submission_id: cycy233-l3-cs-v0-c2_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-cs-v0-c2
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', '<|end_header_id|>', '<|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': 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: 2024-07-08T02:53:35+00:00
model_name: auto
model_group: cycy233/L3-cs-v0-c2
num_battles: 31069
num_wins: 14033
celo_rating: 1162.14
alignment_score: None
alignment_samples: 0
propriety_score: 0.7167325428194994
propriety_total_count: 5313.0
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-c2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.45167208471466735
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-cs-v0-c2-v1-mkmlizer
Waiting for job on cycy233-l3-cs-v0-c2-v1-mkmlizer to finish
cycy233-l3-cs-v0-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-cs-v0-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-cs-v0-c2-v1-mkmlizer: Downloaded to shared memory in 55.956s
cycy233-l3-cs-v0-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-cs-v0-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-cs-v0-c2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 86.95it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 103.67it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 150.48it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-cs-v0-c2-v1-mkmlizer: quantized model in 22.513s
cycy233-l3-cs-v0-c2-v1-mkmlizer: Processed model cycy233/L3-cs-v0-c2 in 78.470s
cycy233-l3-cs-v0-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-cs-v0-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-cs-v0-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-cs-v0-c2-v1
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c2-v1/tokenizer_config.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c2-v1/config.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c2-v1/special_tokens_map.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-cs-v0-c2-v1/tokenizer.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-cs-v0-c2-v1/flywheel_model.0.safetensors
cycy233-l3-cs-v0-c2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-cs-v0-c2-v1-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-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c2-v1-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-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c2-v1-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-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c2-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-cs-v0-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-cs-v0-c2-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-cs-v0-c2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-cs-v0-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-cs-v0-c2-v1-mkmlizer: Saving duration: 0.389s
cycy233-l3-cs-v0-c2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.602s
cycy233-l3-cs-v0-c2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-cs-v0-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-cs-v0-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward/special_tokens_map.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward/merges.txt
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward/tokenizer_config.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward/config.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward/vocab.json
cycy233-l3-cs-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-cs-v0-c2-v1_reward/tokenizer.json
Job cycy233-l3-cs-v0-c2-v1-mkmlizer completed after 124.17s with status: succeeded
Stopping job with name cycy233-l3-cs-v0-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-cs-v0-c2-v1
Waiting for inference service cycy233-l3-cs-v0-c2-v1 to be ready
Inference service cycy233-l3-cs-v0-c2-v1 ready after 40.194052934646606s
Pipeline stage ISVCDeployer completed in 46.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.099092483520508s
Received healthy response to inference request in 1.314873218536377s
Received healthy response to inference request in 1.3024508953094482s
Received healthy response to inference request in 1.272653341293335s
Received healthy response to inference request in 1.354067325592041s
5 requests
0 failed requests
5th percentile: 1.2786128520965576
10th percentile: 1.2845723628997803
20th percentile: 1.2964913845062256
30th percentile: 1.304935359954834
40th percentile: 1.3099042892456054
50th percentile: 1.314873218536377
60th percentile: 1.3305508613586425
70th percentile: 1.3462285041809081
80th percentile: 1.5030723571777345
90th percentile: 1.8010824203491211
95th percentile: 1.9500874519348144
99th percentile: 2.069291477203369
mean time: 1.4686274528503418
Pipeline stage StressChecker completed in 8.54s
cycy233-l3-cs-v0-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-cs-v0-c2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics