submission_id: cycy233-l3-fusion-v0-e1-5_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-fusion-v0-e1.5
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}
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: 2024-07-01T04:02:17+00:00
model_name: auto
model_group: cycy233/L3-fusion-v0-e1.
num_battles: 16953
num_wins: 8289
celo_rating: 1178.04
propriety_score: 0.7106994881793809
propriety_total_count: 8206.0
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-fusion-v0-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-30
win_ratio: 0.4889400106175898
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-fusion-v0-e1-5-v2-mkmlizer
Waiting for job on cycy233-l3-fusion-v0-e1-5-v2-mkmlizer to finish
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ /___/ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-fusion-v0-e1-5-v2-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-fusion-v0-e1-5-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Downloaded to shared memory in 20.520s
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 71.42it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 89.56it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 128.25it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: quantized model in 24.341s
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Processed model cycy233/L3-fusion-v0-e1.5 in 47.633s
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e1-5-v2
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e1-5-v2/config.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e1-5-v2/tokenizer_config.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e1-5-v2/special_tokens_map.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e1-5-v2/tokenizer.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e1-5-v2/flywheel_model.0.safetensors
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-fusion-v0-e1-5-v2-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-fusion-v0-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-fusion-v0-e1-5-v2-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-fusion-v0-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-fusion-v0-e1-5-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-fusion-v0-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-fusion-v0-e1-5-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-fusion-v0-e1-5-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Saving duration: 0.413s
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.636s
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/special_tokens_map.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/merges.txt
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/vocab.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/config.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/tokenizer_config.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/tokenizer.json
cycy233-l3-fusion-v0-e1-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-fusion-v0-e1-5-v2_reward/reward.tensors
Job cycy233-l3-fusion-v0-e1-5-v2-mkmlizer completed after 83.41s with status: succeeded
Stopping job with name cycy233-l3-fusion-v0-e1-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-fusion-v0-e1-5-v2
Waiting for inference service cycy233-l3-fusion-v0-e1-5-v2 to be ready
Inference service cycy233-l3-fusion-v0-e1-5-v2 ready after 50.22006893157959s
Pipeline stage ISVCDeployer completed in 56.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.22969126701355s
Received healthy response to inference request in 1.3893349170684814s
Received healthy response to inference request in 1.3484101295471191s
Received healthy response to inference request in 1.3486566543579102s
Received healthy response to inference request in 1.4021296501159668s
5 requests
0 failed requests
5th percentile: 1.3484594345092773
10th percentile: 1.3485087394714355
20th percentile: 1.348607349395752
30th percentile: 1.3567923069000245
40th percentile: 1.373063611984253
50th percentile: 1.3893349170684814
60th percentile: 1.3944528102874756
70th percentile: 1.3995707035064697
80th percentile: 1.5676419734954836
90th percentile: 1.8986666202545166
95th percentile: 2.064178943634033
99th percentile: 2.1965888023376463
mean time: 1.5436445236206056
Pipeline stage StressChecker completed in 8.37s
cycy233-l3-fusion-v0-e1-5_v2 status is now deployed due to DeploymentManager action
cycy233-l3-fusion-v0-e1-5_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics