developer_uid: Hastagaras
submission_id: hastagaras-l3-malmer-8b_v2
model_name: hastagaras-l3-malmer-8b_v2
model_group: Hastagaras/L3-Malmer-8B
status: torndown
timestamp: 2024-04-25T13:00:55+00:00
num_battles: 8840
num_wins: 4922
celo_rating: 1192.77
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Malmer-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-malmer-8b_v2
is_internal_developer: False
language_model: Hastagaras/L3-Malmer-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-25
win_ratio: 0.5567873303167421
generation_params: {'temperature': 0.88, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '###', '</s>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '### Instructions\nRespond as {bot_name} in a roleplay chat with {user_name}. Use *asterisks* for actions/gestures and `backticks` for thoughts/inner monologue.\n{memory}', 'prompt_template': '\n### Response:\n{bot_name}: {prompt}', 'bot_template': '\n### Response:\n{bot_name}: {message}', '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", 'prompt_template': "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-malmer-8b-v2-mkmlizer
Waiting for job on hastagaras-l3-malmer-8b-v2-mkmlizer to finish
hastagaras-l3-malmer-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-malmer-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-malmer-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-malmer-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-malmer-8b-v2-mkmlizer: Downloaded to shared memory in 19.006s
hastagaras-l3-malmer-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-malmer-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-malmer-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:06,  2.31s/it]
Loading 0:  35%|███▌      | 103/291 [00:05<00:07, 24.17it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:02, 41.11it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-malmer-8b-v2-mkmlizer: Processed model Hastagaras/L3-Malmer-8B in 38.999s
hastagaras-l3-malmer-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-malmer-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-malmer-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v2
hastagaras-l3-malmer-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v2/config.json
hastagaras-l3-malmer-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v2/special_tokens_map.json
hastagaras-l3-malmer-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v2/tokenizer_config.json
hastagaras-l3-malmer-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v2/tokenizer.json
hastagaras-l3-malmer-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v2/flywheel_model.0.safetensors
hastagaras-l3-malmer-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-malmer-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-malmer-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-malmer-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-malmer-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-malmer-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-malmer-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-malmer-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-malmer-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-malmer-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v2_reward/reward.tensors
Job hastagaras-l3-malmer-8b-v2-mkmlizer completed after 63.65s with status: succeeded
Stopping job with name hastagaras-l3-malmer-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 69.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.21s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-malmer-8b-v2
Waiting for inference service hastagaras-l3-malmer-8b-v2 to be ready
Inference service hastagaras-l3-malmer-8b-v2 ready after 40.25674843788147s
Pipeline stage ISVCDeployer completed in 49.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.10314679145813s
Received healthy response to inference request in 1.2758119106292725s
Received healthy response to inference request in 1.2745354175567627s
Received healthy response to inference request in 1.2596051692962646s
Received healthy response to inference request in 1.297325849533081s
5 requests
0 failed requests
5th percentile: 1.2625912189483643
10th percentile: 1.2655772686004638
20th percentile: 1.271549367904663
30th percentile: 1.2747907161712646
40th percentile: 1.2753013134002686
50th percentile: 1.2758119106292725
60th percentile: 1.284417486190796
70th percentile: 1.2930230617523193
80th percentile: 1.458490037918091
90th percentile: 1.7808184146881105
95th percentile: 1.94198260307312
99th percentile: 2.070913953781128
mean time: 1.4420850276947021
Pipeline stage StressChecker completed in 7.86s
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-malmer-8b_v2 status is now deployed due to DeploymentManager action
hastagaras-l3-malmer-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-malmer-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-malmer-8b-v2 is running
Tearing down inference service hastagaras-l3-malmer-8b-v2
Toredown service hastagaras-l3-malmer-8b-v2
Pipeline stage ISVCDeleter completed in 3.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-malmer-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-malmer-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.38s
hastagaras-l3-malmer-8b_v2 status is now torndown due to DeploymentManager action