chaiml-gy-exp107-dpo-ret_7279

developer_uid: bogoconic1

submission_id: chaiml-gy-exp107-dpo-ret_7279_v1

model_name: chaiml-gy-exp107-dpo-ret_7279_v1

model_group: ChaiML/gy-exp107-dpo-ret

status: torndown

timestamp: 2025-07-10T14:57:32+00:00

num_battles: 10111

num_wins: 5471

celo_rating: 1315.93

family_friendly_score: 0.5094000000000001

family_friendly_standard_error: 0.007069818102327669

submission_type: basic

model_repo: ChaiML/gy-exp107-dpo-retry1-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': 0.5190615231324557, 'latency_mean': 1.9264253544807435, 'latency_p50': 1.9334156513214111, 'latency_p90': 2.1401305913925173}, {'batch_size': 3, 'throughput': 1.060271623013707, 'latency_mean': 2.8186681830883025, 'latency_p50': 2.826006531715393, 'latency_p90': 3.0924667596817015}, {'batch_size': 5, 'throughput': 1.347956675518882, 'latency_mean': 3.6819688284397127, 'latency_p50': 3.671866536140442, 'latency_p90': 4.126235437393189}, {'batch_size': 6, 'throughput': 1.4631908388579713, 'latency_mean': 4.077084274291992, 'latency_p50': 4.070796608924866, 'latency_p90': 4.666507840156555}, {'batch_size': 8, 'throughput': 1.5826028781682862, 'latency_mean': 5.013807804584503, 'latency_p50': 5.070032119750977, 'latency_p90': 5.632200837135315}, {'batch_size': 10, 'throughput': 1.6820574360888914, 'latency_mean': 5.875363063812256, 'latency_p50': 5.907822132110596, 'latency_p90': 6.564863681793213}]

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

display_name: chaiml-gy-exp107-dpo-ret_7279_v1

is_internal_developer: False

language_model: ChaiML/gy-exp107-dpo-retry1-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-10

win_ratio: 0.5410938581742657

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-exp107-dpo-ret-7279-v1-mkmlizer
Waiting for job on chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer to finish
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: Downloaded to shared memory in 79.616s
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: Checking if ChaiML/gy-exp107-dpo-retry1-ep2 already exists in ChaiML
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7ee73yok, device:0
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: quantized model in 48.982s
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: Processed model ChaiML/gy-exp107-dpo-retry1-ep2 in 128.599s
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia/config.json
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia/special_tokens_map.json
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia/tokenizer_config.json
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia/tokenizer.json
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp107-dpo-ret-7279-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.50it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.31it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 29.02it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.92it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.79it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.91it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 31.89it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 21.76it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 20.48it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 21.65it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 21.86it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.18it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.76it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.57it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.21it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.99it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 20.47it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.09it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.41it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.88it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.03it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.97it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 26.30it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 26.63it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 26.26it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 21.22it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.73it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.53it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.70it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.97it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.01it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.00it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.65it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.14it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 23.31it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.93it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.04it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.31it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.08it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.58it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 27.95it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.91it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.37it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.90it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.05it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.92it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.40it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.40it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:33,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:10,  2.15it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.81it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  4.01it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.11it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.06it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.54it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.89it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.70it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.44it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.26it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.72it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.33it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.71it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 29.13it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.02it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.02it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.27it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.24it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.49it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.19it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.87it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.69it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.82it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.08it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.14it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.25it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.09it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.83it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.31it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.42it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.59it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 25.97it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.49it/s]
Loading 0:  95%|█████████▌| 346/363 [00:28<00:00, 20.83it/s]
Loading 0:  96%|█████████▌| 349/363 [00:28<00:00, 20.18it/s]
Loading 0:  97%|█████████▋| 353/363 [00:29<00:00, 23.72it/s]
Loading 0:  98%|█████████▊| 357/363 [00:29<00:00, 21.90it/s]
                                                            
Job chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer completed after 156.0s with status: succeeded
Stopping job with name chaiml-gy-exp107-dpo-ret-7279-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.77s
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-exp107-dpo-ret-7279-v1
Waiting for inference service chaiml-gy-exp107-dpo-ret-7279-v1 to be ready
Inference service chaiml-gy-exp107-dpo-ret-7279-v1 ready after 200.75359177589417s
Pipeline stage MKMLDeployer completed in 201.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6397178173065186s
Received healthy response to inference request in 2.2180237770080566s
Received healthy response to inference request in 2.4338138103485107s
Received healthy response to inference request in 2.3330371379852295s
Received healthy response to inference request in 2.3574063777923584s
5 requests
0 failed requests
5th percentile: 2.241026449203491
10th percentile: 2.264029121398926
20th percentile: 2.310034465789795
30th percentile: 2.3379109859466554
40th percentile: 2.3476586818695067
50th percentile: 2.3574063777923584
60th percentile: 2.3879693508148194
70th percentile: 2.4185323238372805
80th percentile: 2.4749946117401125
90th percentile: 2.5573562145233155
95th percentile: 2.598537015914917
99th percentile: 2.631481657028198
mean time: 2.3963997840881346
Pipeline stage StressChecker completed in 13.50s
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 0.70s
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 0.70s
Shutdown handler de-registered
chaiml-gy-exp107-dpo-ret_7279_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 2999.84s
Shutdown handler de-registered
chaiml-gy-exp107-dpo-ret_7279_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp107-dpo-ret_7279_v1 status is now torndown due to DeploymentManager action