submission_id: cycy233-l3-fusion-v1-e3-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-fusion-v1-e3.0
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'], '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: 2024-07-01T04:23:21+00:00
model_name: auto
model_group: cycy233/L3-fusion-v1-e3.
num_battles: 14223
num_wins: 7101
celo_rating: 1184.69
propriety_score: 0.7013062409288824
propriety_total_count: 6890.0
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-v1-e3.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-30
win_ratio: 0.499261759122548
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-fusion-v1-e3-0-v1-mkmlizer
Waiting for job on cycy233-l3-fusion-v1-e3-0-v1-mkmlizer to finish
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ /___/ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-fusion-v1-e3-0-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-fusion-v1-e3-0-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Downloaded to shared memory in 35.929s
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 62.11it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 68.54it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 100.31it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: quantized model in 25.048s
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Processed model cycy233/L3-fusion-v1-e3.0 in 63.664s
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-fusion-v1-e3-0-v1
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-fusion-v1-e3-0-v1/special_tokens_map.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-fusion-v1-e3-0-v1/config.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-fusion-v1-e3-0-v1/tokenizer_config.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-fusion-v1-e3-0-v1/tokenizer.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-fusion-v1-e3-0-v1/flywheel_model.0.safetensors
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-fusion-v1-e3-0-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-fusion-v1-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-fusion-v1-e3-0-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-fusion-v1-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-fusion-v1-e3-0-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-fusion-v1-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-fusion-v1-e3-0-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-fusion-v1-e3-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Saving duration: 0.417s
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.571s
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/special_tokens_map.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/config.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/tokenizer_config.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/merges.txt
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/vocab.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/tokenizer.json
cycy233-l3-fusion-v1-e3-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-fusion-v1-e3-0-v1_reward/reward.tensors
Job cycy233-l3-fusion-v1-e3-0-v1-mkmlizer completed after 93.88s with status: succeeded
Stopping job with name cycy233-l3-fusion-v1-e3-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-fusion-v1-e3-0-v1
Waiting for inference service cycy233-l3-fusion-v1-e3-0-v1 to be ready
Inference service cycy233-l3-fusion-v1-e3-0-v1 ready after 50.26615834236145s
Pipeline stage ISVCDeployer completed in 56.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2527964115142822s
Received healthy response to inference request in 1.4147121906280518s
Received healthy response to inference request in 1.3698699474334717s
Received healthy response to inference request in 1.3320631980895996s
Received healthy response to inference request in 1.428576946258545s
5 requests
0 failed requests
5th percentile: 1.339624547958374
10th percentile: 1.3471858978271485
20th percentile: 1.3623085975646974
30th percentile: 1.3788383960723878
40th percentile: 1.3967752933502198
50th percentile: 1.4147121906280518
60th percentile: 1.420258092880249
70th percentile: 1.4258039951324464
80th percentile: 1.5934208393096925
90th percentile: 1.9231086254119873
95th percentile: 2.0879525184631347
99th percentile: 2.2198276329040527
mean time: 1.55960373878479
Pipeline stage StressChecker completed in 8.52s
cycy233-l3-fusion-v1-e3-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-fusion-v1-e3-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics