unsloth-llama-3-2-3b-instruct

developer_uid: Meliodia

submission_id: unsloth-llama-3-2-3b-instruct_v2

model_name: unsloth-llama-3-2-3b-instruct_v1_empty_memory

model_group: unsloth/Llama-3.2-3B-Ins

status: torndown

timestamp: 2025-11-23T13:21:22+00:00

num_battles: 6972

num_wins: 2682

celo_rating: 1164.02

family_friendly_score: 0.6712

family_friendly_standard_error: 0.006643652007743933

submission_type: basic

model_repo: unsloth/Llama-3.2-3B-Instruct

model_architecture: LlamaForCausalLM

model_num_parameters: 3606752256.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 2.2293930881619493, 'latency_mean': 0.4484358024597168, 'latency_p50': 0.4524807929992676, 'latency_p90': 0.4941184282302856}, {'batch_size': 5, 'throughput': 5.7706579568791945, 'latency_mean': 0.8606017446517944, 'latency_p50': 0.8611878156661987, 'latency_p90': 0.9604674100875854}, {'batch_size': 10, 'throughput': 7.237225680346749, 'latency_mean': 1.3653729307651519, 'latency_p50': 1.3595623970031738, 'latency_p90': 1.5423769235610962}, {'batch_size': 15, 'throughput': 7.82509847897473, 'latency_mean': 1.88132226228714, 'latency_p50': 1.8722004890441895, 'latency_p90': 2.1527266979217528}, {'batch_size': 20, 'throughput': 7.934791636908231, 'latency_mean': 2.466732205152512, 'latency_p50': 2.4319794178009033, 'latency_p90': 2.859188413619995}, {'batch_size': 25, 'throughput': 7.842313830204447, 'latency_mean': 3.0819209372997283, 'latency_p50': 3.084133505821228, 'latency_p90': 3.6961508989334106}, {'batch_size': 30, 'throughput': 7.906060789129408, 'latency_mean': 3.638009750843048, 'latency_p50': 3.759387969970703, 'latency_p90': 4.172491955757141}, {'batch_size': 35, 'throughput': 7.90297738920248, 'latency_mean': 4.197837584018707, 'latency_p50': 4.326266288757324, 'latency_p90': 4.738446545600891}, {'batch_size': 40, 'throughput': 7.874232797848279, 'latency_mean': 4.762296068668365, 'latency_p50': 4.93764054775238, 'latency_p90': 5.461252307891845}, {'batch_size': 45, 'throughput': 7.913935229833155, 'latency_mean': 5.255374962091446, 'latency_p50': 5.549885630607605, 'latency_p90': 6.008650398254394}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: unsloth-llama-3-2-3b-instruct_v1_empty_memory

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: unsloth/Llama-3.2-3B-Instruct

model_size: 4B

ranking_group: single

throughput_3p7s: 8.26

us_pacific_date: 2025-11-20

win_ratio: 0.3846815834767642

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'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

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 unsloth-llama-3-2-3b-instruct-v2-mkmlizer
Waiting for job on unsloth-llama-3-2-3b-instruct-v2-mkmlizer to finish
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  https://mk1.ai                                                     ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  belonging to:                                                      ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  Chai Research Corp.                                                ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: Downloaded to shared memory in 10.726s
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: Checking if unsloth/Llama-3.2-3B-Instruct already exists in ChaiML
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpffw8smq8, device:0
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: quantized model in 44.966s
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: Processed model unsloth/Llama-3.2-3B-Instruct in 55.719s
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: creating bucket guanaco-mkml-models
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/unsloth-llama-3-2-3b-instruct-v2/nvidia
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-instruct-v2/nvidia/config.json
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-instruct-v2/nvidia/special_tokens_map.json
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-instruct-v2/nvidia/tokenizer_config.json
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-instruct-v2/nvidia/tokenizer.json
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/unsloth-llama-3-2-3b-instruct-v2/nvidia/flywheel_model.0.safetensors
unsloth-llama-3-2-3b-instruct-v2-mkmlizer: 
Loading 0:   0%|          | 0/254 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/254 [00:00<00:27,  9.13it/s]
Loading 0:   2%|▏         | 4/254 [00:00<00:44,  5.62it/s]
Loading 0:   2%|▏         | 5/254 [00:01<01:02,  4.01it/s]
Loading 0:   3%|▎         | 8/254 [00:01<00:33,  7.35it/s]
Loading 0:   4%|▍         | 10/254 [00:01<00:31,  7.70it/s]
Loading 0:   5%|▍         | 12/254 [00:01<00:33,  7.12it/s]
Loading 0:   5%|▌         | 13/254 [00:02<00:42,  5.70it/s]
Loading 0:   6%|▌         | 14/254 [00:02<00:53,  4.51it/s]
Loading 0:   7%|▋         | 17/254 [00:02<00:33,  7.17it/s]
Loading 0:   7%|▋         | 18/254 [00:02<00:32,  7.32it/s]
Loading 0:   7%|▋         | 19/254 [00:02<00:30,  7.68it/s]
Loading 0:   8%|▊         | 21/254 [00:03<00:33,  7.01it/s]
Loading 0:   9%|▊         | 22/254 [00:03<00:42,  5.52it/s]
Loading 0:   9%|▉         | 23/254 [00:03<00:53,  4.30it/s]
Loading 0:  10%|█         | 26/254 [00:04<00:32,  7.04it/s]
Loading 0:  11%|█         | 27/254 [00:04<00:31,  7.32it/s]
Loading 0:  11%|█         | 28/254 [00:04<00:29,  7.74it/s]
Loading 0:  12%|█▏        | 30/254 [00:04<00:31,  7.02it/s]
Loading 0:  12%|█▏        | 31/254 [00:04<00:40,  5.50it/s]
Loading 0:  13%|█▎        | 32/254 [00:05<00:51,  4.34it/s]
Loading 0:  14%|█▍        | 35/254 [00:05<00:30,  7.12it/s]
Loading 0:  14%|█▍        | 36/254 [00:05<00:29,  7.36it/s]
Loading 0:  15%|█▍        | 37/254 [00:05<00:27,  7.77it/s]
Loading 0:  15%|█▌        | 39/254 [00:06<00:30,  7.05it/s]
Loading 0:  16%|█▌        | 40/254 [00:06<00:38,  5.51it/s]
Loading 0:  16%|█▌        | 41/254 [00:06<00:49,  4.28it/s]
Loading 0:  17%|█▋        | 44/254 [00:06<00:30,  6.98it/s]
Loading 0:  18%|█▊        | 45/254 [00:07<00:29,  7.19it/s]
Loading 0:  18%|█▊        | 46/254 [00:07<00:27,  7.63it/s]
Loading 0:  19%|█▉        | 48/254 [00:07<00:29,  6.97it/s]
Loading 0:  19%|█▉        | 49/254 [00:07<00:37,  5.49it/s]
Loading 0:  20%|█▉        | 50/254 [00:08<00:47,  4.28it/s]
Loading 0:  21%|██        | 53/254 [00:08<00:28,  6.99it/s]
Loading 0:  21%|██▏       | 54/254 [00:08<00:27,  7.19it/s]
Loading 0:  22%|██▏       | 55/254 [00:08<00:26,  7.60it/s]
Loading 0:  22%|██▏       | 57/254 [00:08<00:28,  6.97it/s]
Loading 0:  23%|██▎       | 58/254 [00:09<00:35,  5.46it/s]
Loading 0:  23%|██▎       | 59/254 [00:09<00:45,  4.30it/s]
Loading 0:  24%|██▍       | 62/254 [00:09<00:27,  7.02it/s]
Loading 0:  25%|██▍       | 63/254 [00:09<00:26,  7.22it/s]
Loading 0:  25%|██▌       | 64/254 [00:10<00:24,  7.64it/s]
Loading 0:  26%|██▌       | 66/254 [00:10<00:26,  6.99it/s]
Loading 0:  26%|██▋       | 67/254 [00:10<00:33,  5.51it/s]
Loading 0:  27%|██▋       | 68/254 [00:11<00:43,  4.27it/s]
Loading 0:  28%|██▊       | 71/254 [00:11<00:26,  7.00it/s]
Loading 0:  28%|██▊       | 72/254 [00:11<00:25,  7.21it/s]
Loading 0:  29%|██▊       | 73/254 [00:11<00:23,  7.63it/s]
Loading 0:  30%|██▉       | 75/254 [00:11<00:25,  7.00it/s]
Loading 0:  30%|██▉       | 76/254 [00:12<00:32,  5.52it/s]
Loading 0:  30%|███       | 77/254 [00:12<00:40,  4.34it/s]
Loading 0:  31%|███▏      | 80/254 [00:12<00:24,  7.14it/s]
Loading 0:  32%|███▏      | 81/254 [00:12<00:23,  7.33it/s]
Loading 0:  32%|███▏      | 82/254 [00:12<00:22,  7.71it/s]
Loading 0:  33%|███▎      | 84/254 [00:13<00:24,  7.03it/s]
Loading 0:  33%|███▎      | 85/254 [00:13<00:30,  5.51it/s]
Loading 0:  34%|███▍      | 86/254 [00:13<00:39,  4.30it/s]
Loading 0:  35%|███▌      | 89/254 [00:14<00:23,  6.99it/s]
Loading 0:  35%|███▌      | 90/254 [00:14<00:22,  7.26it/s]
Loading 0:  36%|███▌      | 91/254 [00:14<00:21,  7.67it/s]
Loading 0:  37%|███▋      | 93/254 [00:14<00:22,  7.00it/s]
Loading 0:  37%|███▋      | 94/254 [00:14<00:29,  5.50it/s]
Loading 0:  37%|███▋      | 95/254 [00:15<00:36,  4.31it/s]
Loading 0:  39%|███▊      | 98/254 [00:15<00:22,  7.01it/s]
Loading 0:  39%|███▉      | 99/254 [00:15<00:21,  7.22it/s]
Loading 0:  39%|███▉      | 100/254 [00:15<00:20,  7.61it/s]
Loading 0:  40%|████      | 102/254 [00:16<00:21,  6.99it/s]
Loading 0:  41%|████      | 103/254 [00:16<00:27,  5.50it/s]
Loading 0:  41%|████      | 104/254 [00:16<00:34,  4.30it/s]
Loading 0:  42%|████▏     | 107/254 [00:16<00:20,  7.07it/s]
Loading 0:  43%|████▎     | 108/254 [00:17<00:20,  7.26it/s]
Loading 0:  43%|████▎     | 109/254 [00:17<00:18,  7.66it/s]
Loading 0:  44%|████▎     | 111/254 [00:17<00:20,  6.98it/s]
Loading 0:  44%|████▍     | 112/254 [00:17<00:25,  5.50it/s]
Loading 0:  44%|████▍     | 113/254 [00:18<00:32,  4.29it/s]
Loading 0:  46%|████▌     | 116/254 [00:18<00:19,  6.98it/s]
Loading 0:  46%|████▌     | 117/254 [00:18<00:19,  7.17it/s]
Loading 0:  46%|████▋     | 118/254 [00:18<00:17,  7.58it/s]
Loading 0:  47%|████▋     | 119/254 [00:18<00:23,  5.66it/s]
Loading 0:  47%|████▋     | 120/254 [00:19<00:30,  4.35it/s]
Loading 0:  48%|████▊     | 122/254 [00:19<00:21,  6.05it/s]
Loading 0:  48%|████▊     | 123/254 [00:19<00:20,  6.52it/s]
Loading 0:  49%|████▉     | 124/254 [00:19<00:18,  7.08it/s]
Loading 0:  50%|████▉     | 126/254 [00:20<00:19,  6.63it/s]
Loading 0:  50%|█████     | 127/254 [00:20<00:24,  5.26it/s]
Loading 0:  50%|█████     | 128/254 [00:20<00:30,  4.18it/s]
Loading 0:  52%|█████▏    | 131/254 [00:20<00:17,  6.96it/s]
Loading 0:  52%|█████▏    | 132/254 [00:20<00:17,  7.18it/s]
Loading 0:  52%|█████▏    | 133/254 [00:21<00:15,  7.60it/s]
Loading 0:  53%|█████▎    | 135/254 [00:21<00:17,  6.98it/s]
Loading 0:  54%|█████▎    | 136/254 [00:21<00:21,  5.49it/s]
Loading 0:  54%|█████▍    | 137/254 [00:22<00:27,  4.27it/s]
Loading 0:  55%|█████▌    | 140/254 [00:22<00:16,  7.04it/s]
Loading 0:  56%|█████▌    | 141/254 [00:22<00:15,  7.24it/s]
Loading 0:  56%|█████▌    | 142/254 [00:22<00:14,  7.64it/s]
Loading 0:  57%|█████▋    | 144/254 [00:22<00:15,  6.99it/s]
Loading 0:  57%|█████▋    | 145/254 [00:23<00:19,  5.50it/s]
Loading 0:  57%|█████▋    | 146/254 [00:23<00:24,  4.33it/s]
Loading 0:  59%|█████▊    | 149/254 [00:23<00:14,  7.11it/s]
Loading 0:  59%|█████▉    | 150/254 [00:23<00:14,  7.29it/s]
Loading 0:  59%|█████▉    | 151/254 [00:23<00:13,  7.67it/s]
Loading 0:  60%|██████    | 153/254 [00:24<00:14,  7.01it/s]
Loading 0:  61%|██████    | 154/254 [00:24<00:18,  5.51it/s]
Loading 0:  61%|██████    | 155/254 [00:24<00:22,  4.31it/s]
Loading 0:  62%|██████▏   | 158/254 [00:25<00:13,  7.13it/s]
Loading 0:  63%|██████▎   | 159/254 [00:25<00:12,  7.40it/s]
Loading 0:  63%|██████▎   | 160/254 [00:25<00:12,  7.76it/s]
Loading 0:  64%|██████▍   | 162/254 [00:25<00:13,  7.04it/s]
Loading 0:  64%|██████▍   | 163/254 [00:26<00:16,  5.54it/s]
Loading 0:  65%|██████▍   | 164/254 [00:26<00:20,  4.35it/s]
Loading 0:  66%|██████▌   | 167/254 [00:26<00:12,  7.11it/s]
Loading 0:  66%|██████▌   | 168/254 [00:26<00:11,  7.29it/s]
Loading 0:  67%|██████▋   | 169/254 [00:26<00:11,  7.68it/s]
Loading 0:  67%|██████▋   | 171/254 [00:27<00:11,  7.01it/s]
Loading 0:  68%|██████▊   | 172/254 [00:27<00:14,  5.51it/s]
Loading 0:  68%|██████▊   | 173/254 [00:27<00:18,  4.34it/s]
Loading 0:  69%|██████▉   | 176/254 [00:27<00:10,  7.13it/s]
Loading 0:  70%|██████▉   | 177/254 [00:28<00:10,  7.32it/s]
Loading 0:  70%|███████   | 178/254 [00:28<00:09,  7.72it/s]
Loading 0:  71%|███████   | 180/254 [00:28<00:10,  7.03it/s]
Loading 0:  71%|███████▏  | 181/254 [00:28<00:13,  5.52it/s]
Loading 0:  72%|███████▏  | 182/254 [00:29<00:16,  4.31it/s]
Loading 0:  73%|███████▎  | 185/254 [00:29<00:09,  7.04it/s]
Loading 0:  73%|███████▎  | 186/254 [00:29<00:09,  7.25it/s]
Loading 0:  74%|███████▎  | 187/254 [00:29<00:08,  7.65it/s]
Loading 0:  74%|███████▍  | 188/254 [00:29<00:08,  7.55it/s]
Loading 0:  74%|███████▍  | 189/254 [00:30<00:11,  5.54it/s]
Loading 0:  76%|███████▌  | 192/254 [00:30<00:08,  7.01it/s]
Loading 0:  76%|███████▌  | 193/254 [00:30<00:10,  5.61it/s]
Loading 0:  76%|███████▋  | 194/254 [00:31<00:13,  4.44it/s]
Loading 0:  78%|███████▊  | 197/254 [00:31<00:08,  7.11it/s]
Loading 0:  78%|███████▊  | 198/254 [00:31<00:07,  7.36it/s]
Loading 0:  78%|███████▊  | 199/254 [00:31<00:07,  7.67it/s]
Loading 0:  79%|███████▉  | 201/254 [00:31<00:07,  7.02it/s]
Loading 0:  80%|███████▉  | 202/254 [00:32<00:09,  5.53it/s]
Loading 0:  80%|███████▉  | 203/254 [00:32<00:11,  4.34it/s]
Loading 0:  81%|████████  | 206/254 [00:32<00:06,  7.10it/s]
Loading 0:  81%|████████▏ | 207/254 [00:32<00:06,  7.33it/s]
Loading 0:  82%|████████▏ | 208/254 [00:32<00:05,  7.71it/s]
Loading 0:  83%|████████▎ | 210/254 [00:33<00:06,  7.03it/s]
Loading 0:  83%|████████▎ | 211/254 [00:33<00:07,  5.53it/s]
Loading 0:  83%|████████▎ | 212/254 [00:33<00:09,  4.35it/s]
Loading 0:  85%|████████▍ | 215/254 [00:34<00:05,  7.07it/s]
Loading 0:  85%|████████▌ | 216/254 [00:34<00:05,  7.26it/s]
Loading 0:  85%|████████▌ | 217/254 [00:34<00:04,  7.66it/s]
Loading 0:  86%|████████▌ | 219/254 [00:34<00:05,  6.99it/s]
Loading 0:  87%|████████▋ | 220/254 [00:35<00:06,  5.51it/s]
Loading 0:  87%|████████▋ | 221/254 [00:35<00:07,  4.29it/s]
Loading 0:  88%|████████▊ | 224/254 [00:35<00:04,  6.83it/s]
Loading 0:  89%|████████▊ | 225/254 [00:35<00:04,  7.05it/s]
Loading 0:  89%|████████▉ | 226/254 [00:35<00:03,  7.48it/s]
Loading 0:  90%|████████▉ | 228/254 [00:36<00:03,  6.87it/s]
Loading 0:  90%|█████████ | 229/254 [00:36<00:04,  5.44it/s]
Loading 0:  91%|█████████ | 230/254 [00:36<00:05,  4.31it/s]
Loading 0:  92%|█████████▏| 233/254 [00:37<00:02,  7.07it/s]
Loading 0:  92%|█████████▏| 234/254 [00:37<00:02,  7.26it/s]
Loading 0:  93%|█████████▎| 235/254 [00:37<00:02,  7.60it/s]
Loading 0:  93%|█████████▎| 237/254 [00:37<00:02,  6.92it/s]
Loading 0:  94%|█████████▎| 238/254 [00:37<00:02,  5.48it/s]
Loading 0:  94%|█████████▍| 239/254 [00:38<00:03,  4.32it/s]
Loading 0:  95%|█████████▌| 242/254 [00:38<00:01,  7.10it/s]
Loading 0:  96%|█████████▌| 243/254 [00:38<00:01,  7.28it/s]
Loading 0:  96%|█████████▌| 244/254 [00:38<00:01,  6.85it/s]
Loading 0:  97%|█████████▋| 246/254 [00:39<00:01,  5.85it/s]
Loading 0:  97%|█████████▋| 247/254 [00:39<00:01,  4.91it/s]
Loading 0:  98%|█████████▊| 248/254 [00:39<00:01,  4.04it/s]
Loading 0:  99%|█████████▉| 251/254 [00:40<00:00,  6.67it/s]
Loading 0:  99%|█████████▉| 252/254 [00:40<00:00,  6.99it/s]
Loading 0: 100%|█████████▉| 253/254 [00:40<00:00,  7.44it/s]
                                                            
Job unsloth-llama-3-2-3b-instruct-v2-mkmlizer completed after 73.78s with status: succeeded
Stopping job with name unsloth-llama-3-2-3b-instruct-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.32s
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 unsloth-llama-3-2-3b-instruct-v2
Waiting for inference service unsloth-llama-3-2-3b-instruct-v2 to be ready
Inference service unsloth-llama-3-2-3b-instruct-v2 ready after 150.73845386505127s
Pipeline stage MKMLDeployer completed in 151.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.9010255336761475s
Received healthy response to inference request in 0.7878520488739014s
Received healthy response to inference request in 1.0578465461730957s
Received healthy response to inference request in 0.9409463405609131s
Received healthy response to inference request in 1.183013916015625s
5 requests
0 failed requests
5th percentile: 0.8104867458343505
10th percentile: 0.8331214427947998
20th percentile: 0.8783908367156983
30th percentile: 0.9090096950531006
40th percentile: 0.9249780178070068
50th percentile: 0.9409463405609131
60th percentile: 0.9877064228057861
70th percentile: 1.0344665050506592
80th percentile: 1.0828800201416016
90th percentile: 1.1329469680786133
95th percentile: 1.1579804420471191
99th percentile: 1.178007221221924
mean time: 0.9741368770599366
Pipeline stage StressChecker completed in 6.63s
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 0.68s
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 0.78s
Shutdown handler de-registered
unsloth-llama-3-2-3b-instruct_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 1512.95s
Shutdown handler de-registered
unsloth-llama-3-2-3b-instruct_v2 status is now inactive due to auto deactivation removed underperforming models
unsloth-llama-3-2-3b-instruct_v2 status is now torndown due to DeploymentManager action