submission_id: cycy233-l3-duduk-v0-e2-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-duduk-v0-e2.5
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': "<|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}
timestamp: 2024-06-28T03:31:03+00:00
model_name: auto
model_group: cycy233/L3-duduk-v0-e2.5
num_battles: 19813
num_wins: 10279
celo_rating: 1195.95
propriety_score: 0.7005566642159438
propriety_total_count: 9521.0
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-duduk-v0-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.5188007873618331
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-duduk-v0-e2-5-v1-mkmlizer
Waiting for job on cycy233-l3-duduk-v0-e2-5-v1-mkmlizer to finish
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: Downloaded to shared memory in 45.181s
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 74.05it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 86.51it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 124.97it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: quantized model in 23.460s
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: Processed model cycy233/L3-duduk-v0-e2.5 in 71.128s
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e2-5-v1
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e2-5-v1/config.json
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e2-5-v1/special_tokens_map.json
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e2-5-v1/tokenizer_config.json
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e2-5-v1/tokenizer.json
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e2-5-v1/flywheel_model.0.safetensors
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-duduk-v0-e2-5-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-duduk-v0-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-duduk-v0-e2-5-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-duduk-v0-e2-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-duduk-v0-e2-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Job cycy233-l3-duduk-v0-e2-5-v1-mkmlizer completed after 129.75s with status: succeeded
Stopping job with name cycy233-l3-duduk-v0-e2-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 130.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-duduk-v0-e2-5-v1
Waiting for inference service cycy233-l3-duduk-v0-e2-5-v1 to be ready
Inference service cycy233-l3-duduk-v0-e2-5-v1 ready after 191.06396436691284s
Pipeline stage ISVCDeployer completed in 198.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3630170822143555s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.32576584815979s
Received healthy response to inference request in 1.3020906448364258s
Received healthy response to inference request in 1.6062088012695312s
Received healthy response to inference request in 1.266831636428833s
Received healthy response to inference request in 1.3240573406219482s
5 requests
0 failed requests
5th percentile: 1.2738834381103517
10th percentile: 1.28093523979187
20th percentile: 1.2950388431549071
30th percentile: 1.3064839839935303
40th percentile: 1.3152706623077393
50th percentile: 1.3240573406219482
60th percentile: 1.324740743637085
70th percentile: 1.3254241466522216
80th percentile: 1.3818544387817384
90th percentile: 1.4940316200256347
95th percentile: 1.5501202106475829
99th percentile: 1.5949910831451415
mean time: 1.3649908542633056
Pipeline stage StressChecker completed in 10.34s
cycy233-l3-duduk-v0-e2-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-duduk-v0-e2-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics