submission_id: cycy233-l3-bm-v0-c3_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bm-v0-c3
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: 2024-07-04T02:28:34+00:00
model_name: cycy233-l3-bm-v0-c3_v1
model_group: cycy233/L3-bm-v0-c3
num_battles: 13386
num_wins: 6858
celo_rating: 1197.26
propriety_score: 0.696605827729747
propriety_total_count: 6246.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-l3-bm-v0-c3_v1
ineligible_reason: None
language_model: cycy233/L3-bm-v0-c3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.5123263110712685
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bm-v0-c3-v1-mkmlizer
Waiting for job on cycy233-l3-bm-v0-c3-v1-mkmlizer to finish
cycy233-l3-bm-v0-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bm-v0-c3-v1-mkmlizer: Downloaded to shared memory in 51.496s
cycy233-l3-bm-v0-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bm-v0-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bm-v0-c3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.57it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 77.99it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 114.31it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bm-v0-c3-v1-mkmlizer: quantized model in 24.951s
cycy233-l3-bm-v0-c3-v1-mkmlizer: Processed model cycy233/L3-bm-v0-c3 in 76.447s
cycy233-l3-bm-v0-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bm-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bm-v0-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bm-v0-c3-v1
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c3-v1/config.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c3-v1/special_tokens_map.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c3-v1/tokenizer_config.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c3-v1/tokenizer.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bm-v0-c3-v1/flywheel_model.0.safetensors
cycy233-l3-bm-v0-c3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bm-v0-c3-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-bm-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c3-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-bm-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c3-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-bm-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c3-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-bm-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c3-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-bm-v0-c3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bm-v0-c3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bm-v0-c3-v1-mkmlizer: Saving duration: 0.386s
cycy233-l3-bm-v0-c3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.603s
cycy233-l3-bm-v0-c3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bm-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bm-v0-c3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/config.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/tokenizer_config.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/merges.txt
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/special_tokens_map.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/vocab.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/tokenizer.json
cycy233-l3-bm-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bm-v0-c3-v1_reward/reward.tensors
Job cycy233-l3-bm-v0-c3-v1-mkmlizer completed after 124.65s with status: succeeded
Stopping job with name cycy233-l3-bm-v0-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bm-v0-c3-v1
Waiting for inference service cycy233-l3-bm-v0-c3-v1 to be ready
Inference service cycy233-l3-bm-v0-c3-v1 ready after 40.19810461997986s
Pipeline stage ISVCDeployer completed in 47.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.081801176071167s
Received healthy response to inference request in 1.26906156539917s
Received healthy response to inference request in 1.2188012599945068s
Received healthy response to inference request in 1.2557265758514404s
Received healthy response to inference request in 1.2221834659576416s
5 requests
0 failed requests
5th percentile: 1.2194777011871338
10th percentile: 1.2201541423797608
20th percentile: 1.2215070247650146
30th percentile: 1.2288920879364014
40th percentile: 1.242309331893921
50th percentile: 1.2557265758514404
60th percentile: 1.2610605716705323
70th percentile: 1.266394567489624
80th percentile: 1.4316094875335694
90th percentile: 1.7567053318023682
95th percentile: 1.9192532539367675
99th percentile: 2.049291591644287
mean time: 1.409514808654785
Pipeline stage StressChecker completed in 8.53s
cycy233-l3-bm-v0-c3_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bm-v0-c3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics