submission_id: cycy233-l3-bm-v2-c3_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bm-v2-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: 2024-07-11T02:28:05+00:00
model_name: auto
model_group: cycy233/L3-bm-v2-c3
num_battles: 27143
num_wins: 13775
celo_rating: 1194.37
propriety_score: 0.7026793431287813
propriety_total_count: 5785.0
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-c3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-10
win_ratio: 0.5074973289614265
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bm-v2-c3-v1-mkmlizer
Waiting for job on cycy233-l3-bm-v2-c3-v1-mkmlizer to finish
cycy233-l3-bm-v2-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ║ ║
cycy233-l3-bm-v2-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bm-v2-c3-v1-mkmlizer: Downloaded to shared memory in 31.217s
cycy233-l3-bm-v2-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bm-v2-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bm-v2-c3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 61.09it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 70.11it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 104.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bm-v2-c3-v1-mkmlizer: quantized model in 29.312s
cycy233-l3-bm-v2-c3-v1-mkmlizer: Processed model cycy233/L3-bm-v2-c3 in 60.529s
cycy233-l3-bm-v2-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bm-v2-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bm-v2-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bm-v2-c3-v1
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c3-v1/special_tokens_map.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c3-v1/config.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c3-v1/tokenizer_config.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bm-v2-c3-v1/tokenizer.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bm-v2-c3-v1/flywheel_model.0.safetensors
cycy233-l3-bm-v2-c3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bm-v2-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-v2-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-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-v2-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-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-v2-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-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-v2-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v2-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-v2-c3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bm-v2-c3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bm-v2-c3-v1-mkmlizer: Saving duration: 0.526s
cycy233-l3-bm-v2-c3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.540s
cycy233-l3-bm-v2-c3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bm-v2-c3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bm-v2-c3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward/config.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward/special_tokens_map.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward/tokenizer_config.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward/vocab.json
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward/merges.txt
cycy233-l3-bm-v2-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bm-v2-c3-v1_reward/tokenizer.json
Job cycy233-l3-bm-v2-c3-v1-mkmlizer completed after 95.72s with status: succeeded
Stopping job with name cycy233-l3-bm-v2-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bm-v2-c3-v1
Waiting for inference service cycy233-l3-bm-v2-c3-v1 to be ready
Inference service cycy233-l3-bm-v2-c3-v1 ready after 40.225253105163574s
Pipeline stage ISVCDeployer completed in 46.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9973845481872559s
Received healthy response to inference request in 1.2439336776733398s
Received healthy response to inference request in 1.238534688949585s
Received healthy response to inference request in 1.2481575012207031s
Received healthy response to inference request in 1.2754969596862793s
5 requests
0 failed requests
5th percentile: 1.239614486694336
10th percentile: 1.240694284439087
20th percentile: 1.2428538799285889
30th percentile: 1.2447784423828125
40th percentile: 1.2464679718017577
50th percentile: 1.2481575012207031
60th percentile: 1.2590932846069336
70th percentile: 1.270029067993164
80th percentile: 1.4198744773864747
90th percentile: 1.7086295127868654
95th percentile: 1.8530070304870605
99th percentile: 1.9685090446472169
mean time: 1.4007014751434326
Pipeline stage StressChecker completed in 7.69s
cycy233-l3-bm-v2-c3_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bm-v2-c3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics