chaiml-gy-exp126-dpo-e_77990

developer_uid: bogoconic1

submission_id: chaiml-gy-exp126-dpo-e_77990_v18

model_name: chaiml-gy-exp126-dpo-e_77990_v18

model_group: ChaiML/gy-exp126-dpo-exp

status: torndown

timestamp: 2025-07-13T19:00:49+00:00

num_battles: 9922

num_wins: 5343

celo_rating: 1321.58

family_friendly_score: 0.4928

family_friendly_standard_error: 0.007070334645545429

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': 0.5170183070494209, 'latency_mean': 1.9340579831600189, 'latency_p50': 1.9305115938186646, 'latency_p90': 2.15375816822052}, {'batch_size': 3, 'throughput': 1.026541137926876, 'latency_mean': 2.9115429520606995, 'latency_p50': 2.918265461921692, 'latency_p90': 3.202950286865234}, {'batch_size': 5, 'throughput': 1.2885633722722283, 'latency_mean': 3.860216522216797, 'latency_p50': 3.8578237295150757, 'latency_p90': 4.276980543136597}, {'batch_size': 6, 'throughput': 1.410409267455098, 'latency_mean': 4.236051779985428, 'latency_p50': 4.191142201423645, 'latency_p90': 4.749398016929626}, {'batch_size': 8, 'throughput': 1.53249211021982, 'latency_mean': 5.180045574903488, 'latency_p50': 5.128735542297363, 'latency_p90': 5.854468035697937}, {'batch_size': 10, 'throughput': 1.58611259028941, 'latency_mean': 6.256043254137039, 'latency_p50': 6.203469514846802, 'latency_p90': 7.0819189786911005}]

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

display_name: chaiml-gy-exp126-dpo-e_77990_v18

is_internal_developer: False

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

model_size: 24B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-13

win_ratio: 0.5385003023583955

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': ['\n', '<|im_start|>', '<|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-v18-mkmlizer
Waiting for job on chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer to finish
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ║                                                                     ║
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: Downloaded to shared memory in 58.982s
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: Checking if ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2 already exists in ChaiML
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4_ukdgxq, device:0
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: quantized model in 50.895s
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: Processed model ChaiML/gy-exp126-dpo-exp54ep6s2-exp122data-ep2 in 109.877s
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia/config.json
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia/special_tokens_map.json
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia/tokenizer_config.json
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia/tokenizer.json
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp126-dpo-e-77990-v18/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.20it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.72it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.52it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 25.49it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:12, 28.26it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 22.87it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:10, 32.88it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:15, 21.69it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:14, 21.99it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:17, 18.53it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.34it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.64it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 25.74it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:11, 26.22it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 25.07it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 25.99it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.60it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.75it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.94it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 23.09it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.55it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.90it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.22it/s]
Loading 0:  27%|██▋       | 99/363 [00:04<00:09, 27.00it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 24.14it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.43it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.40it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.96it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.17it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:09, 24.10it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.36it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.68it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.63it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 27.01it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 24.55it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:07, 29.69it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:10, 20.96it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 19.12it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:10, 20.43it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 20.66it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 22.23it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:08, 23.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.37it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 23.98it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 24.63it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 23.78it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 24.21it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 27.84it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.59it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.10it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 20.50it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 22.31it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 22.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:18,  1.59s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:20,  1.25s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:48,  1.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:20,  1.89it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:58,  2.55it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:38,  3.73it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.78it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:24,  5.73it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.14it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.44it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:10, 12.74it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:08, 14.80it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:07, 16.34it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 20.48it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 19.62it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 24.62it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.29it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:03, 28.94it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 21.78it/s]
Loading 0:  75%|███████▍  | 271/363 [00:26<00:04, 20.15it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 21.22it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:04, 21.48it/s]
Loading 0:  77%|███████▋  | 280/363 [00:26<00:03, 23.24it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:03, 23.77it/s]
Loading 0:  79%|███████▉  | 286/363 [00:27<00:03, 23.39it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 26.34it/s]
Loading 0:  81%|████████  | 294/363 [00:27<00:03, 22.84it/s]
Loading 0:  82%|████████▏ | 298/363 [00:27<00:02, 26.57it/s]
Loading 0:  83%|████████▎ | 303/363 [00:27<00:02, 27.82it/s]
Loading 0:  84%|████████▍ | 306/363 [00:28<00:03, 17.29it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 20.55it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 20.91it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 24.10it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 21.77it/s]
Loading 0:  90%|████████▉ | 325/363 [00:28<00:01, 25.36it/s]
Loading 0:  90%|█████████ | 328/363 [00:28<00:01, 25.70it/s]
Loading 0:  91%|█████████ | 331/363 [00:29<00:01, 24.53it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:01, 24.65it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:01, 23.29it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 13.98it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 19.54it/s]
Loading 0:  96%|█████████▌| 349/363 [00:30<00:00, 18.73it/s]
Loading 0:  97%|█████████▋| 353/363 [00:30<00:00, 21.78it/s]
Loading 0:  98%|█████████▊| 356/363 [00:30<00:00, 23.39it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 22.92it/s]
Loading 0: 100%|█████████▉| 362/363 [00:30<00:00, 24.40it/s]
                                                            
Job chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer completed after 146.58s with status: succeeded
Stopping job with name chaiml-gy-exp126-dpo-e-77990-v18-mkmlizer
Pipeline stage MKMLizer completed in 147.09s
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-exp126-dpo-e-77990-v18
Waiting for inference service chaiml-gy-exp126-dpo-e-77990-v18 to be ready
Inference service chaiml-gy-exp126-dpo-e-77990-v18 ready after 210.83965492248535s
Pipeline stage MKMLDeployer completed in 211.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7878897190093994s
Received healthy response to inference request in 1.9339885711669922s
Received healthy response to inference request in 2.207481622695923s
Received healthy response to inference request in 2.269550323486328s
Received healthy response to inference request in 2.4107909202575684s
5 requests
0 failed requests
5th percentile: 1.9886871814727782
10th percentile: 2.0433857917785643
20th percentile: 2.152783012390137
30th percentile: 2.219895362854004
40th percentile: 2.244722843170166
50th percentile: 2.269550323486328
60th percentile: 2.3260465621948243
70th percentile: 2.3825428009033205
80th percentile: 2.4862106800079347
90th percentile: 2.637050199508667
95th percentile: 2.712469959259033
99th percentile: 2.7728057670593262
mean time: 2.321940231323242
Pipeline stage StressChecker completed in 12.88s
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 0.63s
Shutdown handler de-registered
chaiml-gy-exp126-dpo-e_77990_v18 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 0.12s
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-exp126-dpo-e-77990-v18-profiler
Waiting for inference service chaiml-gy-exp126-dpo-e-77990-v18-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3925.45s
Shutdown handler de-registered
chaiml-gy-exp126-dpo-e_77990_v18 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp126-dpo-e_77990_v18 status is now torndown due to DeploymentManager action