chaiml-gy-exp31-sftlora_23360

developer_uid: bogoconic1

submission_id: chaiml-gy-exp31-sftlora_23360_v2

model_name: chaiml-gy-exp31-sftlora_23360_v2

model_group: ChaiML/gy-exp31-sftlora-

status: torndown

timestamp: 2025-06-27T20:23:05+00:00

num_battles: 6830

num_wins: 3508

celo_rating: 1294.45

family_friendly_score: 0.5278

family_friendly_standard_error: 0.007060129743850322

submission_type: basic

model_repo: ChaiML/gy-exp31-sftlora-gy-datamix-v1-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5184113857334604, 'latency_mean': 1.9288468694686889, 'latency_p50': 1.938057541847229, 'latency_p90': 2.122153639793396}, {'batch_size': 3, 'throughput': 1.0578084196607465, 'latency_mean': 2.8281526613235473, 'latency_p50': 2.831550717353821, 'latency_p90': 3.1748658418655396}, {'batch_size': 5, 'throughput': 1.345711525408889, 'latency_mean': 3.6967914617061615, 'latency_p50': 3.692845940589905, 'latency_p90': 4.160297775268555}, {'batch_size': 6, 'throughput': 1.4482410483898902, 'latency_mean': 4.104677678346634, 'latency_p50': 4.091617703437805, 'latency_p90': 4.627146434783936}, {'batch_size': 8, 'throughput': 1.5804710769612922, 'latency_mean': 5.023586826324463, 'latency_p50': 5.03225576877594, 'latency_p90': 5.609082269668579}, {'batch_size': 10, 'throughput': 1.6556107855106426, 'latency_mean': 5.991677998304367, 'latency_p50': 5.987569570541382, 'latency_p90': 6.694727754592895}]

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

display_name: chaiml-gy-exp31-sftlora_23360_v2

is_internal_developer: True

language_model: ChaiML/gy-exp31-sftlora-gy-datamix-v1-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-06-27

win_ratio: 0.5136163982430454

generation_params: {'temperature': 0.8, '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-exp31-sftlora-23360-v2-mkmlizer
Waiting for job on chaiml-gy-exp31-sftlora-23360-v2-mkmlizer to finish
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: Downloaded to shared memory in 65.877s
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: Checking if ChaiML/gy-exp31-sftlora-gy-datamix-v1-ep2 already exists in ChaiML
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz3j3clt1, device:0
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: quantized model in 62.058s
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: Processed model ChaiML/gy-exp31-sftlora-gy-datamix-v1-ep2 in 127.936s
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2/config.json
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2/special_tokens_map.json
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2/tokenizer_config.json
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2/tokenizer.json
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2/flywheel_model.1.safetensors
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp31-sftlora-23360-v2/flywheel_model.0.safetensors
chaiml-gy-exp31-sftlora-23360-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.19it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.34it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.90it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.54it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.64it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:09, 34.93it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:15, 21.75it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:14, 22.23it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:17, 18.30it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 23.62it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:15, 20.47it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 25.22it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:14, 21.52it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 26.52it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 28.01it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:16, 17.15it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:13, 21.75it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 20.85it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.17it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:12, 22.31it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.23it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.46it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.73it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 23.35it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:13, 18.62it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:11, 21.82it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 19.86it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 24.77it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.01it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 26.27it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.33it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.56it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 25.78it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 24.67it/s]
Loading 0:  40%|████      | 146/363 [00:06<00:07, 27.89it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:10, 20.43it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:12, 17.45it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:10, 20.32it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 20.67it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:08, 23.53it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:09, 20.82it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.42it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 24.28it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 23.56it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 23.82it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 20.32it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:09, 19.14it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.16it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 20.57it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 22.45it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:07, 22.45it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<05:52,  2.17s/it]
Loading 0:  56%|█████▌    | 203/363 [00:29<04:31,  1.70s/it]
Loading 0:  57%|█████▋    | 208/363 [00:29<02:26,  1.06it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<01:46,  1.42it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<01:17,  1.93it/s]
Loading 0:  60%|██████    | 218/363 [00:30<00:50,  2.85it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:38,  3.72it/s]
Loading 0:  62%|██████▏   | 224/363 [00:30<00:30,  4.51it/s]
Loading 0:  63%|██████▎   | 228/363 [00:30<00:21,  6.40it/s]
Loading 0:  64%|██████▎   | 231/363 [00:30<00:17,  7.47it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:12, 10.18it/s]
Loading 0:  66%|██████▌   | 238/363 [00:31<00:10, 12.04it/s]
Loading 0:  66%|██████▋   | 241/363 [00:31<00:08, 13.72it/s]
Loading 0:  68%|██████▊   | 246/363 [00:31<00:06, 17.51it/s]
Loading 0:  69%|██████▊   | 249/363 [00:31<00:06, 17.18it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:05, 21.05it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:04, 21.65it/s]
Loading 0:  71%|███████▏  | 259/363 [00:32<00:04, 21.26it/s]
Loading 0:  72%|███████▏  | 263/363 [00:32<00:03, 25.04it/s]
Loading 0:  74%|███████▎  | 267/363 [00:32<00:05, 19.05it/s]
Loading 0:  74%|███████▍  | 270/363 [00:32<00:05, 16.41it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:04, 19.24it/s]
Loading 0:  76%|███████▋  | 277/363 [00:32<00:04, 19.19it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 20.31it/s]
Loading 0:  78%|███████▊  | 283/363 [00:33<00:03, 21.11it/s]
Loading 0:  79%|███████▉  | 286/363 [00:33<00:03, 20.87it/s]
Loading 0:  80%|███████▉  | 289/363 [00:33<00:03, 22.65it/s]
Loading 0:  80%|████████  | 292/363 [00:33<00:03, 22.81it/s]
Loading 0:  81%|████████▏ | 295/363 [00:33<00:03, 22.27it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:02, 24.00it/s]
Loading 0:  83%|████████▎ | 303/363 [00:34<00:02, 26.06it/s]
Loading 0:  84%|████████▍ | 306/363 [00:34<00:03, 15.60it/s]
Loading 0:  85%|████████▌ | 310/363 [00:34<00:02, 18.72it/s]
Loading 0:  86%|████████▌ | 313/363 [00:34<00:02, 18.94it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 20.74it/s]
Loading 0:  88%|████████▊ | 319/363 [00:34<00:02, 21.43it/s]
Loading 0:  89%|████████▊ | 322/363 [00:35<00:01, 21.36it/s]
Loading 0:  90%|████████▉ | 325/363 [00:35<00:01, 23.13it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:01, 23.41it/s]
Loading 0:  91%|█████████ | 331/363 [00:35<00:01, 23.05it/s]
Loading 0:  92%|█████████▏| 335/363 [00:35<00:01, 23.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.95it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 12.21it/s]
Loading 0:  95%|█████████▌| 346/363 [00:36<00:00, 17.13it/s]
Loading 0:  96%|█████████▌| 349/363 [00:36<00:00, 16.41it/s]
Loading 0:  97%|█████████▋| 353/363 [00:36<00:00, 19.69it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.98it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 21.75it/s]
                                                            
Job chaiml-gy-exp31-sftlora-23360-v2-mkmlizer completed after 169.49s with status: succeeded
Stopping job with name chaiml-gy-exp31-sftlora-23360-v2-mkmlizer
Pipeline stage MKMLizer completed in 169.99s
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-exp31-sftlora-23360-v2
Waiting for inference service chaiml-gy-exp31-sftlora-23360-v2 to be ready
Inference service chaiml-gy-exp31-sftlora-23360-v2 ready after 271.60174560546875s
Pipeline stage MKMLDeployer completed in 272.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.127392292022705s
Received healthy response to inference request in 2.006438970565796s
Received healthy response to inference request in 2.173640012741089s
Received healthy response to inference request in 1.9056549072265625s
Received healthy response to inference request in 1.8890156745910645s
5 requests
0 failed requests
5th percentile: 1.892343521118164
10th percentile: 1.8956713676452637
20th percentile: 1.902327060699463
30th percentile: 1.9258117198944091
40th percentile: 1.9661253452301026
50th percentile: 2.006438970565796
60th percentile: 2.0733193874359133
70th percentile: 2.14019980430603
80th percentile: 2.364390468597412
90th percentile: 2.745891380310059
95th percentile: 2.9366418361663817
99th percentile: 3.0892422008514404
mean time: 2.2204283714294433
Pipeline stage StressChecker completed in 12.63s
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 0.84s
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 0.88s
Shutdown handler de-registered
chaiml-gy-exp31-sftlora_23360_v2 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 3199.31s
Shutdown handler de-registered
chaiml-gy-exp31-sftlora_23360_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp31-sftlora_23360_v2 status is now torndown due to DeploymentManager action