developer_uid: Hastagaras
submission_id: hastagaras-llama3-sebats-8b_v2
model_name: hastagaras-llama3-sebats-8b_v2
model_group: Hastagaras/Llama3-Sebats
status: torndown
timestamp: 2024-04-25T06:29:44+00:00
num_battles: 5853
num_wins: 3204
celo_rating: 1184.41
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Llama3-Sebats-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-llama3-sebats-8b_v2
is_internal_developer: False
language_model: Hastagaras/Llama3-Sebats-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-24
win_ratio: 0.5474115838031779
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n{user_name}', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nThis is a roleplay between {bot_name} and {user_name}. Actions, gestures or narrations are described between asterisks, e.g. *waves hello* or *blushes slightly*. Always insert your thoughts or inner monologue inside backticks, e.g. `Hmm, she's pretty cute,`. Imagine you're {bot_name} and write your reply based on the below information.\n\n{memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>{user_name}<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-sebats-8b-v2-mkmlizer
Waiting for job on hastagaras-llama3-sebats-8b-v2-mkmlizer to finish
hastagaras-llama3-sebats-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-sebats-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-sebats-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-llama3-sebats-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-sebats-8b-v2-mkmlizer: Downloaded to shared memory in 19.390s
hastagaras-llama3-sebats-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-sebats-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-sebats-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:00, 148.81it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 38.45it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-sebats-8b-v2-mkmlizer: quantized model in 16.838s
hastagaras-llama3-sebats-8b-v2-mkmlizer: Processed model Hastagaras/Llama3-Sebats-8B in 37.214s
hastagaras-llama3-sebats-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-sebats-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-sebats-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v2
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v2/tokenizer_config.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v2/special_tokens_map.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v2/config.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v2/tokenizer.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v2/flywheel_model.0.safetensors
hastagaras-llama3-sebats-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-sebats-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-llama3-sebats-8b-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-sebats-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-llama3-sebats-8b-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-sebats-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-llama3-sebats-8b-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-sebats-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-llama3-sebats-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-sebats-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-sebats-8b-v2-mkmlizer: Saving duration: 0.244s
hastagaras-llama3-sebats-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.793s
hastagaras-llama3-sebats-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-sebats-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-sebats-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/config.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/tokenizer_config.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/special_tokens_map.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/vocab.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/merges.txt
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/tokenizer.json
hastagaras-llama3-sebats-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v2_reward/reward.tensors
Job hastagaras-llama3-sebats-8b-v2-mkmlizer completed after 177.0s with status: succeeded
Stopping job with name hastagaras-llama3-sebats-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 182.98s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-sebats-8b-v2
Waiting for inference service hastagaras-llama3-sebats-8b-v2 to be ready
Inference service hastagaras-llama3-sebats-8b-v2 ready after 30.194534063339233s
Pipeline stage ISVCDeployer completed in 37.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1461403369903564s
Received healthy response to inference request in 1.29909348487854s
Received healthy response to inference request in 1.2677998542785645s
Received healthy response to inference request in 1.3401587009429932s
Received healthy response to inference request in 1.2996220588684082s
5 requests
0 failed requests
5th percentile: 1.2740585803985596
10th percentile: 1.2803173065185547
20th percentile: 1.292834758758545
30th percentile: 1.2991991996765138
40th percentile: 1.299410629272461
50th percentile: 1.2996220588684082
60th percentile: 1.3158367156982422
70th percentile: 1.3320513725280763
80th percentile: 1.501355028152466
90th percentile: 1.8237476825714112
95th percentile: 1.9849440097808837
99th percentile: 2.113901071548462
mean time: 1.4705628871917724
Pipeline stage StressChecker completed in 7.98s
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-llama3-sebats-8b_v2 status is now deployed due to DeploymentManager action
hastagaras-llama3-sebats-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-sebats-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-sebats-8b-v2 is running
admin requested tearing down of hastagaras-lm3-8b-lightu_8626_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-lightu-8626-v1 is running
Tearing down inference service hastagaras-llama3-sebats-8b-v2
Toredown service hastagaras-llama3-sebats-8b-v2
Tearing down inference service hastagaras-lm3-8b-lightu-8626-v1
Pipeline stage ISVCDeleter completed in 13.42s
Running pipeline stage MKMLModelDeleter
Toredown service hastagaras-lm3-8b-lightu-8626-v1
Pipeline stage ISVCDeleter completed in 12.04s
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
Cleaning model data from model cache
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-sebats-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from model cache
Deleting key hastagaras-llama3-sebats-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightu-8626-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.67s
Pipeline stage MKMLModelDeleter completed in 3.38s
hastagaras-lm3-8b-lightu_8626_v1 status is now torndown due to DeploymentManager action
hastagaras-llama3-sebats-8b_v2 status is now torndown due to DeploymentManager action