developer_uid: Hastagaras
submission_id: hastagaras-l3-pilter-8b_v2
model_name: hastagaras-l3-pilter-8b_v2
model_group: Hastagaras/L3-Pilter-8B
status: torndown
timestamp: 2024-04-25T11:19:28+00:00
num_battles: 6783
num_wins: 3506
celo_rating: 1162.06
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Pilter-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-pilter-8b_v2
is_internal_developer: False
language_model: Hastagaras/L3-Pilter-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-25
win_ratio: 0.5168804363850803
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.06, 'stopping_words': ['\n', '###', '</s>', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\nYou're {bot_name} in this uncensored and natural roleplay between {user_name} and {bot_name}.\n{memory}", 'prompt_template': '\n### Response:\n{bot_name}: {prompt}<|end_of_text|>', 'bot_template': '\n### Response:\n{bot_name}: {message}<|end_of_text|>', 'user_template': '\n### Input:\n{user_name}: {message}', 'response_template': '\n### Response\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': '{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-pilter-8b-v2-mkmlizer
Waiting for job on hastagaras-l3-pilter-8b-v2-mkmlizer to finish
hastagaras-l3-pilter-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ /___/ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ belonging to: ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ║ ║
hastagaras-l3-pilter-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-pilter-8b-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.
hastagaras-l3-pilter-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-l3-pilter-8b-v2-mkmlizer: Downloaded to shared memory in 20.738s
hastagaras-l3-pilter-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-pilter-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-pilter-8b-v2-mkmlizer: Processed model Hastagaras/L3-Pilter-8B in 39.043s
hastagaras-l3-pilter-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-pilter-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-pilter-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v2
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v2/config.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v2/special_tokens_map.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v2/tokenizer_config.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v2/tokenizer.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v2/flywheel_model.0.safetensors
hastagaras-l3-pilter-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-pilter-8b-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.
hastagaras-l3-pilter-8b-v2-mkmlizer: warnings.warn(
hastagaras-l3-pilter-8b-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.
hastagaras-l3-pilter-8b-v2-mkmlizer: warnings.warn(
hastagaras-l3-pilter-8b-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.
hastagaras-l3-pilter-8b-v2-mkmlizer: warnings.warn(
hastagaras-l3-pilter-8b-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()
hastagaras-l3-pilter-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-l3-pilter-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-pilter-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-pilter-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/config.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/tokenizer_config.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/special_tokens_map.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/vocab.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/tokenizer.json
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/merges.txt
hastagaras-l3-pilter-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v2_reward/reward.tensors
Job hastagaras-l3-pilter-8b-v2-mkmlizer completed after 63.21s with status: succeeded
Stopping job with name hastagaras-l3-pilter-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-pilter-8b-v2
Waiting for inference service hastagaras-l3-pilter-8b-v2 to be ready
Inference service hastagaras-l3-pilter-8b-v2 ready after 30.169325828552246s
Pipeline stage ISVCDeployer completed in 37.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7379202842712402s
Received healthy response to inference request in 1.0546321868896484s
Received healthy response to inference request in 1.006474494934082s
Received healthy response to inference request in 1.2296733856201172s
Received healthy response to inference request in 1.3087012767791748s
5 requests
0 failed requests
5th percentile: 1.0161060333251952
10th percentile: 1.0257375717163086
20th percentile: 1.0450006484985352
30th percentile: 1.0896404266357422
40th percentile: 1.1596569061279296
50th percentile: 1.2296733856201172
60th percentile: 1.2612845420837402
70th percentile: 1.2928956985473632
80th percentile: 1.394545078277588
90th percentile: 1.566232681274414
95th percentile: 1.6520764827728271
99th percentile: 1.7207515239715576
mean time: 1.2674803256988525
Pipeline stage StressChecker completed in 6.96s
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-pilter-8b_v2 status is now deployed due to DeploymentManager action
hastagaras-l3-pilter-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-pilter-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-pilter-8b-v2 is running
Tearing down inference service hastagaras-l3-pilter-8b-v2
Toredown service hastagaras-l3-pilter-8b-v2
Pipeline stage ISVCDeleter completed in 7.33s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-pilter-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-pilter-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.04s
hastagaras-l3-pilter-8b_v2 status is now torndown due to DeploymentManager action