submission_id: cycy233-l3-bm-v1-e2-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bm-v1-e2.0
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: 2024-07-09T10:39:00+00:00
model_name: cycy233-l3-bm-v1-e2-0_v1
model_group: cycy233/L3-bm-v1-e2.0
num_battles: 30689
num_wins: 15336
celo_rating: 1199.87
propriety_score: 0.7197117257499026
propriety_total_count: 5134.0
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-v1-e2-0_v1
ineligible_reason: None
language_model: cycy233/L3-bm-v1-e2.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-09
win_ratio: 0.4997230277949754
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bm-v1-e2-0-v1-mkmlizer
Waiting for job on cycy233-l3-bm-v1-e2-0-v1-mkmlizer to finish
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Downloaded to shared memory in 35.090s
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.97it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 70.23it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 101.53it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: quantized model in 24.999s
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Processed model cycy233/L3-bm-v1-e2.0 in 60.090s
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bm-v1-e2-0-v1
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bm-v1-e2-0-v1/special_tokens_map.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bm-v1-e2-0-v1/config.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bm-v1-e2-0-v1/tokenizer_config.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bm-v1-e2-0-v1/tokenizer.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bm-v1-e2-0-v1/flywheel_model.0.safetensors
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bm-v1-e2-0-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-v1-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v1-e2-0-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-v1-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v1-e2-0-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-v1-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v1-e2-0-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-v1-e2-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Saving duration: 0.428s
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.453s
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/config.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/special_tokens_map.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/tokenizer_config.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/merges.txt
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/vocab.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/tokenizer.json
cycy233-l3-bm-v1-e2-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bm-v1-e2-0-v1_reward/reward.tensors
Job cycy233-l3-bm-v1-e2-0-v1-mkmlizer completed after 83.84s with status: succeeded
Stopping job with name cycy233-l3-bm-v1-e2-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bm-v1-e2-0-v1
Waiting for inference service cycy233-l3-bm-v1-e2-0-v1 to be ready
Inference service cycy233-l3-bm-v1-e2-0-v1 ready after 40.1773738861084s
Pipeline stage ISVCDeployer completed in 47.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0564022064208984s
Received healthy response to inference request in 1.4058077335357666s
Received healthy response to inference request in 1.2206509113311768s
Received healthy response to inference request in 1.251175880432129s
Received healthy response to inference request in 1.2587227821350098s
5 requests
0 failed requests
5th percentile: 1.2267559051513672
10th percentile: 1.2328608989715577
20th percentile: 1.2450708866119384
30th percentile: 1.252685260772705
40th percentile: 1.2557040214538575
50th percentile: 1.2587227821350098
60th percentile: 1.3175567626953124
70th percentile: 1.3763907432556153
80th percentile: 1.535926628112793
90th percentile: 1.7961644172668458
95th percentile: 1.926283311843872
99th percentile: 2.030378427505493
mean time: 1.438551902770996
Pipeline stage StressChecker completed in 7.91s
cycy233-l3-bm-v1-e2-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bm-v1-e2-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics