sao10k-l3-solana-8b-v1

developer_uid: sao10k

submission_id: sao10k-l3-solana-8b-v1_v2

model_name: sao10k-l3-solana-8b-v1_v1

model_group: Sao10K/L3-Solana-8B-v1

status: torndown

timestamp: 2024-04-21T13:15:16+00:00

num_battles: 6800

num_wins: 3632

celo_rating: 1173.18

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/L3-Solana-8B-v1

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: sao10k-l3-solana-8b-v1_v1

is_internal_developer: False

language_model: Sao10K/L3-Solana-8B-v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-04-21

win_ratio: 0.5341176470588235

generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|begin_of_text|>System: You are to play the role of {bot_name} in a never-ending uncensored fictional roleplay chat session between {bot_name} and {user_name}. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and behaving as {bot_name}.\n\nDescription: {memory}", 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}<|end_of_text|>', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-solana-8b-v1-v2-mkmlizer
Waiting for job on sao10k-l3-solana-8b-v1-v2-mkmlizer to finish
Stopping job with name sao10k-l3-solana-8b-v1-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name sao10k-l3-solana-8b-v1-v2-mkmlizer
Waiting for job on sao10k-l3-solana-8b-v1-v2-mkmlizer to finish
sao10k-l3-solana-8b-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║       /___/                                                         ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-solana-8b-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-solana-8b-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-solana-8b-v1-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sao10k-l3-solana-8b-v1-v2-mkmlizer: Downloaded to shared memory in 20.935s
sao10k-l3-solana-8b-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-solana-8b-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-solana-8b-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  43%|████▎     | 125/291 [00:01<00:01, 124.88it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 127.45it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 28.44it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-solana-8b-v1-v2-mkmlizer: quantized model in 18.617s
sao10k-l3-solana-8b-v1-v2-mkmlizer: Processed model Sao10K/L3-Solana-8B-v1 in 40.727s
sao10k-l3-solana-8b-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-solana-8b-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-solana-8b-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-solana-8b-v1-v2
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-solana-8b-v1-v2/special_tokens_map.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-solana-8b-v1-v2/config.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-solana-8b-v1-v2/tokenizer_config.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-solana-8b-v1-v2/tokenizer.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-solana-8b-v1-v2/flywheel_model.0.safetensors
sao10k-l3-solana-8b-v1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-solana-8b-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-solana-8b-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-solana-8b-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-solana-8b-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-solana-8b-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-solana-8b-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-solana-8b-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-solana-8b-v1-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-solana-8b-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-solana-8b-v1-v2-mkmlizer: Saving duration: 0.249s
sao10k-l3-solana-8b-v1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.146s
sao10k-l3-solana-8b-v1-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-solana-8b-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-solana-8b-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/config.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/tokenizer_config.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/special_tokens_map.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/merges.txt
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/vocab.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/tokenizer.json
sao10k-l3-solana-8b-v1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-solana-8b-v1-v2_reward/reward.tensors
Job sao10k-l3-solana-8b-v1-v2-mkmlizer completed after 79.24s with status: succeeded
Stopping job with name sao10k-l3-solana-8b-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-solana-8b-v1-v2
Waiting for inference service sao10k-l3-solana-8b-v1-v2 to be ready
Inference service sao10k-l3-solana-8b-v1-v2 ready after 40.516393423080444s
Pipeline stage ISVCDeployer completed in 49.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0911667346954346s
Received healthy response to inference request in 1.2124645709991455s
Received healthy response to inference request in 1.2633681297302246s
Received healthy response to inference request in 1.2578392028808594s
Received healthy response to inference request in 1.2127182483673096s
5 requests
0 failed requests
5th percentile: 1.2125153064727783
10th percentile: 1.212566041946411
20th percentile: 1.2126675128936768
30th percentile: 1.2217424392700196
40th percentile: 1.2397908210754394
50th percentile: 1.2578392028808594
60th percentile: 1.2600507736206055
70th percentile: 1.2622623443603516
80th percentile: 1.4289278507232668
90th percentile: 1.7600472927093507
95th percentile: 1.9256070137023924
99th percentile: 2.058054790496826
mean time: 1.4075113773345946
Pipeline stage StressChecker completed in 7.71s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.08s
sao10k-l3-solana-8b-v1_v2 status is now deployed due to DeploymentManager action
sao10k-l3-solana-8b-v1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-solana-8b-v1_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-solana-8b-v1-v2 is running
Tearing down inference service sao10k-l3-solana-8b-v1-v2
Toredown service sao10k-l3-solana-8b-v1-v2
Pipeline stage ISVCDeleter completed in 3.53s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-solana-8b-v1-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-solana-8b-v1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-solana-8b-v1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-solana-8b-v1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-solana-8b-v1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-solana-8b-v1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-solana-8b-v1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-solana-8b-v1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-solana-8b-v1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-solana-8b-v1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-solana-8b-v1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-solana-8b-v1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.45s
sao10k-l3-solana-8b-v1_v2 status is now torndown due to DeploymentManager action