chaiml-95p-5ff-chaiml-m_54615

developer_uid: rirv938
submission_id: chaiml-95p-5ff-chaiml-m_54615_v1
model_name: chaiml-95p-5ff-chaiml-m_54615_v1
model_group: ChaiML/95p_5ff_chaiml_mi
status: torndown
timestamp: 2026-02-04T05:37:51+00:00
num_battles: 10874
num_wins: 6014
celo_rating: 1337.37
family_friendly_score: 0.5358
family_friendly_standard_error: 0.007052919395541112
submission_type: basic
model_repo: ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp624_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 112
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2959624202726191, 'latency_mean': 3.3787262558937075, 'latency_p50': 3.396702527999878, 'latency_p90': 3.561141562461853}, {'batch_size': 2, 'throughput': 0.475071436761804, 'latency_mean': 4.208104206323624, 'latency_p50': 4.222553968429565, 'latency_p90': 4.422056078910828}, {'batch_size': 3, 'throughput': 0.5998476515987193, 'latency_mean': 4.991917601823807, 'latency_p50': 4.998661279678345, 'latency_p90': 5.266244125366211}, {'batch_size': 4, 'throughput': 0.6888835802928848, 'latency_mean': 5.773721323013306, 'latency_p50': 5.753350615501404, 'latency_p90': 6.100340557098388}, {'batch_size': 5, 'throughput': 0.7454238178135667, 'latency_mean': 6.680382671356202, 'latency_p50': 6.666752576828003, 'latency_p90': 7.364537858963013}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-95p-5ff-chaiml-m_54615_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp624_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.37
us_pacific_date: 2026-01-31
win_ratio: 0.5530623505609711
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['###', '<|im_start|>', '<|im_end|>', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 112}
formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer
Waiting for job on chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer to finish
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-95p-5ff-chaiml-m-53900-v1-mkmlizer
Waiting for job on chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer to finish
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: bash: no job control in this shell
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: Downloaded to shared memory in 90.171s
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: Checking if ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp312_merged already exists in ChaiML
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpx81w8kq5, device:0
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Downloaded to shared memory in 125.499s
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Checking if ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp624_merged already exists in ChaiML
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpmf4yo2ou, device:0
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Stopping job with name chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer
Waiting for job on chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer to finish
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: bash: no job control in this shell
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ║                                                                     ║
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Downloaded to shared memory in 85.206s
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Checking if ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp624_merged already exists in ChaiML
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpdixl2mia, device:0
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:51, 1.56it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:51, 1.56it/s]
Loading 0:   1%|          | 4.00/363 [00:03<06:15, 1.05s/it]
Loading 0:   1%|          | 4.00/363 [00:03<06:15, 1.05s/it]
Loading 0:   1%|▏         | 5.00/363 [00:05<08:01, 1.35s/it]
Loading 0:   1%|▏         | 5.00/363 [00:05<08:01, 1.35s/it]
Loading 0:   3%|▎         | 12.0/363 [00:07<02:38, 2.21it/s]
Loading 0:   3%|▎         | 12.0/363 [00:07<02:38, 2.21it/s]
Loading 0:   4%|▎         | 13.0/363 [00:08<03:46, 1.55it/s]
Loading 0:   4%|▎         | 13.0/363 [00:08<03:46, 1.55it/s]
Loading 0:   4%|▍         | 14.0/363 [00:10<04:55, 1.18it/s]
Loading 0:   4%|▍         | 14.0/363 [00:10<04:55, 1.18it/s]
Loading 0:   4%|▍         | 15.0/363 [00:12<06:09, 1.06s/it]
Loading 0:   4%|▍         | 15.0/363 [00:12<06:09, 1.06s/it]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:41, 1.54it/s]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:41, 1.54it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:35, 1.24it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:35, 1.24it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:37, 1.01it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:37, 1.01it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:30, 2.20it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:30, 2.20it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:53, 1.90it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:53, 1.90it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:41, 1.48it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:41, 1.48it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:39, 1.17it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:39, 1.17it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:10, 1.29it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:10, 1.29it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:05, 1.06it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:05, 1.06it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:05, 1.14s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:05, 1.14s/it]
Loading 0:  13%|█▎        | 49.0/363 [00:33<02:30, 2.08it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:33<02:30, 2.08it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:35<02:49, 1.83it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:35<02:49, 1.83it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:37<03:35, 1.44it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:37<03:35, 1.44it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:39<04:31, 1.14it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:39<04:31, 1.14it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:41<04:01, 1.27it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:41<04:01, 1.27it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<04:51, 1.05it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<04:51, 1.05it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:45<05:47, 1.14s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:45<05:47, 1.14s/it]
Loading 0:  18%|█▊        | 67.0/363 [00:46<02:22, 2.07it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:46<02:22, 2.07it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:48<02:40, 1.82it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:48<02:40, 1.82it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:50<03:24, 1.43it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:50<03:24, 1.43it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:52<04:19, 1.12it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:52<04:19, 1.12it/s]
Loading 0:  21%|██        | 75.0/363 [00:54<03:49, 1.25it/s]
Loading 0:  21%|██        | 75.0/363 [00:54<03:49, 1.25it/s]
Loading 0:  21%|██        | 76.0/363 [00:56<04:36, 1.04it/s]
Loading 0:  21%|██        | 76.0/363 [00:56<04:36, 1.04it/s]
Loading 0:  21%|██        | 77.0/363 [00:58<05:28, 1.15s/it]
Loading 0:  21%|██        | 77.0/363 [00:58<05:28, 1.15s/it]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:14, 2.06it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:14, 2.06it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:02<02:31, 1.81it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:02<02:31, 1.81it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:03<03:12, 1.43it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:03<03:12, 1.43it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:06<04:00, 1.13it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:06<04:00, 1.13it/s]
Loading 0:  27%|██▋       | 98.0/363 [01:07<01:55, 2.29it/s]
Loading 0:  27%|██▋       | 98.0/363 [01:07<01:55, 2.29it/s]
Loading 0:  28%|██▊       | 101/363 [01:09<02:10, 2.01it/s] 
Loading 0:  28%|██▊       | 101/363 [01:09<02:10, 2.01it/s]
Loading 0:  28%|██▊       | 102/363 [01:11<02:48, 1.55it/s]
Loading 0:  28%|██▊       | 102/363 [01:11<02:48, 1.55it/s]
Loading 0:  28%|██▊       | 103/363 [01:13<03:34, 1.21it/s]
Loading 0:  28%|██▊       | 103/363 [01:13<03:34, 1.21it/s]
Loading 0:  29%|██▉       | 106/363 [01:15<03:18, 1.29it/s]
Loading 0:  29%|██▉       | 106/363 [01:15<03:18, 1.29it/s]
Loading 0:  29%|██▉       | 107/363 [01:17<03:59, 1.07it/s]
Loading 0:  29%|██▉       | 107/363 [01:17<03:59, 1.07it/s]
Loading 0:  30%|██▉       | 108/363 [01:19<04:46, 1.12s/it]
Loading 0:  30%|██▉       | 108/363 [01:19<04:46, 1.12s/it]
Loading 0:  31%|███       | 111/363 [01:21<03:51, 1.09it/s]
Loading 0:  31%|███       | 111/363 [01:21<03:51, 1.09it/s]
Loading 0:  31%|███       | 112/363 [01:22<04:31, 1.08s/it]
Loading 0:  31%|███       | 112/363 [01:22<04:31, 1.08s/it]
Loading 0:  31%|███       | 113/363 [01:25<05:16, 1.27s/it]
Loading 0:  31%|███       | 113/363 [01:25<05:16, 1.27s/it]
Loading 0:  33%|███▎      | 121/363 [01:26<01:59, 2.02it/s]
Loading 0:  33%|███▎      | 121/363 [01:26<01:59, 2.02it/s]
Loading 0:  34%|███▍      | 124/363 [01:28<02:13, 1.79it/s]
Loading 0:  34%|███▍      | 124/363 [01:28<02:13, 1.79it/s]
Loading 0:  34%|███▍      | 125/363 [01:30<02:49, 1.40it/s]
Loading 0:  34%|███▍      | 125/363 [01:30<02:49, 1.40it/s]
Loading 0:  35%|███▍      | 126/363 [01:32<03:32, 1.12it/s]
Loading 0:  35%|███▍      | 126/363 [01:32<03:32, 1.12it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<03:07, 1.25it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<03:07, 1.25it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<03:45, 1.04it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<03:45, 1.04it/s]
Loading 0:  36%|███▌      | 131/363 [01:38<04:26, 1.15s/it]
Loading 0:  36%|███▌      | 131/363 [01:38<04:26, 1.15s/it]
Loading 0:  38%|███▊      | 139/363 [01:39<01:47, 2.08it/s]
Loading 0:  38%|███▊      | 139/363 [01:39<01:47, 2.08it/s]
Loading 0:  39%|███▉      | 142/363 [01:41<02:01, 1.82it/s]
Loading 0:  39%|███▉      | 142/363 [01:41<02:01, 1.82it/s]
Loading 0:  39%|███▉      | 143/363 [01:43<02:34, 1.43it/s]
Loading 0:  39%|███▉      | 143/363 [01:43<02:34, 1.43it/s]
Loading 0:  40%|███▉      | 144/363 [01:45<03:12, 1.14it/s]
Loading 0:  40%|███▉      | 144/363 [01:45<03:12, 1.14it/s]
Loading 0:  40%|████      | 147/363 [01:47<02:50, 1.26it/s]
Loading 0:  40%|████      | 147/363 [01:47<02:50, 1.26it/s]
