developer_uid: shiroe40
submission_id: cycy233-l3-base-v1-e3-0_v2
model_name: base
model_group: cycy233/L3-base-v1-e3.0
status: torndown
timestamp: 2024-06-21T02:39:18+00:00
num_battles: 19539
num_wins: 9933
celo_rating: 1198.95
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-base-v1-e3.0
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: base
is_internal_developer: False
language_model: cycy233/L3-base-v1-e3.0
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-20
win_ratio: 0.5083678796253647
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': True}
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': True, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v1-e3-0-v2-mkmlizer
Waiting for job on cycy233-l3-base-v1-e3-0-v2-mkmlizer to finish
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║       /___/                                                         ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e3-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v1-e3-0-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-l3-base-v1-e3-0-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Downloaded to shared memory in 35.316s
cycy233-l3-base-v1-e3-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v1-e3-0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 84.32it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 100.37it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 145.10it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v1-e3-0-v2-mkmlizer: quantized model in 18.871s
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Processed model cycy233/L3-base-v1-e3.0 in 55.135s
cycy233-l3-base-v1-e3-0-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v1-e3-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v1-e3-0-v2
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e3-0-v2/config.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e3-0-v2/special_tokens_map.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e3-0-v2/tokenizer_config.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e3-0-v2/tokenizer.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v1-e3-0-v2/flywheel_model.0.safetensors
cycy233-l3-base-v1-e3-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v1-e3-0-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-l3-base-v1-e3-0-v2-mkmlizer:   warnings.warn(
cycy233-l3-base-v1-e3-0-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-l3-base-v1-e3-0-v2-mkmlizer:   warnings.warn(
cycy233-l3-base-v1-e3-0-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-l3-base-v1-e3-0-v2-mkmlizer:   warnings.warn(
cycy233-l3-base-v1-e3-0-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-l3-base-v1-e3-0-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Saving duration: 0.297s
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.380s
cycy233-l3-base-v1-e3-0-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v1-e3-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v1-e3-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/special_tokens_map.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/config.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/tokenizer_config.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/merges.txt
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/vocab.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/tokenizer.json
cycy233-l3-base-v1-e3-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v1-e3-0-v2_reward/reward.tensors
Job cycy233-l3-base-v1-e3-0-v2-mkmlizer completed after 84.23s with status: succeeded
Stopping job with name cycy233-l3-base-v1-e3-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v1-e3-0-v2
Waiting for inference service cycy233-l3-base-v1-e3-0-v2 to be ready
Inference service cycy233-l3-base-v1-e3-0-v2 ready after 90.39376211166382s
Pipeline stage ISVCDeployer completed in 96.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1673495769500732s
Received healthy response to inference request in 1.2349202632904053s
Received healthy response to inference request in 2.4575979709625244s
Received healthy response to inference request in 2.2330520153045654s
Received healthy response to inference request in 1.301215410232544s
5 requests
0 failed requests
5th percentile: 1.248179292678833
10th percentile: 1.2614383220672607
20th percentile: 1.2879563808441161
30th percentile: 1.4744422435760498
40th percentile: 1.8208959102630615
50th percentile: 2.1673495769500732
60th percentile: 2.19363055229187
70th percentile: 2.219911527633667
80th percentile: 2.2779612064361574
90th percentile: 2.367779588699341
95th percentile: 2.4126887798309324
99th percentile: 2.448616132736206
mean time: 1.8788270473480224
Pipeline stage StressChecker completed in 10.18s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.06s
cycy233-l3-base-v1-e3-0_v2 status is now deployed due to DeploymentManager action
cycy233-l3-base-v1-e3-0_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-base-v1-e3-0_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-base-v1-e3-0-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.03s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-base-v1-e3-0-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e3-0-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e3-0-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e3-0-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e3-0-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e3-0-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.35s
cycy233-l3-base-v1-e3-0_v2 status is now torndown due to DeploymentManager action