chaiml-gy-exp106-sft-gy_73737

developer_uid: bogoconic1

submission_id: chaiml-gy-exp106-sft-gy_73737_v1

model_name: chaiml-gy-exp106-sft-gy_73737_v1

model_group: ChaiML/gy-exp106-sft-gy-

status: torndown

timestamp: 2025-07-07T09:26:03+00:00

num_battles: 8267

num_wins: 4271

celo_rating: 1302.61

family_friendly_score: 0.5206

family_friendly_standard_error: 0.007065063906292709

submission_type: basic

model_repo: ChaiML/gy-exp106-sft-gy-datamix-v1-bo8-reward-gt0.7-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': 0.5183801340360823, 'latency_mean': 1.928984476327896, 'latency_p50': 1.9278831481933594, 'latency_p90': 2.1397071838378907}, {'batch_size': 3, 'throughput': 1.054530745303193, 'latency_mean': 2.832390688657761, 'latency_p50': 2.8162819147109985, 'latency_p90': 3.1162784576416014}, {'batch_size': 5, 'throughput': 1.3375856395580323, 'latency_mean': 3.7179418098926544, 'latency_p50': 3.7252877950668335, 'latency_p90': 4.135215449333191}, {'batch_size': 6, 'throughput': 1.4534072684459827, 'latency_mean': 4.107394239902496, 'latency_p50': 4.100148916244507, 'latency_p90': 4.606848359107971}, {'batch_size': 8, 'throughput': 1.571406962000952, 'latency_mean': 5.054537025690078, 'latency_p50': 5.064561605453491, 'latency_p90': 5.599111008644104}, {'batch_size': 10, 'throughput': 1.652898691420392, 'latency_mean': 5.980358393192291, 'latency_p50': 5.992491722106934, 'latency_p90': 6.804620623588562}]

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

display_name: chaiml-gy-exp106-sft-gy_73737_v1

is_internal_developer: False

language_model: ChaiML/gy-exp106-sft-gy-datamix-v1-bo8-reward-gt0.7-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-07

win_ratio: 0.5166323938550865

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|>', '<|im_end|>', '\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-exp106-sft-gy-73737-v1-mkmlizer
Waiting for job on chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer to finish
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: Downloaded to shared memory in 77.937s
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: Checking if ChaiML/gy-exp106-sft-gy-datamix-v1-bo8-reward-gt0.7-ep2 already exists in ChaiML
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmz8u67x6, device:0
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: quantized model in 49.090s
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: Processed model ChaiML/gy-exp106-sft-gy-datamix-v1-bo8-reward-gt0.7-ep2 in 127.027s
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp106-sft-gy-73737-v1/nvidia/config.json
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp106-sft-gy-73737-v1/nvidia/special_tokens_map.json
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp106-sft-gy-73737-v1/nvidia/tokenizer_config.json
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp106-sft-gy-73737-v1/nvidia/tokenizer.json
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp106-sft-gy-73737-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp106-sft-gy-73737-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.83it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.85it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.15it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.64it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.69it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.27it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.77it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 19.99it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.49it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.85it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.34it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.43it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.51it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.21it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.27it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 22.87it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.75it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.97it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.95it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.60it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.76it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.25it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 26.77it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 23.64it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 21.03it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 23.91it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 20.76it/s]
Loading 0:  33%|███▎      | 119/363 [00:04<00:09, 26.20it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.21it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 26.24it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.43it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.83it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.95it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:07, 30.41it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.70it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.14it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.22it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.94it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.42it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.32it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.40it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.97it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.27it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.71it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.90it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.93it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.06it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:04,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:32,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.69it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:10,  2.16it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.83it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.06it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.18it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.06it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.53it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.82it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.44it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.04it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.20it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.46it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.19it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.22it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 28.83it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 21.73it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 20.36it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.28it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 21.83it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.12it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 22.14it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.50it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.47it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.98it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.91it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.99it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.99it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.48it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.71it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:28<00:01, 27.50it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.80it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.00it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.32it/s]
Loading 0:  95%|█████████▌| 346/363 [00:28<00:00, 20.62it/s]
Loading 0:  96%|█████████▌| 349/363 [00:29<00:00, 19.85it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 25.12it/s]
Loading 0:  99%|█████████▉| 359/363 [00:29<00:00, 24.76it/s]
                                                            
Job chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer completed after 156.98s with status: succeeded
Stopping job with name chaiml-gy-exp106-sft-gy-73737-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.49s
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-exp106-sft-gy-73737-v1
Waiting for inference service chaiml-gy-exp106-sft-gy-73737-v1 to be ready
Inference service chaiml-gy-exp106-sft-gy-73737-v1 ready after 191.1431803703308s
Pipeline stage MKMLDeployer completed in 191.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8803937435150146s
Received healthy response to inference request in 2.0084164142608643s
Received healthy response to inference request in 2.358746290206909s
Received healthy response to inference request in 1.8739268779754639s
Received healthy response to inference request in 2.18705415725708s
5 requests
0 failed requests
5th percentile: 1.900824785232544
10th percentile: 1.927722692489624
20th percentile: 1.9815185070037842
30th percentile: 2.0441439628601072
40th percentile: 2.1155990600585937
50th percentile: 2.18705415725708
60th percentile: 2.2557310104370116
70th percentile: 2.324407863616943
80th percentile: 2.46307578086853
90th percentile: 2.6717347621917726
95th percentile: 2.7760642528533936
99th percentile: 2.8595278453826904
mean time: 2.2617074966430666
Pipeline stage StressChecker completed in 12.64s
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 0.77s
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 0.73s
Shutdown handler de-registered
chaiml-gy-exp106-sft-gy_73737_v1 status is now deployed due to DeploymentManager action
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 3207.00s
Shutdown handler de-registered
chaiml-gy-exp106-sft-gy_73737_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp106-sft-gy_73737_v1 status is now torndown due to DeploymentManager action