submission_id: cycy233-l3-klee-v2-e2-0_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-klee-v2-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', '<|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: 2024-07-02T02:51:32+00:00
model_name: auto
model_group: cycy233/L3-klee-v2-e2.0
num_battles: 11652
num_wins: 5978
celo_rating: 1183.51
propriety_score: 0.7101296880476691
propriety_total_count: 5706.0
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-klee-v2-e2.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.51304497082046
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v2-e2-0-v2-mkmlizer
Waiting for job on cycy233-l3-klee-v2-e2-0-v2-mkmlizer to finish
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Downloaded to shared memory in 22.053s
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.91it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 78.60it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 114.53it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: quantized model in 24.086s
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Processed model cycy233/L3-klee-v2-e2.0 in 46.140s
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v2
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v2/special_tokens_map.json
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v2/config.json
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v2/tokenizer_config.json
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v2/tokenizer.json
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v2-e2-0-v2-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-klee-v2-e2-0-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-v2-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-klee-v2-e2-0-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-v2-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-klee-v2-e2-0-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-v2-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-klee-v2-e2-0-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-v2-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-klee-v2-e2-0-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Saving duration: 0.403s
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.218s
cycy233-l3-klee-v2-e2-0-v2-mkmlizer: creating bucket guanaco-reward-models
Job cycy233-l3-klee-v2-e2-0-v2-mkmlizer completed after 110.73s with status: succeeded
Stopping job with name cycy233-l3-klee-v2-e2-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 111.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v2-e2-0-v2
Waiting for inference service cycy233-l3-klee-v2-e2-0-v2 to be ready
Connection pool is full, discarding connection: %s
Inference service cycy233-l3-klee-v2-e2-0-v2 ready after 50.92640733718872s
Pipeline stage ISVCDeployer completed in 58.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1910202503204346s
Received healthy response to inference request in 1.4013864994049072s
Received healthy response to inference request in 1.3875203132629395s
Received healthy response to inference request in 1.3449981212615967s
Received healthy response to inference request in 1.7291686534881592s
5 requests
0 failed requests
5th percentile: 1.3535025596618653
10th percentile: 1.3620069980621339
20th percentile: 1.3790158748626709
30th percentile: 1.390293550491333
40th percentile: 1.3958400249481202
50th percentile: 1.4013864994049072
60th percentile: 1.532499361038208
70th percentile: 1.6636122226715087
80th percentile: 1.8215389728546143
90th percentile: 2.0062796115875243
95th percentile: 2.0986499309539792
99th percentile: 2.1725461864471436
mean time: 1.6108187675476073
Pipeline stage StressChecker completed in 8.89s
cycy233-l3-klee-v2-e2-0_v2 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v2-e2-0_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics