submission_id: hastagaras-llama-3-8b-cl_3476_v2
developer_uid: Hastagaras
best_of: 16
celo_rating: 1170.61
display_name: hastagaras-llama-3-8b-test
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this fictional roleplay between {bot_name} and {user_name}.\n\nPersona: {memory}<|eot_id|>", 'prompt_template': "<|start_header_id|>user<|end_header_id|>\n\nLet's begin.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {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': 0.85, 'top_p': 0.9, '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-ClauAS-Alpha
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Llama-3-8b-Cl
model_name: hastagaras-llama-3-8b-test
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Llama-3-8b-ClauAS-Alpha
model_size: 8B
num_battles: 140081
num_wins: 67316
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': 'Memory: {memory}\n\n', 'prompt_template': '{bot_name}: {prompt}\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: 2024-05-06T05:14:20+00:00
us_pacific_date: 2024-05-05
win_ratio: 0.4805505386169431
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-cl-3476-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-cl-3476-v2-mkmlizer to finish
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Downloaded to shared memory in 182.288s
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  38%|███▊      | 112/291 [00:00<00:01, 112.08it/s]
Loading 0:  79%|███████▉  | 231/291 [00:01<00:00, 116.15it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 28.18it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: quantized model in 22.923s
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Processed model Hastagaras/Llama-3-8b-ClauAS-Alpha in 207.844s
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v2
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v2/special_tokens_map.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v2/tokenizer_config.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v2/config.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v2/tokenizer.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Saving duration: 0.413s
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.560s
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward/config.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward/merges.txt
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward/vocab.json
hastagaras-llama-3-8b-cl-3476-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v2_reward/tokenizer.json
Job hastagaras-llama-3-8b-cl-3476-v2-mkmlizer completed after 237.79s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-cl-3476-v2-mkmlizer
Pipeline stage MKMLizer completed in 241.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-cl-3476-v2
Waiting for inference service hastagaras-llama-3-8b-cl-3476-v2 to be ready
Inference service hastagaras-llama-3-8b-cl-3476-v2 ready after 40.20943808555603s
Pipeline stage ISVCDeployer completed in 47.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.263490676879883s
Received healthy response to inference request in 1.2239816188812256s
Received healthy response to inference request in 1.292529821395874s
Received healthy response to inference request in 1.2935841083526611s
Received healthy response to inference request in 1.2552387714385986s
5 requests
0 failed requests
5th percentile: 1.2302330493927003
10th percentile: 1.2364844799041748
20th percentile: 1.248987340927124
30th percentile: 1.2626969814300537
40th percentile: 1.2776134014129639
50th percentile: 1.292529821395874
60th percentile: 1.2929515361785888
70th percentile: 1.2933732509613036
80th percentile: 1.4875654220581056
90th percentile: 1.8755280494689943
95th percentile: 2.069509363174438
99th percentile: 2.224694414138794
mean time: 1.4657649993896484
Pipeline stage StressChecker completed in 7.90s
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-cl_3476_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-cl_3476_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-cl_3476_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-cl-3476-v2 is running
Tearing down inference service hastagaras-llama-3-8b-cl-3476-v2
Toredown service hastagaras-llama-3-8b-cl-3476-v2
Pipeline stage ISVCDeleter completed in 3.66s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-cl-3476-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-cl-3476-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.82s
hastagaras-llama-3-8b-cl_3476_v2 status is now torndown due to DeploymentManager action