Loading 0:  41%|████      | 148/363 [01:49<03:25, 1.04it/s]
Loading 0:  41%|████      | 148/363 [01:49<03:25, 1.04it/s]
Loading 0:  41%|████      | 149/363 [01:51<04:05, 1.15s/it]
Loading 0:  41%|████      | 149/363 [01:51<04:05, 1.15s/it]
Loading 0:  43%|████▎     | 157/363 [01:52<01:39, 2.07it/s]
Loading 0:  43%|████▎     | 157/363 [01:52<01:39, 2.07it/s]
Loading 0:  44%|████▍     | 160/363 [01:54<01:51, 1.82it/s]
Loading 0:  44%|████▍     | 160/363 [01:54<01:51, 1.82it/s]
Loading 0:  44%|████▍     | 161/363 [01:56<02:21, 1.43it/s]
Loading 0:  44%|████▍     | 161/363 [01:56<02:21, 1.43it/s]
Loading 0:  45%|████▍     | 162/363 [01:58<02:57, 1.13it/s]
Loading 0:  45%|████▍     | 162/363 [01:58<02:57, 1.13it/s]
Loading 0:  45%|████▌     | 165/363 [02:00<02:36, 1.26it/s]
Loading 0:  45%|████▌     | 165/363 [02:00<02:36, 1.26it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<03:08, 1.04it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<03:08, 1.04it/s]
Loading 0:  46%|████▌     | 167/363 [02:04<03:44, 1.14s/it]
Loading 0:  46%|████▌     | 167/363 [02:04<03:44, 1.14s/it]
Loading 0:  48%|████▊     | 175/363 [02:05<01:29, 2.09it/s]
Loading 0:  48%|████▊     | 175/363 [02:05<01:29, 2.09it/s]
Loading 0:  49%|████▉     | 178/363 [02:07<01:40, 1.83it/s]
Loading 0:  49%|████▉     | 178/363 [02:07<01:40, 1.83it/s]
Loading 0:  49%|████▉     | 179/363 [02:09<02:08, 1.44it/s]
Loading 0:  49%|████▉     | 179/363 [02:09<02:08, 1.44it/s]
Loading 0:  50%|████▉     | 180/363 [02:11<02:40, 1.14it/s]
Loading 0:  50%|████▉     | 180/363 [02:11<02:40, 1.14it/s]
Loading 0:  50%|█████     | 183/363 [02:13<02:21, 1.27it/s]
Loading 0:  50%|█████     | 183/363 [02:13<02:21, 1.27it/s]
Loading 0:  51%|█████     | 184/363 [02:15<02:50, 1.05it/s]
Loading 0:  51%|█████     | 184/363 [02:15<02:50, 1.05it/s]
Loading 0:  51%|█████     | 185/363 [02:17<03:23, 1.14s/it]
Loading 0:  51%|█████     | 185/363 [02:17<03:23, 1.14s/it]
Loading 0:  53%|█████▎    | 193/363 [02:18<01:21, 2.09it/s]
Loading 0:  53%|█████▎    | 193/363 [02:18<01:21, 2.09it/s]
Loading 0:  54%|█████▍    | 196/363 [02:21<01:31, 1.83it/s]
Loading 0:  54%|█████▍    | 196/363 [02:21<01:31, 1.83it/s]
Loading 0:  54%|█████▍    | 197/363 [02:22<01:55, 1.43it/s]
Loading 0:  54%|█████▍    | 197/363 [02:22<01:55, 1.43it/s]
Loading 0:  55%|█████▍    | 198/363 [02:25<02:26, 1.12it/s]
Loading 0:  55%|█████▍    | 198/363 [02:25<02:26, 1.12it/s]
Loading 0:  55%|█████▌    | 201/363 [02:26<02:08, 1.26it/s]
Loading 0:  55%|█████▌    | 201/363 [02:26<02:08, 1.26it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:34, 1.04it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:34, 1.04it/s]
Loading 0:  56%|█████▌    | 203/363 [02:30<03:03, 1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [02:30<03:03, 1.15s/it]
Loading 0:  58%|█████▊    | 211/363 [02:32<01:12, 2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [02:32<01:12, 2.10it/s]
Loading 0:  59%|█████▉    | 214/363 [02:34<01:21, 1.84it/s]
Loading 0:  59%|█████▉    | 214/363 [02:34<01:21, 1.84it/s]
Loading 0:  59%|█████▉    | 215/363 [02:36<01:42, 1.44it/s]
Loading 0:  59%|█████▉    | 215/363 [02:36<01:42, 1.44it/s]
Loading 0:  60%|█████▉    | 216/363 [02:38<02:08, 1.14it/s]
Loading 0:  60%|█████▉    | 216/363 [02:38<02:08, 1.14it/s]
Loading 0:  60%|██████    | 219/363 [02:40<01:53, 1.27it/s]
Loading 0:  60%|██████    | 219/363 [02:40<01:53, 1.27it/s]
Loading 0:  61%|██████    | 220/363 [02:41<02:16, 1.05it/s]
Loading 0:  61%|██████    | 220/363 [02:41<02:16, 1.05it/s]
Loading 0:  61%|██████    | 221/363 [02:43<02:41, 1.14s/it]
Loading 0:  61%|██████    | 221/363 [02:43<02:41, 1.14s/it]
Loading 0:  63%|██████▎   | 229/363 [02:45<01:03, 2.10it/s]
Loading 0:  63%|██████▎   | 229/363 [02:45<01:03, 2.10it/s]
Loading 0:  64%|██████▍   | 232/363 [02:47<01:11, 1.84it/s]
Loading 0:  64%|██████▍   | 232/363 [02:47<01:11, 1.84it/s]
Loading 0:  64%|██████▍   | 233/363 [02:49<01:30, 1.44it/s]
Loading 0:  64%|██████▍   | 233/363 [02:49<01:30, 1.44it/s]
Loading 0:  64%|██████▍   | 234/363 [02:51<01:53, 1.14it/s]
Loading 0:  64%|██████▍   | 234/363 [02:51<01:53, 1.14it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:39, 1.27it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:39, 1.27it/s]
Loading 0:  66%|██████▌   | 238/363 [02:55<01:59, 1.05it/s]
Loading 0:  66%|██████▌   | 238/363 [02:55<01:59, 1.05it/s]
Loading 0:  66%|██████▌   | 239/363 [02:57<02:21, 1.14s/it]
Loading 0:  66%|██████▌   | 239/363 [02:57<02:21, 1.14s/it]
Loading 0:  68%|██████▊   | 247/363 [02:58<00:55, 2.11it/s]
Loading 0:  68%|██████▊   | 247/363 [02:58<00:55, 2.11it/s]
Loading 0:  69%|██████▉   | 250/363 [03:00<01:01, 1.84it/s]
Loading 0:  69%|██████▉   | 250/363 [03:00<01:01, 1.84it/s]
Loading 0:  69%|██████▉   | 251/363 [03:02<01:18, 1.43it/s]
Loading 0:  69%|██████▉   | 251/363 [03:02<01:18, 1.43it/s]
Loading 0:  69%|██████▉   | 252/363 [03:04<01:37, 1.14it/s]
Loading 0:  69%|██████▉   | 252/363 [03:04<01:37, 1.14it/s]
Loading 0:  70%|███████   | 255/363 [03:06<01:25, 1.27it/s]
Loading 0:  70%|███████   | 255/363 [03:06<01:25, 1.27it/s]
Loading 0:  71%|███████   | 256/363 [03:08<01:42, 1.05it/s]
Loading 0:  71%|███████   | 256/363 [03:08<01:42, 1.05it/s]
Loading 0:  71%|███████   | 257/363 [03:10<02:01, 1.14s/it]
