developer_uid: Hastagaras
submission_id: hastagaras-l3-imoune-8b_v2
model_name: hastagaras-l3-imoune-8b_v2
model_group: Hastagaras/L3-Imoune-8B
status: torndown
timestamp: 2024-04-23T06:21:00+00:00
num_battles: 7548
num_wins: 4104
celo_rating: 1186.15
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Imoune-8B
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-imoune-8b_v2
is_internal_developer: False
language_model: Hastagaras/L3-Imoune-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-22
win_ratio: 0.5437201907790143
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{bot_name}:', '\n{user_name}', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system{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}
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-imoune-8b-v2-mkmlizer
Waiting for job on hastagaras-l3-imoune-8b-v2-mkmlizer to finish
Stopping job with name hastagaras-l3-imoune-8b-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-l3-imoune-8b-v2-mkmlizer
Waiting for job on hastagaras-l3-imoune-8b-v2-mkmlizer to finish
hastagaras-l3-imoune-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-imoune-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-l3-imoune-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-imoune-8b-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-imoune-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-imoune-8b-v2-mkmlizer: Downloaded to shared memory in 31.976s
hastagaras-l3-imoune-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-imoune-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-imoune-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  36%|███▌      | 104/291 [00:01<00:01, 102.95it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 109.27it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 30.39it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-imoune-8b-v2-mkmlizer: quantized model in 18.752s
hastagaras-l3-imoune-8b-v2-mkmlizer: Processed model Hastagaras/L3-Imoune-8B in 51.712s
hastagaras-l3-imoune-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-imoune-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-imoune-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-imoune-8b-v2
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-imoune-8b-v2/config.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-imoune-8b-v2/special_tokens_map.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-imoune-8b-v2/tokenizer_config.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-imoune-8b-v2/tokenizer.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-imoune-8b-v2/flywheel_model.0.safetensors
hastagaras-l3-imoune-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-imoune-8b-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-imoune-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-imoune-8b-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-imoune-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-imoune-8b-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-imoune-8b-v2-mkmlizer:   warnings.warn(
hastagaras-l3-imoune-8b-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-imoune-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-imoune-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-imoune-8b-v2-mkmlizer: Saving duration: 0.279s
hastagaras-l3-imoune-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 10.173s
hastagaras-l3-imoune-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-imoune-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-imoune-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/tokenizer_config.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/config.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/special_tokens_map.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/merges.txt
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/vocab.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/tokenizer.json
hastagaras-l3-imoune-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-imoune-8b-v2_reward/reward.tensors
Job hastagaras-l3-imoune-8b-v2-mkmlizer completed after 84.01s with status: succeeded
Stopping job with name hastagaras-l3-imoune-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 87.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-imoune-8b-v2
Waiting for inference service hastagaras-l3-imoune-8b-v2 to be ready
Inference service hastagaras-l3-imoune-8b-v2 ready after 30.203280448913574s
Pipeline stage ISVCDeployer completed in 37.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1790049076080322s
Received healthy response to inference request in 1.2867002487182617s
Received healthy response to inference request in 1.2957613468170166s
Received healthy response to inference request in 1.3065471649169922s
Received healthy response to inference request in 1.2906005382537842s
5 requests
0 failed requests
5th percentile: 1.2874803066253662
10th percentile: 1.2882603645324706
20th percentile: 1.2898204803466797
30th percentile: 1.2916326999664307
40th percentile: 1.2936970233917235
50th percentile: 1.2957613468170166
60th percentile: 1.3000756740570067
70th percentile: 1.3043900012969971
80th percentile: 1.4810387134552003
90th percentile: 1.8300218105316164
95th percentile: 2.004513359069824
99th percentile: 2.1441065979003904
mean time: 1.4717228412628174
Pipeline stage StressChecker completed in 8.05s
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-l3-imoune-8b_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-imoune-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-imoune-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-imoune-8b-v2 is running
Tearing down inference service hastagaras-l3-imoune-8b-v2
Toredown service hastagaras-l3-imoune-8b-v2
Pipeline stage ISVCDeleter completed in 3.65s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-imoune-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-imoune-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-imoune-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-imoune-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-imoune-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-imoune-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-imoune-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-imoune-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-imoune-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-imoune-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-imoune-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-imoune-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.32s
hastagaras-l3-imoune-8b_v2 status is now torndown due to DeploymentManager action