submission_id: cycy233-l3-base-more-v1-e2-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base_more-v1-e2.0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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}
timestamp: 2024-06-25T03:17:44+00:00
model_name: auto
model_group: cycy233/L3-base_more-v1-
num_battles: 15987
num_wins: 7813
celo_rating: 1184.53
propriety_score: 0.7255933290570878
propriety_total_count: 7795.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
ineligible_reason: None
language_model: cycy233/L3-base_more-v1-e2.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-24
win_ratio: 0.4887095765309314
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-more-v1-e2-0-v1-mkmlizer
Waiting for job on cycy233-l3-base-more-v1-e2-0-v1-mkmlizer to finish
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║                                                                     ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║                                                                     ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║                                                                     ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ║                                                                     ║
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-more-v1-e2-0-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-l3-base-more-v1-e2-0-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Downloaded to shared memory in 36.081s
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 74.51it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 88.42it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 128.68it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: quantized model in 19.376s
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Processed model cycy233/L3-base_more-v1-e2.0 in 56.524s
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-more-v1-e2-0-v1/config.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-more-v1-e2-0-v1/special_tokens_map.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-more-v1-e2-0-v1/tokenizer_config.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-more-v1-e2-0-v1/tokenizer.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-more-v1-e2-0-v1/flywheel_model.0.safetensors
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-more-v1-e2-0-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-l3-base-more-v1-e2-0-v1-mkmlizer:   warnings.warn(
cycy233-l3-base-more-v1-e2-0-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-l3-base-more-v1-e2-0-v1-mkmlizer:   warnings.warn(
cycy233-l3-base-more-v1-e2-0-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-l3-base-more-v1-e2-0-v1-mkmlizer:   warnings.warn(
cycy233-l3-base-more-v1-e2-0-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-l3-base-more-v1-e2-0-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Saving duration: 0.303s
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.095s
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/special_tokens_map.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/config.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/tokenizer_config.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/merges.txt
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/vocab.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/tokenizer.json
cycy233-l3-base-more-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-more-v1-e2-0-v1_reward/reward.tensors
Job cycy233-l3-base-more-v1-e2-0-v1-mkmlizer completed after 84.03s with status: succeeded
Stopping job with name cycy233-l3-base-more-v1-e2-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-more-v1-e2-0-v1
Waiting for inference service cycy233-l3-base-more-v1-e2-0-v1 to be ready
Inference service cycy233-l3-base-more-v1-e2-0-v1 ready after 40.22426152229309s
Pipeline stage ISVCDeployer completed in 45.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 10.67061972618103s
%s, retrying in %s seconds...
Received healthy response to inference request in 6.5390331745147705s
Received healthy response to inference request in 1.2249281406402588s
Received healthy response to inference request in 1.2359590530395508s
Received healthy response to inference request in 1.213179588317871s
Received healthy response to inference request in 1.2292296886444092s
5 requests
0 failed requests
5th percentile: 1.2155292987823487
10th percentile: 1.2178790092468261
20th percentile: 1.2225784301757812
30th percentile: 1.225788450241089
40th percentile: 1.227509069442749
50th percentile: 1.2292296886444092
60th percentile: 1.2319214344024658
70th percentile: 1.2346131801605225
80th percentile: 2.2965738773345956
90th percentile: 4.417803525924683
95th percentile: 5.478418350219726
99th percentile: 6.326910209655762
mean time: 2.2884659290313722
Pipeline stage StressChecker completed in 42.89s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-l3-base-more-v1-e2-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-base-more-v1-e2-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics