hastagaras-l3-8b-dahlah

developer_uid: Hastagaras

submission_id: hastagaras-l3-8b-dahlah_v1

model_name: hastagaras-l3-8b-dahlah_v1

model_group: Hastagaras/L3-8B-Dahlah

status: torndown

timestamp: 2024-05-08T07:11:38+00:00

num_battles: 22107

num_wins: 10812

celo_rating: 1160.47

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/L3-8B-Dahlah

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-l3-8b-dahlah_v1

is_internal_developer: False

language_model: Hastagaras/L3-8B-Dahlah

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-08

win_ratio: 0.4890758583254173

generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '<|eot_id|>', '###'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|begin_of_text|>### Instruction:\nIn this roleplay scenario, you will play the role of `{bot_name}`. Please respond as {bot_name} only, without deciding on `{user_name}'s` action or dialogue.\n\nYour persona as {bot_name}: {memory}\n\n", 'prompt_template': 'Your message example: {prompt}\n\n', 'bot_template': '### Response:\n{bot_name}: {message}\n\n', 'user_template': '### Input:\n{user_name}: {message}\n\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}

model_eval_status: success

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 hastagaras-l3-8b-dahlah-v1-mkmlizer
Waiting for job on hastagaras-l3-8b-dahlah-v1-mkmlizer to finish
hastagaras-l3-8b-dahlah-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-8b-dahlah-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-l3-8b-dahlah-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-8b-dahlah-v1-mkmlizer: Downloaded to shared memory in 27.529s
hastagaras-l3-8b-dahlah-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-8b-dahlah-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-8b-dahlah-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▍      | 100/291 [00:00<00:01, 100.07it/s]
Loading 0:  70%|██████▉   | 203/291 [00:02<00:00, 101.43it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 31.04it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-8b-dahlah-v1-mkmlizer: quantized model in 18.524s
hastagaras-l3-8b-dahlah-v1-mkmlizer: Processed model Hastagaras/L3-8B-Dahlah in 47.192s
hastagaras-l3-8b-dahlah-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-8b-dahlah-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-8b-dahlah-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-v1
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-v1/tokenizer_config.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-v1/special_tokens_map.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-v1/config.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-v1/tokenizer.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-v1/flywheel_model.0.safetensors
hastagaras-l3-8b-dahlah-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-8b-dahlah-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-l3-8b-dahlah-v1-mkmlizer:   warnings.warn(
hastagaras-l3-8b-dahlah-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-l3-8b-dahlah-v1-mkmlizer:   warnings.warn(
hastagaras-l3-8b-dahlah-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-l3-8b-dahlah-v1-mkmlizer:   warnings.warn(
hastagaras-l3-8b-dahlah-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-l3-8b-dahlah-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-8b-dahlah-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-8b-dahlah-v1-mkmlizer: Saving duration: 0.233s
hastagaras-l3-8b-dahlah-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.774s
hastagaras-l3-8b-dahlah-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-8b-dahlah-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-8b-dahlah-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/config.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/special_tokens_map.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/tokenizer_config.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/merges.txt
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/vocab.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/tokenizer.json
hastagaras-l3-8b-dahlah-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-v1_reward/reward.tensors
Job hastagaras-l3-8b-dahlah-v1-mkmlizer completed after 73.2s with status: succeeded
Stopping job with name hastagaras-l3-8b-dahlah-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-8b-dahlah-v1
Waiting for inference service hastagaras-l3-8b-dahlah-v1 to be ready
Inference service hastagaras-l3-8b-dahlah-v1 ready after 40.267269134521484s
Pipeline stage ISVCDeployer completed in 47.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.139385938644409s
Received healthy response to inference request in 1.0631136894226074s
Received healthy response to inference request in 1.2432329654693604s
Received healthy response to inference request in 1.060542345046997s
Received healthy response to inference request in 1.0242865085601807s
5 requests
0 failed requests
5th percentile: 1.0315376758575439
10th percentile: 1.0387888431549073
20th percentile: 1.0532911777496339
30th percentile: 1.0610566139221191
40th percentile: 1.0620851516723633
50th percentile: 1.0631136894226074
60th percentile: 1.1351613998413086
70th percentile: 1.2072091102600098
80th percentile: 1.4224635601043703
90th percentile: 1.7809247493743898
95th percentile: 1.9601553440093993
99th percentile: 2.1035398197174073
mean time: 1.306112289428711
Pipeline stage StressChecker completed in 7.14s
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-l3-8b-dahlah_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-8b-dahlah_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-8b-dahlah_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-8b-dahlah-v1 is running
Tearing down inference service hastagaras-esekembrew-ll-1360-v3
Toredown service hastagaras-esekembrew-ll-1360-v3
Pipeline stage ISVCDeleter completed in 4.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Tearing down inference service hastagaras-l3-8b-dahlah-v1
Toredown service hastagaras-l3-8b-dahlah-v1
Pipeline stage ISVCDeleter completed in 3.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-ll-1360-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-ll-1360-v3/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-ll-1360-v3_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.08s
Pipeline stage MKMLModelDeleter completed in 3.52s
hastagaras-esekembrew-ll_1360_v3 status is now torndown due to DeploymentManager action