chaiml-gy-exp99-dpo-exp_44023

developer_uid: bogoconic1

submission_id: chaiml-gy-exp99-dpo-exp_44023_v2

model_name: chaiml-gy-exp99-dpo-exp_44023_v2

model_group: ChaiML/gy-exp99-dpo-exp8

status: torndown

timestamp: 2025-07-06T16:18:57+00:00

num_battles: 8709

num_wins: 4666

celo_rating: 1313.48

family_friendly_score: 0.49960000000000004

family_friendly_standard_error: 0.007071065549123414

submission_type: basic

model_repo: ChaiML/gy-exp99-dpo-exp87ep20s2-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

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5169594742545772, 'latency_mean': 1.934285433292389, 'latency_p50': 1.9466617107391357, 'latency_p90': 2.129147744178772}, {'batch_size': 3, 'throughput': 1.055125867920887, 'latency_mean': 2.8332671344280245, 'latency_p50': 2.835001826286316, 'latency_p90': 3.1410629510879517}, {'batch_size': 5, 'throughput': 1.3285576172887466, 'latency_mean': 3.745072504281998, 'latency_p50': 3.73483407497406, 'latency_p90': 4.158895778656006}, {'batch_size': 6, 'throughput': 1.4377770103943057, 'latency_mean': 4.144754823446274, 'latency_p50': 4.135065793991089, 'latency_p90': 4.6923706293106076}, {'batch_size': 8, 'throughput': 1.5819631136853023, 'latency_mean': 5.022735813856125, 'latency_p50': 5.005995273590088, 'latency_p90': 5.6798783302307125}, {'batch_size': 10, 'throughput': 1.6384409994259466, 'latency_mean': 6.0426979470252995, 'latency_p50': 6.045184016227722, 'latency_p90': 6.721841192245483}]

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

display_name: chaiml-gy-exp99-dpo-exp_44023_v2

is_internal_developer: False

language_model: ChaiML/gy-exp99-dpo-exp87ep20s2-grok-payloads-0705-rm512-win-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-06

