submission_id: undi95-llama-3-lewdplay-8b-e3_v2
developer_uid: Undi95
status: torndown
model_repo: Undi95/Llama-3-LewdPlay-8B-e3
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': 112}
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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-04-23T19:13:39+00:00
model_name: undi95-llama-3-lewdplay-8b-e3_v2
model_eval_status: success
model_group: Undi95/Llama-3-LewdPlay-
num_battles: 9907
num_wins: 5428
celo_rating: 1183.99
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: 112
display_name: undi95-llama-3-lewdplay-8b-e3_v2
ineligible_reason: max_output_tokens!=64
language_model: Undi95/Llama-3-LewdPlay-8B-e3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-23
win_ratio: 0.5478954274755223
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer
Waiting for job on undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer to finish
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ _____ __ __ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ /___/ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ Version: 0.8.10 ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ belonging to: ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ Chai Research Corp. ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ║ ║
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-lewdplay-8b-e3-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.
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
Retrying (%r) after connection broken by '%r': %s
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Downloaded to shared memory in 22.104s
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 106.94it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 38.63it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: quantized model in 17.541s
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Processed model Undi95/Llama-3-LewdPlay-8B-e3 in 40.626s
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-lewdplay-8b-e3-v2
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-8b-e3-v2/tokenizer.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-8b-e3-v2/special_tokens_map.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-8b-e3-v2/config.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-8b-e3-v2/tokenizer_config.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-lewdplay-8b-e3-v2/flywheel_model.0.safetensors
undi95-llama-3-lewdplay-8b-e3-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.
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-lewdplay-8b-e3-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.
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-8b-e3-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.
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-8b-e3-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()
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Saving duration: 0.238s
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.621s
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/config.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/merges.txt
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/special_tokens_map.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/vocab.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/tokenizer_config.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/tokenizer.json
undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-lewdplay-8b-e3-v2_reward/reward.tensors
Job undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer completed after 95.82s with status: succeeded
Stopping job with name undi95-llama-3-lewdplay-8b-e3-v2-mkmlizer
Pipeline stage MKMLizer completed in 101.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-lewdplay-8b-e3-v2
Waiting for inference service undi95-llama-3-lewdplay-8b-e3-v2 to be ready
Inference service undi95-llama-3-lewdplay-8b-e3-v2 ready after 30.23047184944153s
Pipeline stage ISVCDeployer completed in 37.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5010459423065186s
Received healthy response to inference request in 1.301720380783081s
Received healthy response to inference request in 2.1263890266418457s
Received healthy response to inference request in 1.8980345726013184s
Received healthy response to inference request in 1.8561720848083496s
5 requests
0 failed requests
5th percentile: 1.4126107215881347
10th percentile: 1.5235010623931884
20th percentile: 1.745281744003296
30th percentile: 1.8645445823669433
40th percentile: 1.881289577484131
50th percentile: 1.8980345726013184
60th percentile: 1.9893763542175293
70th percentile: 2.0807181358337403
80th percentile: 2.2013204097747803
90th percentile: 2.3511831760406494
95th percentile: 2.426114559173584
99th percentile: 2.4860596656799316
mean time: 1.9366724014282226
Pipeline stage StressChecker completed in 10.40s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
undi95-llama-3-lewdplay-8b-e3_v2 status is now deployed due to DeploymentManager action
undi95-llama-3-lewdplay-8b-e3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-llama-3-lewdplay-8b-e3_v2
Running pipeline stage ISVCDeleter
Checking if service undi95-llama-3-lewdplay-8b-e3-v2 is running
Tearing down inference service undi95-llama-3-lewdplay-8b-e3-v2
Toredown service undi95-llama-3-lewdplay-8b-e3-v2
Pipeline stage ISVCDeleter completed in 3.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-8b-e3-v2/config.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-8b-e3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.79s
undi95-llama-3-lewdplay-8b-e3_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics