abdulhanan2006-waifuai-l_9428

submission_id: abdulhanan2006-waifuai-l_9428_v1

developer_uid: Azazelle

best_of: 16

celo_rating: 1165.08

display_name: Abdulhanan2006-WaifuAI-8B-8k

family_friendly_score: 0.0

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: Abdulhanan2006/WaifuAI-L3-8B-8k

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Abdulhanan2006/WaifuAI-L

model_name: Abdulhanan2006-WaifuAI-8B-8k

model_num_parameters: 8030261248.0

model_repo: Abdulhanan2006/WaifuAI-L3-8B-8k

model_size: 8B

num_battles: 33303

num_wins: 15787

ranking_group: single

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-06T02:15:21+00:00

us_pacific_date: 2024-07-05

win_ratio: 0.47404137765366483

Resubmit model

Running pipeline stage MKMLizer
Starting job with name abdulhanan2006-waifuai-l-9428-v1-mkmlizer
Waiting for job on abdulhanan2006-waifuai-l-9428-v1-mkmlizer to finish
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║     _____            __           __                                ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║       /___/                                                         ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║                                                                     ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  https://mk1.ai                                                     ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║                                                                     ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  belonging to:                                                      ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║                                                                     ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  Chai Research Corp.                                                ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ║                                                                     ║
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Downloaded to shared memory in 90.482s
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: quantizing model to /dev/shm/model_cache
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:04<06:35,  1.37s/it]
Loading 0:   1%|▏         | 4/291 [00:08<10:35,  2.21s/it]
Loading 0:   2%|▏         | 5/291 [00:13<15:30,  3.25s/it]
Loading 0:   2%|▏         | 7/291 [00:13<08:22,  1.77s/it]
Loading 0:   3%|▎         | 8/291 [00:15<08:06,  1.72s/it]
Loading 0:   3%|▎         | 9/291 [00:17<08:13,  1.75s/it]
Loading 0:   3%|▎         | 10/291 [00:17<06:36,  1.41s/it]
Loading 0:   4%|▍         | 12/291 [00:22<08:51,  1.90s/it]
Loading 0:   4%|▍         | 13/291 [00:23<07:02,  1.52s/it]
Loading 0:   5%|▍         | 14/291 [00:23<05:33,  1.20s/it]
Loading 0:   6%|▌         | 17/291 [00:23<02:42,  1.69it/s]
Loading 0:   7%|▋         | 21/291 [00:23<01:32,  2.92it/s]
Loading 0:   8%|▊         | 23/291 [00:24<01:22,  3.23it/s]
Loading 0:   9%|▉         | 27/291 [00:24<00:51,  5.10it/s]
Loading 0:  10%|█         | 30/291 [00:24<00:40,  6.43it/s]
Loading 0:  11%|█         | 32/291 [00:25<00:45,  5.70it/s]
Loading 0:  12%|█▏        | 36/291 [00:25<00:30,  8.33it/s]
Loading 0:  13%|█▎        | 39/291 [00:25<00:27,  9.09it/s]
Loading 0:  14%|█▍        | 41/291 [00:26<00:35,  7.10it/s]
Loading 0:  15%|█▌        | 45/291 [00:26<00:24, 10.23it/s]
Loading 0:  16%|█▋        | 48/291 [00:26<00:20, 11.77it/s]
Loading 0:  17%|█▋        | 50/291 [00:26<00:18, 12.88it/s]
Loading 0:  23%|██▎       | 66/291 [00:26<00:06, 37.08it/s]
Loading 0:  26%|██▋       | 77/291 [00:26<00:04, 49.07it/s]
Loading 0:  29%|██▉       | 84/291 [00:26<00:05, 37.46it/s]
Loading 0:  33%|███▎      | 95/291 [00:27<00:03, 49.31it/s]
Loading 0:  38%|███▊      | 111/291 [00:27<00:02, 70.95it/s]
Loading 0:  42%|████▏     | 122/291 [00:27<00:02, 78.46it/s]
Loading 0:  47%|████▋     | 138/291 [00:27<00:01, 97.50it/s]
Loading 0:  52%|█████▏    | 150/291 [00:27<00:01, 100.74it/s]
Loading 0:  57%|█████▋    | 165/291 [00:27<00:01, 113.42it/s]
Loading 0:  62%|██████▏   | 179/291 [00:27<00:00, 119.42it/s]
