developer_uid: Hastagaras
submission_id: hastagaras-l3-cukai-8b-dpo_v1
model_name: hastagaras-l3-cukai-8b-dpo_v1
model_group: Hastagaras/L3-Cukai-8B-D
status: torndown
timestamp: 2024-04-25T17:29:27+00:00
num_battles: 7167
num_wins: 4153
celo_rating: 1206.35
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_v1
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: 0.5794614203990512
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '###', '</s>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "Write {bot_name}'s next reply in a fictional roleplay chat between {user_name} and {bot_name}.\n\n{memory}", '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}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{bot_name}: {prompt}\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-l3-cukai-8b-dpo-v1-mkmlizer
Waiting for job on hastagaras-l3-cukai-8b-dpo-v1-mkmlizer to finish
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-cukai-8b-dpo-v1-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-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Downloaded to shared memory in 27.956s
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 139.18it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 38.41it/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-v1-mkmlizer: quantized model in 17.247s
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Processed model Hastagaras/L3-Cukai-8B-DPO in 46.211s
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v1
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v1/tokenizer_config.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v1/tokenizer.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v1/config.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v1/special_tokens_map.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-cukai-8b-dpo-v1/flywheel_model.0.safetensors
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-cukai-8b-dpo-v1-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-v1-mkmlizer:   warnings.warn(
hastagaras-l3-cukai-8b-dpo-v1-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-v1-mkmlizer:   warnings.warn(
hastagaras-l3-cukai-8b-dpo-v1-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-v1-mkmlizer:   warnings.warn(
hastagaras-l3-cukai-8b-dpo-v1-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-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Saving duration: 0.241s
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.764s
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/config.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/vocab.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/merges.txt
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/special_tokens_map.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/tokenizer_config.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/tokenizer.json
hastagaras-l3-cukai-8b-dpo-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-cukai-8b-dpo-v1_reward/reward.tensors
Job hastagaras-l3-cukai-8b-dpo-v1-mkmlizer completed after 73.73s with status: succeeded
Stopping job with name hastagaras-l3-cukai-8b-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-cukai-8b-dpo-v1
Waiting for inference service hastagaras-l3-cukai-8b-dpo-v1 to be ready
Inference service hastagaras-l3-cukai-8b-dpo-v1 ready after 40.3043999671936s
Pipeline stage ISVCDeployer completed in 47.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1230716705322266s
Received healthy response to inference request in 1.277296781539917s
Received healthy response to inference request in 1.2719953060150146s
Received healthy response to inference request in 1.2718617916107178s
Received healthy response to inference request in 1.2280242443084717s
5 requests
0 failed requests
5th percentile: 1.2367917537689208
10th percentile: 1.2455592632293702
20th percentile: 1.2630942821502686
30th percentile: 1.2718884944915771
40th percentile: 1.271941900253296
50th percentile: 1.2719953060150146
60th percentile: 1.2741158962249757
70th percentile: 1.2762364864349365
80th percentile: 1.446451759338379
90th percentile: 1.7847617149353028
95th percentile: 1.9539166927337646
99th percentile: 2.089240674972534
mean time: 1.4344499588012696
Pipeline stage StressChecker completed in 7.82s
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-l3-cukai-8b-dpo_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-cukai-8b-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-cukai-8b-dpo_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-cukai-8b-dpo-v1 is running
Tearing down inference service hastagaras-l3-cukai-8b-dpo-v1
Toredown service hastagaras-l3-cukai-8b-dpo-v1
Pipeline stage ISVCDeleter completed in 3.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-cukai-8b-dpo-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.90s
hastagaras-l3-cukai-8b-dpo_v1 status is now torndown due to DeploymentManager action