submission_id: cycy233-l3-exp-v0-e1-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-exp-v0-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: 2024-06-26T02:15:05+00:00
model_name: auto
model_group: cycy233/L3-exp-v0-e1.5
num_battles: 19816
num_wins: 8984
celo_rating: 1148.41
propriety_score: 0.7082701883524573
propriety_total_count: 9238.0
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-exp-v0-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-25
win_ratio: 0.45337101332256763
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-exp-v0-e1-5-v1-mkmlizer
Waiting for job on cycy233-l3-exp-v0-e1-5-v1-mkmlizer to finish
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-exp-v0-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-l3-exp-v0-e1-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Downloaded to shared memory in 49.817s
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 71.36it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 84.57it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 121.90it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: quantized model in 23.495s
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Processed model cycy233/L3-exp-v0-e1.5 in 75.784s
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-exp-v0-e1-5-v1
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e1-5-v1/config.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e1-5-v1/special_tokens_map.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e1-5-v1/tokenizer_config.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e1-5-v1/tokenizer.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-exp-v0-e1-5-v1/flywheel_model.0.safetensors
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-exp-v0-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-l3-exp-v0-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-exp-v0-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-l3-exp-v0-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-exp-v0-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-l3-exp-v0-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-exp-v0-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-l3-exp-v0-e1-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Saving duration: 0.382s
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.357s
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/special_tokens_map.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/tokenizer_config.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/config.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/merges.txt
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/vocab.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/tokenizer.json
cycy233-l3-exp-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-exp-v0-e1-5-v1_reward/reward.tensors
Job cycy233-l3-exp-v0-e1-5-v1-mkmlizer completed after 105.04s with status: succeeded
Stopping job with name cycy233-l3-exp-v0-e1-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-exp-v0-e1-5-v1
Waiting for inference service cycy233-l3-exp-v0-e1-5-v1 to be ready
Inference service cycy233-l3-exp-v0-e1-5-v1 ready after 70.49488353729248s
Pipeline stage ISVCDeployer completed in 76.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2126903533935547s
Received healthy response to inference request in 1.1965596675872803s
Received healthy response to inference request in 1.2468552589416504s
Received healthy response to inference request in 1.2054688930511475s
Received healthy response to inference request in 1.2369368076324463s
5 requests
0 failed requests
5th percentile: 1.1983415126800536
10th percentile: 1.2001233577728272
20th percentile: 1.2036870479583741
30th percentile: 1.2117624759674073
40th percentile: 1.2243496417999267
50th percentile: 1.2369368076324463
60th percentile: 1.240904188156128
70th percentile: 1.2448715686798095
80th percentile: 1.4400222778320315
90th percentile: 1.826356315612793
95th percentile: 2.0195233345031736
99th percentile: 2.1740569496154785
mean time: 1.4197021961212157
Pipeline stage StressChecker completed in 8.15s
cycy233-l3-exp-v0-e1-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-exp-v0-e1-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics