developer_uid: Hastagaras
submission_id: hastagaras-markites-llama3-8b_v4
model_name: llama-format
model_group: Hastagaras/Markites-llam
status: torndown
timestamp: 2024-05-16T21:32:42+00:00
num_battles: 25075
num_wins: 13653
celo_rating: 1199.07
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Markites-llama3-8b
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: llama-format
is_internal_developer: False
language_model: Hastagaras/Markites-llama3-8b
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-16
win_ratio: 0.5444865403788635
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', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", 'prompt_template': 'Example: {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_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\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-markites-llama3-8b-v4-mkmlizer
Waiting for job on hastagaras-markites-llama3-8b-v4-mkmlizer to finish
hastagaras-markites-llama3-8b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-markites-llama3-8b-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║                                                                     ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║                                                                     ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║                                                                     ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ║                                                                     ║
hastagaras-markites-llama3-8b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-markites-llama3-8b-v4-mkmlizer: Downloaded to shared memory in 14.750s
hastagaras-markites-llama3-8b-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-markites-llama3-8b-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-markites-llama3-8b-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 207.19it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 203.09it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 214.78it/s]
Loading 0:  30%|███       | 88/291 [00:00<00:02, 94.40it/s] 
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 118.94it/s]
Loading 0:  45%|████▍     | 130/291 [00:00<00:01, 132.98it/s]
Loading 0:  52%|█████▏    | 150/291 [00:01<00:00, 148.48it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 167.57it/s]
Loading 0:  66%|██████▋   | 193/291 [00:01<00:00, 104.67it/s]
Loading 0:  74%|███████▍  | 216/291 [00:01<00:00, 127.10it/s]
Loading 0:  82%|████████▏ | 238/291 [00:01<00:00, 144.91it/s]
Loading 0:  89%|████████▉ | 260/291 [00:01<00:00, 161.27it/s]
Loading 0:  97%|█████████▋| 282/291 [00:01<00:00, 171.13it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-markites-llama3-8b-v4-mkmlizer: quantized model in 17.083s
hastagaras-markites-llama3-8b-v4-mkmlizer: Processed model Hastagaras/Markites-llama3-8b in 32.855s
hastagaras-markites-llama3-8b-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-markites-llama3-8b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-markites-llama3-8b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v4
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v4/tokenizer_config.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v4/config.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v4/special_tokens_map.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v4/tokenizer.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v4/flywheel_model.0.safetensors
hastagaras-markites-llama3-8b-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v4-mkmlizer:   warnings.warn(
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v4-mkmlizer:   warnings.warn(
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v4-mkmlizer:   warnings.warn(
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-markites-llama3-8b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-markites-llama3-8b-v4-mkmlizer: Saving duration: 0.231s
hastagaras-markites-llama3-8b-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.431s
hastagaras-markites-llama3-8b-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-markites-llama3-8b-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-markites-llama3-8b-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/tokenizer_config.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/config.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/special_tokens_map.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/merges.txt
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/vocab.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/tokenizer.json
hastagaras-markites-llama3-8b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v4_reward/reward.tensors
Job hastagaras-markites-llama3-8b-v4-mkmlizer completed after 63.04s with status: succeeded
Stopping job with name hastagaras-markites-llama3-8b-v4-mkmlizer
Pipeline stage MKMLizer completed in 66.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-markites-llama3-8b-v4
Waiting for inference service hastagaras-markites-llama3-8b-v4 to be ready
Inference service hastagaras-markites-llama3-8b-v4 ready after 30.203880786895752s
Pipeline stage ISVCDeployer completed in 37.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1042656898498535s
Received healthy response to inference request in 1.3535921573638916s
Received healthy response to inference request in 1.3246469497680664s
Received healthy response to inference request in 1.284163475036621s
Received healthy response to inference request in 1.371253490447998s
5 requests
0 failed requests
5th percentile: 1.2922601699829102
10th percentile: 1.3003568649291992
20th percentile: 1.3165502548217773
30th percentile: 1.3304359912872314
40th percentile: 1.3420140743255615
50th percentile: 1.3535921573638916
60th percentile: 1.3606566905975341
70th percentile: 1.3677212238311767
80th percentile: 1.5178559303283692
90th percentile: 1.8110608100891115
95th percentile: 1.9576632499694824
99th percentile: 2.074945201873779
mean time: 1.4875843524932861
Pipeline stage StressChecker completed in 8.07s
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-markites-llama3-8b_v4 status is now deployed due to DeploymentManager action
hastagaras-markites-llama3-8b_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-markites-llama3-8b_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-markites-llama3-8b-v4 is running
Tearing down inference service hastagaras-markites-llama3-8b-v4
Toredown service hastagaras-markites-llama3-8b-v4
Pipeline stage ISVCDeleter completed in 5.77s
admin requested tearing down of hyperblaze-l3-8b-soliloq_2337_v5
Running pipeline stage MKMLModelDeleter
Running pipeline stage ISVCDeleter
Cleaning model data from S3
Checking if service hyperblaze-l3-8b-soliloq-2337-v5 is running
Cleaning model data from model cache
Deleting key hastagaras-markites-llama3-8b-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-llama3-8b-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-markites-llama3-8b-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-llama3-8b-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-llama3-8b-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-markites-llama3-8b-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-llama3-8b-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-markites-llama3-8b-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-markites-llama3-8b-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-llama3-8b-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-llama3-8b-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-llama3-8b-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.53s
hastagaras-markites-llama3-8b_v4 status is now torndown due to DeploymentManager action