Loading 0:  71%|███████   | 257/363 [03:10<02:01, 1.14s/it]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:46, 2.09it/s]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:46, 2.09it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<00:51, 1.83it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<00:51, 1.83it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:05, 1.44it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:05, 1.44it/s]
Loading 0:  74%|███████▍  | 270/363 [03:17<01:21, 1.14it/s]
Loading 0:  74%|███████▍  | 270/363 [03:17<01:21, 1.14it/s]
Loading 0:  75%|███████▌  | 273/363 [03:32<03:35, 2.40s/it]
Loading 0:  75%|███████▌  | 273/363 [03:32<03:35, 2.40s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<03:26, 2.32s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<03:26, 2.32s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<03:20, 2.27s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<03:20, 2.27s/it]
Loading 0:  78%|███████▊  | 283/363 [03:37<01:08, 1.17it/s]
Loading 0:  78%|███████▊  | 283/363 [03:37<01:08, 1.17it/s]
Loading 0:  79%|███████▉  | 286/363 [03:39<01:03, 1.22it/s]
Loading 0:  79%|███████▉  | 286/363 [03:39<01:03, 1.22it/s]
Loading 0:  79%|███████▉  | 287/363 [03:41<01:11, 1.06it/s]
Loading 0:  79%|███████▉  | 287/363 [03:41<01:11, 1.06it/s]
Loading 0:  79%|███████▉  | 288/363 [03:43<01:21, 1.09s/it]
Loading 0:  79%|███████▉  | 288/363 [03:43<01:21, 1.09s/it]
Loading 0:  80%|████████  | 291/363 [03:45<01:06, 1.09it/s]
Loading 0:  80%|████████  | 291/363 [03:45<01:06, 1.09it/s]
Loading 0:  80%|████████  | 292/363 [03:47<01:15, 1.07s/it]
Loading 0:  80%|████████  | 292/363 [03:47<01:15, 1.07s/it]
Loading 0:  81%|████████  | 293/363 [03:49<01:26, 1.23s/it]
Loading 0:  81%|████████  | 293/363 [03:49<01:26, 1.23s/it]
Loading 0:  83%|████████▎ | 301/363 [03:50<00:31, 1.99it/s]
Loading 0:  83%|████████▎ | 301/363 [03:50<00:31, 1.99it/s]
Loading 0:  84%|████████▎ | 304/363 [03:52<00:33, 1.78it/s]
Loading 0:  84%|████████▎ | 304/363 [03:52<00:33, 1.78it/s]
Loading 0:  84%|████████▍ | 305/363 [03:54<00:41, 1.40it/s]
Loading 0:  84%|████████▍ | 305/363 [03:54<00:41, 1.40it/s]
Loading 0:  84%|████████▍ | 306/363 [03:56<00:50, 1.12it/s]
Loading 0:  84%|████████▍ | 306/363 [03:56<00:50, 1.12it/s]
Loading 0:  85%|████████▌ | 309/363 [03:58<00:43, 1.25it/s]
Loading 0:  85%|████████▌ | 309/363 [03:58<00:43, 1.25it/s]
Loading 0:  85%|████████▌ | 310/363 [04:00<00:50, 1.04it/s]
Loading 0:  85%|████████▌ | 310/363 [04:00<00:50, 1.04it/s]
Loading 0:  86%|████████▌ | 311/363 [04:02<00:59, 1.15s/it]
Loading 0:  86%|████████▌ | 311/363 [04:02<00:59, 1.15s/it]
Loading 0:  88%|████████▊ | 319/363 [04:03<00:21, 2.09it/s]
Loading 0:  88%|████████▊ | 319/363 [04:03<00:21, 2.09it/s]
Loading 0:  89%|████████▊ | 322/363 [04:05<00:22, 1.83it/s]
Loading 0:  89%|████████▊ | 322/363 [04:05<00:22, 1.83it/s]
Loading 0:  89%|████████▉ | 323/363 [04:07<00:27, 1.44it/s]
Loading 0:  89%|████████▉ | 323/363 [04:07<00:27, 1.44it/s]
Loading 0:  89%|████████▉ | 324/363 [04:09<00:34, 1.14it/s]
Loading 0:  89%|████████▉ | 324/363 [04:09<00:34, 1.14it/s]
Loading 0:  90%|█████████ | 327/363 [04:11<00:28, 1.27it/s]
Loading 0:  90%|█████████ | 327/363 [04:11<00:28, 1.27it/s]
Loading 0:  90%|█████████ | 328/363 [04:13<00:33, 1.05it/s]
Loading 0:  90%|█████████ | 328/363 [04:13<00:33, 1.05it/s]
Loading 0:  91%|█████████ | 329/363 [04:15<00:38, 1.14s/it]
Loading 0:  91%|█████████ | 329/363 [04:15<00:38, 1.14s/it]
Loading 0:  93%|█████████▎| 337/363 [04:16<00:12, 2.10it/s]
Loading 0:  93%|█████████▎| 337/363 [04:16<00:12, 2.10it/s]
Loading 0:  94%|█████████▎| 340/363 [04:18<00:12, 1.84it/s]
Loading 0:  94%|█████████▎| 340/363 [04:18<00:12, 1.84it/s]
Loading 0:  94%|█████████▍| 341/363 [04:20<00:15, 1.44it/s]
Loading 0:  94%|█████████▍| 341/363 [04:20<00:15, 1.44it/s]
Loading 0:  94%|█████████▍| 342/363 [04:22<00:18, 1.14it/s]
Loading 0:  94%|█████████▍| 342/363 [04:22<00:18, 1.14it/s]
Loading 0:  95%|█████████▌| 345/363 [04:24<00:14, 1.27it/s]
Loading 0:  95%|█████████▌| 345/363 [04:24<00:14, 1.27it/s]
Loading 0:  95%|█████████▌| 346/363 [04:26<00:16, 1.05it/s]
Loading 0:  95%|█████████▌| 346/363 [04:26<00:16, 1.05it/s]
Loading 0:  96%|█████████▌| 347/363 [04:28<00:18, 1.14s/it]
Loading 0:  96%|█████████▌| 347/363 [04:28<00:18, 1.14s/it]
Loading 0:  98%|█████████▊| 355/363 [04:29<00:03, 2.09it/s]
Loading 0:  98%|█████████▊| 355/363 [04:29<00:03, 2.09it/s]
Loading 0:  99%|█████████▉| 359/363 [04:32<00:02, 1.88it/s]
Loading 0:  99%|█████████▉| 359/363 [04:32<00:02, 1.88it/s]
Loading 0:  99%|█████████▉| 360/363 [04:34<00:02, 1.49it/s]
Loading 0:  99%|█████████▉| 360/363 [04:34<00:02, 1.49it/s]
Loading 0:  99%|█████████▉| 361/363 [04:36<00:01, 1.19it/s]
Loading 0:  99%|█████████▉| 361/363 [04:36<00:01, 1.19it/s]
Loading 0: 100%|██████████| 363/363 [04:36<00:00, 1.19it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [04:36<00:00, 1.31it/s]
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpx81w8kq5' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: quantized model in 282.938s
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: Processed model ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp312_merged in 373.110s
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-53900-v1/nvidia
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-53900-v1/nvidia/config.json
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-53900-v1/nvidia/special_tokens_map.json
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-53900-v1/nvidia/tokenizer_config.json
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-53900-v1/nvidia/flywheel_model.1.safetensors
chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-53900-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer completed after 489.68s with status: succeeded
Stopping job with name chaiml-95p-5ff-chaiml-m-53900-v1-mkmlizer
Pipeline stage MKMLizer completed in 491.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-95p-5ff-chaiml-m-53900-v1
Waiting for inference service chaiml-95p-5ff-chaiml-m-53900-v1 to be ready
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:25, 1.36it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:25, 1.36it/s]
Loading 0:   1%|          | 4.00/363 [00:04<07:11, 1.20s/it]
Loading 0:   1%|          | 4.00/363 [00:04<07:11, 1.20s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<09:14, 1.55s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<09:14, 1.55s/it]
Loading 0:   3%|▎         | 11.0/363 [00:07<03:14, 1.81it/s]
Loading 0:   3%|▎         | 11.0/363 [00:07<03:14, 1.81it/s]
Loading 0:   4%|▎         | 13.0/363 [00:10<04:12, 1.39it/s]
Loading 0:   4%|▎         | 13.0/363 [00:10<04:12, 1.39it/s]
Loading 0:   4%|▍         | 14.0/363 [00:12<05:30, 1.06it/s]
Loading 0:   4%|▍         | 14.0/363 [00:12<05:30, 1.06it/s]
Loading 0:   4%|▍         | 15.0/363 [00:14<06:53, 1.19s/it]
Loading 0:   4%|▍         | 15.0/363 [00:14<06:53, 1.19s/it]
Loading 0:   6%|▌         | 21.0/363 [00:17<04:11, 1.36it/s]
Loading 0:   6%|▌         | 21.0/363 [00:17<04:11, 1.36it/s]
Loading 0:   6%|▌         | 22.0/363 [00:19<05:11, 1.09it/s]
Loading 0:   6%|▌         | 22.0/363 [00:19<05:11, 1.09it/s]
Loading 0:   6%|▋         | 23.0/363 [00:21<06:23, 1.13s/it]
Loading 0:   6%|▋         | 23.0/363 [00:21<06:23, 1.13s/it]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:59, 1.85it/s]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:59, 1.85it/s]
Loading 0:   9%|▉         | 34.0/363 [00:25<03:15, 1.69it/s]
Loading 0:   9%|▉         | 34.0/363 [00:25<03:15, 1.69it/s]
Loading 0:  10%|▉         | 35.0/363 [00:27<04:08, 1.32it/s]
Loading 0:  10%|▉         | 35.0/363 [00:27<04:08, 1.32it/s]
Loading 0:  10%|▉         | 36.0/363 [00:30<05:14, 1.04it/s]
Loading 0:  10%|▉         | 36.0/363 [00:30<05:14, 1.04it/s]
Loading 0:  11%|█         | 39.0/363 [00:32<04:43, 1.14it/s]
Loading 0:  11%|█         | 39.0/363 [00:32<04:43, 1.14it/s]
Loading 0:  11%|█         | 40.0/363 [00:34<05:43, 1.06s/it]
Loading 0:  11%|█         | 40.0/363 [00:34<05:43, 1.06s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:36<06:51, 1.28s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:36<06:51, 1.28s/it]
Loading 0:  13%|█▎        | 48.0/363 [00:37<02:58, 1.76it/s]
Loading 0:  13%|█▎        | 48.0/363 [00:37<02:58, 1.76it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:40<03:09, 1.64it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:40<03:09, 1.64it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:42<04:01, 1.28it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:42<04:01, 1.28it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:45<05:04, 1.02it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:45<05:04, 1.02it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:47<04:33, 1.12it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:47<04:33, 1.12it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:49<05:29, 1.08s/it]
Loading 0:  16%|█▌        | 58.0/363 [00:49<05:29, 1.08s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:51<06:33, 1.29s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:51<06:33, 1.29s/it]
Loading 0:  18%|█▊        | 66.0/363 [00:52<02:50, 1.74it/s]
Loading 0:  18%|█▊        | 66.0/363 [00:52<02:50, 1.74it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:55<03:00, 1.62it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:55<03:00, 1.62it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:57<03:48, 1.28it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:57<03:48, 1.28it/s]
Loading 0:  20%|█▉        | 72.0/363 [01:00<04:47, 1.01it/s]
Loading 0:  20%|█▉        | 72.0/363 [01:00<04:47, 1.01it/s]
Loading 0:  21%|██        | 75.0/363 [01:02<04:16, 1.12it/s]
Loading 0:  21%|██        | 75.0/363 [01:02<04:16, 1.12it/s]
Loading 0:  21%|██        | 76.0/363 [01:04<05:15, 1.10s/it]
Loading 0:  21%|██        | 76.0/363 [01:04<05:15, 1.10s/it]
Loading 0:  21%|██        | 77.0/363 [01:06<06:13, 1.30s/it]
Loading 0:  21%|██        | 77.0/363 [01:06<06:13, 1.30s/it]
Loading 0:  23%|██▎       | 84.0/363 [01:08<02:41, 1.73it/s]
Loading 0:  23%|██▎       | 84.0/363 [01:08<02:41, 1.73it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:10<02:50, 1.62it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:10<02:50, 1.62it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:12<03:35, 1.27it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:12<03:35, 1.27it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:15<04:30, 1.01it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:15<04:30, 1.01it/s]
Loading 0:  27%|██▋       | 97.0/363 [01:16<02:16, 1.95it/s]
Loading 0:  27%|██▋       | 97.0/363 [01:16<02:16, 1.95it/s]
Loading 0:  28%|██▊       | 101/363 [01:18<02:26, 1.79it/s] 
Loading 0:  28%|██▊       | 101/363 [01:18<02:26, 1.79it/s]
Loading 0:  28%|██▊       | 102/363 [01:21<03:08, 1.38it/s]
Loading 0:  28%|██▊       | 102/363 [01:21<03:08, 1.38it/s]
