submission_id: sao10k-l3-rp-v1_v2
developer_uid: sao10k
best_of: 16
celo_rating: 1196.92
display_name: L3-RP-v1-Test-Prompt-2
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are an expert actor that can fully immerse yourself into any role given. You do not break character for any reason, even if someone tries addressing you as an AI or language model. Currently your role is {bot_name}, which is described in detail below. As {bot_name}, continue the exchange with {user_name}.\n\n{bot_name}'s 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}
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}
is_internal_developer: False
language_model: Sao10K/L3-RP-v1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Sao10K/L3-RP-v1
model_name: L3-RP-v1-Test-Prompt-2
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3-RP-v1
model_size: 8B
num_battles: 15434
num_wins: 8313
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-12T13:03:21+00:00
us_pacific_date: 2024-05-12
win_ratio: 0.5386160425035635
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v1-v2-mkmlizer
Waiting for job on sao10k-l3-rp-v1-v2-mkmlizer to finish
sao10k-l3-rp-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v1-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v1-v2-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v1-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v1-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.
sao10k-l3-rp-v1-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v1-v2-mkmlizer: Downloaded to shared memory in 12.655s
sao10k-l3-rp-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<09:50,  2.04s/it]
Loading 0:  48%|████▊     | 139/291 [00:05<00:04, 35.77it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 55.21it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v1-v2-mkmlizer: quantized model in 17.779s
sao10k-l3-rp-v1-v2-mkmlizer: Processed model Sao10K/L3-RP-v1 in 31.500s
sao10k-l3-rp-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v1-v2
sao10k-l3-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v1-v2/tokenizer_config.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v1-v2/config.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v1-v2/special_tokens_map.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v1-v2/tokenizer.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v1-v2/flywheel_model.0.safetensors
sao10k-l3-rp-v1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v1-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.
sao10k-l3-rp-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v1-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.
sao10k-l3-rp-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v1-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.
sao10k-l3-rp-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v1-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()
sao10k-l3-rp-v1-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v1-v2-mkmlizer: Saving duration: 0.247s
sao10k-l3-rp-v1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.690s
sao10k-l3-rp-v1-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/config.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/special_tokens_map.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/tokenizer_config.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/vocab.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/merges.txt
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/tokenizer.json
sao10k-l3-rp-v1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v1-v2_reward/reward.tensors
Job sao10k-l3-rp-v1-v2-mkmlizer completed after 53.64s with status: succeeded
Stopping job with name sao10k-l3-rp-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 56.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v1-v2
Waiting for inference service sao10k-l3-rp-v1-v2 to be ready
Inference service sao10k-l3-rp-v1-v2 ready after 40.21429920196533s
Pipeline stage ISVCDeployer completed in 47.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1929750442504883s
Received healthy response to inference request in 1.3784642219543457s
Received healthy response to inference request in 1.352039098739624s
Received healthy response to inference request in 1.308298110961914s
Received healthy response to inference request in 1.269073486328125s
5 requests
0 failed requests
5th percentile: 1.2769184112548828
10th percentile: 1.2847633361816406
20th percentile: 1.3004531860351562
30th percentile: 1.317046308517456
40th percentile: 1.33454270362854
50th percentile: 1.352039098739624
60th percentile: 1.3626091480255127
70th percentile: 1.3731791973114014
80th percentile: 1.5413663864135745
90th percentile: 1.8671707153320314
95th percentile: 2.0300728797912595
99th percentile: 2.1603946113586425
mean time: 1.5001699924468994
Pipeline stage StressChecker completed in 8.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
sao10k-l3-rp-v1_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
sao10k-l3-rp-v1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v1_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v1-v2 is running
Tearing down inference service sao10k-l3-rp-v1-v2
Toredown service sao10k-l3-rp-v1-v2
Pipeline stage ISVCDeleter completed in 5.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v1-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.94s
sao10k-l3-rp-v1_v2 status is now torndown due to DeploymentManager action