chaiml-hermione-and-gin_37195

developer_uid: chai_backend_admin

submission_id: chaiml-hermione-and-gin_37195_v1

model_name: chaiml-hermione-and-gin_37195_v1

model_group: ChaiML/Hermione-and-Ginn

status: torndown

timestamp: 2025-07-09T05:26:41+00:00

num_battles: 7089

num_wins: 3533

celo_rating: 1297.1

family_friendly_score: 0.5085999999999999

family_friendly_standard_error: 0.0070700217821446625

submission_type: basic

model_repo: ChaiML/Hermione-and-Ginny250708215533_sft

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': 0.5196326471635764, 'latency_mean': 1.9243080735206604, 'latency_p50': 1.9083231687545776, 'latency_p90': 2.1255994558334352}, {'batch_size': 3, 'throughput': 1.0437582571681026, 'latency_mean': 2.8651822113990786, 'latency_p50': 2.8533318042755127, 'latency_p90': 3.1643919944763184}, {'batch_size': 5, 'throughput': 1.3223198108703949, 'latency_mean': 3.766235523223877, 'latency_p50': 3.7666889429092407, 'latency_p90': 4.211232352256775}, {'batch_size': 6, 'throughput': 1.4170822621972479, 'latency_mean': 4.20993395447731, 'latency_p50': 4.261137247085571, 'latency_p90': 4.747565340995789}, {'batch_size': 8, 'throughput': 1.566088991354781, 'latency_mean': 5.062395160198212, 'latency_p50': 4.966760516166687, 'latency_p90': 5.713780856132507}, {'batch_size': 10, 'throughput': 1.6086924123265915, 'latency_mean': 6.148766186237335, 'latency_p50': 6.179842233657837, 'latency_p90': 6.8872086048126215}]

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

display_name: chaiml-hermione-and-gin_37195_v1

is_internal_developer: True

language_model: ChaiML/Hermione-and-Ginny250708215533_sft

model_size: 24B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-07-08

win_ratio: 0.4983777683735365

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####\n', '\n', '####', '</s>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', '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-hermione-and-gin-37195-v1-mkmlizer
Waiting for job on chaiml-hermione-and-gin-37195-v1-mkmlizer to finish
chaiml-hermione-and-gin-37195-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║                                                                     ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║                                                                     ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║                                                                     ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║                                                                     ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ║                                                                     ║
chaiml-hermione-and-gin-37195-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-hermione-and-gin-37195-v1-mkmlizer: Downloaded to shared memory in 75.097s
chaiml-hermione-and-gin-37195-v1-mkmlizer: Checking if ChaiML/Hermione-and-Ginny250708215533_sft already exists in ChaiML
chaiml-hermione-and-gin-37195-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc5rsrj2q, device:0
chaiml-hermione-and-gin-37195-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-hermione-and-gin-37195-v1-mkmlizer: quantized model in 47.142s
chaiml-hermione-and-gin-37195-v1-mkmlizer: Processed model ChaiML/Hermione-and-Ginny250708215533_sft in 122.239s
chaiml-hermione-and-gin-37195-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-hermione-and-gin-37195-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia
chaiml-hermione-and-gin-37195-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia/config.json
chaiml-hermione-and-gin-37195-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia/special_tokens_map.json
chaiml-hermione-and-gin-37195-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia/tokenizer_config.json
chaiml-hermione-and-gin-37195-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia/tokenizer.json
chaiml-hermione-and-gin-37195-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia/flywheel_model.1.safetensors
chaiml-hermione-and-gin-37195-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-hermione-and-gin-37195-v1/nvidia/flywheel_model.0.safetensors
chaiml-hermione-and-gin-37195-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.14it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 38.16it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.40it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.54it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.43it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.69it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:13, 23.38it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 26.00it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:11, 26.98it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.90it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.73it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.57it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.03it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.50it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.67it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.22it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.30it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.50it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.56it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.18it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.06it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.84it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 23.32it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.41it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 24.40it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.46it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.32it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.53it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.65it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.60it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.21it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.72it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.92it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 24.65it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:08, 23.39it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 28.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.15it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.67it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.55it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.29it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.91it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.73it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.46it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.77it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.77it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:56,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:25,  1.10it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:27,  1.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:07,  2.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:50,  2.96it/s]
Loading 0:  60%|██████    | 218/363 [00:21<00:34,  4.23it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.36it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.40it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.43it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.25it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.11it/s]
Loading 0:  66%|██████▌   | 240/363 [00:22<00:07, 15.99it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.44it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.55it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.46it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.42it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 32.01it/s]
Loading 0:  74%|███████▍  | 269/363 [00:23<00:04, 22.59it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:03, 23.24it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:04, 20.06it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.48it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.11it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 28.72it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 27.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.57it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 24.29it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 22.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 23.49it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 24.01it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.03it/s]
Loading 0:  88%|████████▊ | 321/363 [00:25<00:01, 24.36it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.15it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 26.00it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.01it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 26.56it/s]
Loading 0:  94%|█████████▍| 341/363 [00:26<00:01, 15.57it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 21.24it/s]
Loading 0:  96%|█████████▋| 350/363 [00:27<00:00, 22.05it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 25.42it/s]
Loading 0:  99%|█████████▊| 358/363 [00:27<00:00, 23.47it/s]
                                                            
Job chaiml-hermione-and-gin-37195-v1-mkmlizer completed after 156.21s with status: succeeded
Stopping job with name chaiml-hermione-and-gin-37195-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-hermione-and-gin-37195-v1
Waiting for inference service chaiml-hermione-and-gin-37195-v1 to be ready
Inference service chaiml-hermione-and-gin-37195-v1 ready after 200.83025217056274s
Pipeline stage MKMLDeployer completed in 201.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.343777894973755s
Received healthy response to inference request in 1.9997172355651855s
Received healthy response to inference request in 2.0596485137939453s
Received healthy response to inference request in 1.9524602890014648s
Received healthy response to inference request in 2.1427481174468994s
5 requests
0 failed requests
5th percentile: 1.961911678314209
10th percentile: 1.9713630676269531
20th percentile: 1.9902658462524414
30th percentile: 2.0117034912109375
40th percentile: 2.0356760025024414
50th percentile: 2.0596485137939453
60th percentile: 2.092888355255127
70th percentile: 2.1261281967163086
80th percentile: 2.1829540729522705
90th percentile: 2.2633659839630127
95th percentile: 2.303571939468384
99th percentile: 2.335736703872681
mean time: 2.09967041015625
Pipeline stage StressChecker completed in 12.02s
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 0.98s
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 0.72s
Shutdown handler de-registered
chaiml-hermione-and-gin_37195_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 0.10s
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-hermione-and-gin-37195-v1-profiler
Waiting for inference service chaiml-hermione-and-gin-37195-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3961.59s
Shutdown handler de-registered
chaiml-hermione-and-gin_37195_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-hermione-and-gin_37195_v1 status is now torndown due to DeploymentManager action
chaiml-hermione-and-gin_37195_v1 status is now torndown due to DeploymentManager action