submission_id: cycy233-l3-brw-v0-c3_v3
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-brw-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', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-07-04T01:34:40+00:00
model_name: auto
model_group: cycy233/L3-brw-v0-c3
num_battles: 14602
num_wins: 7130
celo_rating: 1175.8
propriety_score: 0.7209233060312733
propriety_total_count: 6715.0
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-c3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.4882892754417203
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-brw-v0-c3-v3-mkmlizer
Waiting for job on cycy233-l3-brw-v0-c3-v3-mkmlizer to finish
cycy233-l3-brw-v0-c3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ /___/ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-brw-v0-c3-v3-mkmlizer: Downloaded to shared memory in 36.108s
cycy233-l3-brw-v0-c3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-brw-v0-c3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-brw-v0-c3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 61.89it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 73.15it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 107.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-brw-v0-c3-v3-mkmlizer: quantized model in 29.833s
cycy233-l3-brw-v0-c3-v3-mkmlizer: Processed model cycy233/L3-brw-v0-c3 in 65.942s
cycy233-l3-brw-v0-c3-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-brw-v0-c3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-brw-v0-c3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v3
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v3/tokenizer_config.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v3/config.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v3/special_tokens_map.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v3/tokenizer.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v3/flywheel_model.0.safetensors
cycy233-l3-brw-v0-c3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-brw-v0-c3-v3-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-c3-v3-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v3-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-c3-v3-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v3-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-c3-v3-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v3-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-c3-v3-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v3-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-c3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-brw-v0-c3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-brw-v0-c3-v3-mkmlizer: Saving duration: 0.529s
cycy233-l3-brw-v0-c3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.408s
cycy233-l3-brw-v0-c3-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-brw-v0-c3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-brw-v0-c3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/config.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/special_tokens_map.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/merges.txt
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/tokenizer_config.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/vocab.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/tokenizer.json
cycy233-l3-brw-v0-c3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v3_reward/reward.tensors
Job cycy233-l3-brw-v0-c3-v3-mkmlizer completed after 94.94s with status: succeeded
Stopping job with name cycy233-l3-brw-v0-c3-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.33s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-brw-v0-c3-v3
Waiting for inference service cycy233-l3-brw-v0-c3-v3 to be ready
Inference service cycy233-l3-brw-v0-c3-v3 ready after 40.22374773025513s
Pipeline stage ISVCDeployer completed in 47.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1432580947875977s
Received healthy response to inference request in 1.349992036819458s
Received healthy response to inference request in 1.30098295211792s
Received healthy response to inference request in 1.2582378387451172s
Received healthy response to inference request in 1.3300251960754395s
5 requests
0 failed requests
5th percentile: 1.2667868614196778
10th percentile: 1.2753358840942384
20th percentile: 1.2924339294433593
30th percentile: 1.306791400909424
40th percentile: 1.3184082984924317
50th percentile: 1.3300251960754395
60th percentile: 1.3380119323730468
70th percentile: 1.3459986686706542
80th percentile: 1.5086452484130861
90th percentile: 1.8259516716003419
95th percentile: 1.9846048831939695
99th percentile: 2.111527452468872
mean time: 1.4764992237091064
Pipeline stage StressChecker completed in 8.06s
cycy233-l3-brw-v0-c3_v3 status is now deployed due to DeploymentManager action
cycy233-l3-brw-v0-c3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics