submission_id: hastagaras-llama3-8b-dar_7411_v3
developer_uid: Hastagaras
best_of: 4
celo_rating: 1154.38
display_name: hastagaras-llama3-8b-dar_7411_v3
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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: success
model_group: Hastagaras/llama3-8b-dar
model_name: hastagaras-llama3-8b-dar_7411_v3
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama3-8b-darktune-KTO
model_size: 8B
num_battles: 6930
num_wins: 3358
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: 2024-05-11T03:48:13+00:00
us_pacific_date: 2024-05-10
win_ratio: 0.4845598845598846
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-dar-7411-v3-mkmlizer
Waiting for job on hastagaras-llama3-8b-dar-7411-v3-mkmlizer to finish
Stopping job with name hastagaras-llama3-8b-dar-7411-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama3-8b-dar-7411-v3-mkmlizer
Waiting for job on hastagaras-llama3-8b-dar-7411-v3-mkmlizer to finish
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-dar-7411-v3-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-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Downloaded to shared memory in 14.592s
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  46%|████▋     | 135/291 [00:00<00:01, 135.11it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 38.36it/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-v3-mkmlizer: quantized model in 16.977s
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Processed model Hastagaras/llama3-8b-darktune-KTO in 32.566s
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v3
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v3/tokenizer_config.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v3/special_tokens_map.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v3/config.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v3/tokenizer.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v3/flywheel_model.0.safetensors
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-dar-7411-v3-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-v3-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-dar-7411-v3-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-v3-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-dar-7411-v3-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-v3-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-dar-7411-v3-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-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Saving duration: 0.224s
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.184s
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/config.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/tokenizer_config.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/special_tokens_map.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/merges.txt
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/vocab.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/tokenizer.json
hastagaras-llama3-8b-dar-7411-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v3_reward/reward.tensors
Job hastagaras-llama3-8b-dar-7411-v3-mkmlizer completed after 62.88s with status: succeeded
Stopping job with name hastagaras-llama3-8b-dar-7411-v3-mkmlizer
Pipeline stage MKMLizer completed in 65.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-dar-7411-v3
Waiting for inference service hastagaras-llama3-8b-dar-7411-v3 to be ready
Inference service hastagaras-llama3-8b-dar-7411-v3 ready after 30.269311904907227s
Pipeline stage ISVCDeployer completed in 37.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9012184143066406s
Received healthy response to inference request in 1.1314234733581543s
Received healthy response to inference request in 1.112074851989746s
Received healthy response to inference request in 1.1471378803253174s
Received healthy response to inference request in 0.9003934860229492s
5 requests
0 failed requests
5th percentile: 0.9427297592163086
10th percentile: 0.985066032409668
20th percentile: 1.0697385787963867
30th percentile: 1.1159445762634277
40th percentile: 1.123684024810791
50th percentile: 1.1314234733581543
60th percentile: 1.1377092361450196
70th percentile: 1.1439949989318847
80th percentile: 1.2979539871215822
90th percentile: 1.5995862007141115
95th percentile: 1.7504023075103758
99th percentile: 1.8710551929473878
mean time: 1.2384496212005616
Pipeline stage StressChecker completed in 6.79s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama3-8b-dar_7411_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-8b-dar_7411_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-dar_7411_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-dar-7411-v3 is running
Tearing down inference service hastagaras-llama3-8b-dar-7411-v3
Toredown service hastagaras-llama3-8b-dar-7411-v3
Pipeline stage ISVCDeleter completed in 6.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7411-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.10s
hastagaras-llama3-8b-dar_7411_v3 status is now torndown due to DeploymentManager action