developer_uid: Hastagaras
submission_id: hastagaras-esekembrew-ll_1360_v4
model_name: mweheh4
model_group: Hastagaras/esekembrew-ll
status: torndown
timestamp: 2024-05-17T09:59:03+00:00
num_battles: 8104
num_wins: 4492
celo_rating: 1205.23
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/esekembrew-llama3-8b
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: mweheh4
is_internal_developer: False
language_model: Hastagaras/esekembrew-llama3-8b
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-17
win_ratio: 0.554294175715696
generation_params: {'temperature': 0.95, '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': 16, '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}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-ll-1360-v4-mkmlizer
Waiting for job on hastagaras-esekembrew-ll-1360-v4-mkmlizer to finish
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-ll-1360-v4-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.
hastagaras-esekembrew-ll-1360-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Downloaded to shared memory in 20.844s
hastagaras-esekembrew-ll-1360-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 126.55it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 149.77it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 149.79it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:01, 146.94it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:01, 147.39it/s]
Loading 0:  32%|███▏      | 92/291 [00:00<00:02, 73.98it/s] 
Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 81.78it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 100.23it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 114.52it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 125.58it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 130.68it/s]
Loading 0:  65%|██████▍   | 188/291 [00:01<00:01, 75.04it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:01<00:01, 85.63it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 101.35it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 114.90it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 126.21it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 135.41it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.67it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-ll-1360-v4-mkmlizer: quantized model in 18.714s
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Processed model Hastagaras/esekembrew-llama3-8b in 40.585s
hastagaras-esekembrew-ll-1360-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-ll-1360-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v4
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v4/config.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v4/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v4/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v4/tokenizer.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-ll-1360-v4-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.
hastagaras-esekembrew-ll-1360-v4-mkmlizer:   warnings.warn(
hastagaras-esekembrew-ll-1360-v4-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.
hastagaras-esekembrew-ll-1360-v4-mkmlizer:   warnings.warn(
hastagaras-esekembrew-ll-1360-v4-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.
hastagaras-esekembrew-ll-1360-v4-mkmlizer:   warnings.warn(
hastagaras-esekembrew-ll-1360-v4-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()
hastagaras-esekembrew-ll-1360-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Saving duration: 0.310s
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.369s
hastagaras-esekembrew-ll-1360-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-ll-1360-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-ll-1360-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward/config.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward/merges.txt
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward/vocab.json
hastagaras-esekembrew-ll-1360-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v4_reward/tokenizer.json
Job hastagaras-esekembrew-ll-1360-v4-mkmlizer completed after 74.23s with status: succeeded
Stopping job with name hastagaras-esekembrew-ll-1360-v4-mkmlizer
Pipeline stage MKMLizer completed in 76.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-ll-1360-v4
Waiting for inference service hastagaras-esekembrew-ll-1360-v4 to be ready
Inference service hastagaras-esekembrew-ll-1360-v4 ready after 40.40178418159485s
Pipeline stage ISVCDeployer completed in 47.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1487810611724854s
Received healthy response to inference request in 1.2925002574920654s
Received healthy response to inference request in 1.2745099067687988s
Received healthy response to inference request in 1.2894363403320312s
Received healthy response to inference request in 1.2661526203155518s
5 requests
0 failed requests
5th percentile: 1.267824077606201
10th percentile: 1.2694955348968506
20th percentile: 1.2728384494781495
30th percentile: 1.2774951934814454
40th percentile: 1.2834657669067382
50th percentile: 1.2894363403320312
60th percentile: 1.290661907196045
70th percentile: 1.2918874740600585
80th percentile: 1.4637564182281495
90th percentile: 1.8062687397003174
95th percentile: 1.9775249004364013
99th percentile: 2.1145298290252685
mean time: 1.4542760372161865
Pipeline stage StressChecker completed in 8.01s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-ll_1360_v4 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-ll_1360_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-esekembrew-ll_1360_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-esekembrew-ll-1360-v4 is running
Tearing down inference service hastagaras-esekembrew-ll-1360-v4
Toredown service hastagaras-esekembrew-ll-1360-v4
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-ll-1360-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.09s
hastagaras-esekembrew-ll_1360_v4 status is now torndown due to DeploymentManager action