developer_uid: shiroe40
submission_id: cycy233-llm3-0_v2
model_name: base
model_group: cycy233/llm3.0
status: torndown
timestamp: 2024-05-09T04:01:14+00:00
num_battles: 24371
num_wins: 11041
celo_rating: 1133.33
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/llm3.0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
is_internal_developer: False
language_model: cycy233/llm3.0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-08
win_ratio: 0.45303844733494725
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-llm3-0-v2-mkmlizer
Waiting for job on cycy233-llm3-0-v2-mkmlizer to finish
Stopping job with name cycy233-llm3-0-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-llm3-0-v2-mkmlizer
Waiting for job on cycy233-llm3-0-v2-mkmlizer to finish
cycy233-llm3-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm3-0-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-llm3-0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-llm3-0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-llm3-0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-llm3-0-v2-mkmlizer: ║       /___/                                                         ║
cycy233-llm3-0-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-0-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
cycy233-llm3-0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-llm3-0-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-llm3-0-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-llm3-0-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-llm3-0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-llm3-0-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-llm3-0-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm3-0-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.
cycy233-llm3-0-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-llm3-0-v2-mkmlizer: Downloaded to shared memory in 17.166s
cycy233-llm3-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm3-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm3-0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  36%|███▋      | 106/291 [00:01<00:01, 96.83it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 92.33it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm3-0-v2-mkmlizer: quantized model in 10.213s
cycy233-llm3-0-v2-mkmlizer: Processed model cycy233/llm3.0 in 28.376s
cycy233-llm3-0-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm3-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm3-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm3-0-v2
cycy233-llm3-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm3-0-v2/special_tokens_map.json
cycy233-llm3-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm3-0-v2/config.json
cycy233-llm3-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm3-0-v2/tokenizer_config.json
cycy233-llm3-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm3-0-v2/tokenizer.json
cycy233-llm3-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm3-0-v2/tokenizer.model
cycy233-llm3-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm3-0-v2/flywheel_model.0.safetensors
cycy233-llm3-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm3-0-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.
cycy233-llm3-0-v2-mkmlizer:   warnings.warn(
cycy233-llm3-0-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.
cycy233-llm3-0-v2-mkmlizer:   warnings.warn(
cycy233-llm3-0-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.
cycy233-llm3-0-v2-mkmlizer:   warnings.warn(
cycy233-llm3-0-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()
cycy233-llm3-0-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-llm3-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm3-0-v2-mkmlizer: Saving duration: 0.267s
cycy233-llm3-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.270s
cycy233-llm3-0-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm3-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm3-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm3-0-v2_reward
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/config.json
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/tokenizer_config.json
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/special_tokens_map.json
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/merges.txt
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/vocab.json
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/tokenizer.json
cycy233-llm3-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm3-0-v2_reward/reward.tensors
Job cycy233-llm3-0-v2-mkmlizer completed after 76.31s with status: succeeded
Stopping job with name cycy233-llm3-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 80.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.20s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm3-0-v2
Waiting for inference service cycy233-llm3-0-v2 to be ready
Inference service cycy233-llm3-0-v2 ready after 40.238213777542114s
Pipeline stage ISVCDeployer completed in 47.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8919129371643066s
Received healthy response to inference request in 1.1710288524627686s
Received healthy response to inference request in 1.1763606071472168s
Received healthy response to inference request in 1.2104668617248535s
Received healthy response to inference request in 1.19734525680542s
5 requests
0 failed requests
5th percentile: 1.1720952033996581
10th percentile: 1.173161554336548
20th percentile: 1.1752942562103272
30th percentile: 1.1805575370788575
40th percentile: 1.1889513969421386
50th percentile: 1.19734525680542
60th percentile: 1.2025938987731934
70th percentile: 1.2078425407409668
80th percentile: 1.3467560768127442
90th percentile: 1.6193345069885254
95th percentile: 1.755623722076416
99th percentile: 1.8646550941467286
mean time: 1.329422903060913
Pipeline stage StressChecker completed in 7.32s
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
cycy233-llm3-0_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-llm3-0_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-llm3-0_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-llm3-0-v2 is running
Tearing down inference service cycy233-llm3-0-v2
Toredown service cycy233-llm3-0-v2
Pipeline stage ISVCDeleter completed in 4.80s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-llm3-0-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-llm3-0-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.95s
cycy233-llm3-0_v2 status is now torndown due to DeploymentManager action