submission_id: vicgalle-roleplay-llama-3-8b_v3
developer_uid: fredi
status: torndown
model_repo: vicgalle/Roleplay-Llama-3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 1.0, 'stopping_words': ['\n', '<|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\nYou are roleplaying "{bot_name}". {bot_name}\'s Persona: {memory}.\n\n', 'prompt_template': '{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\nUser: {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: 2024-04-20T23:12:53+00:00
model_name: RPllama8B
model_eval_status: success
model_group: vicgalle/Roleplay-Llama-
num_battles: 5464
num_wins: 2798
celo_rating: 1156.28
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: RPllama8B
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: 2024-04-20
win_ratio: 0.5120790629575402
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name vicgalle-roleplay-llama-3-8b-v3-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v3-mkmlizer to finish
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ _____ __ __ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ /___/ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ Version: 0.8.10 ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ The license key for the current software has been verified as ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ belonging to: ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ Chai Research Corp. ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: Downloaded to shared memory in 15.850s
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 93.95it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:00, 101.51it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 26.16it/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-v3-mkmlizer: quantized model in 21.570s
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: Processed model vicgalle/Roleplay-Llama-3-8B in 38.523s
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v3
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v3/config.json
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v3/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v3/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v3/tokenizer.json
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v3/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v3-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-v3-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v3-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-v3-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v3-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-v3-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
vicgalle-roleplay-llama-3-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v3_reward/reward.tensors
Job vicgalle-roleplay-llama-3-8b-v3-mkmlizer completed after 63.33s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 68.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v3
Waiting for inference service vicgalle-roleplay-llama-3-8b-v3 to be ready
Inference service vicgalle-roleplay-llama-3-8b-v3 ready after 30.19753360748291s
Pipeline stage ISVCDeployer completed in 38.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1311137676239014s
Received healthy response to inference request in 0.8077974319458008s
Received healthy response to inference request in 0.7413082122802734s
Received healthy response to inference request in 1.2477688789367676s
Received healthy response to inference request in 1.3401503562927246s
5 requests
0 failed requests
5th percentile: 0.754606056213379
10th percentile: 0.7679039001464844
20th percentile: 0.7944995880126953
30th percentile: 0.8957917213439941
40th percentile: 1.071780300140381
50th percentile: 1.2477688789367676
60th percentile: 1.2847214698791505
70th percentile: 1.3216740608215332
80th percentile: 1.49834303855896
90th percentile: 1.8147284030914308
95th percentile: 1.972921085357666
99th percentile: 2.099475231170654
mean time: 1.2536277294158935
Pipeline stage StressChecker completed in 6.92s
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_v3 status is now deployed due to DeploymentManager action
vicgalle-roleplay-llama-3-8b_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v3
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v3 is running
Tearing down inference service vicgalle-roleplay-llama-3-8b-v3
Toredown service vicgalle-roleplay-llama-3-8b-v3
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v3/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.86s
vicgalle-roleplay-llama-3-8b_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics