developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-okay_v5
model_name: another-test-manual
model_group: Hastagaras/llama-3-8b-ok
status: torndown
timestamp: 2024-05-12T14:05:52+00:00
num_battles: 21727
num_wins: 11639
celo_rating: 1193.69
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-okay
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: another-test-manual
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-12
win_ratio: 0.5356929166474893
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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{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: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v5-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v5-mkmlizer to finish
hastagaras-llama-3-8b-okay-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v5-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-llama-3-8b-okay-v5-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v5-mkmlizer: Downloaded to shared memory in 13.470s
hastagaras-llama-3-8b-okay-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:01, 120.87it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 122.78it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.66it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-okay-v5-mkmlizer: quantized model in 17.698s
hastagaras-llama-3-8b-okay-v5-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 32.257s
hastagaras-llama-3-8b-okay-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v5
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v5/tokenizer_config.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v5/special_tokens_map.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v5/config.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v5/tokenizer.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v5/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v5-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-llama-3-8b-okay-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v5-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-llama-3-8b-okay-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v5-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-llama-3-8b-okay-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v5-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-llama-3-8b-okay-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v5-mkmlizer: Saving duration: 0.267s
hastagaras-llama-3-8b-okay-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.295s
hastagaras-llama-3-8b-okay-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/config.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/vocab.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/merges.txt
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v5_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v5-mkmlizer completed after 64.07s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v5-mkmlizer
Pipeline stage MKMLizer completed in 67.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v5
Waiting for inference service hastagaras-llama-3-8b-okay-v5 to be ready
Inference service hastagaras-llama-3-8b-okay-v5 ready after 50.35154151916504s
Pipeline stage ISVCDeployer completed in 57.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.325960159301758s
Received healthy response to inference request in 1.385974407196045s
Received healthy response to inference request in 1.3614585399627686s
Received healthy response to inference request in 1.425901174545288s
Received healthy response to inference request in 1.3900480270385742s
5 requests
0 failed requests
5th percentile: 1.366361713409424
10th percentile: 1.371264886856079
20th percentile: 1.3810712337493896
30th percentile: 1.3867891311645508
40th percentile: 1.3884185791015624
50th percentile: 1.3900480270385742
60th percentile: 1.4043892860412597
70th percentile: 1.4187305450439454
80th percentile: 1.6059129714965823
90th percentile: 1.96593656539917
95th percentile: 2.1459483623504636
99th percentile: 2.289957799911499
mean time: 1.5778684616088867
Pipeline stage StressChecker completed in 8.49s
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-llama-3-8b-okay_v5 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v5
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v5 is running
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v5
Toredown service hastagaras-llama-3-8b-okay-v5
Pipeline stage ISVCDeleter completed in 3.54s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v5/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v5_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.91s
hastagaras-llama-3-8b-okay_v5 status is now torndown due to DeploymentManager action