submission_id: cycy233-l3-brw-v0-c1_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-brw-v0-c1
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}
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: 2024-07-03T16:31:15+00:00
model_name: auto
model_group: cycy233/L3-brw-v0-c1
num_battles: 11634
num_wins: 5800
celo_rating: 1179.48
propriety_score: 0.7249779346866726
propriety_total_count: 5665.0
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-brw-v0-c1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.4985387656867801
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-brw-v0-c1-v1-mkmlizer
Waiting for job on cycy233-l3-brw-v0-c1-v1-mkmlizer to finish
cycy233-l3-brw-v0-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ /___/ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-brw-v0-c1-v1-mkmlizer: Downloaded to shared memory in 43.544s
cycy233-l3-brw-v0-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-brw-v0-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-brw-v0-c1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 74.99it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 88.70it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 126.66it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-brw-v0-c1-v1-mkmlizer: quantized model in 24.851s
cycy233-l3-brw-v0-c1-v1-mkmlizer: Processed model cycy233/L3-brw-v0-c1 in 68.395s
cycy233-l3-brw-v0-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-brw-v0-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-brw-v0-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-brw-v0-c1-v1
cycy233-l3-brw-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c1-v1/config.json
cycy233-l3-brw-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c1-v1/special_tokens_map.json
cycy233-l3-brw-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c1-v1/tokenizer_config.json
cycy233-l3-brw-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c1-v1/tokenizer.json
cycy233-l3-brw-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-brw-v0-c1-v1/flywheel_model.0.safetensors
cycy233-l3-brw-v0-c1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-brw-v0-c1-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-brw-v0-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c1-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-brw-v0-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c1-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-brw-v0-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c1-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-brw-v0-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c1-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-brw-v0-c1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-brw-v0-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-brw-v0-c1-v1-mkmlizer: Saving duration: 0.434s
cycy233-l3-brw-v0-c1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.442s
cycy233-l3-brw-v0-c1-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-brw-v0-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-brw-v0-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-brw-v0-c1-v1_reward
cycy233-l3-brw-v0-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-brw-v0-c1-v1_reward/reward.tensors
Job cycy233-l3-brw-v0-c1-v1-mkmlizer completed after 105.33s with status: succeeded
Stopping job with name cycy233-l3-brw-v0-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-brw-v0-c1-v1
Waiting for inference service cycy233-l3-brw-v0-c1-v1 to be ready
Inference service cycy233-l3-brw-v0-c1-v1 ready after 40.241182804107666s
Pipeline stage ISVCDeployer completed in 47.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.074556350708008s
Received healthy response to inference request in 1.2560887336730957s
Received healthy response to inference request in 1.2659165859222412s
Received healthy response to inference request in 1.2929279804229736s
Received healthy response to inference request in 1.2690682411193848s
5 requests
0 failed requests
5th percentile: 1.2580543041229248
10th percentile: 1.260019874572754
20th percentile: 1.263951015472412
30th percentile: 1.2665469169616699
40th percentile: 1.2678075790405274
50th percentile: 1.2690682411193848
60th percentile: 1.2786121368408203
70th percentile: 1.2881560325622559
80th percentile: 1.4492536544799806
90th percentile: 1.7619050025939942
95th percentile: 1.9182306766510009
99th percentile: 2.0432912158966063
mean time: 1.4317115783691405
Pipeline stage StressChecker completed in 7.82s
cycy233-l3-brw-v0-c1_v1 status is now deployed due to DeploymentManager action
cycy233-l3-brw-v0-c1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics