developer_uid: shiroe40
submission_id: cycy233-llm3-2_v2
model_name: base1
model_group: cycy233/llm3.2
status: torndown
timestamp: 2024-05-09T11:13:35+00:00
num_battles: 28467
num_wins: 12396
celo_rating: 1123.62
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/llm3.2
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: base1
is_internal_developer: False
language_model: cycy233/llm3.2
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-09
win_ratio: 0.4354515755084835
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': 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}
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 cycy233-llm3-2-v2-mkmlizer
Waiting for job on cycy233-llm3-2-v2-mkmlizer to finish
cycy233-llm3-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm3-2-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-llm3-2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-llm3-2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-llm3-2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-llm3-2-v2-mkmlizer: ║       /___/                                                         ║
cycy233-llm3-2-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
cycy233-llm3-2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-llm3-2-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-llm3-2-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-llm3-2-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-llm3-2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-llm3-2-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-llm3-2-v2-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm3-2-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-llm3-2-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-llm3-2-v2-mkmlizer: Downloaded to shared memory in 18.136s
cycy233-llm3-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm3-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm3-2-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  74%|███████▍  | 215/291 [00:01<00:00, 126.24it/s]
Loading 0: 100%|██████████| 291/291 [00:02<00:00, 96.68it/s] 
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm3-2-v2-mkmlizer: quantized model in 9.849s
cycy233-llm3-2-v2-mkmlizer: Processed model cycy233/llm3.2 in 28.865s
cycy233-llm3-2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm3-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm3-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm3-2-v2
cycy233-llm3-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm3-2-v2/config.json
cycy233-llm3-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm3-2-v2/tokenizer.json
cycy233-llm3-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm3-2-v2/tokenizer_config.json
cycy233-llm3-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm3-2-v2/special_tokens_map.json
cycy233-llm3-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm3-2-v2/tokenizer.model
cycy233-llm3-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm3-2-v2/flywheel_model.0.safetensors
cycy233-llm3-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm3-2-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-llm3-2-v2-mkmlizer:   warnings.warn(
cycy233-llm3-2-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-llm3-2-v2-mkmlizer:   warnings.warn(
cycy233-llm3-2-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-llm3-2-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-llm3-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm3-2-v2-mkmlizer: Saving duration: 0.258s
cycy233-llm3-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.882s
cycy233-llm3-2-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm3-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm3-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm3-2-v2_reward
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/special_tokens_map.json
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/tokenizer_config.json
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/merges.txt
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/config.json
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/vocab.json
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/tokenizer.json
cycy233-llm3-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm3-2-v2_reward/reward.tensors
Job cycy233-llm3-2-v2-mkmlizer completed after 52.43s with status: succeeded
Stopping job with name cycy233-llm3-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 56.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm3-2-v2
Waiting for inference service cycy233-llm3-2-v2 to be ready
Inference service cycy233-llm3-2-v2 ready after 30.173774480819702s
Pipeline stage ISVCDeployer completed in 37.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0242605209350586s
Received healthy response to inference request in 1.1368751525878906s
Received healthy response to inference request in 1.1473619937896729s
Received healthy response to inference request in 1.1559395790100098s
Received healthy response to inference request in 1.1361329555511475s
5 requests
0 failed requests
5th percentile: 1.136281394958496
10th percentile: 1.1364298343658448
20th percentile: 1.136726713180542
30th percentile: 1.138972520828247
40th percentile: 1.14316725730896
50th percentile: 1.1473619937896729
60th percentile: 1.1507930278778076
70th percentile: 1.1542240619659423
80th percentile: 1.3296037673950196
90th percentile: 1.676932144165039
95th percentile: 1.8505963325500487
99th percentile: 1.9895276832580566
mean time: 1.3201140403747558
Pipeline stage StressChecker completed in 7.26s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-llm3-2_v2 status is now deployed due to DeploymentManager action
cycy233-llm3-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-llm3-2_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-llm3-2-v2 is running
Tearing down inference service cycy233-llm3-2-v2
Toredown service cycy233-llm3-2-v2
Pipeline stage ISVCDeleter completed in 5.08s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-llm3-2-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-llm3-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.56s
cycy233-llm3-2_v2 status is now torndown due to DeploymentManager action