cycy233-l3-base-v1-e1

developer_uid: shiroe40

submission_id: cycy233-l3-base-v1-e1_v2

model_name: base

model_group: cycy233/L3-base-v1-e1

status: torndown

timestamp: 2024-06-20T07:40:47+00:00

num_battles: 12798

num_wins: 6295

celo_rating: 1184.9

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-base-v1-e1

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-e1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-20

win_ratio: 0.49187373027035475

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-e1-v2-mkmlizer
Waiting for job on cycy233-l3-base-v1-e1-v2-mkmlizer to finish
cycy233-l3-base-v1-e1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v1-e1-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║       /___/                                                         ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-base-v1-e1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v1-e1-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-e1-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v1-e1-v2-mkmlizer: Downloaded to shared memory in 16.458s
cycy233-l3-base-v1-e1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v1-e1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v1-e1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 95.79it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:00, 113.63it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 161.84it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v1-e1-v2-mkmlizer: quantized model in 18.001s
cycy233-l3-base-v1-e1-v2-mkmlizer: Processed model cycy233/L3-base-v1-e1 in 35.392s
cycy233-l3-base-v1-e1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v1-e1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v1-e1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v1-e1-v2
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e1-v2/config.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e1-v2/tokenizer_config.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e1-v2/special_tokens_map.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e1-v2/tokenizer.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v1-e1-v2/flywheel_model.0.safetensors
cycy233-l3-base-v1-e1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v1-e1-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-e1-v2-mkmlizer:   warnings.warn(
cycy233-l3-base-v1-e1-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-e1-v2-mkmlizer:   warnings.warn(
cycy233-l3-base-v1-e1-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-e1-v2-mkmlizer:   warnings.warn(
cycy233-l3-base-v1-e1-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-e1-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-base-v1-e1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v1-e1-v2-mkmlizer: Saving duration: 0.238s
cycy233-l3-base-v1-e1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.002s
cycy233-l3-base-v1-e1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v1-e1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v1-e1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward/config.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward/special_tokens_map.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward/vocab.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward/tokenizer_config.json
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward/merges.txt
cycy233-l3-base-v1-e1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v1-e1-v2_reward/tokenizer.json
Job cycy233-l3-base-v1-e1-v2-mkmlizer completed after 164.4s with status: succeeded
Stopping job with name cycy233-l3-base-v1-e1-v2-mkmlizer
Pipeline stage MKMLizer completed in 167.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v1-e1-v2
Waiting for inference service cycy233-l3-base-v1-e1-v2 to be ready
Inference service cycy233-l3-base-v1-e1-v2 ready after 30.17652654647827s
Pipeline stage ISVCDeployer completed in 37.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1456236839294434s
Received healthy response to inference request in 1.23046875s
Received healthy response to inference request in 1.280515432357788s
Received healthy response to inference request in 1.2447583675384521s
Received healthy response to inference request in 1.2144827842712402s
5 requests
0 failed requests
5th percentile: 1.2176799774169922
10th percentile: 1.2208771705627441
20th percentile: 1.227271556854248
30th percentile: 1.2333266735076904
40th percentile: 1.2390425205230713
50th percentile: 1.2447583675384521
60th percentile: 1.2590611934661866
70th percentile: 1.2733640193939209
80th percentile: 1.4535370826721192
90th percentile: 1.7995803833007813
95th percentile: 1.9726020336151122
99th percentile: 2.111019353866577
mean time: 1.4231698036193847
Pipeline stage StressChecker completed in 8.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-l3-base-v1-e1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-base-v1-e1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-base-v1-e1_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-base-v1-e1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-base-v1-e1-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v1-e1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-base-v1-e1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v1-e1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.22s
cycy233-l3-base-v1-e1_v2 status is now torndown due to DeploymentManager action