submission_id: hastagaras-llama-3-8b-uhh_v4
developer_uid: Hastagaras
best_of: 16
celo_rating: 1195.45
display_name: debug
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this roleplay chat between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following {bot_name}'s persona: {memory}\n\n", 'prompt_template': 'Scenario: {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': 0.7, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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: Hastagaras/llama-3-8b-uhh
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-uh
model_name: debug
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-uhh
model_size: 8B
num_battles: 20279
num_wins: 11014
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: 2024-05-15T11:22:17+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5431234281769318
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-uhh-v4-mkmlizer
Waiting for job on hastagaras-llama-3-8b-uhh-v4-mkmlizer to finish
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-uhh-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-uhh-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-llama-3-8b-uhh-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Downloaded to shared memory in 14.273s
hastagaras-llama-3-8b-uhh-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-uhh-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 199.11it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:01, 183.98it/s]
Loading 0:  22%|██▏       | 64/291 [00:00<00:01, 203.48it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:02, 91.43it/s] 
Loading 0:  36%|███▌      | 104/291 [00:00<00:01, 109.70it/s]
Loading 0:  43%|████▎     | 125/291 [00:00<00:01, 131.21it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:00, 149.28it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 157.68it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 93.66it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 103.88it/s]
Loading 0:  78%|███████▊  | 226/291 [00:01<00:00, 127.98it/s]
Loading 0:  84%|████████▍ | 244/291 [00:01<00:00, 135.16it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 148.99it/s]
Loading 0:  97%|█████████▋| 282/291 [00:02<00:00, 155.47it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-uhh-v4-mkmlizer: quantized model in 17.473s
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Processed model Hastagaras/llama-3-8b-uhh in 32.826s
hastagaras-llama-3-8b-uhh-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-uhh-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v4
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v4/config.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v4/tokenizer_config.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v4/special_tokens_map.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v4/tokenizer.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v4/flywheel_model.0.safetensors
hastagaras-llama-3-8b-uhh-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-uhh-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-llama-3-8b-uhh-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-uhh-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-llama-3-8b-uhh-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-uhh-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-llama-3-8b-uhh-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-uhh-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-llama-3-8b-uhh-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Saving duration: 0.258s
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.301s
hastagaras-llama-3-8b-uhh-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-uhh-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-uhh-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/config.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/special_tokens_map.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/tokenizer_config.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/merges.txt
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/vocab.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/tokenizer.json
hastagaras-llama-3-8b-uhh-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v4_reward/reward.tensors
Job hastagaras-llama-3-8b-uhh-v4-mkmlizer completed after 185.0s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-uhh-v4-mkmlizer
Pipeline stage MKMLizer completed in 188.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-uhh-v4
Waiting for inference service hastagaras-llama-3-8b-uhh-v4 to be ready
Inference service hastagaras-llama-3-8b-uhh-v4 ready after 40.23680233955383s
Pipeline stage ISVCDeployer completed in 47.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9706838130950928s
Received healthy response to inference request in 1.2941324710845947s
Received healthy response to inference request in 1.285733699798584s
Received healthy response to inference request in 1.3433127403259277s
Received healthy response to inference request in 1.3195765018463135s
5 requests
0 failed requests
5th percentile: 1.2874134540557862
10th percentile: 1.2890932083129882
20th percentile: 1.2924527168273925
30th percentile: 1.2992212772369385
40th percentile: 1.309398889541626
50th percentile: 1.3195765018463135
60th percentile: 1.3290709972381591
70th percentile: 1.3385654926300048
80th percentile: 1.4687869548797607
90th percentile: 1.7197353839874268
95th percentile: 1.8452095985412598
99th percentile: 1.945588970184326
mean time: 1.4426878452301026
Pipeline stage StressChecker completed in 7.87s
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-llama-3-8b-uhh_v4 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-uhh_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-uhh_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-uhh-v4 is running
Tearing down inference service hastagaras-llama-3-8b-uhh-v4
Toredown service hastagaras-llama-3-8b-uhh-v4
Pipeline stage ISVCDeleter completed in 4.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-uhh-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.89s
hastagaras-llama-3-8b-uhh_v4 status is now torndown due to DeploymentManager action