submission_id: roleplay4fun-lewdma-3-8b_v4
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': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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}
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: 2024-05-15T11:19:02+00:00
model_name: lewdma_3_8b
model_eval_status: success
model_group: roleplay4fun/Lewdma-3-8B
num_battles: 22080
num_wins: 10466
celo_rating: 1154.8
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
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: 2024-05-15
win_ratio: 0.4740036231884058
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name roleplay4fun-lewdma-3-8b-v4-mkmlizer
Waiting for job on roleplay4fun-lewdma-3-8b-v4-mkmlizer to finish
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ _____ __ __ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ /___/ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ Version: 0.8.14 ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ https://mk1.ai ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ The license key for the current software has been verified as ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ belonging to: ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ Chai Research Corp. ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ║ ║
roleplay4fun-lewdma-3-8b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
roleplay4fun-lewdma-3-8b-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Downloaded to shared memory in 17.378s
roleplay4fun-lewdma-3-8b-v4-mkmlizer: quantizing model to /dev/shm/model_cache
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:37, 2.00s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:36, 7.37it/s] Loading 0: 14%|█▍ | 41/291 [00:04<00:15, 15.87it/s] Loading 0: 21%|██ | 60/291 [00:04<00:08, 26.68it/s] Loading 0: 28%|██▊ | 82/291 [00:04<00:04, 42.43it/s] Loading 0: 35%|███▌ | 103/291 [00:04<00:03, 59.74it/s] Loading 0: 42%|████▏ | 122/291 [00:04<00:02, 75.60it/s] Loading 0: 49%|████▉ | 143/291 [00:04<00:01, 96.31it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 64.68it/s] Loading 0: 64%|██████▍ | 186/291 [00:05<00:01, 80.63it/s] Loading 0: 73%|███████▎ | 211/291 [00:05<00:00, 104.47it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:00, 119.38it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 143.77it/s] Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 153.80it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
roleplay4fun-lewdma-3-8b-v4-mkmlizer: quantized model in 17.453s
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Processed model roleplay4fun/Lewdma-3-8B in 35.874s
roleplay4fun-lewdma-3-8b-v4-mkmlizer: creating bucket guanaco-mkml-models
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
roleplay4fun-lewdma-3-8b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v4
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v4/special_tokens_map.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v4/config.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v4/tokenizer_config.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v4/tokenizer.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/roleplay4fun-lewdma-3-8b-v4/flywheel_model.0.safetensors
roleplay4fun-lewdma-3-8b-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
roleplay4fun-lewdma-3-8b-v4-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-v4-mkmlizer: warnings.warn(
roleplay4fun-lewdma-3-8b-v4-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-v4-mkmlizer: warnings.warn(
roleplay4fun-lewdma-3-8b-v4-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-v4-mkmlizer: warnings.warn(
roleplay4fun-lewdma-3-8b-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Saving duration: 0.226s
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.604s
roleplay4fun-lewdma-3-8b-v4-mkmlizer: creating bucket guanaco-reward-models
roleplay4fun-lewdma-3-8b-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
roleplay4fun-lewdma-3-8b-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/config.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/special_tokens_map.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/tokenizer_config.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/vocab.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/merges.txt
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/tokenizer.json
roleplay4fun-lewdma-3-8b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/roleplay4fun-lewdma-3-8b-v4_reward/reward.tensors
Job roleplay4fun-lewdma-3-8b-v4-mkmlizer completed after 62.67s with status: succeeded
Stopping job with name roleplay4fun-lewdma-3-8b-v4-mkmlizer
Pipeline stage MKMLizer completed in 67.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service roleplay4fun-lewdma-3-8b-v4
Waiting for inference service roleplay4fun-lewdma-3-8b-v4 to be ready
Inference service roleplay4fun-lewdma-3-8b-v4 ready after 30.205609798431396s
Pipeline stage ISVCDeployer completed in 38.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9338774681091309s
Received healthy response to inference request in 1.1190977096557617s
Received healthy response to inference request in 1.1375083923339844s
Received healthy response to inference request in 1.1171674728393555s
Received healthy response to inference request in 0.9166476726531982s
5 requests
0 failed requests
5th percentile: 0.9567516326904297
10th percentile: 0.9968555927276611
20th percentile: 1.077063512802124
30th percentile: 1.1175535202026368
40th percentile: 1.1183256149291991
50th percentile: 1.1190977096557617
60th percentile: 1.1264619827270508
70th percentile: 1.1338262557983398
80th percentile: 1.2967822074890138
90th percentile: 1.6153298377990724
95th percentile: 1.7746036529541014
99th percentile: 1.9020227050781249
mean time: 1.2448597431182862
Pipeline stage StressChecker completed in 6.86s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
roleplay4fun-lewdma-3-8b_v4 status is now deployed due to DeploymentManager action
roleplay4fun-lewdma-3-8b_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of roleplay4fun-lewdma-3-8b_v4
Running pipeline stage ISVCDeleter
Checking if service roleplay4fun-lewdma-3-8b-v4 is running
Tearing down inference service roleplay4fun-lewdma-3-8b-v4
Toredown service roleplay4fun-lewdma-3-8b-v4
Pipeline stage ISVCDeleter completed in 6.97s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key roleplay4fun-lewdma-3-8b-v4/config.json from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key roleplay4fun-lewdma-3-8b-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/config.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key roleplay4fun-lewdma-3-8b-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.97s
roleplay4fun-lewdma-3-8b_v4 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics