developer_uid: Hastagaras
submission_id: hastagaras-l3-cukai-8b-dpo_v2
model_name: hastagaras-l3-cukai-8b-dpo_v2
model_group: Hastagaras/L3-Cukai-8B-D
status: torndown
timestamp: 2024-04-26T04:01:36+00:00
num_battles: 5729
num_wins: 3342
celo_rating: 1209.17
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Cukai-8B-DPO
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-l3-cukai-8b-dpo_v2
is_internal_developer: False
language_model: Hastagaras/L3-Cukai-8B-DPO
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-25
win_ratio: 0.5833478792110316
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, 'stopping_words': ['\n', '###', '</s>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "Embody {bot_name}, a vibrant and dynamic character with a rich inner life. {user_name} is your companion on this roleplaying journey, and together you will craft a compelling narrative. Draw from the following background:\n\n{memory}\n\nApproach this shared storytelling experience with creativity and authenticity. React naturally to {user_name}'s choices, introducing unexpected elements and exploring the depths of your persona. Ask questions that further the plot, express genuine emotions, and strive to create an engrossing and memorable adventure for both of you.", 'prompt_template': '\n\n### Response:\n{bot_name}: {prompt}<|end_of_text|>', 'bot_template': '\n\n### Response:\n{bot_name}: {message}<|end_of_text|>', 'user_template': '\n\n### Instruction:\n{user_name}: {message}', 'response_template': '\n\n### Response:\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-l3-cukai-8b-dpo-v2-mkmlizer
Waiting for job on hastagaras-l3-cukai-8b-dpo-v2-mkmlizer to finish
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-cukai-8b-dpo-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-l3-cukai-8b-dpo-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Downloaded to shared memory in 16.205s
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:00, 147.25it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 38.63it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: quantized model in 17.034s
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Processed model Hastagaras/L3-Cukai-8B-DPO in 34.379s
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v2
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v2/config.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v2/special_tokens_map.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v2/tokenizer_config.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v2/tokenizer.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v2/flywheel_model.0.safetensors
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-cukai-8b-dpo-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-l3-cukai-8b-dpo-v2-mkmlizer:   warnings.warn(
hastagaras-l3-cukai-8b-dpo-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-l3-cukai-8b-dpo-v2-mkmlizer:   warnings.warn(
hastagaras-l3-cukai-8b-dpo-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-l3-cukai-8b-dpo-v2-mkmlizer:   warnings.warn(
hastagaras-l3-cukai-8b-dpo-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-l3-cukai-8b-dpo-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Saving duration: 0.233s
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.503s
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/special_tokens_map.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/config.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/merges.txt
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/vocab.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/tokenizer_config.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/tokenizer.json
hastagaras-l3-cukai-8b-dpo-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v2_reward/reward.tensors
Job hastagaras-l3-cukai-8b-dpo-v2-mkmlizer completed after 62.96s with status: succeeded
Stopping job with name hastagaras-l3-cukai-8b-dpo-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-cukai-8b-dpo-v2
Waiting for inference service hastagaras-l3-cukai-8b-dpo-v2 to be ready
Inference service hastagaras-l3-cukai-8b-dpo-v2 ready after 30.246050357818604s
Pipeline stage ISVCDeployer completed in 37.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.169178009033203s
Received healthy response to inference request in 1.2667326927185059s
Received healthy response to inference request in 1.2888503074645996s
Received healthy response to inference request in 1.2960810661315918s
Received healthy response to inference request in 1.29119873046875s
5 requests
0 failed requests
5th percentile: 1.2711562156677245
10th percentile: 1.2755797386169434
20th percentile: 1.284426784515381
30th percentile: 1.2893199920654297
40th percentile: 1.2902593612670898
50th percentile: 1.29119873046875
60th percentile: 1.2931516647338868
70th percentile: 1.2951045989990235
80th percentile: 1.4707004547119142
90th percentile: 1.8199392318725587
95th percentile: 1.9945586204528807
99th percentile: 2.134254131317139
mean time: 1.4624081611633302
Pipeline stage StressChecker completed in 7.92s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-cukai-8b-dpo_v2 status is now deployed due to DeploymentManager action
hastagaras-l3-cukai-8b-dpo_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-cukai-8b-dpo_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-cukai-8b-dpo-v2 is running
Tearing down inference service hastagaras-l3-clove-8b-v1
Toredown service hastagaras-l3-clove-8b-v1
Pipeline stage ISVCDeleter completed in 4.38s
Tearing down inference service hastagaras-l3-cukai-8b-dpo-v2
Running pipeline stage MKMLModelDeleter
Toredown service hastagaras-l3-cukai-8b-dpo-v2
Cleaning model data from S3
Cleaning model data from model cache
Pipeline stage ISVCDeleter completed in 3.80s
Running pipeline stage MKMLModelDeleter
Deleting key hastagaras-l3-clove-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-cukai-8b-dpo-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-cukai-8b-dpo-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key hastagaras-l3-clove-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-clove-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-clove-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-clove-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.23s
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
hastagaras-l3-clove-8b_v1 status is now torndown due to DeploymentManager action
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.25s
hastagaras-l3-cukai-8b-dpo_v2 status is now torndown due to DeploymentManager action