Loading 0:  28%|██▊       | 103/363 [01:23<03:59, 1.08it/s]
Loading 0:  28%|██▊       | 103/363 [01:23<03:59, 1.08it/s]
Loading 0:  29%|██▉       | 106/363 [01:25<03:43, 1.15it/s]
Loading 0:  29%|██▉       | 106/363 [01:25<03:43, 1.15it/s]
Loading 0:  29%|██▉       | 107/363 [01:27<04:30, 1.06s/it]
Loading 0:  29%|██▉       | 107/363 [01:27<04:30, 1.06s/it]
Loading 0:  30%|██▉       | 108/363 [01:30<05:23, 1.27s/it]
Loading 0:  30%|██▉       | 108/363 [01:30<05:23, 1.27s/it]
Loading 0:  31%|███       | 111/363 [01:32<04:21, 1.04s/it]
Loading 0:  31%|███       | 111/363 [01:32<04:21, 1.04s/it]
Loading 0:  31%|███       | 112/363 [01:34<05:08, 1.23s/it]
Loading 0:  31%|███       | 112/363 [01:34<05:08, 1.23s/it]
Loading 0:  31%|███       | 113/363 [01:36<05:59, 1.44s/it]
Loading 0:  31%|███       | 113/363 [01:36<05:59, 1.44s/it]
Loading 0:  33%|███▎      | 120/363 [01:37<02:23, 1.69it/s]
Loading 0:  33%|███▎      | 120/363 [01:37<02:23, 1.69it/s]
Loading 0:  34%|███▍      | 124/363 [01:40<02:30, 1.59it/s]
Loading 0:  34%|███▍      | 124/363 [01:40<02:30, 1.59it/s]
Loading 0:  34%|███▍      | 125/363 [01:42<03:10, 1.25it/s]
Loading 0:  34%|███▍      | 125/363 [01:42<03:10, 1.25it/s]
Loading 0:  35%|███▍      | 126/363 [01:45<03:58, 1.01s/it]
Loading 0:  35%|███▍      | 126/363 [01:45<03:58, 1.01s/it]
Loading 0:  36%|███▌      | 129/363 [01:47<03:31, 1.11it/s]
Loading 0:  36%|███▌      | 129/363 [01:47<03:31, 1.11it/s]
Loading 0:  36%|███▌      | 130/363 [01:49<04:14, 1.09s/it]
Loading 0:  36%|███▌      | 130/363 [01:49<04:14, 1.09s/it]
Loading 0:  36%|███▌      | 131/363 [01:51<05:03, 1.31s/it]
Loading 0:  36%|███▌      | 131/363 [01:51<05:03, 1.31s/it]
Loading 0:  38%|███▊      | 138/363 [01:53<02:09, 1.74it/s]
Loading 0:  38%|███▊      | 138/363 [01:53<02:09, 1.74it/s]
Loading 0:  39%|███▉      | 142/363 [01:55<02:16, 1.62it/s]
Loading 0:  39%|███▉      | 142/363 [01:55<02:16, 1.62it/s]
Loading 0:  39%|███▉      | 143/363 [01:58<02:52, 1.27it/s]
Loading 0:  39%|███▉      | 143/363 [01:58<02:52, 1.27it/s]
Loading 0:  40%|███▉      | 144/363 [02:00<03:38, 1.00it/s]
Loading 0:  40%|███▉      | 144/363 [02:00<03:38, 1.00it/s]
Loading 0:  40%|████      | 147/363 [02:02<03:16, 1.10it/s]
Loading 0:  40%|████      | 147/363 [02:02<03:16, 1.10it/s]
Loading 0:  41%|████      | 148/363 [02:04<03:55, 1.09s/it]
Loading 0:  41%|████      | 148/363 [02:04<03:55, 1.09s/it]
Loading 0:  41%|████      | 149/363 [02:07<04:38, 1.30s/it]
Loading 0:  41%|████      | 149/363 [02:07<04:38, 1.30s/it]
Loading 0:  43%|████▎     | 156/363 [02:08<01:59, 1.73it/s]
Loading 0:  43%|████▎     | 156/363 [02:08<01:59, 1.73it/s]
Loading 0:  44%|████▍     | 160/363 [02:10<02:05, 1.62it/s]
Loading 0:  44%|████▍     | 160/363 [02:11<02:05, 1.62it/s]
Loading 0:  44%|████▍     | 161/363 [02:13<02:38, 1.27it/s]
Loading 0:  44%|████▍     | 161/363 [02:13<02:38, 1.27it/s]
Loading 0:  45%|████▍     | 162/363 [02:15<03:18, 1.01it/s]
Loading 0:  45%|████▍     | 162/363 [02:15<03:18, 1.01it/s]
Loading 0:  45%|████▌     | 165/363 [02:17<02:58, 1.11it/s]
Loading 0:  45%|████▌     | 165/363 [02:17<02:58, 1.11it/s]
Loading 0:  46%|████▌     | 166/363 [02:19<03:34, 1.09s/it]
Loading 0:  46%|████▌     | 166/363 [02:19<03:34, 1.09s/it]
Loading 0:  46%|████▌     | 167/363 [02:22<04:15, 1.30s/it]
Loading 0:  46%|████▌     | 167/363 [02:22<04:15, 1.30s/it]
Loading 0:  48%|████▊     | 174/363 [02:23<01:49, 1.73it/s]
Loading 0:  48%|████▊     | 174/363 [02:23<01:49, 1.73it/s]
Loading 0:  49%|████▉     | 178/363 [02:26<01:54, 1.62it/s]
Loading 0:  49%|████▉     | 178/363 [02:26<01:54, 1.62it/s]
Loading 0:  49%|████▉     | 179/363 [02:28<02:24, 1.27it/s]
Loading 0:  49%|████▉     | 179/363 [02:28<02:24, 1.27it/s]
Loading 0:  50%|████▉     | 180/363 [02:30<03:07, 1.02s/it]
Loading 0:  50%|████▉     | 180/363 [02:30<03:07, 1.02s/it]
Loading 0:  50%|█████     | 183/363 [02:33<02:44, 1.09it/s]
Loading 0:  50%|█████     | 183/363 [02:33<02:44, 1.09it/s]
Loading 0:  51%|█████     | 184/363 [02:35<03:17, 1.10s/it]
Loading 0:  51%|█████     | 184/363 [02:35<03:17, 1.10s/it]
Loading 0:  51%|█████     | 185/363 [02:37<03:53, 1.31s/it]
Loading 0:  51%|█████     | 185/363 [02:37<03:53, 1.31s/it]
Loading 0:  53%|█████▎    | 192/363 [02:38<01:39, 1.72it/s]
Loading 0:  53%|█████▎    | 192/363 [02:38<01:39, 1.72it/s]
Loading 0:  54%|█████▍    | 196/363 [02:41<01:43, 1.61it/s]
Loading 0:  54%|█████▍    | 196/363 [02:41<01:43, 1.61it/s]
Loading 0:  54%|█████▍    | 197/363 [02:43<02:11, 1.27it/s]
Loading 0:  54%|█████▍    | 197/363 [02:43<02:11, 1.27it/s]
Loading 0:  55%|█████▍    | 198/363 [02:45<02:43, 1.01it/s]
Loading 0:  55%|█████▍    | 198/363 [02:45<02:43, 1.01it/s]
Loading 0:  55%|█████▌    | 201/363 [02:48<02:25, 1.12it/s]
Loading 0:  55%|█████▌    | 201/363 [02:48<02:25, 1.12it/s]
Loading 0:  56%|█████▌    | 202/363 [02:50<02:54, 1.08s/it]
Loading 0:  56%|█████▌    | 202/363 [02:50<02:54, 1.08s/it]
Loading 0:  56%|█████▌    | 203/363 [02:52<03:27, 1.29s/it]
Loading 0:  56%|█████▌    | 203/363 [02:52<03:27, 1.29s/it]
Loading 0:  58%|█████▊    | 210/363 [02:53<01:27, 1.74it/s]
Loading 0:  58%|█████▊    | 210/363 [02:53<01:27, 1.74it/s]
Loading 0:  59%|█████▉    | 214/363 [02:56<01:31, 1.62it/s]
Loading 0:  59%|█████▉    | 214/363 [02:56<01:31, 1.62it/s]
Loading 0:  59%|█████▉    | 215/363 [02:58<01:56, 1.27it/s]
Loading 0:  59%|█████▉    | 215/363 [02:58<01:56, 1.27it/s]
Loading 0:  60%|█████▉    | 216/363 [03:01<02:33, 1.05s/it]
Loading 0:  60%|█████▉    | 216/363 [03:01<02:33, 1.05s/it]
Loading 0:  60%|██████    | 219/363 [03:03<02:15, 1.06it/s]
Loading 0:  60%|██████    | 219/363 [03:03<02:15, 1.06it/s]
Loading 0:  61%|██████    | 220/363 [03:05<02:40, 1.12s/it]
Loading 0:  61%|██████    | 220/363 [03:05<02:40, 1.12s/it]
Loading 0:  61%|██████    | 221/363 [03:08<03:08, 1.33s/it]
Loading 0:  61%|██████    | 221/363 [03:08<03:08, 1.33s/it]
Loading 0:  63%|██████▎   | 228/363 [03:09<01:19, 1.70it/s]
Loading 0:  63%|██████▎   | 228/363 [03:09<01:19, 1.70it/s]
Loading 0:  64%|██████▍   | 232/363 [03:12<01:22, 1.59it/s]
Loading 0:  64%|██████▍   | 232/363 [03:12<01:22, 1.59it/s]
Loading 0:  64%|██████▍   | 233/363 [03:14<01:43, 1.26it/s]
Loading 0:  64%|██████▍   | 233/363 [03:14<01:43, 1.26it/s]
Loading 0:  64%|██████▍   | 234/363 [03:16<02:08, 1.00it/s]
Loading 0:  64%|██████▍   | 234/363 [03:16<02:08, 1.00it/s]
Loading 0:  65%|██████▌   | 237/363 [03:18<01:53, 1.11it/s]
Loading 0:  65%|██████▌   | 237/363 [03:18<01:53, 1.11it/s]
Loading 0:  66%|██████▌   | 238/363 [03:20<02:16, 1.09s/it]
Loading 0:  66%|██████▌   | 238/363 [03:20<02:16, 1.09s/it]
Loading 0:  66%|██████▌   | 239/363 [03:23<02:42, 1.31s/it]
Loading 0:  66%|██████▌   | 239/363 [03:23<02:42, 1.31s/it]
Loading 0:  68%|██████▊   | 246/363 [03:24<01:07, 1.72it/s]
Loading 0:  68%|██████▊   | 246/363 [03:24<01:07, 1.72it/s]
Loading 0:  69%|██████▉   | 250/363 [03:27<01:10, 1.61it/s]
Loading 0:  69%|██████▉   | 250/363 [03:27<01:10, 1.61it/s]
Loading 0:  69%|██████▉   | 251/363 [03:29<01:28, 1.26it/s]
Loading 0:  69%|██████▉   | 251/363 [03:29<01:28, 1.26it/s]
Loading 0:  69%|██████▉   | 252/363 [03:31<01:50, 1.01it/s]
Loading 0:  69%|██████▉   | 252/363 [03:31<01:50, 1.01it/s]
Loading 0:  70%|███████   | 255/363 [03:33<01:36, 1.11it/s]
Loading 0:  70%|███████   | 255/363 [03:33<01:36, 1.11it/s]
Loading 0:  71%|███████   | 256/363 [03:36<01:56, 1.09s/it]
Loading 0:  71%|███████   | 256/363 [03:36<01:56, 1.09s/it]
Loading 0:  71%|███████   | 257/363 [03:38<02:18, 1.31s/it]
Loading 0:  71%|███████   | 257/363 [03:38<02:18, 1.31s/it]
Loading 0:  73%|███████▎  | 264/363 [03:39<00:57, 1.72it/s]
Loading 0:  73%|███████▎  | 264/363 [03:39<00:57, 1.72it/s]
Loading 0:  74%|███████▍  | 268/363 [03:42<00:59, 1.60it/s]
Loading 0:  74%|███████▍  | 268/363 [03:42<00:59, 1.60it/s]
Loading 0:  74%|███████▍  | 269/363 [03:44<01:14, 1.26it/s]
Loading 0:  74%|███████▍  | 269/363 [03:44<01:14, 1.26it/s]
Loading 0:  74%|███████▍  | 270/363 [03:46<01:33, 1.00s/it]
Loading 0:  74%|███████▍  | 270/363 [03:46<01:33, 1.00s/it]
Loading 0:  75%|███████▌  | 273/363 [04:03<03:57, 2.64s/it]
Loading 0:  75%|███████▌  | 273/363 [04:03<03:57, 2.64s/it]
Loading 0:  75%|███████▌  | 274/363 [04:05<03:48, 2.57s/it]
Loading 0:  75%|███████▌  | 274/363 [04:05<03:48, 2.57s/it]
Loading 0:  76%|███████▌  | 275/363 [04:07<03:42, 2.53s/it]
Loading 0:  76%|███████▌  | 275/363 [04:07<03:42, 2.53s/it]
Loading 0:  78%|███████▊  | 282/363 [04:08<01:22, 1.02s/it]
Loading 0:  78%|███████▊  | 282/363 [04:08<01:22, 1.02s/it]
Loading 0:  79%|███████▉  | 286/363 [04:11<01:09, 1.10it/s]
Loading 0:  79%|███████▉  | 286/363 [04:11<01:09, 1.10it/s]
Loading 0:  79%|███████▉  | 287/363 [04:13<01:19, 1.05s/it]
Loading 0:  79%|███████▉  | 287/363 [04:13<01:19, 1.05s/it]
Loading 0:  79%|███████▉  | 288/363 [04:16<01:31, 1.21s/it]
Loading 0:  79%|███████▉  | 288/363 [04:16<01:31, 1.21s/it]
Loading 0:  80%|████████  | 291/363 [04:18<01:14, 1.04s/it]
Loading 0:  80%|████████  | 291/363 [04:18<01:14, 1.04s/it]
Loading 0:  80%|████████  | 292/363 [04:20<01:25, 1.21s/it]
Loading 0:  80%|████████  | 292/363 [04:20<01:25, 1.21s/it]
Loading 0:  81%|████████  | 293/363 [04:22<01:37, 1.40s/it]
Loading 0:  81%|████████  | 293/363 [04:22<01:37, 1.40s/it]
Loading 0:  83%|████████▎ | 300/363 [04:23<00:38, 1.66it/s]
Loading 0:  83%|████████▎ | 300/363 [04:23<00:38, 1.66it/s]
Loading 0:  84%|████████▎ | 304/363 [04:26<00:37, 1.58it/s]
Loading 0:  84%|████████▎ | 304/363 [04:26<00:37, 1.58it/s]
Loading 0:  84%|████████▍ | 305/363 [04:28<00:46, 1.25it/s]
Loading 0:  84%|████████▍ | 305/363 [04:28<00:46, 1.25it/s]
Loading 0:  84%|████████▍ | 306/363 [04:31<00:57, 1.00s/it]
Loading 0:  84%|████████▍ | 306/363 [04:31<00:57, 1.00s/it]
Loading 0:  85%|████████▌ | 309/363 [04:33<00:48, 1.11it/s]
Loading 0:  85%|████████▌ | 309/363 [04:33<00:48, 1.11it/s]
Loading 0:  85%|████████▌ | 310/363 [04:35<00:57, 1.09s/it]
Loading 0:  85%|████████▌ | 310/363 [04:35<00:57, 1.09s/it]
Loading 0:  86%|████████▌ | 311/363 [04:37<01:07, 1.31s/it]
Loading 0:  86%|████████▌ | 311/363 [04:37<01:07, 1.31s/it]
Loading 0:  88%|████████▊ | 318/363 [04:38<00:25, 1.75it/s]
Loading 0:  88%|████████▊ | 318/363 [04:38<00:25, 1.75it/s]
Loading 0:  89%|████████▊ | 322/363 [04:41<00:25, 1.63it/s]
Loading 0:  89%|████████▊ | 322/363 [04:41<00:25, 1.63it/s]
Loading 0:  89%|████████▉ | 323/363 [04:43<00:31, 1.28it/s]
Loading 0:  89%|████████▉ | 323/363 [04:43<00:31, 1.28it/s]
Loading 0:  89%|████████▉ | 324/363 [04:46<00:38, 1.01it/s]
Loading 0:  89%|████████▉ | 324/363 [04:46<00:38, 1.01it/s]
Loading 0:  90%|█████████ | 327/363 [04:48<00:32, 1.12it/s]
Loading 0:  90%|█████████ | 327/363 [04:48<00:32, 1.12it/s]
Loading 0:  90%|█████████ | 328/363 [04:50<00:37, 1.08s/it]
Loading 0:  90%|█████████ | 328/363 [04:50<00:37, 1.08s/it]
Loading 0:  91%|█████████ | 329/363 [04:52<00:44, 1.30s/it]
Loading 0:  91%|█████████ | 329/363 [04:52<00:44, 1.30s/it]
Loading 0:  93%|█████████▎| 336/363 [04:53<00:15, 1.75it/s]
Loading 0:  93%|█████████▎| 336/363 [04:53<00:15, 1.75it/s]
Loading 0:  94%|█████████▎| 340/363 [04:56<00:14, 1.63it/s]
Loading 0:  94%|█████████▎| 340/363 [04:56<00:14, 1.63it/s]
Loading 0:  94%|█████████▍| 341/363 [04:58<00:17, 1.28it/s]
Loading 0:  94%|█████████▍| 341/363 [04:58<00:17, 1.28it/s]
Loading 0:  94%|█████████▍| 342/363 [05:01<00:20, 1.00it/s]
Loading 0:  94%|█████████▍| 342/363 [05:01<00:20, 1.00it/s]
Loading 0:  95%|█████████▌| 345/363 [05:03<00:16, 1.11it/s]
Loading 0:  95%|█████████▌| 345/363 [05:03<00:16, 1.11it/s]
Loading 0:  95%|█████████▌| 346/363 [05:05<00:18, 1.09s/it]
Loading 0:  95%|█████████▌| 346/363 [05:05<00:18, 1.09s/it]
Loading 0:  96%|█████████▌| 347/363 [05:07<00:20, 1.30s/it]
Loading 0:  96%|█████████▌| 347/363 [05:07<00:20, 1.30s/it]
Loading 0:  98%|█████████▊| 354/363 [05:09<00:05, 1.74it/s]
Loading 0:  98%|█████████▊| 354/363 [05:09<00:05, 1.74it/s]
Loading 0:  99%|█████████▉| 359/363 [05:12<00:02, 1.66it/s]
Loading 0:  99%|█████████▉| 359/363 [05:12<00:02, 1.66it/s]
Loading 0:  99%|█████████▉| 360/363 [05:14<00:02, 1.32it/s]
Loading 0:  99%|█████████▉| 360/363 [05:14<00:02, 1.32it/s]
Loading 0:  99%|█████████▉| 361/363 [05:16<00:01, 1.05it/s]
Loading 0:  99%|█████████▉| 361/363 [05:16<00:01, 1.05it/s]
Loading 0: 100%|██████████| 363/363 [05:16<00:00, 1.05it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [05:16<00:00, 1.15it/s]
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpdixl2mia' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: quantized model in 324.050s
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Processed model ChaiML/95p_5ff_chaiml_mistral_24b_2048_chosen_paras_cp624_merged in 409.257s
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia/config.json
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia/special_tokens_map.json
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia/tokenizer_config.json
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia/tokenizer.json
Inference service chaiml-95p-5ff-chaiml-m-53900-v1 ready after 162.51623249053955s
Pipeline stage MKMLDeployer completed in 164.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4881060123443604s
Received healthy response to inference request in 2.8335940837860107s
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia/flywheel_model.1.safetensors
Received healthy response to inference request in 3.4357409477233887s
Received healthy response to inference request in 2.8781025409698486s
Received healthy response to inference request in 2.772921085357666s
5 requests
0 failed requests
5th percentile: 2.785055685043335
10th percentile: 2.797190284729004
20th percentile: 2.821459484100342
30th percentile: 2.8424957752227784
40th percentile: 2.8602991580963133
50th percentile: 2.8781025409698486
60th percentile: 3.1011579036712646
70th percentile: 3.3242132663726807
80th percentile: 3.446213960647583
90th percentile: 3.4671599864959717
95th percentile: 3.477632999420166
99th percentile: 3.4860114097595214
mean time: 3.081692934036255
Pipeline stage StressChecker completed in 22.58s
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 2.01s
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 1.85s
Shutdown handler de-registered
chaiml-95p-5ff-chaiml-m_53900_v1 status is now deployed due to DeploymentManager action
chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-95p-5ff-chaiml-m-54615-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer completed after 512.93s with status: succeeded
Stopping job with name chaiml-95p-5ff-chaiml-m-54615-v1-mkmlizer
Pipeline stage MKMLizer completed in 699.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.27s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-95p-5ff-chaiml-m-54615-v1
Waiting for inference service chaiml-95p-5ff-chaiml-m-54615-v1 to be ready
Inference service chaiml-95p-5ff-chaiml-m-54615-v1 ready after 152.32705855369568s
Pipeline stage MKMLDeployer completed in 153.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1804723739624023s
Received healthy response to inference request in 2.6748526096343994s
Received healthy response to inference request in 3.021786689758301s
Received healthy response to inference request in 3.5291008949279785s
Received healthy response to inference request in 3.1004841327667236s
5 requests
0 failed requests
5th percentile: 2.7442394256591798
10th percentile: 2.81362624168396
20th percentile: 2.9523998737335204
30th percentile: 3.037526178359985
40th percentile: 3.0690051555633544
50th percentile: 3.1004841327667236
60th percentile: 3.132479429244995
70th percentile: 3.1644747257232666
80th percentile: 3.2501980781555178
90th percentile: 3.389649486541748
95th percentile: 3.459375190734863
99th percentile: 3.5151557540893554
mean time: 3.101339340209961
Pipeline stage StressChecker completed in 18.68s
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 1.29s
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 1.29s
Shutdown handler de-registered
chaiml-95p-5ff-chaiml-m_54615_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2829.44s
Shutdown handler de-registered
chaiml-95p-5ff-chaiml-m_54615_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-95p-5ff-chaiml-m_54615_v1 status is now torndown due to DeploymentManager action