hastagaras-l3-uduts-8b

developer_uid: Hastagaras

submission_id: hastagaras-l3-uduts-8b_v2

model_name: hastagaras-l3-uduts-8b_v2

model_group: Hastagaras/L3-Uduts-8B

status: torndown

timestamp: 2024-04-25T09:17:48+00:00

num_battles: 6285

num_wins: 3494

celo_rating: 1189.67

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/L3-Uduts-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-uduts-8b_v2

is_internal_developer: False

language_model: Hastagaras/L3-Uduts-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2024-04-25

win_ratio: 0.5559268098647574

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

formatter: {'memory_template': "### Instruction:\nYou're {bot_name} in this is a never-ending roleplay between {user_name} and {bot_name}. Gestures and other non-verbal actions are written between asterisks (for example, *waves hello* or *moves closer*). Write your next reply as {bot_name}, based on the following information:\n\n{memory}\n", 'prompt_template': '### Response:\n{bot_name}: {prompt}<|end_of_text|>\n', 'bot_template': '### Response:\n{bot_name}: {message}<|end_of_text|>\n', 'user_template': '### Input:\n{user_name}: {message}\n', 'response_template': '### 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': '{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-uduts-8b-v2-mkmlizer
Waiting for job on hastagaras-l3-uduts-8b-v2-mkmlizer to finish
hastagaras-l3-uduts-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-uduts-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-uduts-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-uduts-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-uduts-8b-v2-mkmlizer: Downloaded to shared memory in 21.417s
hastagaras-l3-uduts-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-uduts-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-uduts-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  35%|███▌      | 102/291 [00:01<00:01, 102.00it/s]
Loading 0:  70%|██████▉   | 203/291 [00:02<00:00, 101.08it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.00it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-uduts-8b-v2-mkmlizer: quantized model in 19.631s
hastagaras-l3-uduts-8b-v2-mkmlizer: Processed model Hastagaras/L3-Uduts-8B in 42.019s
hastagaras-l3-uduts-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-uduts-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-uduts-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v2
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v2/config.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v2/special_tokens_map.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v2/tokenizer_config.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v2/tokenizer.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v2/flywheel_model.0.safetensors
hastagaras-l3-uduts-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-uduts-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-uduts-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-uduts-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-uduts-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-uduts-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-uduts-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-uduts-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-uduts-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-uduts-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-uduts-8b-v2-mkmlizer: Saving duration: 0.222s
hastagaras-l3-uduts-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.642s
hastagaras-l3-uduts-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-uduts-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-uduts-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/config.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/special_tokens_map.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/tokenizer_config.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/merges.txt
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/vocab.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/tokenizer.json
hastagaras-l3-uduts-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v2_reward/reward.tensors
Job hastagaras-l3-uduts-8b-v2-mkmlizer completed after 63.08s with status: succeeded
Stopping job with name hastagaras-l3-uduts-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 69.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-uduts-8b-v2
Waiting for inference service hastagaras-l3-uduts-8b-v2 to be ready
Inference service hastagaras-l3-uduts-8b-v2 ready after 30.176470279693604s
Pipeline stage ISVCDeployer completed in 38.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.123070240020752s
Received healthy response to inference request in 1.2994871139526367s
Received healthy response to inference request in 1.2811064720153809s
Received healthy response to inference request in 1.2713899612426758s
Received healthy response to inference request in 1.269881010055542s
5 requests
0 failed requests
5th percentile: 1.2701828002929687
10th percentile: 1.2704845905303954
20th percentile: 1.271088171005249
30th percentile: 1.2733332633972168
40th percentile: 1.277219867706299
50th percentile: 1.2811064720153809
60th percentile: 1.2884587287902831
70th percentile: 1.2958109855651856
80th percentile: 1.46420373916626
90th percentile: 1.793636989593506
95th percentile: 1.9583536148071288
99th percentile: 2.0901269149780273
mean time: 1.4489869594573974
Pipeline stage StressChecker completed in 7.96s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-uduts-8b_v2 status is now deployed due to DeploymentManager action
hastagaras-l3-uduts-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-uduts-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-uduts-8b-v2 is running
Tearing down inference service hastagaras-l3-uduts-8b-v2
Toredown service hastagaras-l3-uduts-8b-v2
Pipeline stage ISVCDeleter completed in 3.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-uduts-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-uduts-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.90s
hastagaras-l3-uduts-8b_v2 status is now torndown due to DeploymentManager action