chaiml-gy-exp93-dpo-exp_76449

developer_uid: bogoconic1

submission_id: chaiml-gy-exp93-dpo-exp_76449_v1

model_name: chaiml-gy-exp93-dpo-exp_76449_v1

model_group: ChaiML/gy-exp93-dpo-exp8

status: torndown

timestamp: 2025-07-06T08:10:27+00:00

num_battles: 6996

num_wins: 3633

celo_rating: 1302.63

family_friendly_score: 0.48919999999999997

family_friendly_standard_error: 0.007069418080719233

submission_type: basic

model_repo: ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-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': 0.5230446597515086, 'latency_mean': 1.911786744594574, 'latency_p50': 1.894056797027588, 'latency_p90': 2.13056275844574}, {'batch_size': 3, 'throughput': 1.0574087720682992, 'latency_mean': 2.8347274112701415, 'latency_p50': 2.8129595518112183, 'latency_p90': 3.1023373126983644}, {'batch_size': 5, 'throughput': 1.3337728613631372, 'latency_mean': 3.716168168783188, 'latency_p50': 3.7493481636047363, 'latency_p90': 4.125708389282226}, {'batch_size': 6, 'throughput': 1.4458487135230087, 'latency_mean': 4.120158469676971, 'latency_p50': 4.140803098678589, 'latency_p90': 4.654013133049011}, {'batch_size': 8, 'throughput': 1.5795964315171935, 'latency_mean': 5.034904134273529, 'latency_p50': 5.039201021194458, 'latency_p90': 5.633099794387817}, {'batch_size': 10, 'throughput': 1.6643188700968496, 'latency_mean': 5.949955738782883, 'latency_p50': 5.961361050605774, 'latency_p90': 6.662641286849976}]

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

display_name: chaiml-gy-exp93-dpo-exp_76449_v1

is_internal_developer: True

language_model: ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-06

win_ratio: 0.5192967409948542

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_end|>', '\n', '<|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-exp93-dpo-exp-76449-v1-mkmlizer
Waiting for job on chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer to finish
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: Downloaded to shared memory in 75.399s
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: Checking if ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep1 already exists in ChaiML
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpagztc5_e, device:0
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: quantized model in 49.767s
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: Processed model ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep1 in 125.167s
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-76449-v1/nvidia
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-76449-v1/nvidia/tokenizer_config.json
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-76449-v1/nvidia/tokenizer.json
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-76449-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.17it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.13it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.75it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.12it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.07it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 25.02it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:10, 30.91it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:13, 24.10it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 20.61it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.04it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.87it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.34it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:12, 24.48it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.61it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.79it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.35it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.55it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.89it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.88it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.78it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.41it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.87it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.46it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.05it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.45it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.58it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.41it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.71it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.59it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.81it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.41it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.84it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.55it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.33it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.62it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.09it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.37it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.84it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.16it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.96it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 26.75it/s]
Loading 0:  48%|████▊     | 175/363 [00:06<00:06, 26.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:07, 24.91it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.55it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.96it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.27it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.58it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:06, 23.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:19,  1.23s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:43,  1.02s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:37,  1.59it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:14,  2.04it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:55,  2.70it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:37,  3.88it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  4.96it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.96it/s]
Loading 0:  63%|██████▎   | 229/363 [00:24<00:15,  8.85it/s]
Loading 0:  64%|██████▍   | 232/363 [00:24<00:12, 10.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.49it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.25it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.96it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 21.72it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 25.10it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.68it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 29.09it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.54it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.23it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:03, 22.62it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 23.28it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.95it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 24.23it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.44it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.18it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.66it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.83it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.83it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 24.09it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 27.70it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.38it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.68it/s]
Loading 0:  91%|█████████ | 331/363 [00:28<00:01, 27.99it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:00, 29.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.61it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.38it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.18it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 22.16it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 26.53it/s]
Loading 0:  99%|█████████▉| 359/363 [00:29<00:00, 25.65it/s]
                                                            
Job chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer completed after 155.82s with status: succeeded
Stopping job with name chaiml-gy-exp93-dpo-exp-76449-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp93-dpo-exp-76449-v1
Waiting for inference service chaiml-gy-exp93-dpo-exp-76449-v1 to be ready
Inference service chaiml-gy-exp93-dpo-exp-76449-v1 ready after 221.0250642299652s
Pipeline stage MKMLDeployer completed in 221.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.795257329940796s
Received healthy response to inference request in 1.9334402084350586s
Received healthy response to inference request in 2.048435688018799s
Received healthy response to inference request in 1.8658077716827393s
Received healthy response to inference request in 2.253974199295044s
5 requests
0 failed requests
5th percentile: 1.8793342590332032
10th percentile: 1.892860746383667
20th percentile: 1.9199137210845947
30th percentile: 1.9564393043518067
40th percentile: 2.0024374961853026
50th percentile: 2.048435688018799
60th percentile: 2.130651092529297
70th percentile: 2.212866497039795
80th percentile: 2.3622308254241946
90th percentile: 2.578744077682495
95th percentile: 2.6870007038116452
99th percentile: 2.7736060047149658
mean time: 2.1793830394744873
Pipeline stage StressChecker completed in 12.23s
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 0.91s
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 0.68s
Shutdown handler de-registered
chaiml-gy-exp93-dpo-exp_76449_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp93-dpo-exp-76449-v1-profiler
Waiting for inference service chaiml-gy-exp93-dpo-exp-76449-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 3152.51s
Shutdown handler de-registered
chaiml-gy-exp93-dpo-exp_76449_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp93-dpo-exp_76449_v1 status is now torndown due to DeploymentManager action