Loading 0:  66%|██████▌   | 192/291 [00:28<00:01, 70.76it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:28<00:01, 76.80it/s]
Loading 0:  75%|███████▌  | 219/291 [00:28<00:00, 93.85it/s]
Loading 0:  79%|███████▉  | 231/291 [00:28<00:00, 97.51it/s]
Loading 0:  85%|████████▍ | 246/291 [00:28<00:00, 108.70it/s]
Loading 0:  89%|████████▉ | 259/291 [00:28<00:00, 111.33it/s]
Loading 0:  94%|█████████▍| 274/291 [00:28<00:00, 115.87it/s]
Loading 0:  99%|█████████▊| 287/291 [00:34<00:00,  7.35it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: quantized model in 69.715s
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Processed model Abdulhanan2006/WaifuAI-L3-8B-8k in 160.197s
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: creating bucket guanaco-mkml-models
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/abdulhanan2006-waifuai-l-9428-v1/flywheel_model.0.safetensors
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
abdulhanan2006-waifuai-l-9428-v1-mkmlizer:   warnings.warn(
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
abdulhanan2006-waifuai-l-9428-v1-mkmlizer:   warnings.warn(
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
abdulhanan2006-waifuai-l-9428-v1-mkmlizer:   warnings.warn(
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
abdulhanan2006-waifuai-l-9428-v1-mkmlizer:   warnings.warn(
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
abdulhanan2006-waifuai-l-9428-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Saving duration: 0.423s
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.969s
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: creating bucket guanaco-reward-models
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
abdulhanan2006-waifuai-l-9428-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/abdulhanan2006-waifuai-l-9428-v1_reward
Job abdulhanan2006-waifuai-l-9428-v1-mkmlizer completed after 201.43s with status: succeeded
Stopping job with name abdulhanan2006-waifuai-l-9428-v1-mkmlizer
Pipeline stage MKMLizer completed in 202.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service abdulhanan2006-waifuai-l-9428-v1
Waiting for inference service abdulhanan2006-waifuai-l-9428-v1 to be ready
Inference service abdulhanan2006-waifuai-l-9428-v1 ready after 40.23912048339844s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.054556131362915s
Received healthy response to inference request in 1.333791971206665s
Received healthy response to inference request in 1.3252944946289062s
Received healthy response to inference request in 1.3078396320343018s
Received healthy response to inference request in 1.3892993927001953s
5 requests
0 failed requests
5th percentile: 1.3113306045532227
10th percentile: 1.3148215770721436
20th percentile: 1.3218035221099853
30th percentile: 1.326993989944458
40th percentile: 1.3303929805755614
50th percentile: 1.333791971206665
60th percentile: 1.3559949398040771
70th percentile: 1.3781979084014893
80th percentile: 1.5223507404327394
90th percentile: 1.7884534358978272
95th percentile: 1.921504783630371
99th percentile: 2.027945861816406
mean time: 1.4821563243865967
Pipeline stage StressChecker completed in 8.12s
abdulhanan2006-waifuai-l_9428_v1 status is now deployed due to DeploymentManager action
abdulhanan2006-waifuai-l_9428_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of abdulhanan2006-waifuai-l_9428_v1
Running pipeline stage ISVCDeleter
Checking if service abdulhanan2006-waifuai-l-9428-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key abdulhanan2006-waifuai-l-9428-v1/config.json from bucket guanaco-mkml-models
Deleting key abdulhanan2006-waifuai-l-9428-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key abdulhanan2006-waifuai-l-9428-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key abdulhanan2006-waifuai-l-9428-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key abdulhanan2006-waifuai-l-9428-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/config.json from bucket guanaco-reward-models
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key abdulhanan2006-waifuai-l-9428-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.74s
abdulhanan2006-waifuai-l_9428_v1 status is now torndown due to DeploymentManager action