chaiml-gy-exp150-sft-gy_54863

developer_uid: bogoconic1

submission_id: chaiml-gy-exp150-sft-gy_54863_v1

model_name: chaiml-gy-exp150-sft-gy_54863_v1

model_group: ChaiML/gy-exp150-sft-gy-

status: torndown

timestamp: 2025-07-12T06:36:23+00:00

num_battles: 11468

num_wins: 5922

celo_rating: 1306.06

family_friendly_score: 0.5206

family_friendly_standard_error: 0.007065063906292709

submission_type: basic

model_repo: ChaiML/gy-exp150-sft-gy-datamix-v4.1-add-v3-dpo-bo8-chosen-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': 0.5244701583197999, 'latency_mean': 1.9065619027614593, 'latency_p50': 1.9074666500091553, 'latency_p90': 2.1099630117416384}, {'batch_size': 3, 'throughput': 1.0683402696147923, 'latency_mean': 2.801764382123947, 'latency_p50': 2.7993310689926147, 'latency_p90': 3.118729758262634}, {'batch_size': 5, 'throughput': 1.3533502451348198, 'latency_mean': 3.6624186182022096, 'latency_p50': 3.68566632270813, 'latency_p90': 4.016768980026245}, {'batch_size': 6, 'throughput': 1.4433420876090088, 'latency_mean': 4.132822008132934, 'latency_p50': 4.157497406005859, 'latency_p90': 4.628001499176025}, {'batch_size': 8, 'throughput': 1.577921501728691, 'latency_mean': 5.021383858919144, 'latency_p50': 5.030027151107788, 'latency_p90': 5.61311411857605}, {'batch_size': 10, 'throughput': 1.6795894613624445, 'latency_mean': 5.898149081468582, 'latency_p50': 5.932031512260437, 'latency_p90': 6.725109529495239}]

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

display_name: chaiml-gy-exp150-sft-gy_54863_v1

is_internal_developer: False

language_model: ChaiML/gy-exp150-sft-gy-datamix-v4.1-add-v3-dpo-bo8-chosen-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-07-11

win_ratio: 0.5163934426229508

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|>', '<|im_start|>', '\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-exp150-sft-gy-54863-v1-mkmlizer
Waiting for job on chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer to finish
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: Downloaded to shared memory in 77.976s
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: Checking if ChaiML/gy-exp150-sft-gy-datamix-v4.1-add-v3-dpo-bo8-chosen-ep2 already exists in ChaiML
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb9thwv9b, device:0
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: quantized model in 47.640s
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: Processed model ChaiML/gy-exp150-sft-gy-datamix-v4.1-add-v3-dpo-bo8-chosen-ep2 in 125.616s
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia/config.json
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia/special_tokens_map.json
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia/tokenizer_config.json
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia/tokenizer.json
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp150-sft-gy-54863-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.35it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 27.75it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.59it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.68it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.49it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 25.54it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:10, 33.10it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.69it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.59it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.73it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.08it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:12, 24.44it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.19it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.55it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.83it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.93it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.52it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.70it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.85it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.84it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.83it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.58it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.19it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.38it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.16it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 25.04it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.98it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.44it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.01it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.07it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.53it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.33it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.76it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 22.95it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 21.66it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.61it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.33it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.97it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.33it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.82it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.84it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.43it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.83it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.82it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 23.90it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.90it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:00,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.89it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.15it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.28it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.26it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.27it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.05it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.15it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.73it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.07it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.68it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.22it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 28.77it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 21.83it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 20.86it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.28it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.82it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.69it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.13it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.86it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.42it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.01it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.38it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.49it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.99it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.51it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 30.10it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.74it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 30.17it/s]
Loading 0:  93%|█████████▎| 339/363 [00:27<00:00, 30.11it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 17.44it/s]
Loading 0:  96%|█████████▌| 348/363 [00:28<00:00, 19.36it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.63it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 26.13it/s]
                                                            
Job chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer completed after 156.05s with status: succeeded
Stopping job with name chaiml-gy-exp150-sft-gy-54863-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.51s
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-exp150-sft-gy-54863-v1
Waiting for inference service chaiml-gy-exp150-sft-gy-54863-v1 to be ready
Inference service chaiml-gy-exp150-sft-gy-54863-v1 ready after 200.89524483680725s
Pipeline stage MKMLDeployer completed in 201.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5985004901885986s
Received healthy response to inference request in 2.2089765071868896s
Received healthy response to inference request in 2.1839046478271484s
Received healthy response to inference request in 2.1148264408111572s
Received healthy response to inference request in 2.175339937210083s
5 requests
0 failed requests
5th percentile: 2.1269291400909425
10th percentile: 2.1390318393707277
20th percentile: 2.1632372379302978
30th percentile: 2.177052879333496
40th percentile: 2.1804787635803224
50th percentile: 2.1839046478271484
60th percentile: 2.193933391571045
70th percentile: 2.2039621353149412
80th percentile: 2.2868813037872315
90th percentile: 2.442690896987915
95th percentile: 2.5205956935882567
99th percentile: 2.5829195308685304
mean time: 2.2563096046447755
Pipeline stage StressChecker completed in 12.97s
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 0.68s
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 0.87s
Shutdown handler de-registered
chaiml-gy-exp150-sft-gy_54863_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 0.13s
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-exp150-sft-gy-54863-v1-profiler
Waiting for inference service chaiml-gy-exp150-sft-gy-54863-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5680.13s
Shutdown handler de-registered
chaiml-gy-exp150-sft-gy_54863_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp150-sft-gy_54863_v1 status is now torndown due to DeploymentManager action