submission_id: vicgalle-roleplay-llama-3-8b_v20
developer_uid: Jellywibble
best_of: 16
celo_rating: 1191.49
display_name: vicgalle-tl-proptest
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\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': True}
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}
is_internal_developer: True
language_model: vicgalle/Roleplay-Llama-3-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: vicgalle/Roleplay-Llama-
model_name: vicgalle-tl-proptest
model_num_parameters: 8030261248.0
model_repo: vicgalle/Roleplay-Llama-3-8B
model_size: 8B
num_battles: 23536
num_wins: 11766
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: 2024-06-15T02:28:50+00:00
us_pacific_date: 2024-06-14
win_ratio: 0.49991502379333785
Resubmit model
Running pipeline stage MKMLizer
Starting job with name vicgalle-roleplay-llama-3-8b-v20-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v20-mkmlizer to finish
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║     _____            __           __                                ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║       /___/                                                         ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  Version: 0.8.14                                                    ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  https://mk1.ai                                                     ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  The license key for the current software has been verified as      ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  belonging to:                                                      ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  Chai Research Corp.                                                ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v20-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.
vicgalle-roleplay-llama-3-8b-v20-mkmlizer:   warnings.warn(warning_message, FutureWarning)
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: Downloaded to shared memory in 35.695s
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v20/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v20-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.
vicgalle-roleplay-llama-3-8b-v20-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v20-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.
vicgalle-roleplay-llama-3-8b-v20-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v20-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.
vicgalle-roleplay-llama-3-8b-v20-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v20-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()
vicgalle-roleplay-llama-3-8b-v20-mkmlizer:   return self.fget.__get__(instance, owner)()
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: Saving duration: 0.413s
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.470s
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: creating bucket guanaco-reward-models
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: Bucket 's3://guanaco-reward-models/' created
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/merges.txt
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/config.json
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/vocab.json
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/tokenizer.json
vicgalle-roleplay-llama-3-8b-v20-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v20_reward/reward.tensors
Job vicgalle-roleplay-llama-3-8b-v20-mkmlizer completed after 103.41s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v20-mkmlizer
Pipeline stage MKMLizer completed in 108.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v20
Waiting for inference service vicgalle-roleplay-llama-3-8b-v20 to be ready
Inference service vicgalle-roleplay-llama-3-8b-v20 ready after 40.24933576583862s
Pipeline stage ISVCDeployer completed in 47.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.248054265975952s
Received healthy response to inference request in 1.315840244293213s
Received healthy response to inference request in 1.2955422401428223s
Received healthy response to inference request in 1.2500693798065186s
Received healthy response to inference request in 1.3021395206451416s
5 requests
0 failed requests
5th percentile: 1.2591639518737794
10th percentile: 1.26825852394104
20th percentile: 1.2864476680755614
30th percentile: 1.2968616962432862
40th percentile: 1.2995006084442138
50th percentile: 1.3021395206451416
60th percentile: 1.3076198101043701
70th percentile: 1.3131000995635986
80th percentile: 1.502283048629761
90th percentile: 1.8751686573028565
95th percentile: 2.061611461639404
99th percentile: 2.2107657051086425
mean time: 1.4823291301727295
Pipeline stage StressChecker completed in 8.36s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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
vicgalle-roleplay-llama-3-8b_v20 status is now deployed due to DeploymentManager action
vicgalle-roleplay-llama-3-8b_v20 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v20
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v20 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.19s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v20/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v20/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v20/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v20/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v20/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v20_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.24s
vicgalle-roleplay-llama-3-8b_v20 status is now torndown due to DeploymentManager action