submission_id: cycy233-l3-klee-v1-e1-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-klee-v1-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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_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: 2024-07-01T03:01:43+00:00
model_name: auto
model_group: cycy233/L3-klee-v1-e1.5
num_battles: 16491
num_wins: 8202
celo_rating: 1184.18
propriety_score: 0.7006777108433735
propriety_total_count: 7968.0
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-klee-v1-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-30
win_ratio: 0.4973621975623067
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v1-e1-5-v1-mkmlizer
Waiting for job on cycy233-l3-klee-v1-e1-5-v1-mkmlizer to finish
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v1-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-klee-v1-e1-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Downloaded to shared memory in 29.851s
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 93.27it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 109.54it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 158.16it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: quantized model in 17.605s
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Processed model cycy233/L3-klee-v1-e1.5 in 48.525s
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v1-e1-5-v1
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e1-5-v1/config.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e1-5-v1/tokenizer_config.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e1-5-v1/special_tokens_map.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e1-5-v1/tokenizer.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-klee-v1-e1-5-v1/flywheel_model.0.safetensors
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v1-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-klee-v1-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v1-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-klee-v1-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v1-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-klee-v1-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v1-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-klee-v1-e1-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Saving duration: 0.233s
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.925s
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/config.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/special_tokens_map.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/merges.txt
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/tokenizer_config.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/vocab.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/tokenizer.json
cycy233-l3-klee-v1-e1-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-klee-v1-e1-5-v1_reward/reward.tensors
Job cycy233-l3-klee-v1-e1-5-v1-mkmlizer completed after 73.13s with status: succeeded
Stopping job with name cycy233-l3-klee-v1-e1-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v1-e1-5-v1
Waiting for inference service cycy233-l3-klee-v1-e1-5-v1 to be ready
Inference service cycy233-l3-klee-v1-e1-5-v1 ready after 40.1892466545105s
Pipeline stage ISVCDeployer completed in 46.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.235537528991699s
Received healthy response to inference request in 1.354743242263794s
Received healthy response to inference request in 1.324512243270874s
Received healthy response to inference request in 1.301682472229004s
Received healthy response to inference request in 1.3865902423858643s
5 requests
0 failed requests
5th percentile: 1.306248426437378
10th percentile: 1.310814380645752
20th percentile: 1.3199462890625
30th percentile: 1.330558443069458
40th percentile: 1.342650842666626
50th percentile: 1.354743242263794
60th percentile: 1.3674820423126222
70th percentile: 1.3802208423614502
80th percentile: 1.5563796997070314
90th percentile: 1.8959586143493654
95th percentile: 2.065748071670532
99th percentile: 2.2015796375274657
mean time: 1.520613145828247
Pipeline stage StressChecker completed in 8.24s
cycy233-l3-klee-v1-e1-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v1-e1-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics