developer_uid: Hastagaras
submission_id: hastagaras-l3-kretek-8b_v1
model_name: hastagaras-l3-kretek-8b_v1
model_group: Hastagaras/L3-Kretek-8B
status: torndown
timestamp: 2024-04-24T17:04:10+00:00
num_battles: 8171
num_wins: 4511
celo_rating: 1189.74
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Kretek-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-kretek-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Kretek-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-24
win_ratio: 0.5520744094970016
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '\n{user_name}:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|start_header_id|>system<|end_header_id|>\n\nYou\'re {bot_name} in this uncensored fictional roleplay between {bot_name} and {user_name}. Write your next reply in vivid detail. Use *asterisks* for actions and "Quotes" for dialogue.\n\n{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': 'Memory: {memory}\n', 'prompt_template': '{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-kretek-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-kretek-8b-v1-mkmlizer to finish
Stopping job with name hastagaras-l3-kretek-8b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-l3-kretek-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-kretek-8b-v1-mkmlizer to finish
hastagaras-l3-kretek-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-kretek-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-kretek-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-kretek-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-kretek-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-kretek-8b-v1-mkmlizer: Downloaded to shared memory in 42.426s
hastagaras-l3-kretek-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-kretek-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-kretek-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:52,  2.46s/it]
Loading 0:  20%|██        | 59/291 [00:05<00:17, 13.10it/s]
Loading 0:  46%|████▋     | 135/291 [00:06<00:05, 28.35it/s]
Loading 0:  73%|███████▎  | 213/291 [00:07<00:01, 41.09it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-kretek-8b-v1-mkmlizer: quantized model in 21.432s
hastagaras-l3-kretek-8b-v1-mkmlizer: Processed model Hastagaras/L3-Kretek-8B in 65.409s
hastagaras-l3-kretek-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-kretek-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-kretek-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-kretek-8b-v1
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-kretek-8b-v1/config.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-kretek-8b-v1/special_tokens_map.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-kretek-8b-v1/tokenizer_config.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-kretek-8b-v1/tokenizer.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-kretek-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-kretek-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-kretek-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-kretek-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-kretek-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-kretek-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-kretek-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-kretek-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-kretek-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-kretek-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-kretek-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-kretek-8b-v1-mkmlizer: Saving duration: 0.319s
hastagaras-l3-kretek-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.629s
hastagaras-l3-kretek-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-kretek-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-kretek-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/special_tokens_map.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/tokenizer_config.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/merges.txt
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/config.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/vocab.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/tokenizer.json
hastagaras-l3-kretek-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-kretek-8b-v1_reward/reward.tensors
Job hastagaras-l3-kretek-8b-v1-mkmlizer completed after 94.19s with status: succeeded
Stopping job with name hastagaras-l3-kretek-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-kretek-8b-v1
Waiting for inference service hastagaras-l3-kretek-8b-v1 to be ready
Inference service hastagaras-l3-kretek-8b-v1 ready after 101.29633045196533s
Pipeline stage ISVCDeployer completed in 108.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2248692512512207s
Received healthy response to inference request in 1.3254656791687012s
Received healthy response to inference request in 1.5338385105133057s
Received healthy response to inference request in 1.3664264678955078s
Received healthy response to inference request in 1.323533535003662s
5 requests
0 failed requests
5th percentile: 1.3239199638366699
10th percentile: 1.3243063926696776
20th percentile: 1.3250792503356934
30th percentile: 1.3336578369140626
40th percentile: 1.3500421524047852
50th percentile: 1.3664264678955078
60th percentile: 1.433391284942627
70th percentile: 1.500356101989746
80th percentile: 1.6720446586608888
90th percentile: 1.9484569549560549
95th percentile: 2.0866631031036373
99th percentile: 2.197228021621704
mean time: 1.5548266887664794
Pipeline stage StressChecker completed in 9.20s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-kretek-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-kretek-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-kretek-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-kretek-8b-v1 is running
Tearing down inference service hastagaras-l3-kretek-8b-v1
Toredown service hastagaras-l3-kretek-8b-v1
Pipeline stage ISVCDeleter completed in 3.13s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-kretek-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-kretek-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-kretek-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-kretek-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-kretek-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-kretek-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-kretek-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-kretek-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-kretek-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-kretek-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-kretek-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-kretek-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.37s
hastagaras-l3-kretek-8b_v1 status is now torndown due to DeploymentManager action