developer_uid: sao10k
submission_id: sao10k-l3-8b-chara-v1-alpha_v1
model_name: Chara-User-Asst
model_group: Sao10K/L3-8B-Chara-v1-Al
status: torndown
timestamp: 2024-06-30T10:41:07+00:00
num_battles: 31106
num_wins: 15711
celo_rating: 1177.17
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-8B-Chara-v1-Alpha
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: Chara-User-Asst
is_internal_developer: False
language_model: Sao10K/L3-8B-Chara-v1-Alpha
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-30
win_ratio: 0.5050794059023983
generation_params: {'temperature': 1.4, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, '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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{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\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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer
Waiting for job on sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer to finish
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-chara-v1-alpha-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-l3-8b-chara-v1-alpha-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Downloaded to shared memory in 30.944s
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 71.93it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 90.96it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 133.46it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: quantized model in 23.462s
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Processed model Sao10K/L3-8B-Chara-v1-Alpha in 57.001s
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v1
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v1/config.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v1/special_tokens_map.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v1/tokenizer_config.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v1/tokenizer.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v1/flywheel_model.0.safetensors
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-8b-chara-v1-alpha-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-l3-8b-chara-v1-alpha-v1-mkmlizer:   warnings.warn(
sao10k-l3-8b-chara-v1-alpha-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-l3-8b-chara-v1-alpha-v1-mkmlizer:   warnings.warn(
sao10k-l3-8b-chara-v1-alpha-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-l3-8b-chara-v1-alpha-v1-mkmlizer:   warnings.warn(
sao10k-l3-8b-chara-v1-alpha-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-l3-8b-chara-v1-alpha-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Saving duration: 0.411s
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.063s
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/special_tokens_map.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/tokenizer_config.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/merges.txt
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/config.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/vocab.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/tokenizer.json
sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v1_reward/reward.tensors
Job sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer completed after 84.08s with status: succeeded
Stopping job with name sao10k-l3-8b-chara-v1-alpha-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-8b-chara-v1-alpha-v1
Waiting for inference service sao10k-l3-8b-chara-v1-alpha-v1 to be ready
Inference service sao10k-l3-8b-chara-v1-alpha-v1 ready after 40.1954448223114s
Pipeline stage ISVCDeployer completed in 47.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.076479434967041s
Received healthy response to inference request in 1.3294777870178223s
Received healthy response to inference request in 1.3905243873596191s
Received healthy response to inference request in 1.214226245880127s
Received healthy response to inference request in 1.2230901718139648s
5 requests
0 failed requests
5th percentile: 1.2159990310668944
10th percentile: 1.2177718162536622
20th percentile: 1.2213173866271974
30th percentile: 1.2443676948547364
40th percentile: 1.2869227409362793
50th percentile: 1.3294777870178223
60th percentile: 1.353896427154541
70th percentile: 1.3783150672912599
80th percentile: 1.5277153968811037
90th percentile: 1.8020974159240724
95th percentile: 1.9392884254455565
99th percentile: 2.049041233062744
mean time: 1.4467596054077148
Pipeline stage StressChecker completed in 8.04s
sao10k-l3-8b-chara-v1-alpha_v1 status is now deployed due to DeploymentManager action
sao10k-l3-8b-chara-v1-alpha_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-8b-chara-v1-alpha_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-8b-chara-v1-alpha-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.49s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-8b-chara-v1-alpha-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
sao10k-l3-8b-chara-v1-alpha_v1 status is now torndown due to DeploymentManager action