submission_id: cycy233-l3-cms-v0-c4_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-cms-v0-c4
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: 2024-07-09T02:25:58+00:00
model_name: auto
model_group: cycy233/L3-cms-v0-c4
num_battles: 31630
num_wins: 14392
celo_rating: 1162.83
alignment_score: None
alignment_samples: 0
propriety_score: 0.709592641261498
propriety_total_count: 5327.0
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-cms-v0-c4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.45501106544419856
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-cms-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-cms-v0-c4-v1-mkmlizer to finish
cycy233-l3-cms-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-cms-v0-c4-v1-mkmlizer: Downloaded to shared memory in 30.330s
cycy233-l3-cms-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-cms-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-cms-v0-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 68.48it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 79.02it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 114.15it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-cms-v0-c4-v1-mkmlizer: quantized model in 24.666s
cycy233-l3-cms-v0-c4-v1-mkmlizer: Processed model cycy233/L3-cms-v0-c4 in 54.996s
cycy233-l3-cms-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-cms-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-cms-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-cms-v0-c4-v1
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-cms-v0-c4-v1/special_tokens_map.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-cms-v0-c4-v1/tokenizer_config.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-cms-v0-c4-v1/config.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-cms-v0-c4-v1/tokenizer.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-cms-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-cms-v0-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-cms-v0-c4-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-cms-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c4-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-cms-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c4-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-cms-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c4-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-cms-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c4-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-cms-v0-c4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-cms-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-cms-v0-c4-v1-mkmlizer: Saving duration: 0.385s
cycy233-l3-cms-v0-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.842s
cycy233-l3-cms-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-cms-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-cms-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/config.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/merges.txt
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/vocab.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/tokenizer.json
cycy233-l3-cms-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-cms-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-cms-v0-c4-v1-mkmlizer completed after 83.61s with status: succeeded
Stopping job with name cycy233-l3-cms-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-cms-v0-c4-v1
Waiting for inference service cycy233-l3-cms-v0-c4-v1 to be ready
Inference service cycy233-l3-cms-v0-c4-v1 ready after 40.49835276603699s
Pipeline stage ISVCDeployer completed in 47.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.121674060821533s
Received healthy response to inference request in 1.3359243869781494s
Received healthy response to inference request in 1.3078327178955078s
Received healthy response to inference request in 1.276535987854004s
Received healthy response to inference request in 1.35640287399292s
5 requests
0 failed requests
5th percentile: 1.2827953338623046
10th percentile: 1.2890546798706055
20th percentile: 1.3015733718872071
30th percentile: 1.3134510517120361
40th percentile: 1.3246877193450928
50th percentile: 1.3359243869781494
60th percentile: 1.3441157817840577
70th percentile: 1.352307176589966
80th percentile: 1.5094571113586428
90th percentile: 1.815565586090088
95th percentile: 1.9686198234558103
99th percentile: 2.091063213348389
mean time: 1.4796740055084228
Pipeline stage StressChecker completed in 8.12s
cycy233-l3-cms-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-cms-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics