/363 [00:26<00:01, 29.00it/s]
Loading 0:  91%|█████████ | 329/363 [00:26<00:01, 25.05it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 30.76it/s]
Loading 0:  93%|█████████▎| 339/363 [00:26<00:00, 30.37it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 17.77it/s]
Loading 0:  96%|█████████▌| 348/363 [00:27<00:00, 19.45it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 26.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:27<00:00, 25.72it/s]
                                                            
Job chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer completed after 156.16s with status: succeeded
Stopping job with name chaiml-gy-exp103-dpo-ex-40450-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp103-dpo-ex-40450-v1
Waiting for inference service chaiml-gy-exp103-dpo-ex-40450-v1 to be ready
Inference service chaiml-gy-exp103-dpo-ex-40450-v1 ready after 190.6700325012207s
Pipeline stage MKMLDeployer completed in 191.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7005774974823s
Received healthy response to inference request in 2.2815451622009277s
Received healthy response to inference request in 2.061314821243286s
Received healthy response to inference request in 2.2877445220947266s
Received healthy response to inference request in 2.0989186763763428s
5 requests
0 failed requests
5th percentile: 2.0688355922698975
10th percentile: 2.076356363296509
20th percentile: 2.0913979053497314
30th percentile: 2.1354439735412596
40th percentile: 2.2084945678710937
50th percentile: 2.2815451622009277
60th percentile: 2.2840249061584474
70th percentile: 2.2865046501159667
80th percentile: 2.3703111171722413
90th percentile: 2.5354443073272703
95th percentile: 2.618010902404785
99th percentile: 2.6840641784667967
mean time: 2.2860201358795167
Pipeline stage StressChecker completed in 13.17s
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 0.76s
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 1.13s
Shutdown handler de-registered
chaiml-gy-exp103-dpo-ex_40450_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp103-dpo-ex-40450-v1-profiler
Waiting for inference service chaiml-gy-exp103-dpo-ex-40450-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 3265.71s
Shutdown handler de-registered
chaiml-gy-exp103-dpo-ex_40450_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp103-dpo-ex_40450_v1 status is now torndown due to DeploymentManager action