submission_id: cycy233-l3-cms-v0-c3_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-cms-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: 2024-07-09T02:25:43+00:00
model_name: auto
model_group: cycy233/L3-cms-v0-c3
num_battles: 31357
num_wins: 14080
celo_rating: 1158.88
propriety_score: 0.7131316926545181
propriety_total_count: 5323.0
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-c3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.4490225467997576
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-cms-v0-c3-v1-mkmlizer
Waiting for job on cycy233-l3-cms-v0-c3-v1-mkmlizer to finish
cycy233-l3-cms-v0-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ /___/ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-cms-v0-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-cms-v0-c3-v1-mkmlizer: Downloaded to shared memory in 27.081s
cycy233-l3-cms-v0-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-cms-v0-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-cms-v0-c3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 75.29it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 89.63it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 130.00it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-cms-v0-c3-v1-mkmlizer: quantized model in 20.689s
cycy233-l3-cms-v0-c3-v1-mkmlizer: Processed model cycy233/L3-cms-v0-c3 in 47.770s
cycy233-l3-cms-v0-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-cms-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-cms-v0-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-cms-v0-c3-v1
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-cms-v0-c3-v1/flywheel_model.0.safetensors
cycy233-l3-cms-v0-c3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-cms-v0-c3-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-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c3-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-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c3-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-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c3-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-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-cms-v0-c3-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-c3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-cms-v0-c3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-cms-v0-c3-v1-mkmlizer: Saving duration: 0.270s
cycy233-l3-cms-v0-c3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.258s
cycy233-l3-cms-v0-c3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-cms-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-cms-v0-c3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/config.json
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/vocab.json
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/special_tokens_map.json
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/tokenizer_config.json
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/merges.txt
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/tokenizer.json
cycy233-l3-cms-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-cms-v0-c3-v1_reward/reward.tensors
Job cycy233-l3-cms-v0-c3-v1-mkmlizer completed after 73.21s with status: succeeded
Stopping job with name cycy233-l3-cms-v0-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-cms-v0-c3-v1
Waiting for inference service cycy233-l3-cms-v0-c3-v1 to be ready
Inference service cycy233-l3-cms-v0-c3-v1 ready after 40.20611834526062s
Pipeline stage ISVCDeployer completed in 47.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.026111364364624s
Received healthy response to inference request in 1.3506884574890137s
Received healthy response to inference request in 1.3222630023956299s
Received healthy response to inference request in 1.3073551654815674s
Received healthy response to inference request in 1.3823957443237305s
5 requests
0 failed requests
5th percentile: 1.3103367328643798
10th percentile: 1.3133183002471924
20th percentile: 1.3192814350128175
30th percentile: 1.3279480934143066
40th percentile: 1.3393182754516602
50th percentile: 1.3506884574890137
60th percentile: 1.3633713722229004
70th percentile: 1.376054286956787
80th percentile: 1.5111388683319094
90th percentile: 1.7686251163482667
95th percentile: 1.8973682403564451
99th percentile: 2.000362739562988
mean time: 1.4777627468109131
Pipeline stage StressChecker completed in 8.08s
cycy233-l3-cms-v0-c3_v1 status is now deployed due to DeploymentManager action
cycy233-l3-cms-v0-c3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics