developer_uid: zonemercy
submission_id: vicgalle-roleplay-llama-3-8b_v18
model_name: ptptpt
model_group: vicgalle/Roleplay-Llama-
status: torndown
timestamp: 2024-05-09T00:48:14+00:00
num_battles: 10127
num_wins: 5603
celo_rating: 1214.5
family_friendly_score: 0.0
submission_type: basic
model_repo: vicgalle/Roleplay-Llama-3-8B
model_architecture: LlamaForCausalLM
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 112
display_name: ptptpt
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: vicgalle/Roleplay-Llama-3-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-08
win_ratio: 0.5532734274711169
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': 112}
formatter: {'memory_template': "Bot's Name: {bot_name}\nBot's Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {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 vicgalle-roleplay-llama-3-8b-v18-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v18-mkmlizer to finish
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║     _____            __           __                                ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║       /___/                                                         ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  Version: 0.8.10                                                    ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  belonging to:                                                      ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  Chai Research Corp.                                                ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ║                                                                     ║
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v18-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-v18-mkmlizer:   warnings.warn(warning_message, FutureWarning)
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Downloaded to shared memory in 21.870s
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:02, 89.89it/s]
Loading 0:  65%|██████▍   | 188/291 [00:02<00:01, 94.16it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.82it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: quantized model in 18.826s
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Processed model vicgalle/Roleplay-Llama-3-8B in 41.724s
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: creating bucket guanaco-mkml-models
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v18
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v18/config.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v18/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v18/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v18/tokenizer.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v18/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v18-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-v18-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v18-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-v18-mkmlizer:   warnings.warn(
vicgalle-roleplay-llama-3-8b-v18-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-v18-mkmlizer:   return self.fget.__get__(instance, owner)()
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Saving duration: 0.242s
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.710s
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: creating bucket guanaco-reward-models
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: Bucket 's3://guanaco-reward-models/' created
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/config.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/vocab.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/merges.txt
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/tokenizer.json
vicgalle-roleplay-llama-3-8b-v18-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v18_reward/reward.tensors
Job vicgalle-roleplay-llama-3-8b-v18-mkmlizer completed after 73.26s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v18-mkmlizer
Pipeline stage MKMLizer completed in 76.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v18
Waiting for inference service vicgalle-roleplay-llama-3-8b-v18 to be ready
Inference service vicgalle-roleplay-llama-3-8b-v18 ready after 30.1732439994812s
Pipeline stage ISVCDeployer completed in 37.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7002995014190674s
Received healthy response to inference request in 1.9383642673492432s
Received healthy response to inference request in 1.9000988006591797s
Received healthy response to inference request in 1.6543662548065186s
Received healthy response to inference request in 1.8929293155670166s
5 requests
0 failed requests
5th percentile: 1.7020788669586182
10th percentile: 1.7497914791107179
20th percentile: 1.845216703414917
30th percentile: 1.8943632125854493
40th percentile: 1.8972310066223144
50th percentile: 1.9000988006591797
60th percentile: 1.915404987335205
70th percentile: 1.9307111740112304
80th percentile: 2.0907513141632084
90th percentile: 2.395525407791138
95th percentile: 2.547912454605102
99th percentile: 2.6698220920562745
mean time: 2.0172116279602053
Pipeline stage StressChecker completed in 10.73s
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
vicgalle-roleplay-llama-3-8b_v18 status is now deployed due to DeploymentManager action
vicgalle-roleplay-llama-3-8b_v18 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v18
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v18 is running
Tearing down inference service vicgalle-roleplay-llama-3-8b-v18
Toredown service vicgalle-roleplay-llama-3-8b-v18
Pipeline stage ISVCDeleter completed in 8.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v18/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v18/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v18/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v18/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v18/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v18_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.99s
vicgalle-roleplay-llama-3-8b_v18 status is now torndown due to DeploymentManager action