submission_id: cycy233-l3i-base-v2-e1-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3i-base-v2-e1.5
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: 2024-06-26T02:20:12+00:00
model_name: auto
model_group: cycy233/L3i-base-v2-e1.5
num_battles: 18978
num_wins: 10132
celo_rating: 1200.22
propriety_score: 0.6933562428407789
propriety_total_count: 8730.0
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/L3i-base-v2-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-25
win_ratio: 0.5338813362841185
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3i-base-v2-e1-5-v1-mkmlizer
Waiting for job on cycy233-l3i-base-v2-e1-5-v1-mkmlizer to finish
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3i-base-v2-e1-5-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-l3i-base-v2-e1-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Downloaded to shared memory in 37.866s
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 81.76it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.98it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 137.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: quantized model in 23.488s
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Processed model cycy233/L3i-base-v2-e1.5 in 63.927s
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3i-base-v2-e1-5-v1
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e1-5-v1/tokenizer.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e1-5-v1/tokenizer_config.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e1-5-v1/config.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e1-5-v1/special_tokens_map.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3i-base-v2-e1-5-v1/flywheel_model.0.safetensors
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3i-base-v2-e1-5-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-l3i-base-v2-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3i-base-v2-e1-5-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-l3i-base-v2-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3i-base-v2-e1-5-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-l3i-base-v2-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3i-base-v2-e1-5-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-l3i-base-v2-e1-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Saving duration: 0.419s
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.586s
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/config.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/special_tokens_map.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/tokenizer_config.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/vocab.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/merges.txt
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/tokenizer.json
cycy233-l3i-base-v2-e1-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3i-base-v2-e1-5-v1_reward/reward.tensors
Job cycy233-l3i-base-v2-e1-5-v1-mkmlizer completed after 94.16s with status: succeeded
Stopping job with name cycy233-l3i-base-v2-e1-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3i-base-v2-e1-5-v1
Waiting for inference service cycy233-l3i-base-v2-e1-5-v1 to be ready
Inference service cycy233-l3i-base-v2-e1-5-v1 ready after 30.15952444076538s
Pipeline stage ISVCDeployer completed in 35.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0630223751068115s
Received healthy response to inference request in 1.212604284286499s
Received healthy response to inference request in 1.1958246231079102s
Received healthy response to inference request in 1.1859593391418457s
Received healthy response to inference request in 1.1896817684173584s
5 requests
0 failed requests
5th percentile: 1.1867038249969482
10th percentile: 1.1874483108520508
20th percentile: 1.188937282562256
30th percentile: 1.1909103393554688
40th percentile: 1.1933674812316895
50th percentile: 1.1958246231079102
60th percentile: 1.2025364875793456
70th percentile: 1.2092483520507813
80th percentile: 1.3826879024505616
90th percentile: 1.7228551387786866
95th percentile: 1.892938756942749
99th percentile: 2.029005651473999
mean time: 1.369418478012085
Pipeline stage StressChecker completed in 7.57s
cycy233-l3i-base-v2-e1-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3i-base-v2-e1-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics