submission_id: hastagaras-llama-3-8b-okay_v4
developer_uid: Hastagaras
best_of: 16
celo_rating: 1237.21
display_name: just-to-make-sure
family_friendly_score: 0.0
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}
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': 112}
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
max_input_tokens: 512
max_output_tokens: 112
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
model_name: just-to-make-sure
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-okay
model_size: 8B
num_battles: 15987
num_wins: 9554
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-12T08:58:00+00:00
us_pacific_date: 2024-05-12
win_ratio: 0.5976105585788453
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v4-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v4-mkmlizer to finish
hastagaras-llama-3-8b-okay-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v4-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-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v4-mkmlizer: Downloaded to shared memory in 22.700s
hastagaras-llama-3-8b-okay-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 128.33it/s]
Loading 0:  93%|█████████▎| 270/291 [00:02<00:00, 135.58it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 29.07it/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-v4-mkmlizer: quantized model in 17.532s
hastagaras-llama-3-8b-okay-v4-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 41.374s
hastagaras-llama-3-8b-okay-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v4
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v4/config.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v4/tokenizer_config.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v4/special_tokens_map.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v4/tokenizer.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v4/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v4-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-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v4-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-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v4-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-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v4-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-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v4-mkmlizer: Saving duration: 0.235s
hastagaras-llama-3-8b-okay-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.244s
hastagaras-llama-3-8b-okay-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward/config.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward/merges.txt
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward/vocab.json
hastagaras-llama-3-8b-okay-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v4_reward/tokenizer.json
Job hastagaras-llama-3-8b-okay-v4-mkmlizer completed after 73.01s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v4-mkmlizer
Pipeline stage MKMLizer completed in 75.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v4
Waiting for inference service hastagaras-llama-3-8b-okay-v4 to be ready
Inference service hastagaras-llama-3-8b-okay-v4 ready after 30.154797792434692s
Pipeline stage ISVCDeployer completed in 36.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.089055299758911s
Received healthy response to inference request in 2.412027359008789s
Received healthy response to inference request in 1.9875435829162598s
Received healthy response to inference request in 2.0831499099731445s
Received healthy response to inference request in 1.9709515571594238s
5 requests
0 failed requests
5th percentile: 1.974269962310791
10th percentile: 1.9775883674621582
20th percentile: 1.9842251777648925
30th percentile: 2.006664848327637
40th percentile: 2.0449073791503904
50th percentile: 2.0831499099731445
60th percentile: 2.2147008895874025
70th percentile: 2.34625186920166
80th percentile: 2.5474329471588137
90th percentile: 2.818244123458862
95th percentile: 2.9536497116088865
99th percentile: 3.0619741821289064
mean time: 2.308545541763306
Pipeline stage StressChecker completed in 12.23s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-okay_v4 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v4 status is now inactive due to auto deactivation removed underperforming models
hastagaras-llama-3-8b-okay_v4 status is now deployed due to admin request
hastagaras-llama-3-8b-okay_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v4 is running
Tearing down inference service hastagaras-llama-3-8b-okay-v4
Toredown service hastagaras-llama-3-8b-okay-v4
Pipeline stage ISVCDeleter completed in 4.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.33s
hastagaras-llama-3-8b-okay_v4 status is now torndown due to DeploymentManager action