developer_uid: Hastagaras
submission_id: hastagaras-llama3-8b-darktune_v1
model_name: hastagaras-llama3-8b-darktune_v1
model_group: Hastagaras/llama3-8b-dar
status: torndown
timestamp: 2024-05-09T09:44:13+00:00
num_battles: 10381
num_wins: 5698
celo_rating: 1191.17
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama3-8b-darktune
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-llama3-8b-darktune_v1
is_internal_developer: False
language_model: Hastagaras/llama3-8b-darktune
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-09
win_ratio: 0.5488873904248146
generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n{bot_name}', '\n{user_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nAct as {bot_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}
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-llama3-8b-darktune-v1-mkmlizer
Waiting for job on hastagaras-llama3-8b-darktune-v1-mkmlizer to finish
Stopping job with name hastagaras-llama3-8b-darktune-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama3-8b-darktune-v1-mkmlizer
Waiting for job on hastagaras-llama3-8b-darktune-v1-mkmlizer to finish
hastagaras-llama3-8b-darktune-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-darktune-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-darktune-v1-mkmlizer: Downloaded to shared memory in 31.989s
hastagaras-llama3-8b-darktune-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-darktune-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-darktune-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  44%|████▎     | 127/291 [00:00<00:01, 127.01it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 122.32it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.65it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-darktune-v1-mkmlizer: quantized model in 17.882s
hastagaras-llama3-8b-darktune-v1-mkmlizer: Processed model Hastagaras/llama3-8b-darktune in 50.997s
hastagaras-llama3-8b-darktune-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-darktune-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-darktune-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v1
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v1/tokenizer_config.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v1/config.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v1/special_tokens_map.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v1/tokenizer.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v1/flywheel_model.0.safetensors
hastagaras-llama3-8b-darktune-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-darktune-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-darktune-v1-mkmlizer: Saving duration: 0.249s
hastagaras-llama3-8b-darktune-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.251s
hastagaras-llama3-8b-darktune-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-darktune-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-darktune-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/config.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/tokenizer_config.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/merges.txt
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/vocab.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/special_tokens_map.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/tokenizer.json
hastagaras-llama3-8b-darktune-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v1_reward/reward.tensors
Job hastagaras-llama3-8b-darktune-v1-mkmlizer completed after 84.08s with status: succeeded
Stopping job with name hastagaras-llama3-8b-darktune-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-darktune-v1
Waiting for inference service hastagaras-llama3-8b-darktune-v1 to be ready
Inference service hastagaras-llama3-8b-darktune-v1 ready after 30.17285680770874s
Pipeline stage ISVCDeployer completed in 36.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.189469575881958s
Received healthy response to inference request in 1.3151416778564453s
Received healthy response to inference request in 1.270261287689209s
Received healthy response to inference request in 1.3709514141082764s
Received healthy response to inference request in 1.3107798099517822s
5 requests
0 failed requests
5th percentile: 1.2783649921417237
10th percentile: 1.2864686965942382
20th percentile: 1.3026761054992675
30th percentile: 1.3116521835327148
40th percentile: 1.31339693069458
50th percentile: 1.3151416778564453
60th percentile: 1.3374655723571778
70th percentile: 1.3597894668579102
80th percentile: 1.5346550464630129
90th percentile: 1.8620623111724854
95th percentile: 2.0257659435272215
99th percentile: 2.1567288494110106
mean time: 1.491320753097534
Pipeline stage StressChecker completed in 8.09s
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-llama3-8b-darktune_v1 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-darktune_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-darktune_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-darktune-v1 is running
Tearing down inference service hastagaras-llama3-8b-darktune-v1
Toredown service hastagaras-llama3-8b-darktune-v1
Pipeline stage ISVCDeleter completed in 7.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-darktune-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-darktune-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-darktune-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-darktune-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-darktune-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-darktune-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-darktune-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-darktune-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-darktune-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-darktune-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-darktune-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-darktune-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.11s
hastagaras-llama3-8b-darktune_v1 status is now torndown due to DeploymentManager action