submission_id: cycy233-l3-cs-v0-c4_v3
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-cs-v0-c4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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': True}
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': True}
timestamp: 2024-07-08T04:16:48+00:00
model_name: auto
model_group: cycy233/L3-cs-v0-c4
num_battles: 30443
num_wins: 13475
celo_rating: 1158.65
propriety_score: 0.720876585928489
propriety_total_count: 5202.0
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-cs-v0-c4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.4426304897677627
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-cs-v0-c4-v3-mkmlizer
Waiting for job on cycy233-l3-cs-v0-c4-v3-mkmlizer to finish
Stopping job with name cycy233-l3-cs-v0-c4-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-cs-v0-c4-v3-mkmlizer
Waiting for job on cycy233-l3-cs-v0-c4-v3-mkmlizer to finish
cycy233-l3-cs-v0-c4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ /___/ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-cs-v0-c4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-cs-v0-c4-v3-mkmlizer: Downloaded to shared memory in 16.466s
cycy233-l3-cs-v0-c4-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-cs-v0-c4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-cs-v0-c4-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 68.39it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 82.05it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 120.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-cs-v0-c4-v3-mkmlizer: quantized model in 19.812s
cycy233-l3-cs-v0-c4-v3-mkmlizer: Processed model cycy233/L3-cs-v0-c4 in 36.278s
cycy233-l3-cs-v0-c4-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-cs-v0-c4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-cs-v0-c4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-cs-v0-c4-v3
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c4-v3/tokenizer_config.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c4-v3/special_tokens_map.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c4-v3/config.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c4-v3/tokenizer.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-cs-v0-c4-v3/flywheel_model.0.safetensors
cycy233-l3-cs-v0-c4-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-cs-v0-c4-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-cs-v0-c4-v3-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c4-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cycy233-l3-cs-v0-c4-v3-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c4-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-cs-v0-c4-v3-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c4-v3-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-cs-v0-c4-v3-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c4-v3-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-cs-v0-c4-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-cs-v0-c4-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-cs-v0-c4-v3-mkmlizer: Saving duration: 0.246s
cycy233-l3-cs-v0-c4-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.315s
cycy233-l3-cs-v0-c4-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-cs-v0-c4-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-cs-v0-c4-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/config.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/tokenizer_config.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/special_tokens_map.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/vocab.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/merges.txt
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/tokenizer.json
cycy233-l3-cs-v0-c4-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-cs-v0-c4-v3_reward/reward.tensors
Job cycy233-l3-cs-v0-c4-v3-mkmlizer completed after 73.67s with status: succeeded
Stopping job with name cycy233-l3-cs-v0-c4-v3-mkmlizer
Pipeline stage MKMLizer completed in 75.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-cs-v0-c4-v3
Waiting for inference service cycy233-l3-cs-v0-c4-v3 to be ready
Inference service cycy233-l3-cs-v0-c4-v3 ready after 40.21434211730957s
Pipeline stage ISVCDeployer completed in 46.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.146641492843628s
Received healthy response to inference request in 1.3038790225982666s
Received healthy response to inference request in 1.2486622333526611s
Received healthy response to inference request in 1.2981369495391846s
Received healthy response to inference request in 1.2871673107147217s
5 requests
0 failed requests
5th percentile: 1.2563632488250733
10th percentile: 1.2640642642974853
20th percentile: 1.2794662952423095
30th percentile: 1.2893612384796143
40th percentile: 1.2937490940093994
50th percentile: 1.2981369495391846
60th percentile: 1.3004337787628173
70th percentile: 1.3027306079864502
80th percentile: 1.472431516647339
90th percentile: 1.8095365047454834
95th percentile: 1.9780889987945556
99th percentile: 2.1129309940338135
mean time: 1.4568974018096923
Pipeline stage StressChecker completed in 7.99s
cycy233-l3-cs-v0-c4_v3 status is now deployed due to DeploymentManager action
cycy233-l3-cs-v0-c4_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics