submission_id: roleplay4fun-lewdma-3-8b_v2
developer_uid: gau
status: torndown
model_repo: roleplay4fun/Lewdma-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': ['<|eot_id|>'], '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\nImmerse yourself in the ongoing, uncensored fictional roleplay chat between {bot_name} and User. Your task is to write {bot_name}'s next reply, staying true to the character's description, personality, and provided dialogue examples.\n\nActions and narrations should be enclosed in asterisks. Craft your response as a detailed, third-person narrative.\n\nCharacter description: {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}\\####\\", 'prompt_template': '{prompt}\\<START>\\', 'bot_template': '{bot_name}: {message}\\', 'user_template': '{user_name}: {message}\\', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-05-15T06:37:51+00:00
model_name: lewdma_3_8b
model_eval_status: success
model_group: roleplay4fun/Lewdma-3-8B
num_battles: 10464
num_wins: 5257
celo_rating: 1173.98
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: lewdma_3_8b
ineligible_reason: propriety_total_count < 800
language_model: roleplay4fun/Lewdma-3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-14
win_ratio: 0.5023891437308868
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name roleplay4fun-lewdma-3-8b-v2-mkmlizer
Waiting for job on roleplay4fun-lewdma-3-8b-v2-mkmlizer to finish
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ _____ __ __ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ /___/ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ Version: 0.8.14 ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ https://mk1.ai ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ belonging to: ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ Chai Research Corp. ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
roleplay4fun-lewdma-3-8b-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.
roleplay4fun-lewdma-3-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Downloaded to shared memory in 13.585s
roleplay4fun-lewdma-3-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:38, 2.00s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:36, 7.36it/s] Loading 0: 14%|█▍ | 42/291 [00:04<00:15, 16.33it/s] Loading 0: 23%|██▎ | 67/291 [00:04<00:07, 30.87it/s] Loading 0: 30%|██▉ | 87/291 [00:04<00:04, 44.27it/s] Loading 0: 37%|███▋ | 109/291 [00:04<00:02, 62.38it/s] Loading 0: 45%|████▌ | 131/291 [00:04<00:01, 81.43it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:01, 99.26it/s] Loading 0: 59%|█████▉ | 171/291 [00:05<00:01, 62.21it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:01, 80.60it/s] Loading 0: 73%|███████▎ | 212/291 [00:05<00:00, 96.45it/s] Loading 0: 80%|████████ | 234/291 [00:05<00:00, 117.52it/s] Loading 0: 88%|████████▊ | 257/291 [00:05<00:00, 137.71it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 151.12it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
roleplay4fun-lewdma-3-8b-v2-mkmlizer: quantized model in 17.137s
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Processed model roleplay4fun/Lewdma-3-8B in 31.715s
roleplay4fun-lewdma-3-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
roleplay4fun-lewdma-3-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v2
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v2/config.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v2/special_tokens_map.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v2/tokenizer_config.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v2/tokenizer.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v2/flywheel_model.0.safetensors
roleplay4fun-lewdma-3-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
roleplay4fun-lewdma-3-8b-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.
roleplay4fun-lewdma-3-8b-v2-mkmlizer: warnings.warn(
roleplay4fun-lewdma-3-8b-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.
roleplay4fun-lewdma-3-8b-v2-mkmlizer: warnings.warn(
roleplay4fun-lewdma-3-8b-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.
roleplay4fun-lewdma-3-8b-v2-mkmlizer: warnings.warn(
roleplay4fun-lewdma-3-8b-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()
roleplay4fun-lewdma-3-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Saving duration: 0.253s
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.423s
roleplay4fun-lewdma-3-8b-v2-mkmlizer: creating bucket guanaco-reward-models
roleplay4fun-lewdma-3-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
roleplay4fun-lewdma-3-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/merges.txt
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/vocab.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/config.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/special_tokens_map.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/tokenizer_config.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/tokenizer.json
roleplay4fun-lewdma-3-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v2_reward/reward.tensors
Job roleplay4fun-lewdma-3-8b-v2-mkmlizer completed after 62.78s with status: succeeded
Stopping job with name roleplay4fun-lewdma-3-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service roleplay4fun-lewdma-3-8b-v2
Waiting for inference service roleplay4fun-lewdma-3-8b-v2 to be ready
Inference service roleplay4fun-lewdma-3-8b-v2 ready after 50.25194787979126s
Pipeline stage ISVCDeployer completed in 58.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3119595050811768s
Received healthy response to inference request in 1.3000907897949219s
Received healthy response to inference request in 1.2963554859161377s
Received healthy response to inference request in 1.2787251472473145s
Received healthy response to inference request in 1.3239996433258057s
5 requests
0 failed requests
5th percentile: 1.2822512149810792
10th percentile: 1.2857772827148437
20th percentile: 1.292829418182373
30th percentile: 1.2971025466918946
40th percentile: 1.2985966682434082
50th percentile: 1.3000907897949219
60th percentile: 1.3096543312072755
70th percentile: 1.3192178726196289
80th percentile: 1.52159161567688
90th percentile: 1.9167755603790284
95th percentile: 2.1143675327301024
99th percentile: 2.272441110610962
mean time: 1.5022261142730713
Pipeline stage StressChecker completed in 8.18s
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
roleplay4fun-lewdma-3-8b_v2 status is now deployed due to DeploymentManager action
roleplay4fun-lewdma-3-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of roleplay4fun-lewdma-3-8b_v2
Running pipeline stage ISVCDeleter
Checking if service roleplay4fun-lewdma-3-8b-v2 is running
Tearing down inference service roleplay4fun-lewdma-3-8b-v2
Toredown service roleplay4fun-lewdma-3-8b-v2
Pipeline stage ISVCDeleter completed in 5.66s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key roleplay4fun-lewdma-3-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.37s
roleplay4fun-lewdma-3-8b_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics