submission_id: hastagaras-llama3-8b-dar_7411_v5
developer_uid: Hastagaras
best_of: 16
celo_rating: 1174.18
display_name: drktune-retry-kto2
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nPlay the role of {bot_name} in this roleplay chat between `{bot_name}` and `{user_name}`. {bot_name}'s persona: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {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': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 35, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama3-8b-darktune-KTO
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: pending
model_group: Hastagaras/llama3-8b-dar
model_name: drktune-retry-kto2
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama3-8b-darktune-KTO
model_size: 8B
num_battles: 15209
num_wins: 7514
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-11T04:25:49+00:00
us_pacific_date: 2024-05-10
win_ratio: 0.4940495759090012
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-dar-7411-v5-mkmlizer
Waiting for job on hastagaras-llama3-8b-dar-7411-v5-mkmlizer to finish
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-dar-7411-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-llama3-8b-dar-7411-v5-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Downloaded to shared memory in 15.159s
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 139.27it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 38.22it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: quantized model in 16.963s
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Processed model Hastagaras/llama3-8b-darktune-KTO in 33.130s
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v5
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v5/special_tokens_map.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v5/tokenizer_config.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v5/config.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v5/tokenizer.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v5/flywheel_model.0.safetensors
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-dar-7411-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-llama3-8b-dar-7411-v5-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-dar-7411-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-llama3-8b-dar-7411-v5-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-dar-7411-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-llama3-8b-dar-7411-v5-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-dar-7411-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-llama3-8b-dar-7411-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Saving duration: 0.222s
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 2.985s
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/config.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/special_tokens_map.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/tokenizer_config.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/merges.txt
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/vocab.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/tokenizer.json
hastagaras-llama3-8b-dar-7411-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v5_reward/reward.tensors
Job hastagaras-llama3-8b-dar-7411-v5-mkmlizer completed after 62.69s with status: succeeded
Stopping job with name hastagaras-llama3-8b-dar-7411-v5-mkmlizer
Pipeline stage MKMLizer completed in 65.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-dar-7411-v5
Waiting for inference service hastagaras-llama3-8b-dar-7411-v5 to be ready
Inference service hastagaras-llama3-8b-dar-7411-v5 ready after 30.222615242004395s
Pipeline stage ISVCDeployer completed in 36.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5029704570770264s
Received healthy response to inference request in 1.3220958709716797s
Received healthy response to inference request in 1.2700221538543701s
Received healthy response to inference request in 1.391937017440796s
Received healthy response to inference request in 1.4234988689422607s
5 requests
0 failed requests
5th percentile: 1.280436897277832
10th percentile: 1.290851640701294
20th percentile: 1.3116811275482179
30th percentile: 1.336064100265503
40th percentile: 1.3640005588531494
50th percentile: 1.391937017440796
60th percentile: 1.4045617580413818
70th percentile: 1.4171864986419678
80th percentile: 1.639393186569214
90th percentile: 2.0711818218231204
95th percentile: 2.287076139450073
99th percentile: 2.459791593551636
mean time: 1.5821048736572265
Pipeline stage StressChecker completed in 9.36s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.12s
hastagaras-llama3-8b-dar_7411_v5 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-dar_7411_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-dar_7411_v5
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-dar-7411-v5 is running
Tearing down inference service hastagaras-llama3-8b-dar-7411-v5
Toredown service hastagaras-llama3-8b-dar-7411-v5
Pipeline stage ISVCDeleter completed in 7.16s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7411-v5/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.84s
hastagaras-llama3-8b-dar_7411_v5 status is now torndown due to DeploymentManager action