developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-okay_v3
model_name: test-format-okay
model_group: Hastagaras/llama-3-8b-ok
status: torndown
timestamp: 2024-05-12T06:38:25+00:00
num_battles: 9611
num_wins: 5740
celo_rating: 1236.7
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: 112
display_name: test-format-okay
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-11
win_ratio: 0.5972323379461034
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}
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}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v3-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v3-mkmlizer to finish
hastagaras-llama-3-8b-okay-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v3-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-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v3-mkmlizer: Downloaded to shared memory in 14.335s
hastagaras-llama-3-8b-okay-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  40%|███▉      | 116/291 [00:01<00:01, 115.93it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 129.73it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.88it/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-v3-mkmlizer: quantized model in 17.587s
hastagaras-llama-3-8b-okay-v3-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 32.996s
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v3/special_tokens_map.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v3/config.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v3/tokenizer.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v3/tokenizer_config.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v3/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v3-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-v3-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v3-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-v3-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v3-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-v3-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v3-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-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v3-mkmlizer: Saving duration: 0.249s
hastagaras-llama-3-8b-okay-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.384s
hastagaras-llama-3-8b-okay-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/config.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/merges.txt
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/vocab.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v3_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v3-mkmlizer completed after 62.45s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v3-mkmlizer
Pipeline stage MKMLizer completed in 66.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v3
Waiting for inference service hastagaras-llama-3-8b-okay-v3 to be ready
Inference service hastagaras-llama-3-8b-okay-v3 ready after 30.185335159301758s
Pipeline stage ISVCDeployer completed in 37.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9096763134002686s
Received healthy response to inference request in 2.0306036472320557s
Received healthy response to inference request in 1.965876817703247s
Received healthy response to inference request in 2.067517042160034s
Received healthy response to inference request in 2.0213546752929688s
5 requests
0 failed requests
5th percentile: 1.9769723892211915
10th percentile: 1.9880679607391358
20th percentile: 2.0102591037750246
30th percentile: 2.023204469680786
40th percentile: 2.026904058456421
50th percentile: 2.0306036472320557
60th percentile: 2.045369005203247
70th percentile: 2.0601343631744387
80th percentile: 2.235948896408081
90th percentile: 2.572812604904175
95th percentile: 2.7412444591522216
99th percentile: 2.875989942550659
mean time: 2.199005699157715
Pipeline stage StressChecker completed in 11.59s
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-llama-3-8b-okay_v3 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v3 is running
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v3
Toredown service hastagaras-llama-3-8b-okay-v3
Pipeline stage ISVCDeleter completed in 4.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.40s
hastagaras-llama-3-8b-okay_v3 status is now torndown due to DeploymentManager action