wespro-psykidelicllama3

submission_id: wespro-psykidelicllama3_v1

developer_uid: WesPro

best_of: 4

celo_rating: 1164.15

display_name: wespro-psykidelicllama3_v1

family_friendly_score: 0.0

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}

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': 512, 'best_of': 4, 'max_output_tokens': 64}

is_internal_developer: False

language_model: WesPro/PsykidelicLlama3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: WesPro/PsykidelicLlama3

model_name: wespro-psykidelicllama3_v1

model_num_parameters: 8030261248.0

model_repo: WesPro/PsykidelicLlama3

model_size: 8B

num_battles: 21862

num_wins: 10452

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: 2024-06-05T16:56:12+00:00

us_pacific_date: 2024-06-05

win_ratio: 0.4780898362455402

Resubmit model

Running pipeline stage MKMLizer
Starting job with name wespro-psykidelicllama3-v1-mkmlizer
Waiting for job on wespro-psykidelicllama3-v1-mkmlizer to finish
Stopping job with name wespro-psykidelicllama3-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name wespro-psykidelicllama3-v1-mkmlizer
Waiting for job on wespro-psykidelicllama3-v1-mkmlizer to finish
wespro-psykidelicllama3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-psykidelicllama3-v1-mkmlizer: ║     _____            __           __                                ║
wespro-psykidelicllama3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-psykidelicllama3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-psykidelicllama3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-psykidelicllama3-v1-mkmlizer: ║       /___/                                                         ║
wespro-psykidelicllama3-v1-mkmlizer: ║                                                                     ║
wespro-psykidelicllama3-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-psykidelicllama3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-psykidelicllama3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-psykidelicllama3-v1-mkmlizer: ║                                                                     ║
wespro-psykidelicllama3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-psykidelicllama3-v1-mkmlizer: ║  belonging to:                                                      ║
wespro-psykidelicllama3-v1-mkmlizer: ║                                                                     ║
wespro-psykidelicllama3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-psykidelicllama3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-psykidelicllama3-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-psykidelicllama3-v1-mkmlizer: ║                                                                     ║
wespro-psykidelicllama3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-psykidelicllama3-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
wespro-psykidelicllama3-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-psykidelicllama3-v1-mkmlizer: Downloaded to shared memory in 28.580s
wespro-psykidelicllama3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-psykidelicllama3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-psykidelicllama3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 116.54it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:01, 135.00it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:02, 118.44it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:01, 129.27it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:01, 127.70it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:01, 126.93it/s]
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 134.27it/s]
Loading 0:  41%|████      | 119/291 [00:00<00:01, 139.65it/s]
Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 143.30it/s]
Loading 0:  53%|█████▎    | 154/291 [00:01<00:00, 148.56it/s]
Loading 0:  59%|█████▉    | 172/291 [00:01<00:00, 151.93it/s]
Loading 0:  65%|██████▍   | 188/291 [00:07<00:11,  8.93it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:07<00:07, 11.86it/s]
Loading 0:  76%|███████▌  | 220/291 [00:07<00:04, 17.03it/s]
Loading 0:  80%|████████  | 233/291 [00:07<00:02, 21.77it/s]
Loading 0:  85%|████████▌ | 248/291 [00:07<00:01, 28.91it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 39.42it/s]
Loading 0:  97%|█████████▋| 283/291 [00:07<00:00, 52.30it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-psykidelicllama3-v1-mkmlizer: quantized model in 22.490s
wespro-psykidelicllama3-v1-mkmlizer: Processed model WesPro/PsykidelicLlama3 in 52.319s
wespro-psykidelicllama3-v1-mkmlizer: creating bucket guanaco-mkml-models
wespro-psykidelicllama3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-psykidelicllama3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-psykidelicllama3-v1
wespro-psykidelicllama3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-psykidelicllama3-v1/config.json
wespro-psykidelicllama3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-psykidelicllama3-v1/tokenizer_config.json
wespro-psykidelicllama3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-psykidelicllama3-v1/special_tokens_map.json
wespro-psykidelicllama3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-psykidelicllama3-v1/tokenizer.json
wespro-psykidelicllama3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-psykidelicllama3-v1/flywheel_model.0.safetensors
wespro-psykidelicllama3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-psykidelicllama3-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
wespro-psykidelicllama3-v1-mkmlizer:   warnings.warn(
wespro-psykidelicllama3-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
wespro-psykidelicllama3-v1-mkmlizer:   warnings.warn(
wespro-psykidelicllama3-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.
wespro-psykidelicllama3-v1-mkmlizer:   warnings.warn(
wespro-psykidelicllama3-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()
wespro-psykidelicllama3-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-psykidelicllama3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-psykidelicllama3-v1-mkmlizer: Saving duration: 0.301s
wespro-psykidelicllama3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.304s
wespro-psykidelicllama3-v1-mkmlizer: creating bucket guanaco-reward-models
wespro-psykidelicllama3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-psykidelicllama3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/special_tokens_map.json
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/config.json
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/tokenizer_config.json
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/vocab.json
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/merges.txt
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/tokenizer.json
wespro-psykidelicllama3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-psykidelicllama3-v1_reward/reward.tensors
Job wespro-psykidelicllama3-v1-mkmlizer completed after 73.99s with status: succeeded
Stopping job with name wespro-psykidelicllama3-v1-mkmlizer
Pipeline stage MKMLizer completed in 79.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service wespro-psykidelicllama3-v1
Waiting for inference service wespro-psykidelicllama3-v1 to be ready
Inference service wespro-psykidelicllama3-v1 ready after 100.58827877044678s
Pipeline stage ISVCDeployer completed in 108.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0273489952087402s
Received healthy response to inference request in 1.1377522945404053s
Received healthy response to inference request in 1.1367356777191162s
Received healthy response to inference request in 1.1705775260925293s
Received healthy response to inference request in 1.132624626159668s
5 requests
0 failed requests
5th percentile: 1.1334468364715575
10th percentile: 1.1342690467834473
20th percentile: 1.1359134674072267
30th percentile: 1.136939001083374
40th percentile: 1.1373456478118897
50th percentile: 1.1377522945404053
60th percentile: 1.1508823871612548
70th percentile: 1.1640124797821045
80th percentile: 1.3419318199157717
90th percentile: 1.6846404075622559
95th percentile: 1.8559947013854978
99th percentile: 1.9930781364440917
mean time: 1.3210078239440919
Pipeline stage StressChecker completed in 7.21s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
wespro-psykidelicllama3_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
wespro-psykidelicllama3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-psykidelicllama3_v1
Running pipeline stage ISVCDeleter
Checking if service wespro-psykidelicllama3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.32s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-psykidelicllama3-v1/config.json from bucket guanaco-mkml-models
Deleting key wespro-psykidelicllama3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-psykidelicllama3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-psykidelicllama3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-psykidelicllama3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-psykidelicllama3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-psykidelicllama3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-psykidelicllama3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-psykidelicllama3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-psykidelicllama3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-psykidelicllama3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-psykidelicllama3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.10s
wespro-psykidelicllama3_v1 status is now torndown due to DeploymentManager action