developer_uid: Hastagaras
submission_id: hastagaras-llama3-8b-uhh_v2
model_name: uhh-not-okay-2
model_group: Hastagaras/llama3-8b-uhh
status: torndown
timestamp: 2024-05-13T07:47:48+00:00
num_battles: 9020
num_wins: 4710
celo_rating: 1192.21
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama3-8b-uhh
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: uhh-not-okay-2
is_internal_developer: False
language_model: Hastagaras/llama3-8b-uhh
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-13
win_ratio: 0.5221729490022173
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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a fictional roleplay chat between {bot_name} and {user_name}. Description: {memory}\n", 'prompt_template': 'Example conversation:\n{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}
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-uhh-v2-mkmlizer
Waiting for job on hastagaras-llama3-8b-uhh-v2-mkmlizer to finish
hastagaras-llama3-8b-uhh-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-uhh-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-uhh-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-llama3-8b-uhh-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-uhh-v2-mkmlizer: Downloaded to shared memory in 15.372s
hastagaras-llama3-8b-uhh-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-uhh-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-uhh-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:01, 121.96it/s]
Loading 0:  83%|████████▎ | 242/291 [00:02<00:00, 120.66it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.35it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-uhh-v2-mkmlizer: quantized model in 17.922s
hastagaras-llama3-8b-uhh-v2-mkmlizer: Processed model Hastagaras/llama3-8b-uhh in 34.415s
hastagaras-llama3-8b-uhh-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-uhh-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-uhh-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-uhh-v2
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-uhh-v2/config.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-uhh-v2/special_tokens_map.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-uhh-v2/tokenizer_config.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-uhh-v2/tokenizer.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-uhh-v2/flywheel_model.0.safetensors
hastagaras-llama3-8b-uhh-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-uhh-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-llama3-8b-uhh-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-uhh-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-llama3-8b-uhh-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-uhh-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-llama3-8b-uhh-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-uhh-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-llama3-8b-uhh-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-uhh-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-uhh-v2-mkmlizer: Saving duration: 0.263s
hastagaras-llama3-8b-uhh-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.133s
hastagaras-llama3-8b-uhh-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-uhh-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-uhh-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/config.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/tokenizer_config.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/special_tokens_map.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/merges.txt
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/vocab.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/tokenizer.json
hastagaras-llama3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-uhh-v2_reward/reward.tensors
Job hastagaras-llama3-8b-uhh-v2-mkmlizer completed after 62.67s with status: succeeded
Stopping job with name hastagaras-llama3-8b-uhh-v2-mkmlizer
Pipeline stage MKMLizer completed in 65.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-uhh-v2
Waiting for inference service hastagaras-llama3-8b-uhh-v2 to be ready
Inference service hastagaras-llama3-8b-uhh-v2 ready after 40.210097789764404s
Pipeline stage ISVCDeployer completed in 47.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1680591106414795s
Received healthy response to inference request in 1.3174538612365723s
Received healthy response to inference request in 1.2795383930206299s
Received healthy response to inference request in 1.341428279876709s
Received healthy response to inference request in 1.4939947128295898s
5 requests
0 failed requests
5th percentile: 1.2871214866638183
10th percentile: 1.2947045803070067
20th percentile: 1.3098707675933838
30th percentile: 1.3222487449645997
40th percentile: 1.3318385124206542
50th percentile: 1.341428279876709
60th percentile: 1.4024548530578613
70th percentile: 1.4634814262390137
80th percentile: 1.6288075923919678
90th percentile: 1.8984333515167238
95th percentile: 2.0332462310791013
99th percentile: 2.141096534729004
mean time: 1.520094871520996
Pipeline stage StressChecker completed in 8.27s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
hastagaras-llama3-8b-uhh_v2 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-uhh_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-uhh_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-uhh-v2 is running
Tearing down inference service hastagaras-llama3-8b-meh-v2
Tearing down inference service hastagaras-llama3-8b-uhh-v2
Toredown service hastagaras-llama3-8b-uhh-v2
Pipeline stage ISVCDeleter completed in 4.52s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Toredown service hastagaras-llama3-8b-meh-v2
Deleting key hastagaras-llama3-8b-uhh-v2/config.json from bucket guanaco-mkml-models
Pipeline stage ISVCDeleter completed in 6.82s
Deleting key hastagaras-llama3-8b-uhh-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-uhh-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-uhh-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-uhh-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-uhh-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-uhh-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-uhh-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-uhh-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-uhh-v2_reward/tokenizer.json from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-uhh-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-uhh-v2_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v2_reward/merges.txt from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.05s
Deleting key hastagaras-llama3-8b-meh-v2_reward/reward.tensors from bucket guanaco-reward-models
hastagaras-llama3-8b-uhh_v2 status is now torndown due to DeploymentManager action
Deleting key hastagaras-llama3-8b-meh-v2_reward/special_tokens_map.json from bucket guanaco-reward-models