chaiml-gy-exp89-dpo-exp_46831

developer_uid: bogoconic1

submission_id: chaiml-gy-exp89-dpo-exp_46831_v1

model_name: chaiml-gy-exp89-dpo-exp_46831_v1

model_group: ChaiML/gy-exp89-dpo-exp8

status: torndown

timestamp: 2025-07-05T10:00:58+00:00

num_battles: 8152

num_wins: 4334

celo_rating: 1307.06

family_friendly_score: 0.46419999999999995

family_friendly_standard_error: 0.0070529193955411115

submission_type: basic

model_repo: ChaiML/gy-exp89-dpo-exp87ep2s2-exp72data-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5234034635216251, 'latency_mean': 1.9104470813274383, 'latency_p50': 1.908368706703186, 'latency_p90': 2.11416335105896}, {'batch_size': 3, 'throughput': 1.0539252767867269, 'latency_mean': 2.839427672624588, 'latency_p50': 2.8155044317245483, 'latency_p90': 3.110178279876709}, {'batch_size': 5, 'throughput': 1.3307018733905969, 'latency_mean': 3.723019909858704, 'latency_p50': 3.7352373600006104, 'latency_p90': 4.205294466018676}, {'batch_size': 6, 'throughput': 1.4368408028498167, 'latency_mean': 4.14306135892868, 'latency_p50': 4.172936320304871, 'latency_p90': 4.616898822784424}, {'batch_size': 8, 'throughput': 1.5800373398974343, 'latency_mean': 5.004744395017624, 'latency_p50': 4.957930564880371, 'latency_p90': 5.699381566047668}, {'batch_size': 10, 'throughput': 1.667765811946019, 'latency_mean': 5.94292954325676, 'latency_p50': 5.913136005401611, 'latency_p90': 6.760632705688477}]

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

display_name: chaiml-gy-exp89-dpo-exp_46831_v1

is_internal_developer: True

language_model: ChaiML/gy-exp89-dpo-exp87ep2s2-exp72data-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-05

win_ratio: 0.531648675171737

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-exp89-dpo-exp-46831-v1-mkmlizer
Waiting for job on chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer to finish
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: Downloaded to shared memory in 77.464s
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: Checking if ChaiML/gy-exp89-dpo-exp87ep2s2-exp72data-ep1 already exists in ChaiML
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqnkme5up, device:0
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: quantized model in 47.960s
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: Processed model ChaiML/gy-exp89-dpo-exp87ep2s2-exp72data-ep1 in 125.424s
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia/config.json
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia/special_tokens_map.json
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia/tokenizer_config.json
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia/tokenizer.json
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp89-dpo-exp-46831-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 32.18it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 27.26it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.62it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.60it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.30it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 25.43it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:10, 32.98it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.69it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.51it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.75it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.28it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.73it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:12, 24.12it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.59it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.01it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.97it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.64it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.11it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.44it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.74it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.66it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.11it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.70it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.98it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.40it/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, 28.96it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.77it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.07it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 28.90it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.54it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.11it/s]
Loading 0:  40%|████      | 146/363 [00:05<00:06, 31.40it/s]
Loading 0:  41%|████▏     | 150/363 [00:05<00:08, 24.20it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:10, 20.82it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 24.19it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 24.71it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 28.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.71it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.19it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.15it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.00it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.46it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.54it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.77it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.30it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.30it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:02,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.87it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.11it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.25it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.24it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.23it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.83it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.90it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.71it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.74it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.23it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.96it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.43it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 30.03it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 22.67it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.50it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.86it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.92it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.65it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.10it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.09it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.45it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.56it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.62it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.46it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.90it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.70it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.66it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 30.08it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.26it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.58it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.27it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.78it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.88it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 25.09it/s]
                                                            
Job chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer completed after 155.84s with status: succeeded
Stopping job with name chaiml-gy-exp89-dpo-exp-46831-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.34s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp89-dpo-exp-46831-v1
Waiting for inference service chaiml-gy-exp89-dpo-exp-46831-v1 to be ready
Inference service chaiml-gy-exp89-dpo-exp-46831-v1 ready after 220.8285858631134s
Pipeline stage MKMLDeployer completed in 221.29s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.5763461589813232s
Received healthy response to inference request in 2.7064602375030518s
Received healthy response to inference request in 2.1037867069244385s
Received healthy response to inference request in 2.2298872470855713s
5 requests
1 failed requests
5th percentile: 2.129006814956665
10th percentile: 2.1542269229888915
20th percentile: 2.2046671390533445
30th percentile: 2.299179029464722
40th percentile: 2.4377625942230225
50th percentile: 2.5763461589813232
60th percentile: 2.6283917903900145
70th percentile: 2.680437421798706
80th percentile: 6.217742633819583
90th percentile: 13.240307426452638
95th percentile: 16.751589822769162
99th percentile: 19.56061573982239
mean time: 5.975870513916016
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1646506786346436s
Received healthy response to inference request in 1.8398408889770508s
Received healthy response to inference request in 2.397587776184082s
Received healthy response to inference request in 1.9949557781219482s
Received healthy response to inference request in 2.2320988178253174s
5 requests
0 failed requests
5th percentile: 1.8708638668060302
10th percentile: 1.9018868446350097
20th percentile: 1.9639328002929688
30th percentile: 2.0288947582244874
40th percentile: 2.0967727184295653
50th percentile: 2.1646506786346436
60th percentile: 2.191629934310913
70th percentile: 2.2186091899871827
80th percentile: 2.26519660949707
90th percentile: 2.331392192840576
95th percentile: 2.3644899845123293
99th percentile: 2.3909682178497316
mean time: 2.1258267879486086
Pipeline stage StressChecker completed in 43.20s
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 0.74s
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 0.71s
Shutdown handler de-registered
chaiml-gy-exp89-dpo-exp_46831_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3052.10s
Shutdown handler de-registered
chaiml-gy-exp89-dpo-exp_46831_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp89-dpo-exp_46831_v1 status is now torndown due to DeploymentManager action