developer_uid: sao10k
submission_id: sao10k-l3-rp-v2-2_v1
model_name: L3-RP-v2-Test2-ITR
model_group: Sao10K/L3-RP-v2.2
status: torndown
timestamp: 2024-05-19T11:24:09+00:00
num_battles: 20983
num_wins: 10700
celo_rating: 1184.42
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-RP-v2.2
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: L3-RP-v2-Test2-ITR
is_internal_developer: False
language_model: Sao10K/L3-RP-v2.2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-19
win_ratio: 0.5099366153552876
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.', 'prompt_template': '\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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v2-2-v1-mkmlizer
Waiting for job on sao10k-l3-rp-v2-2-v1-mkmlizer to finish
sao10k-l3-rp-v2-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v2-2-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v2-2-v1-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-v2-2-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v2-2-v1-mkmlizer: Downloaded to shared memory in 26.851s
sao10k-l3-rp-v2-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v2-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v2-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:10,  2.11s/it]
Loading 0:   8%|▊         | 23/291 [00:04<00:36,  7.30it/s]
Loading 0:  14%|█▍        | 42/291 [00:04<00:16, 15.40it/s]
Loading 0:  21%|██        | 60/291 [00:04<00:10, 21.37it/s]
Loading 0:  28%|██▊       | 82/291 [00:04<00:06, 34.73it/s]
Loading 0:  35%|███▌      | 103/291 [00:05<00:03, 49.87it/s]
Loading 0:  42%|████▏     | 122/291 [00:05<00:02, 64.97it/s]
Loading 0:  48%|████▊     | 141/291 [00:05<00:01, 81.18it/s]
Loading 0:  56%|█████▌    | 163/291 [00:05<00:01, 103.42it/s]
Loading 0:  63%|██████▎   | 182/291 [00:05<00:01, 69.39it/s] 
Loading 0:  68%|██████▊   | 197/291 [00:05<00:01, 79.06it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 102.21it/s]
Loading 0:  82%|████████▏ | 240/291 [00:06<00:00, 118.54it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 143.30it/s]
Loading 0:  98%|█████████▊| 284/291 [00:06<00:00, 99.45it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v2-2-v1-mkmlizer: Processed model Sao10K/L3-RP-v2.2 in 45.589s
sao10k-l3-rp-v2-2-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v2-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v2-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v2-2-v1
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-2-v1/config.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-2-v1/special_tokens_map.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-2-v1/tokenizer_config.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-2-v1/tokenizer.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v2-2-v1/flywheel_model.0.safetensors
sao10k-l3-rp-v2-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v2-2-v1-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-v2-2-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v2-2-v1-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-v2-2-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v2-2-v1-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-v2-2-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v2-2-v1-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-v2-2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v2-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v2-2-v1-mkmlizer: Saving duration: 0.233s
sao10k-l3-rp-v2-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.227s
sao10k-l3-rp-v2-2-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v2-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v2-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/config.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/special_tokens_map.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/merges.txt
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/tokenizer_config.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/vocab.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/tokenizer.json
sao10k-l3-rp-v2-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v2-2-v1_reward/reward.tensors
Job sao10k-l3-rp-v2-2-v1-mkmlizer completed after 82.89s with status: succeeded
Stopping job with name sao10k-l3-rp-v2-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.23s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v2-2-v1
Waiting for inference service sao10k-l3-rp-v2-2-v1 to be ready
Inference service sao10k-l3-rp-v2-2-v1 ready after 30.156904935836792s
Pipeline stage ISVCDeployer completed in 36.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9848523139953613s
Received healthy response to inference request in 1.1685163974761963s
Received healthy response to inference request in 1.1408066749572754s
Received healthy response to inference request in 1.1744704246520996s
Received healthy response to inference request in 1.1683106422424316s
5 requests
0 failed requests
5th percentile: 1.1463074684143066
10th percentile: 1.151808261871338
20th percentile: 1.1628098487854004
30th percentile: 1.1683517932891845
40th percentile: 1.1684340953826904
50th percentile: 1.1685163974761963
60th percentile: 1.1708980083465577
70th percentile: 1.173279619216919
80th percentile: 1.336546802520752
90th percentile: 1.6606995582580568
95th percentile: 1.8227759361267089
99th percentile: 1.9524370384216307
mean time: 1.3273912906646728
Pipeline stage StressChecker completed in 7.27s
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-v2-2_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
sao10k-l3-rp-v2-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v2-2_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v2-2-v1 is running
Tearing down inference service sao10k-l3-rp-v2-2-v1
Toredown service sao10k-l3-rp-v2-2-v1
Pipeline stage ISVCDeleter completed in 4.29s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-2-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.95s
sao10k-l3-rp-v2-2_v1 status is now torndown due to DeploymentManager action