unsloth-llama-3-2-3b

developer_uid: Meliodia
submission_id: unsloth-llama-3-2-3b_v1
model_name: unsloth-llama-3-2-3b_v1
model_group: unsloth/Llama-3.2-3B
status: torndown
timestamp: 2025-11-23T13:21:23+00:00
num_battles: 7305
num_wins: 2816
celo_rating: 1170.51
family_friendly_score: 0.5766
family_friendly_standard_error: 0.00698759529452014
submission_type: basic
model_repo: unsloth/Llama-3.2-3B
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': 2.253578452350362, 'latency_mean': 0.4436439418792725, 'latency_p50': 0.44252943992614746, 'latency_p90': 0.4962716579437256}, {'batch_size': 5, 'throughput': 5.80958336145112, 'latency_mean': 0.8550154483318329, 'latency_p50': 0.8537366390228271, 'latency_p90': 0.9566331386566161}, {'batch_size': 10, 'throughput': 7.20558490965768, 'latency_mean': 1.3726157033443451, 'latency_p50': 1.3681137561798096, 'latency_p90': 1.549433970451355}, {'batch_size': 15, 'throughput': 7.63444465274536, 'latency_mean': 1.9312888276576996, 'latency_p50': 1.9280061721801758, 'latency_p90': 2.2186601161956787}, {'batch_size': 20, 'throughput': 7.802945952990956, 'latency_mean': 2.5090022134780883, 'latency_p50': 2.5183968544006348, 'latency_p90': 2.854899024963379}, {'batch_size': 25, 'throughput': 8.024045214761998, 'latency_mean': 3.017529661655426, 'latency_p50': 3.061675190925598, 'latency_p90': 3.4168567657470703}, {'batch_size': 30, 'throughput': 7.9358418740882435, 'latency_mean': 3.6152492594718932, 'latency_p50': 3.7015055418014526, 'latency_p90': 4.088833045959473}, {'batch_size': 35, 'throughput': 8.051340332468804, 'latency_mean': 4.124749771356583, 'latency_p50': 4.271483659744263, 'latency_p90': 4.653613018989563}, {'batch_size': 40, 'throughput': 7.992771125388647, 'latency_mean': 4.691939755678177, 'latency_p50': 4.861692667007446, 'latency_p90': 5.346293377876282}, {'batch_size': 45, 'throughput': 7.893809793298427, 'latency_mean': 5.275615854263306, 'latency_p50': 5.58286190032959, 'latency_p90': 6.008100461959839}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: unsloth-llama-3-2-3b_v1
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: unsloth/Llama-3.2-3B
model_size: 4B
ranking_group: single
throughput_3p7s: 8.33
us_pacific_date: 2025-11-20
win_ratio: 0.3854893908281999
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': "{bot_name}'s Persona: {memory}\n####\n", '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-v1-mkmlizer
Waiting for job on unsloth-llama-3-2-3b-v1-mkmlizer to finish
unsloth-llama-3-2-3b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
unsloth-llama-3-2-3b-v1-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  belonging to:                                                      ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
unsloth-llama-3-2-3b-v1-mkmlizer: ║                                                                     ║
unsloth-llama-3-2-3b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
unsloth-llama-3-2-3b-v1-mkmlizer: Downloaded to shared memory in 13.021s
unsloth-llama-3-2-3b-v1-mkmlizer: Checking if unsloth/Llama-3.2-3B already exists in ChaiML
unsloth-llama-3-2-3b-v1-mkmlizer: Creating repo ChaiML/Llama-3.2-3B and uploading /tmp/tmpm28fs9wm to it
unsloth-llama-3-2-3b-v1-mkmlizer: 
Processing Files (0 / 0)                : |          |  0.00B /  0.00B            
unsloth-llama-3-2-3b-v1-mkmlizer: 
New Data Upload                         : |          |  0.00B /  0.00B            [A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
Processing Files (0 / 1)                :   0%|          |  295kB / 6.44GB,   ???B/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:   6%|▌         | 88.0MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   1%|          | 48.0MB / 4.97GB            [A[A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:   6%|▌         | 88.0MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   1%|          | 48.0MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :   2%|▏         |  136MB / 6.44GB,  680MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  12%|█▏        |  174MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   3%|▎         |  128MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :   5%|▍         |  302MB / 6.44GB,  754MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  16%|█▌        |  231MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   4%|▍         |  207MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :   7%|▋         |  438MB / 6.44GB,  731MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  16%|█▌        |  231MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   6%|▌         |  295MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :   8%|▊         |  526MB / 6.44GB,  657MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  20%|█▉        |  288MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   8%|▊         |  381MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  10%|█         |  669MB / 6.44GB,  669MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  25%|██▌       |  368MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:   9%|▉         |  470MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  13%|█▎        |  838MB / 6.44GB,  699MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  32%|███▏      |  464MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  10%|█         |  510MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  15%|█▌        |  975MB / 6.44GB,  696MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  32%|███▏      |  472MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  10%|█         |  510MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  15%|█▌        |  983MB / 6.44GB,  614MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  36%|███▋      |  530MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  12%|█▏        |  577MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  17%|█▋        | 1.11GB / 6.44GB,  615MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  42%|████▏     |  610MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  13%|█▎        |  661MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  20%|█▉        | 1.27GB / 6.44GB,  636MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  47%|████▋     |  691MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  15%|█▌        |  753MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  22%|██▏       | 1.44GB / 6.44GB,  656MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  53%|█████▎    |  779MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  17%|█▋        |  834MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  25%|██▌       | 1.61GB / 6.44GB,  672MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  59%|█████▉    |  868MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  17%|█▋        |  866MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  27%|██▋       | 1.73GB / 6.44GB,  667MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  63%|██████▎   |  925MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  18%|█▊        |  907MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  28%|██▊       | 1.83GB / 6.44GB,  654MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  63%|██████▎   |  925MB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  20%|██        |  995MB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  30%|██▉       | 1.92GB / 6.44GB,  640MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  69%|██████▉   | 1.01GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  22%|██▏       | 1.08GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  32%|███▏      | 2.08GB / 6.44GB,  651MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  75%|███████▌  | 1.10GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  22%|██▏       | 1.10GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  34%|███▍      | 2.20GB / 6.44GB,  647MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  81%|████████  | 1.18GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  24%|██▍       | 1.19GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  37%|███▋      | 2.38GB / 6.44GB,  660MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  87%|████████▋ | 1.26GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  26%|██▌       | 1.29GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  40%|███▉      | 2.55GB / 6.44GB,  671MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  92%|█████████▏| 1.35GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  27%|██▋       | 1.36GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  42%|████▏     | 2.71GB / 6.44GB,  677MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  29%|██▉       | 1.45GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  45%|████▍     | 2.87GB / 6.44GB,  683MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  31%|███       | 1.55GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  46%|████▌     | 2.96GB / 6.44GB,  673MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  33%|███▎      | 1.65GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  47%|████▋     | 3.06GB / 6.44GB,  665MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  35%|███▍      | 1.74GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  49%|████▉     | 3.15GB / 6.44GB,  657MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  37%|███▋      | 1.83GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  50%|█████     | 3.24GB / 6.44GB,  649MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  39%|███▊      | 1.92GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  52%|█████▏    | 3.34GB / 6.44GB,  642MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  41%|████      | 2.01GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  53%|█████▎    | 3.43GB / 6.44GB,  635MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  43%|████▎     | 2.11GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  55%|█████▍    | 3.53GB / 6.44GB,  630MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  44%|████▍     | 2.21GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  56%|█████▌    | 3.62GB / 6.44GB,  624MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  46%|████▋     | 2.30GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  58%|█████▊    | 3.71GB / 6.44GB,  619MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  48%|████▊     | 2.39GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  59%|█████▉    | 3.80GB / 6.44GB,  614MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  50%|████▉     | 2.48GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  60%|██████    | 3.90GB / 6.44GB,  609MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  52%|█████▏    | 2.57GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  62%|██████▏   | 3.99GB / 6.44GB,  604MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  54%|█████▍    | 2.67GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  63%|██████▎   | 4.09GB / 6.44GB,  601MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  56%|█████▌    | 2.77GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  65%|██████▍   | 4.18GB / 6.44GB,  597MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00001-of-00002.safetensors:  58%|█████▊    | 2.86GB / 4.97GB            [A[A[A[A
Processing Files (0 / 3)                :  66%|██████▋   | 4.27GB / 6.44GB,  593MB/s  
unsloth-llama-3-2-3b-v1-mkmlizer: 
  /tmp/tmpm28fs9wm/tokenizer.json       :   2%|▏         |  295kB / 17.2MB            [A[A
unsloth-llama-3-2-3b-v1-mkmlizer: 
  ...wm/model-00002-of-00002.safetensors:  97%|█████████▋| 1.41GB / 1.46GB            [A[A[A
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-v1-mkmlizer: quantized model in 45.250s
unsloth-llama-3-2-3b-v1-mkmlizer: Processed model unsloth/Llama-3.2-3B in 79.633s
unsloth-llama-3-2-3b-v1-mkmlizer: creating bucket guanaco-mkml-models
unsloth-llama-3-2-3b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
unsloth-llama-3-2-3b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/unsloth-llama-3-2-3b-v1/nvidia
unsloth-llama-3-2-3b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-v1/nvidia/config.json
unsloth-llama-3-2-3b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-v1/nvidia/special_tokens_map.json
unsloth-llama-3-2-3b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-v1/nvidia/tokenizer_config.json
unsloth-llama-3-2-3b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/unsloth-llama-3-2-3b-v1/nvidia/tokenizer.json
unsloth-llama-3-2-3b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/unsloth-llama-3-2-3b-v1/nvidia/flywheel_model.0.safetensors
unsloth-llama-3-2-3b-v1-mkmlizer: 
Loading 0:   0%|          | 0/254 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/254 [00:00<00:27,  8.99it/s]
Loading 0:   2%|▏         | 4/254 [00:00<00:45,  5.53it/s]
Loading 0:   2%|▏         | 5/254 [00:01<01:03,  3.91it/s]
Loading 0:   3%|▎         | 8/254 [00:01<00:34,  7.19it/s]
Loading 0:   4%|▎         | 9/254 [00:01<00:33,  7.32it/s]
Loading 0:   4%|▍         | 10/254 [00:01<00:31,  7.66it/s]
Loading 0:   5%|▍         | 12/254 [00:01<00:34,  6.95it/s]
Loading 0:   5%|▌         | 13/254 [00:02<00:44,  5.41it/s]
Loading 0:   6%|▌         | 14/254 [00:02<00:57,  4.19it/s]
Loading 0:   7%|▋         | 17/254 [00:02<00:34,  6.95it/s]
Loading 0:   7%|▋         | 18/254 [00:02<00:32,  7.21it/s]
Loading 0:   7%|▋         | 19/254 [00:02<00:30,  7.59it/s]
Loading 0:   8%|▊         | 21/254 [00:03<00:33,  6.92it/s]
Loading 0:   9%|▊         | 22/254 [00:03<00:42,  5.44it/s]
Loading 0:   9%|▉         | 23/254 [00:03<00:53,  4.28it/s]
Loading 0:  10%|█         | 26/254 [00:04<00:32,  6.98it/s]
Loading 0:  11%|█         | 27/254 [00:04<00:31,  7.19it/s]
Loading 0:  11%|█         | 28/254 [00:04<00:29,  7.57it/s]
Loading 0:  12%|█▏        | 30/254 [00:04<00:32,  6.89it/s]
Loading 0:  12%|█▏        | 31/254 [00:05<00:41,  5.43it/s]
Loading 0:  13%|█▎        | 32/254 [00:05<00:52,  4.22it/s]
Loading 0:  14%|█▍        | 35/254 [00:05<00:31,  6.96it/s]
Loading 0:  14%|█▍        | 36/254 [00:05<00:30,  7.16it/s]
Loading 0:  15%|█▍        | 37/254 [00:05<00:28,  7.56it/s]
Loading 0:  15%|█▌        | 39/254 [00:06<00:31,  6.91it/s]
Loading 0:  16%|█▌        | 40/254 [00:06<00:39,  5.44it/s]
Loading 0:  16%|█▌        | 41/254 [00:06<00:49,  4.28it/s]
Loading 0:  17%|█▋        | 44/254 [00:07<00:29,  7.04it/s]
Loading 0:  18%|█▊        | 45/254 [00:07<00:28,  7.23it/s]
Loading 0:  18%|█▊        | 46/254 [00:07<00:27,  7.60it/s]
Loading 0:  19%|█▉        | 48/254 [00:07<00:29,  6.95it/s]
Loading 0:  19%|█▉        | 49/254 [00:07<00:37,  5.45it/s]
Loading 0:  20%|█▉        | 50/254 [00:08<00:47,  4.28it/s]
Loading 0:  21%|██        | 53/254 [00:08<00:28,  6.98it/s]
Loading 0:  21%|██▏       | 54/254 [00:08<00:27,  7.25it/s]
Loading 0:  22%|██▏       | 55/254 [00:08<00:26,  7.65it/s]
Loading 0:  22%|██▏       | 57/254 [00:09<00:28,  6.97it/s]
Loading 0:  23%|██▎       | 58/254 [00:09<00:35,  5.47it/s]
Loading 0:  23%|██▎       | 59/254 [00:09<00:45,  4.30it/s]
Loading 0:  24%|██▍       | 62/254 [00:09<00:27,  7.06it/s]
Loading 0:  25%|██▍       | 63/254 [00:10<00:26,  7.24it/s]
Loading 0:  25%|██▌       | 64/254 [00:10<00:24,  7.60it/s]
Loading 0:  26%|██▌       | 66/254 [00:10<00:27,  6.95it/s]
Loading 0:  26%|██▋       | 67/254 [00:10<00:34,  5.47it/s]
Loading 0:  27%|██▋       | 68/254 [00:11<00:43,  4.24it/s]
Loading 0:  28%|██▊       | 71/254 [00:11<00:26,  6.99it/s]
Loading 0:  28%|██▊       | 72/254 [00:11<00:25,  7.19it/s]
Loading 0:  29%|██▊       | 73/254 [00:11<00:23,  7.60it/s]
Loading 0:  30%|██▉       | 75/254 [00:11<00:25,  6.97it/s]
Loading 0:  30%|██▉       | 76/254 [00:12<00:32,  5.49it/s]
Loading 0:  30%|███       | 77/254 [00:12<00:40,  4.32it/s]
Loading 0:  31%|███▏      | 80/254 [00:12<00:24,  7.04it/s]
Loading 0:  32%|███▏      | 81/254 [00:12<00:23,  7.31it/s]
Loading 0:  32%|███▏      | 82/254 [00:12<00:22,  7.69it/s]
Loading 0:  33%|███▎      | 84/254 [00:13<00:24,  7.02it/s]
Loading 0:  33%|███▎      | 85/254 [00:13<00:30,  5.52it/s]
Loading 0:  34%|███▍      | 86/254 [00:14<00:38,  4.33it/s]
Loading 0:  35%|███▌      | 89/254 [00:14<00:23,  7.09it/s]
Loading 0:  35%|███▌      | 90/254 [00:14<00:22,  7.28it/s]
Loading 0:  36%|███▌      | 91/254 [00:14<00:21,  7.50it/s]
Loading 0:  37%|███▋      | 93/254 [00:14<00:23,  6.93it/s]
Loading 0:  37%|███▋      | 94/254 [00:15<00:29,  5.47it/s]
Loading 0:  37%|███▋      | 95/254 [00:15<00:36,  4.32it/s]
Loading 0:  39%|███▊      | 98/254 [00:15<00:22,  7.03it/s]
Loading 0:  39%|███▉      | 99/254 [00:15<00:21,  7.23it/s]
Loading 0:  39%|███▉      | 100/254 [00:15<00:20,  7.56it/s]
Loading 0:  40%|████      | 102/254 [00:16<00:21,  6.94it/s]
Loading 0:  41%|████      | 103/254 [00:16<00:27,  5.48it/s]
Loading 0:  41%|████      | 104/254 [00:16<00:34,  4.31it/s]
Loading 0:  42%|████▏     | 107/254 [00:17<00:20,  7.09it/s]
Loading 0:  43%|████▎     | 108/254 [00:17<00:19,  7.36it/s]
Loading 0:  43%|████▎     | 109/254 [00:17<00:18,  7.74it/s]
Loading 0:  44%|████▎     | 111/254 [00:17<00:20,  7.05it/s]
Loading 0:  44%|████▍     | 112/254 [00:17<00:25,  5.53it/s]
Loading 0:  44%|████▍     | 113/254 [00:18<00:32,  4.34it/s]
Loading 0:  46%|████▌     | 116/254 [00:18<00:19,  7.05it/s]
Loading 0:  46%|████▌     | 117/254 [00:18<00:18,  7.23it/s]
Loading 0:  46%|████▋     | 118/254 [00:18<00:17,  7.63it/s]
Loading 0:  47%|████▋     | 119/254 [00:19<00:23,  5.66it/s]
Loading 0:  47%|████▋     | 120/254 [00:19<00:30,  4.33it/s]
Loading 0:  48%|████▊     | 122/254 [00:19<00:21,  6.03it/s]
Loading 0:  48%|████▊     | 123/254 [00:19<00:20,  6.47it/s]
Loading 0:  49%|████▉     | 124/254 [00:19<00:18,  7.02it/s]
Loading 0:  50%|████▉     | 126/254 [00:20<00:19,  6.63it/s]
Loading 0:  50%|█████     | 127/254 [00:20<00:24,  5.25it/s]
Loading 0:  50%|█████     | 128/254 [00:20<00:30,  4.16it/s]
Loading 0:  52%|█████▏    | 131/254 [00:20<00:17,  7.00it/s]
Loading 0:  52%|█████▏    | 132/254 [00:21<00:16,  7.27it/s]
Loading 0:  52%|█████▏    | 133/254 [00:21<00:15,  7.66it/s]
Loading 0:  53%|█████▎    | 135/254 [00:21<00:17,  6.96it/s]
Loading 0:  54%|█████▎    | 136/254 [00:21<00:21,  5.48it/s]
Loading 0:  54%|█████▍    | 137/254 [00:22<00:27,  4.26it/s]
Loading 0:  55%|█████▌    | 140/254 [00:22<00:16,  7.02it/s]
Loading 0:  56%|█████▌    | 141/254 [00:22<00:15,  7.22it/s]
Loading 0:  56%|█████▌    | 142/254 [00:22<00:14,  7.60it/s]
Loading 0:  57%|█████▋    | 144/254 [00:22<00:15,  6.96it/s]
Loading 0:  57%|█████▋    | 145/254 [00:23<00:19,  5.49it/s]
Loading 0:  57%|█████▋    | 146/254 [00:23<00:25,  4.31it/s]
Loading 0:  59%|█████▊    | 149/254 [00:23<00:14,  7.02it/s]
Loading 0:  59%|█████▉    | 150/254 [00:23<00:14,  7.22it/s]
Loading 0:  59%|█████▉    | 151/254 [00:24<00:16,  6.22it/s]
Loading 0:  60%|██████    | 153/254 [00:24<00:18,  5.46it/s]
Loading 0:  61%|██████    | 154/254 [00:24<00:21,  4.68it/s]
Loading 0:  61%|██████    | 155/254 [00:25<00:25,  3.90it/s]
Loading 0:  62%|██████▏   | 158/254 [00:25<00:14,  6.53it/s]
Loading 0:  63%|██████▎   | 159/254 [00:25<00:13,  6.87it/s]
Loading 0:  63%|██████▎   | 160/254 [00:25<00:12,  7.31it/s]
Loading 0:  64%|██████▍   | 162/254 [00:26<00:13,  6.79it/s]
Loading 0:  64%|██████▍   | 163/254 [00:26<00:16,  5.40it/s]
Loading 0:  65%|██████▍   | 164/254 [00:26<00:21,  4.22it/s]
Loading 0:  66%|██████▌   | 167/254 [00:26<00:12,  6.89it/s]
Loading 0:  66%|██████▌   | 168/254 [00:27<00:11,  7.17it/s]
Loading 0:  67%|██████▋   | 169/254 [00:27<00:11,  7.52it/s]
Loading 0:  67%|██████▋   | 171/254 [00:27<00:12,  6.90it/s]
Loading 0:  68%|██████▊   | 172/254 [00:27<00:15,  5.44it/s]
Loading 0:  68%|██████▊   | 173/254 [00:28<00:18,  4.27it/s]
Loading 0:  69%|██████▉   | 176/254 [00:28<00:11,  7.01it/s]
Loading 0:  70%|██████▉   | 177/254 [00:28<00:10,  7.27it/s]
Loading 0:  70%|███████   | 178/254 [00:28<00:09,  7.66it/s]
Loading 0:  71%|███████   | 180/254 [00:29<00:11,  6.24it/s]
Loading 0:  71%|███████▏  | 181/254 [00:29<00:14,  5.10it/s]
Loading 0:  72%|███████▏  | 182/254 [00:29<00:17,  4.12it/s]
Loading 0:  73%|███████▎  | 185/254 [00:29<00:10,  6.81it/s]
Loading 0:  73%|███████▎  | 186/254 [00:30<00:09,  7.10it/s]
Loading 0:  74%|███████▎  | 187/254 [00:30<00:08,  7.51it/s]
Loading 0:  74%|███████▍  | 188/254 [00:30<00:09,  7.04it/s]
Loading 0:  74%|███████▍  | 189/254 [00:30<00:12,  5.31it/s]
Loading 0:  76%|███████▌  | 192/254 [00:30<00:09,  6.79it/s]
Loading 0:  76%|███████▌  | 193/254 [00:31<00:11,  5.48it/s]
Loading 0:  76%|███████▋  | 194/254 [00:31<00:13,  4.32it/s]
Loading 0:  78%|███████▊  | 197/254 [00:31<00:08,  6.96it/s]
Loading 0:  78%|███████▊  | 198/254 [00:31<00:07,  7.22it/s]
Loading 0:  78%|███████▊  | 199/254 [00:32<00:07,  7.57it/s]
Loading 0:  79%|███████▉  | 201/254 [00:32<00:07,  6.94it/s]
Loading 0:  80%|███████▉  | 202/254 [00:32<00:09,  5.45it/s]
Loading 0:  80%|███████▉  | 203/254 [00:33<00:11,  4.29it/s]
Loading 0:  81%|████████  | 206/254 [00:33<00:06,  7.02it/s]
Loading 0:  81%|████████▏ | 207/254 [00:33<00:06,  7.21it/s]
Loading 0:  82%|████████▏ | 208/254 [00:33<00:06,  7.60it/s]
Loading 0:  83%|████████▎ | 210/254 [00:33<00:06,  6.96it/s]
Loading 0:  83%|████████▎ | 211/254 [00:34<00:07,  5.48it/s]
Loading 0:  83%|████████▎ | 212/254 [00:34<00:09,  4.31it/s]
Loading 0:  85%|████████▍ | 215/254 [00:34<00:05,  7.05it/s]
Loading 0:  85%|████████▌ | 216/254 [00:34<00:05,  7.24it/s]
Loading 0:  85%|████████▌ | 217/254 [00:34<00:04,  7.44it/s]
Loading 0:  86%|████████▌ | 219/254 [00:35<00:05,  6.86it/s]
Loading 0:  87%|████████▋ | 220/254 [00:35<00:06,  5.43it/s]
Loading 0:  87%|████████▋ | 221/254 [00:35<00:07,  4.29it/s]
Loading 0:  88%|████████▊ | 224/254 [00:36<00:04,  7.02it/s]
Loading 0:  89%|████████▊ | 225/254 [00:36<00:04,  7.23it/s]
Loading 0:  89%|████████▉ | 226/254 [00:36<00:03,  7.60it/s]
Loading 0:  90%|████████▉ | 228/254 [00:36<00:03,  6.92it/s]
Loading 0:  90%|█████████ | 229/254 [00:37<00:04,  5.45it/s]
Loading 0:  91%|█████████ | 230/254 [00:37<00:05,  4.25it/s]
Loading 0:  92%|█████████▏| 233/254 [00:37<00:03,  6.98it/s]
Loading 0:  92%|█████████▏| 234/254 [00:37<00:02,  7.18it/s]
Loading 0:  93%|█████████▎| 235/254 [00:37<00:02,  7.51it/s]
Loading 0:  93%|█████████▎| 237/254 [00:38<00:02,  6.87it/s]
Loading 0:  94%|█████████▎| 238/254 [00:38<00:02,  5.43it/s]
Loading 0:  94%|█████████▍| 239/254 [00:38<00:03,  4.28it/s]
Loading 0:  95%|█████████▌| 242/254 [00:39<00:01,  7.03it/s]
Loading 0:  96%|█████████▌| 243/254 [00:39<00:01,  7.22it/s]
Loading 0:  96%|█████████▌| 244/254 [00:39<00:01,  7.61it/s]
Loading 0:  97%|█████████▋| 246/254 [00:39<00:01,  6.91it/s]
Loading 0:  97%|█████████▋| 247/254 [00:39<00:01,  5.45it/s]
Loading 0:  98%|█████████▊| 248/254 [00:40<00:01,  4.30it/s]
Loading 0:  99%|█████████▉| 251/254 [00:40<00:00,  7.07it/s]
Loading 0:  99%|█████████▉| 252/254 [00:40<00:00,  7.26it/s]
Loading 0: 100%|█████████▉| 253/254 [00:40<00:00,  7.62it/s]
                                                            
Job unsloth-llama-3-2-3b-v1-mkmlizer completed after 102.43s with status: succeeded
Stopping job with name unsloth-llama-3-2-3b-v1-mkmlizer
Pipeline stage MKMLizer completed in 103.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service unsloth-llama-3-2-3b-v1
Waiting for inference service unsloth-llama-3-2-3b-v1 to be ready
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', '')
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', '')
Inference service unsloth-llama-3-2-3b-v1 ready after 150.73896503448486s
Pipeline stage MKMLDeployer completed in 151.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.9084200859069824s
Received healthy response to inference request in 0.7826497554779053s
Received healthy response to inference request in 0.5763659477233887s
Received healthy response to inference request in 0.6504068374633789s
Received healthy response to inference request in 0.5480749607086182s
5 requests
0 failed requests
5th percentile: 0.5537331581115723
10th percentile: 0.5593913555145263
20th percentile: 0.5707077503204345
30th percentile: 0.5911741256713867
40th percentile: 0.6207904815673828
50th percentile: 0.6504068374633789
60th percentile: 0.7033040046691894
70th percentile: 0.756201171875
80th percentile: 0.8078038215637208
90th percentile: 0.8581119537353515
95th percentile: 0.8832660198211669
99th percentile: 0.9033892726898193
mean time: 0.6931835174560547
Pipeline stage StressChecker completed in 6.18s
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 0.90s
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 1.02s
Shutdown handler de-registered
unsloth-llama-3-2-3b_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 1548.71s
Shutdown handler de-registered
unsloth-llama-3-2-3b_v1 status is now inactive due to auto deactivation removed underperforming models
unsloth-llama-3-2-3b_v1 status is now torndown due to DeploymentManager action