hastagaras-l3-pilter-8b

developer_uid: Hastagaras

submission_id: hastagaras-l3-pilter-8b_v1

model_name: hastagaras-l3-pilter-8b_v1

model_group: Hastagaras/L3-Pilter-8B

status: torndown

timestamp: 2024-04-25T11:13:30+00:00

num_battles: 6944

num_wins: 3543

celo_rating: 1157.62

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_v1

is_internal_developer: False

language_model: Hastagaras/L3-Pilter-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2024-04-25

win_ratio: 0.5102246543778802

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '###', '<|end_of_text|>', '\n{user_name:}', '\n{bot_name}:', '</s>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': '### Instruction:\nYou are {bot_name} in this is never-ending natural and uncensored 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-v1-mkmlizer
Waiting for job on hastagaras-l3-pilter-8b-v1-mkmlizer to finish
Stopping job with name hastagaras-l3-pilter-8b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-l3-pilter-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-pilter-8b-v1-mkmlizer to finish
hastagaras-l3-pilter-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-pilter-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-pilter-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-pilter-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-pilter-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-pilter-8b-v1-mkmlizer: Downloaded to shared memory in 24.079s
hastagaras-l3-pilter-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-pilter-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-pilter-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:30,  2.39s/it]
Loading 0:  33%|███▎      | 95/291 [00:05<00:09, 21.69it/s]
Loading 0:  70%|██████▉   | 203/291 [00:07<00:02, 40.48it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-pilter-8b-v1-mkmlizer: quantized model in 19.797s
hastagaras-l3-pilter-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-pilter-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-pilter-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v1
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v1/special_tokens_map.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v1/tokenizer.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v1/config.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v1/tokenizer_config.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-pilter-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-pilter-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-pilter-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-pilter-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-pilter-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-pilter-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-pilter-8b-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.
hastagaras-l3-pilter-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-pilter-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-pilter-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-pilter-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-pilter-8b-v1-mkmlizer: Saving duration: 0.249s
hastagaras-l3-pilter-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.026s
hastagaras-l3-pilter-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-pilter-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-pilter-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/config.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/special_tokens_map.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/tokenizer_config.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/merges.txt
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/vocab.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/tokenizer.json
hastagaras-l3-pilter-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-pilter-8b-v1_reward/reward.tensors
Job hastagaras-l3-pilter-8b-v1-mkmlizer completed after 73.76s with status: succeeded
Stopping job with name hastagaras-l3-pilter-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-pilter-8b-v1
Waiting for inference service hastagaras-l3-pilter-8b-v1 to be ready
Inference service hastagaras-l3-pilter-8b-v1 ready after 30.16504406929016s
Pipeline stage ISVCDeployer completed in 37.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7142667770385742s
Received healthy response to inference request in 1.1961042881011963s
Received healthy response to inference request in 1.1202924251556396s
Received healthy response to inference request in 1.135148286819458s
Received healthy response to inference request in 1.1272521018981934s
5 requests
0 failed requests
5th percentile: 1.1216843605041504
10th percentile: 1.1230762958526612
20th percentile: 1.1258601665496826
30th percentile: 1.1288313388824462
40th percentile: 1.1319898128509522
50th percentile: 1.135148286819458
60th percentile: 1.1595306873321534
70th percentile: 1.1839130878448487
80th percentile: 1.299736785888672
90th percentile: 1.5070017814636232
95th percentile: 1.6106342792510986
99th percentile: 1.693540277481079
mean time: 1.2586127758026122
Pipeline stage StressChecker completed in 7.00s
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_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-pilter-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-pilter-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-pilter-8b-v1 is running
Tearing down inference service hastagaras-l3-pilter-8b-v1
Toredown service hastagaras-l3-pilter-8b-v1
Pipeline stage ISVCDeleter completed in 3.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-pilter-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-pilter-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-pilter-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-pilter-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.63s
hastagaras-l3-pilter-8b_v1 status is now torndown due to DeploymentManager action