developer_uid: Hastagaras
submission_id: hastagaras-esekembrew-ll_1360_v2
model_name: mweheh2
model_group: Hastagaras/esekembrew-ll
status: torndown
timestamp: 2024-05-17T08:32:46+00:00
num_battles: 13405
num_wins: 7190
celo_rating: 1202.09
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: mweheh2
is_internal_developer: False
language_model: Hastagaras/esekembrew-llama3-8b
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-17
win_ratio: 0.536367027228646
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 100, '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-v2-mkmlizer
Waiting for job on hastagaras-esekembrew-ll-1360-v2-mkmlizer to finish
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ║                                                                     ║
hastagaras-esekembrew-ll-1360-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-ll-1360-v2-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-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Downloaded to shared memory in 16.772s
hastagaras-esekembrew-ll-1360-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 178.13it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 195.05it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:01, 187.56it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 93.91it/s] 
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 111.93it/s]
Loading 0:  42%|████▏     | 122/291 [00:00<00:01, 128.51it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:00, 149.26it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 163.68it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 100.98it/s]
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 111.26it/s]
Loading 0:  78%|███████▊  | 228/291 [00:01<00:00, 137.27it/s]
Loading 0:  85%|████████▌ | 248/291 [00:01<00:00, 149.23it/s]
Loading 0:  94%|█████████▍| 273/291 [00:01<00:00, 172.96it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-ll-1360-v2-mkmlizer: quantized model in 17.687s
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Processed model Hastagaras/esekembrew-llama3-8b in 35.502s
hastagaras-esekembrew-ll-1360-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-ll-1360-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v2
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v2/config.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v2/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v2/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v2/tokenizer.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v2/flywheel_model.0.safetensors
hastagaras-esekembrew-ll-1360-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-ll-1360-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-esekembrew-ll-1360-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-esekembrew-ll-1360-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-esekembrew-ll-1360-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Saving duration: 0.235s
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.141s
hastagaras-esekembrew-ll-1360-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-ll-1360-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-ll-1360-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/config.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/merges.txt
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/vocab.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/tokenizer.json
hastagaras-esekembrew-ll-1360-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v2_reward/reward.tensors
Job hastagaras-esekembrew-ll-1360-v2-mkmlizer completed after 63.3s with status: succeeded
Stopping job with name hastagaras-esekembrew-ll-1360-v2-mkmlizer
Pipeline stage MKMLizer completed in 65.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-ll-1360-v2
Waiting for inference service hastagaras-esekembrew-ll-1360-v2 to be ready
Inference service hastagaras-esekembrew-ll-1360-v2 ready after 40.24508333206177s
Pipeline stage ISVCDeployer completed in 47.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.106539249420166s
Received healthy response to inference request in 1.26373291015625s
Received healthy response to inference request in 1.2939717769622803s
Received healthy response to inference request in 1.2632908821105957s
Received healthy response to inference request in 1.2763361930847168s
5 requests
0 failed requests
5th percentile: 1.2633792877197265
10th percentile: 1.2634676933288573
20th percentile: 1.2636445045471192
30th percentile: 1.2662535667419434
40th percentile: 1.2712948799133301
50th percentile: 1.2763361930847168
60th percentile: 1.283390426635742
70th percentile: 1.2904446601867676
80th percentile: 1.4564852714538576
90th percentile: 1.7815122604370117
95th percentile: 1.9440257549285886
99th percentile: 2.0740365505218508
mean time: 1.4407742023468018
Pipeline stage StressChecker completed in 7.84s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-ll_1360_v2 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-ll_1360_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-esekembrew-ll_1360_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-esekembrew-ll-1360-v2 is running
Tearing down inference service hastagaras-esekembrew-ll-1360-v2
Toredown service hastagaras-esekembrew-ll-1360-v2
Pipeline stage ISVCDeleter completed in 4.67s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-ll-1360-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.07s
hastagaras-esekembrew-ll_1360_v2 status is now torndown due to DeploymentManager action