developer_uid: shiroe40
submission_id: cycy233-llm3-2_v1
model_name: base
model_group: cycy233/llm3.2
status: torndown
timestamp: 2024-05-09T10:05:57+00:00
num_battles: 24637
num_wins: 11187
celo_rating: 1135.73
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: base
is_internal_developer: False
language_model: cycy233/llm3.2
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-09
win_ratio: 0.4540731420221618
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-llm3-2-v1-mkmlizer
Waiting for job on cycy233-llm3-2-v1-mkmlizer to finish
cycy233-llm3-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm3-2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-llm3-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-llm3-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-llm3-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-llm3-2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-llm3-2-v1-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
cycy233-llm3-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-llm3-2-v1-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-llm3-2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-llm3-2-v1-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-llm3-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-llm3-2-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-llm3-2-v1-mkmlizer: ║                                                                     ║
cycy233-llm3-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm3-2-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.
cycy233-llm3-2-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-llm3-2-v1-mkmlizer: Downloaded to shared memory in 25.117s
cycy233-llm3-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm3-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm3-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  36%|███▋      | 106/291 [00:01<00:01, 103.49it/s]
Loading 0: 100%|██████████| 291/291 [00:02<00:00, 101.24it/s]
                                                             
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm3-2-v1-mkmlizer: quantized model in 9.705s
cycy233-llm3-2-v1-mkmlizer: Processed model cycy233/llm3.2 in 35.656s
cycy233-llm3-2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm3-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm3-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm3-2-v1
cycy233-llm3-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm3-2-v1/config.json
cycy233-llm3-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm3-2-v1/special_tokens_map.json
cycy233-llm3-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm3-2-v1/tokenizer_config.json
cycy233-llm3-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm3-2-v1/tokenizer.model
cycy233-llm3-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm3-2-v1/tokenizer.json
cycy233-llm3-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm3-2-v1/flywheel_model.0.safetensors
cycy233-llm3-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm3-2-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.
cycy233-llm3-2-v1-mkmlizer:   warnings.warn(
cycy233-llm3-2-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.
cycy233-llm3-2-v1-mkmlizer:   warnings.warn(
cycy233-llm3-2-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.
cycy233-llm3-2-v1-mkmlizer:   warnings.warn(
cycy233-llm3-2-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()
cycy233-llm3-2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-llm3-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm3-2-v1-mkmlizer: Saving duration: 0.230s
cycy233-llm3-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.201s
cycy233-llm3-2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm3-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm3-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm3-2-v1_reward
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/config.json
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/special_tokens_map.json
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/tokenizer_config.json
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/vocab.json
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/merges.txt
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/tokenizer.json
cycy233-llm3-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm3-2-v1_reward/reward.tensors
Job cycy233-llm3-2-v1-mkmlizer completed after 62.75s with status: succeeded
Stopping job with name cycy233-llm3-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 66.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm3-2-v1
Waiting for inference service cycy233-llm3-2-v1 to be ready
Inference service cycy233-llm3-2-v1 ready after 150.81905221939087s
Pipeline stage ISVCDeployer completed in 158.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9801921844482422s
Received healthy response to inference request in 1.2176470756530762s
Received healthy response to inference request in 1.2146668434143066s
Received healthy response to inference request in 1.1611502170562744s
Received healthy response to inference request in 1.1924049854278564s
5 requests
0 failed requests
5th percentile: 1.167401170730591
10th percentile: 1.1736521244049072
20th percentile: 1.18615403175354
30th percentile: 1.1968573570251464
40th percentile: 1.2057621002197265
50th percentile: 1.2146668434143066
60th percentile: 1.2158589363098145
70th percentile: 1.2170510292053223
80th percentile: 1.3701560974121094
90th percentile: 1.675174140930176
95th percentile: 1.827683162689209
99th percentile: 1.9496903800964356
mean time: 1.353212261199951
Pipeline stage StressChecker completed in 7.37s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cycy233-llm3-2_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-llm3-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-llm3-2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-llm3-2-v1 is running
Tearing down inference service cycy233-llm3-2-v1
Toredown service cycy233-llm3-2-v1
Pipeline stage ISVCDeleter completed in 5.79s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-llm3-2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-llm3-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-llm3-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.76s
cycy233-llm3-2_v1 status is now torndown due to DeploymentManager action