developer_uid: Hastagaras
submission_id: hastagaras-l3-linting-8b_v1
model_name: hastagaras-l3-linting-8b_v1
model_group: Hastagaras/l3-linting-8b
status: torndown
timestamp: 2024-04-30T00:41:11+00:00
num_battles: 5633
num_wins: 3038
celo_rating: 1184.77
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/l3-linting-8b
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: hastagaras-l3-linting-8b_v1
is_internal_developer: False
language_model: Hastagaras/l3-linting-8b
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-29
win_ratio: 0.5393218533641044
generation_params: {'temperature': 0.85, 'top_p': 0.9, '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}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}\n\n", '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}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{bot_name}: {prompt}\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 hastagaras-l3-linting-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-linting-8b-v1-mkmlizer to finish
hastagaras-l3-linting-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-linting-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-linting-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-linting-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-linting-8b-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.
hastagaras-l3-linting-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-linting-8b-v1-mkmlizer: Downloaded to shared memory in 37.670s
hastagaras-l3-linting-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-linting-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-linting-8b-v1-mkmlizer: quantized model in 18.270s
hastagaras-l3-linting-8b-v1-mkmlizer: Processed model Hastagaras/l3-linting-8b in 57.058s
hastagaras-l3-linting-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-linting-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-linting-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v1
hastagaras-l3-linting-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v1/config.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v1/special_tokens_map.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v1/tokenizer_config.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v1/tokenizer.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-linting-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-linting-8b-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.
hastagaras-l3-linting-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-linting-8b-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.
hastagaras-l3-linting-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-linting-8b-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()
hastagaras-l3-linting-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-linting-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-linting-8b-v1-mkmlizer: Saving duration: 0.244s
hastagaras-l3-linting-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.101s
hastagaras-l3-linting-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-linting-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-linting-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/tokenizer_config.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/config.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/vocab.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/merges.txt
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/special_tokens_map.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/tokenizer.json
hastagaras-l3-linting-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-linting-8b-v1_reward/reward.tensors
Job hastagaras-l3-linting-8b-v1-mkmlizer completed after 83.21s with status: succeeded
Stopping job with name hastagaras-l3-linting-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-linting-8b-v1
Waiting for inference service hastagaras-l3-linting-8b-v1 to be ready
Inference service hastagaras-l3-linting-8b-v1 ready after 40.2787139415741s
Pipeline stage ISVCDeployer completed in 47.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1945419311523438s
Received healthy response to inference request in 1.3471815586090088s
Received healthy response to inference request in 1.299870252609253s
Received healthy response to inference request in 1.2709200382232666s
Received healthy response to inference request in 1.3438279628753662s
5 requests
0 failed requests
5th percentile: 1.276710081100464
10th percentile: 1.2825001239776612
20th percentile: 1.2940802097320556
30th percentile: 1.3086617946624757
40th percentile: 1.326244878768921
50th percentile: 1.3438279628753662
60th percentile: 1.3451694011688233
70th percentile: 1.3465108394622802
80th percentile: 1.5166536331176759
90th percentile: 1.8555977821350098
95th percentile: 2.0250698566436767
99th percentile: 2.1606475162506102
mean time: 1.4912683486938476
Pipeline stage StressChecker completed in 8.05s
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
hastagaras-l3-linting-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-linting-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-linting-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-linting-8b-v1 is running
Tearing down inference service hastagaras-l3-linting-8b-v1
Toredown service hastagaras-l3-linting-8b-v1
Pipeline stage ISVCDeleter completed in 4.51s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-linting-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-linting-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-linting-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-linting-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-linting-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-linting-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-linting-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-linting-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-linting-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-linting-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-linting-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-linting-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.47s
hastagaras-l3-linting-8b_v1 status is now torndown due to DeploymentManager action