chaiml-gy-exp126-dpo-e_77990

developer_uid: bogoconic1

submission_id: chaiml-gy-exp126-dpo-e_77990_v19

model_name: chaiml-gy-exp126-dpo-e_77990_v19

model_group: ChaiML/gy-exp126-dpo-exp

status: torndown

timestamp: 2025-07-14T07:00:54+00:00

num_battles: 7415

num_wins: 3968

celo_rating: 1320.43

family_friendly_score: 0.502

family_friendly_standard_error: 0.0070710112430967045

submission_type: basic

model_repo: ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-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': 0.5174469065674345, 'latency_mean': 1.9324611473083495, 'latency_p50': 1.9422078132629395, 'latency_p90': 2.143753266334534}, {'batch_size': 3, 'throughput': 1.057583484809399, 'latency_mean': 2.8292345821857454, 'latency_p50': 2.826700210571289, 'latency_p90': 3.115176296234131}, {'batch_size': 5, 'throughput': 1.349989177051528, 'latency_mean': 3.6809083342552187, 'latency_p50': 3.6794458627700806, 'latency_p90': 4.099224948883057}, {'batch_size': 6, 'throughput': 1.458256892158595, 'latency_mean': 4.085550047159195, 'latency_p50': 4.0991432666778564, 'latency_p90': 4.559676694869995}, {'batch_size': 8, 'throughput': 1.5904203631187903, 'latency_mean': 4.987687861919403, 'latency_p50': 5.003605484962463, 'latency_p90': 5.534607696533203}, {'batch_size': 10, 'throughput': 1.6835050627875485, 'latency_mean': 5.89049733042717, 'latency_p50': 5.879401087760925, 'latency_p90': 6.686170744895935}]

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

display_name: chaiml-gy-exp126-dpo-e_77990_v19

is_internal_developer: False

language_model: ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-14

win_ratio: 0.5351314902225219

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-exp126-dpo-e-77990-v19-mkmlizer
Waiting for job on chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer to finish
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: Downloaded to shared memory in 64.624s
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: Checking if ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2 already exists in ChaiML
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplg7299y7, device:0
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: quantized model in 59.335s
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: Processed model ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2 in 123.960s
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia/special_tokens_map.json
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia/config.json
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia/tokenizer_config.json
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia/tokenizer.json
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v19/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 30.56it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:15, 23.21it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:14, 24.45it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:18, 19.25it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:14, 23.99it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:14, 24.04it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:14, 22.97it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:12, 27.05it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:17, 18.80it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:20, 15.78it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:17, 18.85it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:16, 19.32it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:15, 20.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:14, 21.65it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 21.95it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:12, 25.32it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 21.78it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.11it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:10, 26.83it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:16, 17.27it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:16, 17.58it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:14, 19.65it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:16, 17.00it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:15, 18.36it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:16, 16.53it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:13, 19.90it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:13, 19.60it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:12, 21.42it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 22.07it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:12, 20.62it/s]
Loading 0:  29%|██▉       | 106/363 [00:05<00:11, 22.31it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:15, 16.70it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:13, 18.45it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:13, 18.34it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 20.55it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:11, 21.63it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:11, 21.57it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:10, 23.29it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:09, 23.68it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 21.68it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 22.84it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 23.13it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:10, 21.87it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:09, 23.50it/s]
Loading 0:  41%|████      | 149/363 [00:07<00:08, 26.35it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:12, 17.00it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 18.11it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:13, 15.50it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 21.13it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:08, 22.04it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:08, 21.95it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 23.63it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 23.05it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 22.66it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:07, 23.32it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 20.44it/s]
Loading 0:  52%|█████▏    | 190/363 [00:09<00:09, 18.37it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:08, 19.46it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 20.15it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:07, 22.09it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:07, 22.09it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<05:03,  1.87s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:55,  1.47s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<02:06,  1.22it/s]
Loading 0:  58%|█████▊    | 211/363 [00:27<01:32,  1.64it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:14,  2.00it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:46,  3.11it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:35,  4.02it/s]
Loading 0:  61%|██████▏   | 223/363 [00:28<00:26,  5.36it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:21,  6.35it/s]
Loading 0:  63%|██████▎   | 229/363 [00:28<00:16,  8.19it/s]
Loading 0:  64%|██████▍   | 232/363 [00:28<00:13,  9.98it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:09, 13.86it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:08, 14.16it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:06, 17.91it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:06, 19.32it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:05, 20.20it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:04, 23.51it/s]
Loading 0:  71%|███████   | 258/363 [00:29<00:05, 20.20it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:04, 23.93it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:03, 27.29it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:05, 16.68it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:04, 19.72it/s]
Loading 0:  76%|███████▋  | 277/363 [00:30<00:04, 20.25it/s]
Loading 0:  78%|███████▊  | 282/363 [00:30<00:03, 23.16it/s]
Loading 0:  79%|███████▊  | 285/363 [00:31<00:03, 21.04it/s]
Loading 0:  80%|████████  | 291/363 [00:31<00:02, 25.31it/s]
Loading 0:  81%|████████  | 294/363 [00:31<00:03, 21.92it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:02, 25.26it/s]
Loading 0:  83%|████████▎ | 303/363 [00:31<00:02, 25.70it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 16.66it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:02, 19.59it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 20.10it/s]
Loading 0:  88%|████████▊ | 318/363 [00:32<00:01, 22.86it/s]
Loading 0:  88%|████████▊ | 321/363 [00:32<00:02, 20.86it/s]
Loading 0:  90%|████████▉ | 325/363 [00:32<00:01, 23.60it/s]
Loading 0:  90%|█████████ | 328/363 [00:32<00:01, 23.44it/s]
Loading 0:  91%|█████████ | 331/363 [00:33<00:01, 22.72it/s]
Loading 0:  92%|█████████▏| 335/363 [00:33<00:01, 23.49it/s]
Loading 0:  93%|█████████▎| 338/363 [00:33<00:01, 22.26it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:01, 12.68it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 17.22it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 16.88it/s]
Loading 0:  97%|█████████▋| 353/363 [00:34<00:00, 20.45it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 21.84it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 22.14it/s]
                                                            
Job chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer completed after 156.84s with status: succeeded
Stopping job with name chaiml-gy-exp126-dpo-e-77990-v19-mkmlizer
Pipeline stage MKMLizer completed in 157.41s
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-exp126-dpo-e-77990-v19
Waiting for inference service chaiml-gy-exp126-dpo-e-77990-v19 to be ready
Inference service chaiml-gy-exp126-dpo-e-77990-v19 ready after 231.1574649810791s
Pipeline stage MKMLDeployer completed in 231.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.918375253677368s
Received healthy response to inference request in 2.102303981781006s
Received healthy response to inference request in 1.9242031574249268s
Received healthy response to inference request in 1.9324545860290527s
Received healthy response to inference request in 2.317167282104492s
5 requests
0 failed requests
5th percentile: 1.925853443145752
10th percentile: 1.927503728866577
20th percentile: 1.9308043003082276
30th percentile: 1.9664244651794434
40th percentile: 2.0343642234802246
50th percentile: 2.102303981781006
60th percentile: 2.1882493019104006
70th percentile: 2.274194622039795
80th percentile: 2.4374088764190676
90th percentile: 2.677892065048218
95th percentile: 2.798133659362793
99th percentile: 2.894326934814453
mean time: 2.2389008522033693
Pipeline stage StressChecker completed in 12.51s
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 0.82s
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 0.92s
Shutdown handler de-registered
chaiml-gy-exp126-dpo-e_77990_v19 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
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 3137.64s
Shutdown handler de-registered
chaiml-gy-exp126-dpo-e_77990_v19 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp126-dpo-e_77990_v19 status is now torndown due to DeploymentManager action