submission_id: cycy233-l3-bm-v2-c4_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bm-v2-c4
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: 2024-07-11T02:28:20+00:00
model_name: auto
model_group: cycy233/L3-bm-v2-c4
num_battles: 27234
num_wins: 13908
celo_rating: 1196.4
propriety_score: 0.6946749654218534
propriety_total_count: 5784.0
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-bm-v2-c4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-10
win_ratio: 0.5106851729455827
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bm-v2-c4-v1-mkmlizer
Waiting for job on cycy233-l3-bm-v2-c4-v1-mkmlizer to finish
cycy233-l3-bm-v2-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bm-v2-c4-v1-mkmlizer: Downloaded to shared memory in 33.818s
cycy233-l3-bm-v2-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bm-v2-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bm-v2-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:04, 49.19it/s] Loading 0: 64%|██████▍ | 187/291 [00:03<00:01, 62.86it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 93.70it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bm-v2-c4-v1-mkmlizer: quantized model in 29.829s
cycy233-l3-bm-v2-c4-v1-mkmlizer: Processed model cycy233/L3-bm-v2-c4 in 63.647s
cycy233-l3-bm-v2-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bm-v2-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bm-v2-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bm-v2-c4-v1
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c4-v1/config.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c4-v1/tokenizer_config.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c4-v1/special_tokens_map.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c4-v1/tokenizer.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bm-v2-c4-v1/flywheel_model.0.safetensors
cycy233-l3-bm-v2-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bm-v2-c4-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-v2-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-c4-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-v2-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-c4-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-v2-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-c4-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-v2-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-c4-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-v2-c4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bm-v2-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bm-v2-c4-v1-mkmlizer: Saving duration: 0.531s
cycy233-l3-bm-v2-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.715s
cycy233-l3-bm-v2-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bm-v2-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bm-v2-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/config.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/merges.txt
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/tokenizer_config.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/special_tokens_map.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/vocab.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/tokenizer.json
cycy233-l3-bm-v2-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bm-v2-c4-v1_reward/reward.tensors
Job cycy233-l3-bm-v2-c4-v1-mkmlizer completed after 94.59s with status: succeeded
Stopping job with name cycy233-l3-bm-v2-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bm-v2-c4-v1
Waiting for inference service cycy233-l3-bm-v2-c4-v1 to be ready
Inference service cycy233-l3-bm-v2-c4-v1 ready after 60.26984643936157s
Pipeline stage ISVCDeployer completed in 67.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0111310482025146s
Received healthy response to inference request in 1.2314701080322266s
Received healthy response to inference request in 1.2584407329559326s
Received healthy response to inference request in 1.293762445449829s
Received healthy response to inference request in 1.2409391403198242s
5 requests
0 failed requests
5th percentile: 1.2333639144897461
10th percentile: 1.2352577209472657
20th percentile: 1.2390453338623046
30th percentile: 1.244439458847046
40th percentile: 1.2514400959014893
50th percentile: 1.2584407329559326
60th percentile: 1.2725694179534912
70th percentile: 1.2866981029510498
80th percentile: 1.4372361660003663
90th percentile: 1.7241836071014405
95th percentile: 1.8676573276519775
99th percentile: 1.9824363040924071
mean time: 1.4071486949920655
Pipeline stage StressChecker completed in 7.74s
cycy233-l3-bm-v2-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bm-v2-c4_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics