submission_id: vicgalle-roleplay-llama-3-8b_v9
developer_uid: Meliodia
status: torndown
model_repo: vicgalle/Roleplay-Llama-3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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 never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}\'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nFor example:\n"""\nMila: *Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn\'t it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?\n"""\n\nDescription: {memory}', '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: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-21T16:55:47+00:00
model_name: vicgalle-roleplay-llama-3-8b_v9
model_eval_status: success
model_group: vicgalle/Roleplay-Llama-
num_battles: 5443
num_wins: 2916
celo_rating: 1172.17
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: vicgalle-roleplay-llama-3-8b_v9
ineligible_reason: propriety_total_count < 800
language_model: vicgalle/Roleplay-Llama-3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.5357339702370016
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name vicgalle-roleplay-llama-3-8b-v9-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v9-mkmlizer to finish
Stopping job with name vicgalle-roleplay-llama-3-8b-v9-mkmlizer
%s, retrying in %s seconds...
Starting job with name vicgalle-roleplay-llama-3-8b-v9-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v9-mkmlizer to finish
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ _____ __ __ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ /___/ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ Version: 0.8.10 ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ The license key for the current software has been verified as ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ belonging to: ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ Chai Research Corp. ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v9-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-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: Downloaded to shared memory in 17.874s
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 71.24it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 81.11it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 26.67it/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-v9-mkmlizer: quantized model in 19.923s
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: Processed model vicgalle/Roleplay-Llama-3-8B in 39.175s
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: creating bucket guanaco-mkml-models
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v9
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v9/config.json
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v9/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v9/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v9/tokenizer.json
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v9/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v9-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-v9-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v9-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-v9-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v9-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-v9-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v9_reward/reward.tensors
Job vicgalle-roleplay-llama-3-8b-v9-mkmlizer completed after 66.61s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v9-mkmlizer
Pipeline stage MKMLizer completed in 72.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v9
Waiting for inference service vicgalle-roleplay-llama-3-8b-v9 to be ready
Inference service vicgalle-roleplay-llama-3-8b-v9 ready after 51.76762127876282s
Pipeline stage ISVCDeployer completed in 59.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.113713264465332s
Received healthy response to inference request in 1.3759284019470215s
Received healthy response to inference request in 1.342897653579712s
Received healthy response to inference request in 1.2824513912200928s
Received healthy response to inference request in 1.2932000160217285s
5 requests
0 failed requests
5th percentile: 1.2846011161804198
10th percentile: 1.2867508411407471
20th percentile: 1.2910502910614015
30th percentile: 1.3031395435333253
40th percentile: 1.3230185985565186
50th percentile: 1.342897653579712
60th percentile: 1.3561099529266358
70th percentile: 1.3693222522735595
80th percentile: 1.5234853744506838
90th percentile: 1.818599319458008
95th percentile: 1.9661562919616697
99th percentile: 2.0842018699645997
mean time: 1.4816381454467773
Pipeline stage StressChecker completed in 8.00s
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_v9 status is now deployed due to DeploymentManager action
vicgalle-roleplay-llama-3-8b_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v9
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v9 is running
Tearing down inference service vicgalle-roleplay-llama-3-8b-v9
Toredown service vicgalle-roleplay-llama-3-8b-v9
Pipeline stage ISVCDeleter completed in 3.52s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v9/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.86s
vicgalle-roleplay-llama-3-8b_v9 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics