chaiml-gy-exp149-dpo-ex_66125

developer_uid: bogoconic1

submission_id: chaiml-gy-exp149-dpo-ex_66125_v1

model_name: chaiml-gy-exp149-dpo-ex_66125_v1

model_group: ChaiML/gy-exp149-dpo-exp

status: torndown

timestamp: 2025-07-11T21:26:54+00:00

num_battles: 8885

num_wins: 4788

celo_rating: 1314.35

family_friendly_score: 0.4968

family_friendly_standard_error: 0.007070922994913747

submission_type: basic

model_repo: ChaiML/gy-exp149-dpo-exp54ep6s2-gy-datamix-v3-bo8-gt0.7-chs-max-rej-random-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': 0.5220041658712872, 'latency_mean': 1.9155698013305664, 'latency_p50': 1.910523772239685, 'latency_p90': 2.1150229454040526}, {'batch_size': 3, 'throughput': 1.0563501960635522, 'latency_mean': 2.82564262509346, 'latency_p50': 2.7879945039749146, 'latency_p90': 3.11237633228302}, {'batch_size': 5, 'throughput': 1.3384923762228536, 'latency_mean': 3.713797169923782, 'latency_p50': 3.720465064048767, 'latency_p90': 4.209317231178284}, {'batch_size': 6, 'throughput': 1.447253254704893, 'latency_mean': 4.122106763124466, 'latency_p50': 4.136919736862183, 'latency_p90': 4.658932137489319}, {'batch_size': 8, 'throughput': 1.5645961040863026, 'latency_mean': 5.061900238990784, 'latency_p50': 5.0453280210494995, 'latency_p90': 5.712042474746704}, {'batch_size': 10, 'throughput': 1.6380239231441611, 'latency_mean': 6.026898515224457, 'latency_p50': 6.070658445358276, 'latency_p90': 6.784228277206421}]

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

display_name: chaiml-gy-exp149-dpo-ex_66125_v1

is_internal_developer: False

language_model: ChaiML/gy-exp149-dpo-exp54ep6s2-gy-datamix-v3-bo8-gt0.7-chs-max-rej-random-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-11

win_ratio: 0.538885762521103

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|>', '<|im_end|>', '\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-exp149-dpo-ex-66125-v1-mkmlizer
Waiting for job on chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer to finish
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: Downloaded to shared memory in 112.440s
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: Checking if ChaiML/gy-exp149-dpo-exp54ep6s2-gy-datamix-v3-bo8-gt0.7-chs-max-rej-random-ep2 already exists in ChaiML
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp99uxdv0m, device:0
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: quantized model in 47.677s
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: Processed model ChaiML/gy-exp149-dpo-exp54ep6s2-gy-datamix-v3-bo8-gt0.7-chs-max-rej-random-ep2 in 160.118s
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia/config.json
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia/special_tokens_map.json
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia/tokenizer_config.json
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia/tokenizer.json
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp149-dpo-ex-66125-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.24it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.90it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.09it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.35it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.71it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.57it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:09, 33.73it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.83it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.51it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.82it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.39it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.00it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:12, 24.37it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.36it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.39it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.73it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.37it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.54it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.88it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.65it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.73it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.48it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.21it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.34it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.56it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.32it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.36it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.81it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.71it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.33it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.82it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.94it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.21it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.65it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.27it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 21.91it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.09it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.58it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.55it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.99it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.92it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.60it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.15it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.46it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.87it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.94it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.60it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 23.60it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:00,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.13it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.26it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.20it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.16it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 10.92it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.62it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.48it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.76it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.30it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.01it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.40it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 21.97it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 20.42it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.85it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.51it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.82it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.41it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.25it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.26it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.67it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.55it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.34it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.49it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.78it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 26.74it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.23it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.77it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.74it/s]
Loading 0:  92%|█████████▏| 334/363 [00:27<00:01, 28.84it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.76it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.14it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.63it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.20it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 22.69it/s]
Loading 0:  98%|█████████▊| 357/363 [00:28<00:00, 21.44it/s]
                                                            
Job chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer completed after 187.87s with status: succeeded
Stopping job with name chaiml-gy-exp149-dpo-ex-66125-v1-mkmlizer
Pipeline stage MKMLizer completed in 188.39s
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-exp149-dpo-ex-66125-v1
Waiting for inference service chaiml-gy-exp149-dpo-ex-66125-v1 to be ready
Inference service chaiml-gy-exp149-dpo-ex-66125-v1 ready after 200.9360318183899s
Pipeline stage MKMLDeployer completed in 201.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.540893316268921s
Received healthy response to inference request in 1.8423974514007568s
Received healthy response to inference request in 2.1146414279937744s
Received healthy response to inference request in 1.9349122047424316s
Received healthy response to inference request in 1.8963418006896973s
5 requests
0 failed requests
5th percentile: 1.8531863212585449
10th percentile: 1.863975191116333
20th percentile: 1.8855529308319092
30th percentile: 1.9040558815002442
40th percentile: 1.9194840431213378
50th percentile: 1.9349122047424316
60th percentile: 2.0068038940429687
70th percentile: 2.0786955833435057
80th percentile: 2.1998918056488037
90th percentile: 2.3703925609588623
95th percentile: 2.4556429386138916
99th percentile: 2.523843240737915
mean time: 2.0658372402191163
Pipeline stage StressChecker completed in 11.53s
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 0.64s
Shutdown handler de-registered
chaiml-gy-exp149-dpo-ex_66125_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp149-dpo-ex-66125-v1-profiler
Waiting for inference service chaiml-gy-exp149-dpo-ex-66125-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 3201.23s
Shutdown handler de-registered
chaiml-gy-exp149-dpo-ex_66125_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp149-dpo-ex_66125_v1 status is now torndown due to DeploymentManager action