win_ratio: 0.5357675967390056

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-exp99-dpo-exp-44023-v2-mkmlizer
Waiting for job on chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer to finish
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: Downloaded to shared memory in 210.417s
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: Checking if ChaiML/gy-exp99-dpo-exp87ep20s2-grok-payloads-0705-rm512-win-ep1 already exists in ChaiML
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmponilrnoh, device:0
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: quantized model in 56.310s
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: Processed model ChaiML/gy-exp99-dpo-exp87ep20s2-grok-payloads-0705-rm512-win-ep1 in 266.728s
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia/config.json
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia/special_tokens_map.json
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia/tokenizer_config.json
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia/tokenizer.json
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp99-dpo-exp-44023-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:12, 29.88it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:15, 22.78it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.37it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.55it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.33it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.77it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 32.01it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.27it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.40it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.41it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.57it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.54it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.67it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.66it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.18it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.22it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.02it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 20.32it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.31it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.17it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.29it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.03it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.64it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.39it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 26.68it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.20it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.41it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 22.24it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.17it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.16it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.35it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.69it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.82it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.55it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.03it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:09, 22.94it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:08, 23.41it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:10, 19.54it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.77it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 25.98it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.21it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 26.58it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.12it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.74it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.74it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.72it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:06, 23.72it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<03:59,  1.48s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:17,  1.23s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<01:58,  1.31it/s]
Loading 0:  58%|█████▊    | 211/363 [00:27<01:30,  1.68it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:06,  2.22it/s]
Loading 0:  60%|██████    | 218/363 [00:27<00:44,  3.22it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:34,  4.17it/s]
Loading 0:  62%|██████▏   | 224/363 [00:28<00:27,  5.13it/s]
Loading 0:  63%|██████▎   | 228/363 [00:28<00:18,  7.28it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:15,  8.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:09, 13.17it/s]
Loading 0:  66%|██████▌   | 240/363 [00:28<00:08, 14.05it/s]
Loading 0:  68%|██████▊   | 246/363 [00:28<00:05, 19.65it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:05, 20.74it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:04, 24.69it/s]
Loading 0:  71%|███████▏  | 259/363 [00:29<00:04, 23.95it/s]
Loading 0:  73%|███████▎  | 265/363 [00:29<00:03, 30.59it/s]
Loading 0:  74%|███████▍  | 269/363 [00:29<00:04, 21.98it/s]
Loading 0:  75%|███████▌  | 273/363 [00:30<00:04, 21.80it/s]
Loading 0:  76%|███████▌  | 276/363 [00:30<00:04, 20.32it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:03, 23.72it/s]
Loading 0:  78%|███████▊  | 283/363 [00:30<00:03, 24.47it/s]
Loading 0:  79%|███████▉  | 286/363 [00:30<00:03, 24.09it/s]
Loading 0:  80%|████████  | 291/363 [00:30<00:02, 26.70it/s]
Loading 0:  81%|████████  | 294/363 [00:30<00:02, 23.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:31<00:02, 26.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:31<00:02, 24.06it/s]
Loading 0:  85%|████████▍ | 307/363 [00:31<00:02, 22.07it/s]
Loading 0:  85%|████████▌ | 310/363 [00:31<00:02, 22.79it/s]
Loading 0:  86%|████████▌ | 313/363 [00:31<00:02, 23.38it/s]
Loading 0:  88%|████████▊ | 318/363 [00:31<00:01, 26.90it/s]
Loading 0:  88%|████████▊ | 321/363 [00:31<00:01, 23.58it/s]
Loading 0:  90%|█████████ | 327/363 [00:32<00:01, 28.90it/s]
Loading 0:  91%|█████████ | 330/363 [00:32<00:01, 25.01it/s]
Loading 0:  92%|█████████▏| 335/363 [00:32<00:00, 28.87it/s]
Loading 0:  93%|█████████▎| 339/363 [00:32<00:00, 28.57it/s]
Loading 0:  94%|█████████▍| 342/363 [00:32<00:01, 16.61it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:00, 20.19it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:00, 20.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:00, 25.01it/s]
Loading 0:  99%|█████████▊| 358/363 [00:33<00:00, 22.84it/s]
                                                            
Job chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer completed after 300.03s with status: succeeded
Stopping job with name chaiml-gy-exp99-dpo-exp-44023-v2-mkmlizer
Pipeline stage MKMLizer completed in 302.19s
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-exp99-dpo-exp-44023-v2
Waiting for inference service chaiml-gy-exp99-dpo-exp-44023-v2 to be ready
Inference service chaiml-gy-exp99-dpo-exp-44023-v2 ready after 211.31814527511597s
Pipeline stage MKMLDeployer completed in 211.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.478485345840454s
Received healthy response to inference request in 1.9263231754302979s
Received healthy response to inference request in 2.3718299865722656s
Received healthy response to inference request in 1.9401953220367432s
Received healthy response to inference request in 2.293529987335205s
5 requests
0 failed requests
5th percentile: 1.9290976047515869
10th percentile: 1.9318720340728759
20th percentile: 1.9374208927154541
30th percentile: 2.0108622550964355
40th percentile: 2.1521961212158205
50th percentile: 2.293529987335205
60th percentile: 2.324849987030029
70th percentile: 2.3561699867248533
80th percentile: 2.3931610584259033
90th percentile: 2.4358232021331787
95th percentile: 2.4571542739868164
99th percentile: 2.4742191314697264
mean time: 2.202072763442993
Pipeline stage StressChecker completed in 12.40s
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 0.89s
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-exp99-dpo-exp_44023_v2 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp99-dpo-exp-44023-v2-profiler
Waiting for inference service chaiml-gy-exp99-dpo-exp-44023-v2-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 3400.66s
Shutdown handler de-registered
chaiml-gy-exp99-dpo-exp_44023_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp99-dpo-exp_44023_v2 status is now torndown due to DeploymentManager action